CN115413346A - Artificial intelligence selection and configuration - Google Patents
Artificial intelligence selection and configuration Download PDFInfo
- Publication number
- CN115413346A CN115413346A CN202180026383.8A CN202180026383A CN115413346A CN 115413346 A CN115413346 A CN 115413346A CN 202180026383 A CN202180026383 A CN 202180026383A CN 115413346 A CN115413346 A CN 115413346A
- Authority
- CN
- China
- Prior art keywords
- artificial intelligence
- model
- component
- loan
- input
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 546
- 238000000034 method Methods 0.000 claims abstract description 677
- 230000008569 process Effects 0.000 claims abstract description 307
- 230000015654 memory Effects 0.000 claims abstract description 46
- 238000005065 mining Methods 0.000 claims abstract description 9
- 238000012544 monitoring process Methods 0.000 claims description 697
- 238000013480 data collection Methods 0.000 claims description 625
- 230000009471 action Effects 0.000 claims description 491
- 238000013528 artificial neural network Methods 0.000 claims description 466
- 230000000694 effects Effects 0.000 claims description 327
- 230000008901 benefit Effects 0.000 claims description 279
- 238000012549 training Methods 0.000 claims description 265
- 238000007726 management method Methods 0.000 claims description 183
- 230000010354 integration Effects 0.000 claims description 176
- 238000012545 processing Methods 0.000 claims description 170
- 230000004044 response Effects 0.000 claims description 133
- 238000003860 storage Methods 0.000 claims description 124
- 230000006870 function Effects 0.000 claims description 108
- 230000008859 change Effects 0.000 claims description 100
- 238000004422 calculation algorithm Methods 0.000 claims description 92
- 230000003044 adaptive effect Effects 0.000 claims description 81
- 238000010801 machine learning Methods 0.000 claims description 57
- 210000004556 brain Anatomy 0.000 claims description 55
- 230000000670 limiting effect Effects 0.000 claims description 51
- 238000004458 analytical method Methods 0.000 claims description 43
- 238000012795 verification Methods 0.000 claims description 40
- 230000033001 locomotion Effects 0.000 claims description 35
- 230000000007 visual effect Effects 0.000 claims description 34
- 238000001514 detection method Methods 0.000 claims description 30
- 238000012552 review Methods 0.000 claims description 25
- 238000013500 data storage Methods 0.000 claims description 23
- 238000003384 imaging method Methods 0.000 claims description 21
- 230000007246 mechanism Effects 0.000 claims description 21
- 238000003909 pattern recognition Methods 0.000 claims description 20
- 238000005457 optimization Methods 0.000 claims description 18
- 230000002123 temporal effect Effects 0.000 claims description 16
- 238000012384 transportation and delivery Methods 0.000 claims description 16
- 238000005259 measurement Methods 0.000 claims description 13
- 239000000463 material Substances 0.000 claims description 9
- 210000000478 neocortex Anatomy 0.000 claims description 9
- 238000012790 confirmation Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 8
- 230000001423 neocortical effect Effects 0.000 claims description 8
- 238000005516 engineering process Methods 0.000 claims description 7
- 230000004438 eyesight Effects 0.000 claims description 7
- 230000035945 sensitivity Effects 0.000 claims description 7
- 239000000126 substance Substances 0.000 claims description 7
- 210000003205 muscle Anatomy 0.000 claims description 6
- 230000007177 brain activity Effects 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 4
- 239000008186 active pharmaceutical agent Substances 0.000 claims 3
- 230000001627 detrimental effect Effects 0.000 claims 1
- 230000037023 motor activity Effects 0.000 claims 1
- 231100000430 skin reaction Toxicity 0.000 claims 1
- 230000001360 synchronised effect Effects 0.000 claims 1
- 238000012731 temporal analysis Methods 0.000 claims 1
- 238000004801 process automation Methods 0.000 description 304
- 230000003993 interaction Effects 0.000 description 167
- 230000006399 behavior Effects 0.000 description 113
- 230000001105 regulatory effect Effects 0.000 description 94
- 239000003795 chemical substances by application Substances 0.000 description 85
- 239000000047 product Substances 0.000 description 80
- 238000004891 communication Methods 0.000 description 79
- 230000006854 communication Effects 0.000 description 79
- 230000014759 maintenance of location Effects 0.000 description 73
- 230000033228 biological regulation Effects 0.000 description 62
- 239000010437 gem Substances 0.000 description 56
- 235000013361 beverage Nutrition 0.000 description 55
- 238000013527 convolutional neural network Methods 0.000 description 55
- 229910001751 gemstone Inorganic materials 0.000 description 55
- 239000010970 precious metal Substances 0.000 description 55
- -1 jewelry ornaments Substances 0.000 description 53
- 230000006872 improvement Effects 0.000 description 51
- 230000000977 initiatory effect Effects 0.000 description 49
- 210000002569 neuron Anatomy 0.000 description 48
- 238000012358 sourcing Methods 0.000 description 45
- 238000003012 network analysis Methods 0.000 description 43
- 230000036541 health Effects 0.000 description 42
- 238000010276 construction Methods 0.000 description 39
- 238000013135 deep learning Methods 0.000 description 36
- 230000002776 aggregation Effects 0.000 description 34
- 238000004220 aggregation Methods 0.000 description 34
- 230000002452 interceptive effect Effects 0.000 description 33
- 230000000306 recurrent effect Effects 0.000 description 32
- 238000004088 simulation Methods 0.000 description 32
- 238000007637 random forest analysis Methods 0.000 description 31
- 238000005295 random walk Methods 0.000 description 31
- 230000004308 accommodation Effects 0.000 description 29
- 230000000875 corresponding effect Effects 0.000 description 29
- 102000037983 regulatory factors Human genes 0.000 description 28
- 108091008025 regulatory factors Proteins 0.000 description 28
- 230000004048 modification Effects 0.000 description 27
- 238000012986 modification Methods 0.000 description 27
- 238000013145 classification model Methods 0.000 description 26
- 238000012546 transfer Methods 0.000 description 25
- 230000007613 environmental effect Effects 0.000 description 24
- 238000012423 maintenance Methods 0.000 description 24
- 239000013598 vector Substances 0.000 description 24
- 238000004519 manufacturing process Methods 0.000 description 23
- 230000006855 networking Effects 0.000 description 22
- 230000002860 competitive effect Effects 0.000 description 19
- 238000009826 distribution Methods 0.000 description 18
- 238000011156 evaluation Methods 0.000 description 18
- 238000007689 inspection Methods 0.000 description 18
- 230000008520 organization Effects 0.000 description 18
- 230000003542 behavioural effect Effects 0.000 description 17
- 238000007596 consolidation process Methods 0.000 description 17
- 230000008521 reorganization Effects 0.000 description 17
- 230000004913 activation Effects 0.000 description 16
- 238000001994 activation Methods 0.000 description 16
- 238000007792 addition Methods 0.000 description 13
- 230000002068 genetic effect Effects 0.000 description 13
- 230000001960 triggered effect Effects 0.000 description 12
- 230000007547 defect Effects 0.000 description 11
- 230000004931 aggregating effect Effects 0.000 description 10
- 230000003466 anti-cipated effect Effects 0.000 description 10
- 230000005540 biological transmission Effects 0.000 description 10
- 230000008093 supporting effect Effects 0.000 description 10
- 238000012550 audit Methods 0.000 description 9
- PICOTJKHYPEGGN-UHFFFAOYSA-N 4-[nitroso(prop-2-enyl)amino]butanoic acid Chemical compound OC(=O)CCCN(N=O)CC=C PICOTJKHYPEGGN-UHFFFAOYSA-N 0.000 description 8
- 210000004027 cell Anatomy 0.000 description 8
- 230000006378 damage Effects 0.000 description 8
- 238000011161 development Methods 0.000 description 8
- 230000018109 developmental process Effects 0.000 description 8
- 238000005067 remediation Methods 0.000 description 8
- 230000002457 bidirectional effect Effects 0.000 description 7
- 238000012797 qualification Methods 0.000 description 7
- 238000006467 substitution reaction Methods 0.000 description 7
- 238000012706 support-vector machine Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 238000011049 filling Methods 0.000 description 6
- 230000001976 improved effect Effects 0.000 description 6
- 238000013507 mapping Methods 0.000 description 6
- 230000003278 mimic effect Effects 0.000 description 6
- 238000007670 refining Methods 0.000 description 6
- 230000007704 transition Effects 0.000 description 6
- 238000010200 validation analysis Methods 0.000 description 6
- 230000001133 acceleration Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000002349 favourable effect Effects 0.000 description 5
- 238000007667 floating Methods 0.000 description 5
- 239000000203 mixture Substances 0.000 description 5
- 230000001537 neural effect Effects 0.000 description 5
- 230000036961 partial effect Effects 0.000 description 5
- 230000000737 periodic effect Effects 0.000 description 5
- 238000010248 power generation Methods 0.000 description 5
- 230000002265 prevention Effects 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 239000013589 supplement Substances 0.000 description 5
- 239000000725 suspension Substances 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 230000006978 adaptation Effects 0.000 description 4
- 230000003592 biomimetic effect Effects 0.000 description 4
- 210000002364 input neuron Anatomy 0.000 description 4
- 238000003064 k means clustering Methods 0.000 description 4
- 239000003550 marker Substances 0.000 description 4
- 230000001737 promoting effect Effects 0.000 description 4
- 230000001953 sensory effect Effects 0.000 description 4
- 101150110932 US19 gene Proteins 0.000 description 3
- 238000010835 comparative analysis Methods 0.000 description 3
- 230000003111 delayed effect Effects 0.000 description 3
- 238000005265 energy consumption Methods 0.000 description 3
- 238000002599 functional magnetic resonance imaging Methods 0.000 description 3
- 208000014674 injury Diseases 0.000 description 3
- 239000007788 liquid Substances 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 239000002184 metal Substances 0.000 description 3
- 229910052751 metal Inorganic materials 0.000 description 3
- 238000003058 natural language processing Methods 0.000 description 3
- 238000002610 neuroimaging Methods 0.000 description 3
- 238000013439 planning Methods 0.000 description 3
- 238000006116 polymerization reaction Methods 0.000 description 3
- 238000013139 quantization Methods 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 238000012421 spiking Methods 0.000 description 3
- 238000013530 stochastic neural network Methods 0.000 description 3
- 238000012800 visualization Methods 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 238000006424 Flood reaction Methods 0.000 description 2
- 241000282412 Homo Species 0.000 description 2
- 238000012896 Statistical algorithm Methods 0.000 description 2
- 241000700605 Viruses Species 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 2
- 238000012152 algorithmic method Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 238000013474 audit trail Methods 0.000 description 2
- 238000013398 bayesian method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008827 biological function Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 239000002775 capsule Substances 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 239000007795 chemical reaction product Substances 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 230000001149 cognitive effect Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000002591 computed tomography Methods 0.000 description 2
- 238000013479 data entry Methods 0.000 description 2
- 230000034994 death Effects 0.000 description 2
- 230000001934 delay Effects 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000005315 distribution function Methods 0.000 description 2
- 238000005553 drilling Methods 0.000 description 2
- 238000000537 electroencephalography Methods 0.000 description 2
- 238000004146 energy storage Methods 0.000 description 2
- 238000003920 environmental process Methods 0.000 description 2
- 230000004424 eye movement Effects 0.000 description 2
- 239000012530 fluid Substances 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 230000001939 inductive effect Effects 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 229910052500 inorganic mineral Inorganic materials 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000005304 joining Methods 0.000 description 2
- 238000012886 linear function Methods 0.000 description 2
- 238000011068 loading method Methods 0.000 description 2
- 150000002739 metals Chemical class 0.000 description 2
- 230000005012 migration Effects 0.000 description 2
- 238000013508 migration Methods 0.000 description 2
- 239000011707 mineral Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 210000004205 output neuron Anatomy 0.000 description 2
- 230000002085 persistent effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 230000000246 remedial effect Effects 0.000 description 2
- 230000010076 replication Effects 0.000 description 2
- 230000003362 replicative effect Effects 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 239000000779 smoke Substances 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000013179 statistical model Methods 0.000 description 2
- 230000036962 time dependent Effects 0.000 description 2
- 210000000857 visual cortex Anatomy 0.000 description 2
- 206010000372 Accident at work Diseases 0.000 description 1
- 208000012260 Accidental injury Diseases 0.000 description 1
- 241000083700 Ambystoma tigrinum virus Species 0.000 description 1
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 1
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 1
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 1
- 230000005355 Hall effect Effects 0.000 description 1
- CBENFWSGALASAD-UHFFFAOYSA-N Ozone Chemical compound [O-][O+]=O CBENFWSGALASAD-UHFFFAOYSA-N 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000000137 annealing Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000002567 autonomic effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 239000000090 biomarker Substances 0.000 description 1
- 229910021418 black silicon Inorganic materials 0.000 description 1
- 230000003925 brain function Effects 0.000 description 1
- 235000021152 breakfast Nutrition 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 229910002091 carbon monoxide Inorganic materials 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000001010 compromised effect Effects 0.000 description 1
- 238000010205 computational analysis Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013502 data validation Methods 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 230000009849 deactivation Effects 0.000 description 1
- 230000006837 decompression Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 230000010006 flight Effects 0.000 description 1
- 125000000524 functional group Chemical group 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000008103 glucose Substances 0.000 description 1
- 230000013632 homeostatic process Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 229910001349 ledeburite Inorganic materials 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 230000000116 mitigating effect Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000004220 muscle function Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 230000037081 physical activity Effects 0.000 description 1
- 230000003334 potential effect Effects 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 238000013442 quality metrics Methods 0.000 description 1
- 238000012857 repacking Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000004043 responsiveness Effects 0.000 description 1
- 230000002207 retinal effect Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000009919 sequestration Effects 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 230000003319 supportive effect Effects 0.000 description 1
- 230000008685 targeting Effects 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/405—Establishing or using transaction specific rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0208—Trade or exchange of goods or services in exchange for incentives or rewards
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0215—Including financial accounts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0278—Product appraisal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
- H04L9/3236—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using cryptographic hash functions
- H04L9/3239—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using cryptographic hash functions involving non-keyed hash functions, e.g. modification detection codes [MDCs], MD5, SHA or RIPEMD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L2209/00—Additional information or applications relating to cryptographic mechanisms or cryptographic arrangements for secret or secure communication H04L9/00
- H04L2209/56—Financial cryptography, e.g. electronic payment or e-cash
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/50—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols using hash chains, e.g. blockchains or hash trees
Abstract
A system includes an opportunity mining module configured to receive input regarding attributes of a task or a domain, and process the input to determine whether an artificial intelligence system can be applied to the task or the domain; an artificial intelligence search engine configured to receive the input and to perform a search of an artificial intelligence memory of a plurality of domain-specific and general artificial intelligence models and model components using the input and at least one selection criterion to identify at least one of an artificial intelligence model or model component to be applied to the task or the domain; an artificial intelligence configuration module configured to configure one or more data inputs for the at least one artificial intelligence model or model component.
Description
Cross-referencing
The priority of U.S. patent application serial No. 16/780,519 (attorney docket SFTX-0012-U01), entitled "adaptive intelligent and shared infrastructure loan transaction support platform responsive to crowdsourcing information", filed 3/2/2020, is claimed and is a continuation-in-part hereof.
U.S. patent application No. 16/780,519 (attorney docket No. SFTX-0012-U01) claims the benefit of priority of PCT application No. PCT/US19/58647 (attorney docket No. SFTX-0009-WO) entitled "adaptive intelligence and shared infrastructure loan transaction support platform" filed on 29/10 in 2019 and is a continuation-in-part hereof.
PCT application Ser. No. PCT/US19/58647 (attorney docket No. SFTX-0009-WO) claims benefit of priority from the following U.S. provisional patent applications: U.S. provisional patent application No. 62/751,713 (attorney docket No. SFTX-0003-P01), entitled "method and system for improving machines and systems for automatically performing distributed ledger and other transactions in spot and forward markets for energy, computing, storage, and other resources", filed on 29/10.2018; U.S. provisional patent application serial No. 62/843,992 (attorney docket No. SFFX-0005-P01), entitled "adaptive intelligent and shared infrastructure loan transaction support platform with robotic process architecture" filed 5/6/2019; U.S. provisional patent application serial No. 62/818,100 (attorney docket No. SFTX-0006-P01), entitled "robotic process automation architecture, system, and method in a trading environment" filed 3/13/2019; U.S. provisional patent application No. 62/843,455 (attorney docket No. SFTX-0007-P01), entitled "adaptive intelligent and shared infrastructure loan transaction support platform employing robotic process architecture", filed 5/2019; and U.S. provisional patent application serial No. 62/843,456 (attorney docket No. SFTX-0008-P01), entitled "adaptive intelligent and shared infrastructure loan transaction support platform employing robotic process architecture" filed 5/2019.
PCT application No. PCT/US19/58647 also claims the benefit of priority of PCT application No. PC/US2019/030934 filed on 6.5.2019, entitled "method and system for improving machines and systems for automatically performing distributed ledger and other transactions in spot and forward markets for energy, computing, storage, and other resources" (attorney docket No. SFTX-0004-WO) and is a continuation-in-part thereof.
U.S. patent application No. 16/780,519 (attorney docket No. SFTX-0012-U01) claims the benefit of priority of PCT application No. PCT/US2019/030934 (attorney docket No. SFTX-0004-WO) entitled "method and system for improving machines and systems for automatically performing distributed ledger and other transactions in spot and forward markets for energy, computing, storage, and other resources", filed on 6.5.2019, and filed on a continuing part thereof.
PCT application No. PCT/US2019/030934 (attorney docket No. SFTX-0004-WO) claims benefit of priority to the following U.S. provisional patent applications: U.S. provisional patent application serial No. 62/787,206 (attorney docket No. SFTX-0001-P01), entitled "method and system for improving machines and systems for automatically performing distributed ledger and other transactions in spot and forward markets for energy, computing, storage, and other resources", filed on 2018, 12/31; U.S. provisional patent application serial No. 62/667,550 (attorney docket No. SFTX-0002-P01), entitled "method and system for improving machines and systems for automatically performing distributed ledger and other transactions in spot and forward markets for energy, computing, storage, and other resources", filed 5/6/2018; and U.S. provisional patent application serial No. 62/751,713 (attorney docket No. SFTX-0003-P01), entitled "method and system for improving machines and systems for automatically performing distributed ledger and other transactions in spot and forward markets for energy, computing, storage, and other resources," filed 2018, 10, 29.
This application also claims priority from the following U.S. provisional patent applications: U.S. provisional patent application serial No. 63/127,980 (attorney docket No. SFTX-0016-P01), entitled "market coordination system for facilitating electronic market trading" filed 12, 18, 2020; U.S. provisional patent application serial No. 63/069,542 (attorney docket No. SFTX-0015-P01), entitled "system and method for trading artificial intelligence information technology with digital twin" filed 24/8/2020; and U.S. provisional patent application serial No. 62/994,581 (attorney docket No. SFTX-0014-P01), entitled "compliance system to promote personality rights approval," filed 3, 25, 2020.
The above applications are each incorporated herein by reference in their entirety.
Background
Technical Field. The present application relates to the field of lending and, more particularly, to the field of adaptive intelligent systems for effecting lending transactions.
Description of the Related Art. Loan transactions provide financing for housing and various needs of education to corporate and government projects,while enabling the borrower to obtain financial benefits. However, loan transactions suffer from a number of problems, including opacity and asymmetry of the information, ethical risks due to transfer of consequences of risk or inappropriate behavior, complexity of the application and negotiation process, heavy regulatory and policy regimes, difficulty in determining the value of the property being used as collateral or liability warranty, difficulty in determining the reliability or financial health of the entity, and so forth. There is a need for a lending system that addresses these and other problems with lending transactions and environments.
Disclosure of Invention
A loan transaction support platform is provided having a set of data integration microservices including data collection and monitoring services, blockchain services, and intelligent contract services for processing loan entities and transactions. The platform enables a wide range of proprietary solutions that can share data collection and storage infrastructure and can share or exchange inputs, events, activities and outputs to enhance learning, automate and enable adaptive intelligence among various solutions.
In an embodiment, a lending platform is provided having an internet of things and a sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing ownership of a set of collateral and at least one of a set of events associated with the set of collateral.
In an embodiment, a lending platform is provided having an intelligent contract system that automatically adjusts the interest rate of a loan based on information collected via at least one of an internet of things system, a crowd-sourcing system, a set of social network analysis services, and a set of data collection and monitoring services.
In an embodiment, a lending platform is provided having a crowdsourcing system for obtaining information regarding at least one of a status of a set of collateral for a loan and a status of an entity associated with a guarantee of the loan.
In an embodiment, a lending platform is provided having an intelligent contract that automatically adjusts the interest rate of a loan based on at least one of regulatory factors and market factors of a particular jurisdiction.
In an embodiment, a lending platform is provided having an intelligent contract that automatically reorganizes debts based on monitored conditions.
In an embodiment, a loan platform is provided having a social network monitoring system for verifying the reliability of a loan guarantee.
In an embodiment, a lending platform is provided having an internet of things data collection and monitoring system for verifying the reliability of a loan guarantee.
In an embodiment, a lending platform is provided having a robotic process automation system for negotiating a set of terms and conditions for a loan.
In an embodiment, a loan platform is provided having a robotic process automation system for loan payment.
In an embodiment, a lending platform is provided having a robotic process automation system for consolidating a set of loans.
In an embodiment, a lending platform is provided having a robotic process automation system for managing warranty loans.
In an embodiment, a lending platform is provided having a robotic process automation system for brokering mortgage loans.
In an embodiment, a lending platform is provided having a crowd sourcing and automatic classification system for verifying the condition of a bond issuer.
In an embodiment, a lending platform is provided having a social network monitoring system employing artificial intelligence for classifying conditions about bonds.
In an embodiment, a lending platform is provided having an internet of things data collection and monitoring system employing artificial intelligence for classifying conditions about bonds.
In an embodiment, a lending platform is provided having a system that changes terms and conditions of subsidized loans based on internet of things (IoT) monitored parameters.
In an embodiment, a lending platform is provided having a system that varies terms and conditions of a subsidized loan based on parameters monitored in a social network.
In an embodiment, a lending platform is provided having a system for altering terms and conditions of a subsidized loan based on parameters monitored by crowdsourcing.
In an embodiment, a loan platform is provided having an automated blockchain retention service for managing a set of retained assets.
In an embodiment, a lending platform is provided with a loan underwriting system having a set of data integration microservices including data collection and monitoring services, blockchain services, artificial intelligence services, and intelligent contract services for underwriting lending entities and transactions.
In an embodiment, a loan platform is provided having a loan marketing system with a set of data integration microservices including data collection and monitoring services, block chain services, artificial intelligence services, and intelligent contract services for marketing loans to a set of potential parties.
In an embodiment, a loan platform is provided having a rating system with a set of data integration microservices including data collection and monitoring services, blockchain services, artificial intelligence services, and intelligent contract services for rating a set of loan-related entities.
In an embodiment, a lending platform is provided having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies applicable to lending transactions.
One aspect of the present disclosure is directed to a method for electronically facilitating licensing one or more personalities of a licensor. The method may include receiving an access request from a licensee to obtain approval of the license personality from a set of available licensees. The method may include selectively granting access to a licensee based on the access request. The method may include receiving a deposit confirmation of the amount of funds from the licensee. The method may include issuing an amount of cryptocurrency corresponding to the amount of funds deposited by the licensee to an account of the licensee. The method may include receiving a smart contract request to create a smart contract that manages licensing of one or more personalities of a licensee by a licensee. The smart contract request may indicate one or more terms including a bid amount of cryptocurrency to be paid to the licensor in exchange for one or more obligations of the licensor. The method may include generating an intelligent contract based on the intelligent contract request. The method may include escrowing the cryptocurrency counter amount from an account of the licensee. The method may include deploying an intelligent contract to a distributed ledger. The method may include verifying, by the smart contract, that the licensor has fulfilled the one or more obligations. The method may include releasing at least a portion of the cryptocurrency bid amount into a licensor account of the licensor in response to receiving verification that the licensor has fulfilled the one or more obligations. The method may include outputting a record to the distributed ledger indicating that the approval transaction defined by the smart contract has been completed.
In some embodiments of the method, the intelligent contracts may be generated using intelligent contract templates provided by interested third parties.
In some embodiments of the method, the third party of interest may be one of a university, a sports team, or a university sports management organization.
In some embodiments of the method, the distributed ledger can be audited by a set of third parties (including interested third parties).
In some embodiments of the method, the cryptocurrency may be one of bitcoin, ethercoin, ledeburite coin, and rembo coin.
In some embodiments of the method, the cryptocurrency may be a proprietary cryptocurrency.
In some embodiments of the method, the cryptocurrency may be hooked up to a particular type of real currency.
In some embodiments of the method, the distributed ledger may be a public ledger.
In some embodiments of the method, the distributed ledger can be a specialized ledger that is only kept on computing devices associated with third parties of interest.
In some embodiments of the method, the distributed ledger can be a blockchain.
In some embodiments of the method, verifying that the licensor may have fulfilled the one or more obligations comprises receiving location data from a wearable device associated with the licensor. In some embodiments of the method, verifying that the licensor has possibly fulfilled the one or more obligations comprises verifying that the licensor has fulfilled the one or more obligations based on the location data.
In some embodiments of the method, verifying that the licensor may have fulfilled the one or more obligations comprises receiving social media data from a social media website. In some embodiments of the method, verifying that the licensor has possibly fulfilled the one or more obligations comprises verifying that the licensor has performed the one or more obligations based on social media data.
In some embodiments of the method, verifying that the licensor may have fulfilled the one or more obligations includes receiving the media content from an external data source. In some embodiments of the method, verifying that the licensor has possibly fulfilled the one or more obligations comprises verifying that the licensor has performed the one or more obligations based on the media content.
In some embodiments of the method, the media content may be one of a video recording, a photograph, or an audio recording.
In some embodiments of the method, selectively granting access to the licensor may include receiving a set of affiliations of the licensee. In some embodiments of the method, selectively granting access to the licensor may include verifying that the licensee is allowed to associate with a set of licensees, including the licensee, based on the set of dependencies. In some embodiments of the method, selectively granting access to the licensor may include approving the licensee to associate with the set of licensees in response to verifying that the licensee is allowed to associate with the set of licensees.
In some embodiments of the method, the set of affiliations of the licensee may include an organization to which the licensee belongs or an organization donated to or owned by a party associated with the licensee.
In some embodiments of the method, releasing at least a portion of the cryptocurrency consideration amount into the licensee account of the licensee may include identifying an assigned smart contract associated with the licensee. In some embodiments of the method, the distribution intelligence contract may define distribution rules governing the manner in which funds resulting from the licensing of one or more personalities are to be distributed between the licensor and one or more additional entities. In some embodiments of the method, releasing at least a portion of the cryptocurrency counter amount into the licensee account of the licensee may include allocating the counter amount of the cryptocurrency according to allocation rules.
In some embodiments of the method, the additional entity may include one or more of a teammate of the licensing party, a coach of the licensing party, a team of the licensing party, a university of the licensee, and an NCAA.
In some embodiments of the method, it may include obtaining a set of records from the distributed ledger indicating that a set of respective transactions has been completed. In some embodiments of the method, the set of records may include a record indicating that the transaction defined by the smart contract was completed. In some embodiments of the method, it may include determining whether an organization associated with the licensor may violate one or more regulations based on the set of records and the fraud detection model.
In some embodiments of the method, the fraud detection model may be trained using training data indicative of transactions allowed and fraudulent transactions.
Another aspect of the invention relates to a system for electronically facilitating licensing of one or more personal rights of a licensor. The system may include one or more hardware processors configured by machine-readable instructions. The one or more processors may be configured to receive an access request from a licensee to obtain approval of a license personality from a set of available licensees. The one or more processors may be configured to selectively grant access to a licensee based on an access request. The one or more processors may be operable to receive a deposit confirmation of the amount of funds from the licensee. The one or more processors may be operable to issue to an account of the licensee an amount of cryptocurrency corresponding to an amount of funds deposited by the licensee. The one or more processors may be configured to receive an intelligent contract request to create an intelligent contract that manages licensing of one or more personalities of a licensee by a licensee. The smart contract request may indicate one or more terms including a bid amount of cryptocurrency to be paid to the licensor in exchange for one or more obligations of the licensor. The one or more processors may be configured to generate an intelligent contract based on the intelligent contract request. The one or more processors may be operable to escrow a cryptocurrency counter amount from an account of a licensee. The one or more processors may be configured to deploy the smart contract to the distributed ledger. The one or more processors may be operable to verify, via the smart contract, that the licensor has fulfilled the one or more obligations. The one or more processors may be operative to release at least a portion of the cryptocurrency bid amount into a licensor account of the licensor in response to receiving verification that the licensor has fulfilled the one or more obligations. The one or more processors may be configured to output a record to the distributed ledger indicating that the permit transaction defined by the smart contract has been completed.
Drawings
FIG. 1 depicts the components and interactions of an embodiment of a lending platform having a set of data integration microservices including data collection and monitoring services for processing lending entities and transactions.
FIG. 2 depicts the components and interactions of an embodiment of a lending platform in which a set of lending solutions are supported by a set of data-integrated data collection and monitoring services, an adaptive intelligence system, and a data storage system.
FIG. 3 depicts the components and interactions of an embodiment of a lending platform having a set of data integration blockchain services, intelligent contract services, social network analysis services, crowd-sourced resources services, and Internet of things data collection and monitoring services for collecting, monitoring, and processing information about entities involved in or related to lending transactions.
FIG. 4 depicts the components and interactions of a lending platform having an Internet of things and a sensor platform for monitoring at least one of a set of assets, a set of collateral and a collateral for a loan, a bond or a debt transaction.
FIG. 5 depicts the components and interactions of a lending platform having a crowd sourcing system for collecting information related to entities involved in lending transactions.
Fig. 6 depicts an embodiment of a crowdsourcing workflow enabled by a lending platform.
Fig. 7 depicts the components and interactions of an embodiment of a lending platform having an intelligent contract system that automatically adjusts the interest rate of a loan based on information collected via at least one of an internet of things system, a crowd sourcing system, a set of social network analysis services, and a set of data collection and monitoring services.
Figure 8 depicts the components and interactions of an embodiment of a lending platform having intelligent contracts that automatically reorganize debts based on monitored conditions.
FIG. 9 depicts the components and interactions of a lending platform having a set of data collection and monitoring systems for verifying the reliability of a loan guarantee, including an Internet of things system and a social network analysis system.
FIG. 10 depicts the components and interactions of a lending platform having a robotic process automation system for negotiating a set of terms and conditions for a loan.
FIG. 11 depicts the components and interactions of a lending platform having a robotic process automation system for loan collection.
FIG. 12 depicts the components and interactions of a lending platform having a robotic process automation system for consolidating a set of loans.
FIG. 13 depicts the components and interactions of a lending platform having a robotic process automation system for managing warranty loans.
FIG. 14 depicts the components and interactions of a lending platform having a robotic process automation system for brokering mortgage loans.
Fig. 15 depicts the components and interactions of a lending platform having a crowd sourcing and automatic classification system for verifying the condition of a bond issuer, a social network monitoring system employing artificial intelligence for classifying the condition about bonds, and an internet of things data collection and monitoring system employing artificial intelligence for classifying the condition about bonds.
Fig. 16 describes the components and interactions of a lending platform having a system that manages the terms and conditions of a loan based on parameters monitored by the IoT, parameters determined by a social network analytics system, or parameters determined by a crowdsourcing system.
FIG. 17 depicts the components and interactions of a lending platform with an automated blockchain retention service for managing a set of retention assets.
FIG. 18 depicts the components and interactions of a lending platform having a loan underwriting system with a set of data integration microservices including data collection and monitoring services, blockchain services, artificial intelligence services, and intelligent contract services for underwriting lending entities and transactions.
FIG. 19 depicts the components and interactions of a loan platform having a loan marketing system with a set of data integration microservices including data collection and monitoring services, block chain services, artificial intelligence services, and intelligent contract services for marketing loans to a set of potential parties.
FIG. 20 depicts the components and interactions of a lending platform having a rating system with a set of data integration microservices including data collection and monitoring services, block chain services, artificial intelligence services, and intelligent contract services for rating a set of loan-related entities.
FIG. 21 depicts the components and interactions of a lending platform having a compliance system with a set of data integration microservices including data collection and monitoring services, blockchain services, artificial intelligence services, and intelligent contract services for automatically facilitating compliance with at least one of laws, regulations, and policies applicable to lending transactions.
Fig. 22-49 are schematic diagrams of embodiments of a neural network system connectable to, integrated in, and accessible by a platform for implementing intelligent transactions, including systems involving expert systems, ad hoc, machine learning, and artificial intelligence, and including neural network systems trained for pattern recognition, for classification of one or more parameters, characteristics, or phenomena, for supporting autonomous control, and other purposes, in accordance with embodiments of the present disclosure.
FIG. 50 depicts the general components and interactions of a lending platform.
FIG. 51 depicts the components and interactions of a lending platform that utilizes entity data to identify lending events and initiate automated loan actions.
Fig. 52 depicts a method of processing entity data to initiate an automated loan action.
FIG. 53 illustrates the components and interactions of a lending platform to value and determine the condition of a collateral.
Fig. 54 depicts a method of processing collateral data to determine the condition of the collateral and in response initiate a loan action.
FIG. 55 illustrates the components and interactions of the lending platform.
FIG. 56 illustrates a method of the lending platform.
FIG. 57 depicts the components and interactions of a lending platform that recognizes collateral events and initiates automated actions in response.
FIG. 58 illustrates a method for a lending platform to automatically initiate a loan action in response to a mortgage event.
FIG. 59 illustrates the components and interactions of the lending platform.
FIG. 60 illustrates a method of the lending platform.
FIG. 61 illustrates the components and interactions of the lending platform.
FIG. 62 illustrates a method of the lending platform.
FIG. 63 illustrates the components and interactions of the lending platform.
FIG. 64 illustrates a method of the lending platform.
FIG. 65 illustrates the components and interactions of the lending platform.
FIG. 66 illustrates a method of the lending platform.
FIG. 67 illustrates the components and interactions of the lending platform.
FIG. 68 illustrates a method of the lending platform.
FIG. 69 illustrates the components and interactions of the lending platform.
FIG. 70 illustrates a method of the lending platform.
FIG. 71 illustrates the components and interactions of the lending platform.
FIG. 72 illustrates a method of the lending platform.
FIG. 73 illustrates the components and interactions of the lending platform.
FIG. 74 illustrates a method of the lending platform.
FIG. 75 illustrates the components and interactions of the lending platform.
FIG. 76 illustrates a method of the lending platform.
FIG. 77 illustrates the components and interactions of the lending platform.
FIG. 78 illustrates a method of the lending platform.
FIG. 79 illustrates the components and interactions of the lending platform.
FIG. 80 illustrates a method of the lending platform.
FIG. 81 illustrates the components and interactions of the lending platform.
FIG. 82 illustrates a method of the lending platform.
FIG. 83 illustrates the components and interactions of the lending platform.
FIG. 84 illustrates a method of the lending platform.
FIG. 85 illustrates the components and interactions of the lending platform.
FIG. 86 illustrates a method of the lending platform.
FIG. 87 illustrates the components and interactions of the lending platform.
FIG. 88 illustrates a method of the lending platform.
FIG. 89 illustrates the components and interactions of the lending platform.
FIG. 90 illustrates a method of the lending platform.
FIG. 91 illustrates the components and interactions of the lending platform.
FIG. 92 illustrates a method of the lending platform.
FIG. 93 illustrates the components and interactions of the lending platform.
FIG. 94 illustrates a method of the lending platform.
FIG. 95 illustrates the components and interactions of the lending platform.
FIG. 96 illustrates a method of the lending platform.
FIG. 97 illustrates the components and interactions of the lending platform.
FIG. 98 illustrates a method of the lending platform.
FIG. 99 illustrates the components and interactions of the lending platform.
Fig. 100 illustrates a methodology of the lending platform.
FIG. 101 illustrates the components and interactions of the lending platform.
FIG. 102 illustrates a method of the lending platform.
FIG. 103 illustrates the components and interactions of the lending platform.
FIG. 104 illustrates a method of the lending platform.
FIG. 105 illustrates the components and interactions of the lending platform.
FIG. 106 illustrates a method of the lending platform.
FIG. 107 illustrates the components and interactions of the lending platform.
FIG. 108 illustrates a method of the lending platform.
FIG. 109 illustrates the components and interactions of the lending platform.
FIG. 110 illustrates a method of the lending platform.
Figure 111 depicts a schematic diagram illustrating an example of a portion of a transaction artificial intelligence information technology system utilizing a digital twin in accordance with some embodiments of the present disclosure.
Figure 112 depicts a schematic diagram that illustrates a compliance system that facilitates licensing of personality rights, according to some embodiments of the present disclosure.
FIG. 113 depicts a schematic diagram that illustrates a set of example components of a compliance system, according to some embodiments of the present disclosure.
Fig. 114 describes a set of operations of a method for reviewing potential licensees for the purpose of licensing the personality rights of the licensor according to some embodiments of the present disclosure.
FIG. 115 describes a set of operations of a method for facilitating licensing of personality rights of a licensee by a licensee in accordance with some embodiments of the present disclosure.
FIG. 116 depicts a set of operations of a method for detecting potential circumvention of a rule or regulation by a licensor and/or licensee in accordance with some embodiments of the present disclosure.
Fig. 117 shows a method for selecting an AI solution.
Fig. 118 shows a method for selecting an AI solution.
Fig. 119 depicts an example of an assembled AI solution.
Fig. 120 illustrates a method for selecting an AI solution.
Fig. 121 shows a method for selecting an AI solution.
Fig. 122 shows an AI solution selection and configuration system.
Fig. 123 shows an AI solution selection and configuration system.
Fig. 124 shows an AI solution selection and configuration system.
Fig. 125 depicts a component configuration circuit.
Fig. 126 shows an AI solution selection and configuration system.
FIG. 127 depicts a system for selecting and configuring artificial intelligence models.
FIG. 128 depicts a method of selecting and configuring an artificial intelligence model.
Detailed Description
The term "service"/"microservice" (and similar terms) as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, a service/microservice includes any system (or platform) for functionally executing service operations, where the system may be a data integration system including data collection circuitry, blockchain circuitry, artificial intelligence circuitry, and/or intelligent contract circuitry for processing lending entities and transactions. Services/microservices may facilitate data processing and may include facilities for data extraction, conversion and loading, data cleansing and deduplication facilities, data normalization facilities; a data synchronization facility; data security facilities, computing facilities (e.g., for performing predefined computing operations on data streams and providing output streams), compression and decompression facilities, analysis facilities (e.g., automated production providing data visualization), data processing facilities, and/or data storage facilities (including storage reservation, formatting, compression, migration, etc.), and the like.
The service/microservice may include controllers, processors, network infrastructure, input/output devices, servers, client devices (e.g., laptops, desktops, terminal devices, mobile devices, and/or application-specific devices), sensors (e.g., ioT sensors associated with one or more entities, devices, and/or collateral), actuators (e.g., auto-locks, notification devices, lights, camera controls, etc.), virtualized versions of any one or more of the above (e.g., outsourced computing resources such as cloud storage, computing operations, etc.; virtual sensors; stock or commodity prices, subscription data that logs awaiting collection), and/or components that serve as computer-readable instructions that, when executed by a processor, cause the processor to perform one or more functions of the service, etc. A service may be distributed across multiple devices and/or the functions of a service may be performed by one or more devices cooperatively performing a given function of the service.
The service/microservice may include application programming interfaces that facilitate connections between system components that perform the service (e.g., microservice) and between the system and entities external to the system (e.g., programs, websites, user devices, etc.). Without being limited to any other aspect of the disclosure, an example microservice that may exist in certain embodiments includes (a) a set of multi-mode data collection circuits that collect information about and monitor entities related to loan transactions; (b) Blockchain circuitry to maintain a security history ledger for events related to the loan, the blockchain circuitry having access control features to manage access by a group of parties involved in the loan; (c) A set of application programming interfaces, data integration services, data processing workflows, and user interfaces for processing loan-related events and loan-related activities; and (d) intelligent contract circuitry for specifying terms and conditions of an intelligent contract governing at least one of loan terms and conditions, loan-related events, and loan-related activities. Any service/microservice may be controlled by or to the controller. Some systems may not be considered services/microservices. For example, a point of sale device that only charges a fixed cost for goods or services may not be a service. In another example, a service that tracks the cost of goods or services and triggers a notification when value changes may not be a rating service itself, but may rely on a rating service, and/or may form part of a rating service in some embodiments. It will be appreciated that in some embodiments a given circuit, controller or device may be a service or part of a service, for example when the functionality or capabilities of the circuit, controller or device are used to support a service or microservice as described herein, but for other embodiments (for example where the functionality or capabilities of the circuit, controller or device are not related to the service or microservice described herein) may not be a service or part of a service. In another example, a mobile device operated by a user may form part of a service described herein at a first point in time (e.g., when the user accesses features of the service through an application or other communication from the mobile device, and/or when a monitoring function is performed via the mobile device), but may not form part of the service at a second point in time (e.g., after a transaction is completed, after the user uninstalls the application, and/or when the monitoring function is stopped and/or passed to another device). Thus, the benefits of the present disclosure may apply to a variety of processes or systems, and any such process or system may be considered a service (or part of a service) herein.
With the benefit of the disclosure herein and understanding of expected systems that are generally available, one of ordinary skill in the art can readily determine which aspects of the present disclosure will benefit a particular system, how to combine the processes and systems in the present disclosure to construct, provide performance characteristics (e.g., bandwidth, computing power, time response, etc.), and/or provide operational capabilities (e.g., check interval times, uptime requirements including vertical (e.g., continuous operating time) and/or sequential (e.g., time of day, calendar time, etc.) including normal runtime), sensing resolution and/or accuracy, data determination (e.g., accuracy, time, data volume), and/or actuator confirmation capabilities) of a service component sufficient to provide a given embodiment of the services, platforms, and/or microservices described herein. In determining the configuration of components, circuits, controllers, and/or devices to implement the services, platforms, and/or microservices (the "services" listed below) described herein, certain considerations by those skilled in the art include, but are not limited to: a balance of capital and operating costs to implement and operate the service; availability, speed, and/or bandwidth of network services available to system components, service users, and/or other entities interacting with the services; response time for service consideration (e.g., how quickly decisions within a service must be performed to support business functions of the service, operating time for various artificial intelligence or other advanced computing operations), and/or capital or operating cost to support a given response time; the location of the service interaction components, and the impact of these locations on service operation (e.g., data storage locations and associated regulatory schemes, network communication limitations and/or costs, cost of electricity as a function of location, availability of support for time zones associated with the service, etc.); the availability of certain sensor types, the associated support for these sensors, and the availability of adequate replacements for sensing purposes (e.g., a camera may require supportive lighting and/or high network bandwidth or local storage); one aspect of the underlying value of one aspect of the service (e.g., principal amount of loan, value of collateral, volatility of collateral value, equity or relative equity of the borrower, guarantor, and/or borrower, etc.), including time sensitivity of the underlying value (e.g., where it changes rapidly or slowly with respect to service operations or loan terms); trust metrics between transaction parties (e.g., performance history between parties, credit rating, social rating, or other external metrics, whether activities related to the transaction meet industry standards or other normalized transaction types, etc.); and/or the availability of cost-recovery options (e.g., subscriptions, fees, service payments, etc.) for a given configuration and/or functionality of a service, platform, and/or microservice. Without being limited to any other aspect of the disclosure, certain operations performed by the service herein include: performing real-time modifications to the loan based on the tracked data; executing a collateral secured intelligent contract using the data; reevaluating the debt transaction in response to the tracked conditions or data, and the like. Although specific examples of services/microservices and considerations are described herein for illustrative purposes, any system that would benefit from the disclosure herein and any consideration understood by one of ordinary skill in the art having the benefit of the disclosure herein is specifically contemplated within the scope of the present disclosure.
Services include, but are not limited to, financial services (e.g., loan transaction services), data collection services (e.g., data collection services for collecting and monitoring data), blockchain services (e.g., blockchain services for maintaining secure data), data integration services (e.g., data integration services for aggregating data), smart contract services (e.g., smart contract services for determining aspects of a smart contract), software services (e.g., software services for extracting data related to entities from public information websites), crowdsourcing services (e.g., crowdsourcing services for requesting and reporting information), internet of things services (e.g., internet of things services for monitoring an environment), publishing services (e.g., publishing services for publishing data), microservices (e.g., having a set of application programming interfaces that facilitate connections between microservices), valuation services (e.g., setting a value of a collateral based on information using a valuation model), artificial intelligence services, market value data collection services (e.g., monitoring and reporting information), financial services (e.g., for grouping collateral items based on attribute similarities), social networking services (e.g., enabling social networking services to perform a set of identity verification and identity verification functions, such as authentication and identity verification of financial institutions, and similar. Example services herein that perform one or more functions include computing devices, servers, networking devices, user interfaces, communication protocols, inter-device interfaces such as shared information and/or information storage and/or Application Programming Interfaces (APIs), sensors (e.g., ioT sensors operatively coupled to monitored components, devices, locations, etc.), distributed ledgers, circuitry, and/or computer readable code for causing a processor to perform one or more functions of a service. One or more aspects or components of the services herein may be distributed across multiple devices and/or may be incorporated in whole or in part on a given device. In embodiments, aspects or components of services herein may be implemented at least in part by circuitry, such as, in a non-limiting example, a data collection service implemented at least in part as data collection circuitry configured to collect and monitor data, a blockchain service implemented at least in part as blockchain circuitry configured to maintain secure data, a data integration service implemented at least in part as data integration circuitry configured to aggregate data, a smart contract service implemented at least in part as smart contract circuitry configured to determine aspects of a smart contract, a software service implemented at least in part as software service configured to extract data related to an entity from a publicly available information website, a crowdsourcing service implemented at least in part as crowdsourcing circuitry configured to request and report information, an internet of things service implemented at least in part as internet of things circuitry configured to monitor an environment, the publication service is implemented at least in part as a publication service circuit configured to publish data, the microservice is implemented at least in part as a microservice circuit configured to interconnect a plurality of service circuits, the valuation service is implemented at least in part as a valuation service circuit configured to access a valuation model to set a value of a collateral based on data, the artificial intelligence service is implemented at least in part as an artificial intelligence service circuit, the market value data collection service is implemented at least in part as a market value data collection service circuit configured to monitor and report market information, the clustering service is implemented at least in part as a clustering service circuit configured to group the collateral based on similarity of attributes, the social networking service is implemented at least in part as a social networking analysis service circuit configured to configure parameters for social networking, the asset identification service is implemented at least in part as asset identification service circuitry for identifying a set of assets that the financial institution is responsible for custody, and the identity management service is implemented at least in part as identity management service circuitry that enables the financial institution to verify identity and credentials, and the like. Thus, the benefits of the present disclosure may apply to a variety of systems, and any such systems may be considered herein as relating to goods and services, while in certain embodiments a given system may not be considered herein as relating to goods and services. Given the disclosure herein and an understanding of commonly available prospective systems, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit from a particular system and/or how to combine the processes and systems of the present disclosure to enhance the operation of a prospective system. Considerations that may be considered by one skilled in the art to determine the configuration of a particular service include: allocation and access devices available to one or more parties to a particular transaction; jurisdiction limitations for storage, entry, and communication of certain types of information; security and authentication requirements or desired aspects of service information communication; the algorithm, machine learning component and/or artificial intelligence component of the service performs information collection, inter-party communication and determined response time; cost considerations for the service, including capital expenditures and operating costs, as well as the parties or entities that will bear the costs and the feasibility of recovering the costs, such as through subscriptions, service fees, etc.; the amount of information stored and/or transmitted to support the service; and/or processing or computing power for supporting the service.
The terms "item" and "service" (and similar terms) as used herein should be construed broadly. Without being limited to any other aspect or description of the present disclosure, the goods and services include any goods and services, including but not limited to: items and services that are used as rewards, as collateral, as co-branded items, etc., such as, but not limited to, applying for warranties or warranties on items that are subject of loan, loan collateral, or the like (e.g., products, services, offers, solutions, physical products, software, service levels, quality of service, financial instruments, debts, collateral, service fulfillment, or other items). Without being limited to any other aspect or description of the disclosure, the goods and services include any goods and services, including but not limited to: articles and services applied to physical objects (e.g., vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, antiques, fixtures, furniture, equipment, tools, machinery, and personal property), financial objects (e.g., commodities, securities, currency, value tokens, tickets, crypto currency), consumables (e.g., edible items, beverages), high-value objects (e.g., precious metals, jewelry ornaments, gemstones), intellectual items (e.g., intellectual property items, intellectual property rights, contractual rights), and the like. Thus, the benefits of the present disclosure may apply to a variety of systems, and any such systems may be considered herein as relating to goods and services, while in certain embodiments a given system may not be considered herein as relating to goods and services. Given the benefit of the disclosure herein and knowing the intended systems that are generally available, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit from a particular system and/or how to combine the processes and systems of the present disclosure to enhance the operation of the intended system.
The terms "agent," "automatic agent," and similar terms as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, an agent or automated agent may process events related to at least one of value, status, and ownership of a collateral or asset. The agent or automated agent may also take actions related to the loan to which the mortgage or asset belongs, the debt transaction, the bond transaction, the subsidy loan, etc., e.g., in response to the processed event. An agent or automated agent may interact with the marketplace to collect data, test spot market transactions, execute transactions, etc., where dynamic system behavior involves complex interactions that a user may wish to understand, predict, control, and/or optimize. Some systems may not be considered proxies or automatic proxies. For example, if only events are collected and not processed, the system may not be a proxy or an automated proxy. In some embodiments, if the loan-related action is not taken in response to the processed event, it may not be taken by an agent or an automated agent. Those skilled in the art, with the benefit of the disclosure herein and understanding of contemplated systems that are generally available, can readily determine which aspects of the present disclosure include and/or benefit from an agent or an automated agent. Some considerations that may be made by one skilled in the art or by embodiments of the present disclosure with respect to agents or automated agents include, but are not limited to: rules that determine when a change in value, status, or ownership of an asset or collateral occurs; and/or rules that determine whether the change warrants further action on the loan or other transaction; and other considerations. Although specific examples of market values and market information are described herein for illustrative purposes, any embodiments that benefit from the disclosure herein, as well as any considerations understood by those skilled in the art to benefit from the disclosure herein, are specifically contemplated within the scope of the present disclosure.
The terms "market information," "market value," and similar terms as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, market information and market value describe the status or value of a property, collateral, food, or service at a defined point in time or time period. Market value may refer to an expected value set for an item in a market or auction environment, or pricing or financial data for items similar to the item, asset, or collateral in at least one public market. For a company, the market value may be the product of its number of circulating shares and the current stock price. The valuation service can include a market value data collection service that monitors and reports market information related to the value (e.g., market value) of a collateral, an issuer, a set of bonds, a set of assets, a set of subsidies, a party, etc. Market values can be dynamic in nature as they depend on a variety of factors, from actual business conditions to economic climate to supply and demand dynamics. The market value may be affected by the following factors, and the market information may include the following factors: proximity to other assets, inventory or supply of assets, demand for assets, source of an item, history of an item, potential current value of a component of an item, bankruptcy status of an entity, redemption status of an entity, contract breach status of an entity, violation status of an entity, criminal status of an entity, export regulation status of an entity, contraband status of an entity, duty status of an entity, tax status of an entity, credit reports of an entity, credit rating of an entity, website rating of an entity, a set of customer reviews of a product of an entity, social network rating of an entity, a set of credentials of an entity, a set of referrals of an entity, a set of proofs of an entity, a set of behaviors of an entity, a location of an entity, and a geographic location of an entity. In some embodiments, market values may include such things as volatility of value, sensitivity of value (e.g., relative to other parameters with associated uncertainty), and/or a particular value of a valuation object for a particular principal (e.g., an item owned by a first principal may be more valuable than an item owned by a second principal).
Some information may not be market information or market value. For example, variables related to value are not market derived, they may be in-use value or investment value. In some embodiments, the investment value may be considered a market value (e.g., when the assessing party intends to use the asset as a post-acquisition investment) rather than a market value in other embodiments (e.g., when the assessing party intends to clear a post-acquisition investment immediately). Those skilled in the art, with the benefit of the disclosure herein and understanding of contemplated systems that are generally available, can readily determine which aspects of the present disclosure would benefit from market information or market value. In determining whether the term "market value" refers to a property, item, collateral, good or service, certain considerations by those skilled in the art include: other similar assets exist in the market, location-dependent value changes, opening prices for items over bid prices, and other considerations. Although specific examples of market values and market information are described herein for illustrative purposes, any embodiments that benefit from the disclosure herein, as well as any considerations understood by those skilled in the art to benefit from the disclosure herein, are specifically contemplated within the scope of the present disclosure.
The term "apportioned value" or "apportioned value" and similar terms as used herein should be broadly construed. Without being limited to any other aspect or description of the disclosure, apportioned value describes the process of apportioning or apportioning value, or dividing and distributing value according to a proportion rule. The value may be apportioned to several parties (e.g., beneficiaries that are each part of the value), to several transactions (e.g., each transaction uses a part of the value), and/or in a many-to-many relationship (e.g., a set of objects has an aggregate value apportioned among multiple parties and/or transactions). In some embodiments, the value may be a net loss and the apportioned value is a liability allocation for each entity. In other embodiments, the value apportioned may refer to allocation or allocation of economic benefits, real estate, mortgage, and the like. In some embodiments, the apportionment may include consideration of value relative to the respective parties-for example, when allocating a $ 1000 ten thousand asset between two parties at 50/50, if two parties have different value considerations for the asset, it may result in one party crediting versus apportioning a different resulting value. In some embodiments, the apportionment may include consideration of value relative to a given transaction-for example, a first type of transaction (e.g., a long-term loan) may have a different valuation of a given property than a second type of transaction (e.g., a short-term line of credit).
Certain conditions or processes may not be associated with the value of the apportionment. For example, the total value of an item may provide its intrinsic value, but may not provide the value held by each identified entity. Given the benefit of the disclosure herein and an appreciation of the value of the apportionment, one of ordinary skill in the art can readily determine which aspects of the present disclosure will benefit from a particular application of the apportioned value. Some considerations of value to the apportionment by those skilled in the art or embodiments of the present disclosure include, but are not limited to: currency of principal amount, type of expected transaction (loan, bond, or debt), particular type of collateral, rate of loan to value, rate of collateral to loan, total transaction/loan amount, principal amount, amount of entity owed, value of collateral, and the like. Although specific examples of apportioned values are described herein for illustrative purposes, any embodiments that benefit from the disclosure herein, as well as any considerations understood by those skilled in the art to benefit from the disclosure herein, are specifically contemplated within the scope of this disclosure.
The term "financial condition" and similar terms as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, the financial condition describes a current state of the asset, liability and equity condition of the entity at a defined point in time or period of time. The financial status may be logged into a financial statement. The financial condition may also include an assessment of the ability of the entity to live or fulfill future or due liabilities in future risk situations. The financial condition may be based on a set of attributes of the entity from among: public valuation of an entity, valuation of a set of properties owned by an entity as indicated by a public record, bankruptcy status of an entity, redemption-up status of an entity, contract default status of an entity, violation status of an entity, criminal status of an entity, export regulation status of an entity, contraband status of an entity, duty status of an entity, tax status of an entity; a credit report of an entity, a credit rating of an entity, a website rating of an entity, a set of customer reviews of a product of an entity, a social network rating of an entity, a set of credentials of an entity, a set of referrals of an entity, a set of proofs of an entity, a set of behaviors of an entity, a location of an entity, and a geographic location of an entity. The financial condition may also describe a requirement or threshold for an agreement or loan. For example, the conditions that allow a developer to continue development may be various certifications and their consent to financial expenditures. That is, the ability of a developer to continue development depends on financial factors and the like. Some conditions may not be financial conditions. For example, a credit card balance may itself be a clue to a financial condition, but may not be the financial condition itself. In another example, a payment plan may determine that a debt may be on a physical asset liability statement, but may not accurately provide financial status. Deadlines will benefit from the disclosure herein and knowing the expected systems that are generally available, one of ordinary skill in the art can readily determine which aspects of the present disclosure include and/or will benefit from financial conditions. In determining whether the term "financial status" refers to the current state of an entity's assets, liabilities, and equity status at defined points in time or periods of time and/or for a given purpose, certain considerations by those skilled in the art include: reports of more than one financial data point, the ratio of loan to collateral value, the ratio of collateral to loan, the total transaction/loan amount, the credit scores of the borrower and lender, and other considerations. Although specific examples of financial situations are described herein for illustrative purposes, any embodiments that benefit from the disclosure herein, as well as any considerations understood by those skilled in the art to benefit from the disclosure herein, are specifically contemplated within the scope of the present disclosure.
The term "interest rate" and similar terms as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, the interest rate includes an amount of interest that expires each time period in proportion to an amount of the loan, deposit, or debit. The total interest in the loan or debit may depend on the principal total, interest rate, frequency of the rebate, and the length of time the loan, deposit or debit is made. Generally, interest rates are expressed in annual percentage, but may be defined for any period of time. The interest rate is related to the amount of money collected for the loan of the bank or other borrower, or to the deposit interest rate paid by the bank or other entity to the depositor. Interest rates may be variable or fixed. For example, interest rates may vary according to special characteristics such as government or other stakeholder instructions, the currency of the principal being borrowed or borrowed, the expiration date of the investment, the perceived default probability of the borrower, market supply and demand, the number of collateral items, economic conditions, or redemption terms. In certain embodiments, the interest rate may be a relative interest rate (e.g., relative to a baseline interest rate, currency expansion index, etc.). In some embodiments, the interest rate may further consider the cost or expense (e.g., "basepoint") of the application of adjusting the interest rate. The nominal interest rate may not be adjusted for inflation of the currency, whereas the actual interest rate should take into account inflation of the currency. Some examples may not be interest rates for the purposes of particular embodiments. For example, a bank account that grows in a fixed dollar amount and/or a fixed fee amount each year may not be an example of an interest rate for some embodiments. Persons of ordinary skill in the art may readily determine the characteristics of interest rates for particular embodiments, given the benefit of the disclosure herein and understanding the interest rate. Some considerations of interest to those skilled in the art or to the presently disclosed embodiments include, but are not limited to: currency of the principal amount, variables used to set the interest rate, criteria used to modify the interest rate, the type of anticipated transaction (loans, bonds, or debts), particular types of collateral, the ratio of loans to value, the ratio of collateral to loans, the total transaction/loan amount, the principal amount, the appropriate terms of the particular industry's transactions and/or collateral, the possibility of the borrower selling and/or merging loans before the terms, and so forth. Although specific examples of interest have been described herein for purposes of illustration, any embodiment that would benefit from the disclosure herein, as well as any consideration understood by one of ordinary skill in the art having the benefit of the disclosure herein, is specifically contemplated within the scope of the present disclosure.
The term "rating service" (and similar terms) as used herein should be construed broadly. Without being limited to any other aspect or description of the present disclosure, a valuation service includes any service that sets the value of a good or service. The valuation service can use a valuation model to set the value of a collateral based on information from the data collection and monitoring service. The intelligent contract service may process the output from a set of valuation services and assign collateral sufficient to provide a loan guarantee and/or to spread the value of the collateral among a set of borrowers and/or transactions. The valuation service can include an artificial intelligence service that can iteratively refine the valuation model based on result data related to the collateral transactions. The valuation service can include a market value data collection service that can monitor and report market information related to the value of a collateral. Some processes may not be considered a rating service. For example, a point of sale device that charges only a fixed cost for goods or services may not be a valuation service. In another example, a service that tracks the cost of goods or services and triggers a notification when value changes may not be a rating service itself, but may rely on and/or form part of a rating service. Thus, the benefits of the present disclosure may be applied to a variety of process systems, and any such process or system may be considered a valuation service herein, while in certain embodiments, a given service may not be considered a valuation service herein. Given the disclosure herein and the knowledge of commonly available prospective systems, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit a particular system and how to combine the processes and systems of the present disclosure to enhance the operation of the prospective system and/or provide valuation services. Certain considerations of those skilled in the art in determining whether a prospective system refers to a valuation service and/or whether aspects of the present disclosure can benefit or enhance the prospective system include, but are not limited to: performing real-time alteration of the loan based on the value of the mortgage; executing a collateral secured intelligent contract using market data; reevaluating the collateral based on the storage conditions or geographic location; the value of the collateral fluctuates, trends to be utilized and/or diverted, etc. Although specific examples of valuation services and considerations are described herein for illustrative purposes, any system that would benefit from the disclosure herein, as well as any considerations understood by those skilled in the art to benefit from the disclosure herein, are specifically contemplated within the scope of the present disclosure.
The term "collateral attribute" (and similar terms) as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, collateral attributes include durability (the ability of the collateral to withstand wear or the useful life of the collateral), value, identification (whether the collateral has positive characteristics for easy identification or marketing), value stability (whether the collateral retains value over time), standardization, grade, quality, marketability, flowability, transferability, availability, traceability, deliverable (the ability of the collateral to be delivered or transferred without a deterioration in value), market transparency (i.e. the collateral value is easy to verify or widely agreed), any identification of entity or virtual. The collateral attributes may be measured in absolute or relative terms, and/or may include qualitative (e.g., categorical) or quantitative descriptions. Collateral properties may vary from industry to industry, products, elements, uses, and the like. The collateral properties may be quantitative or qualitative. The value associated with the collateral attribute may be based on a scale (e.g., 1-10) or relative name (high, low, better, etc.). The collateral may include various components; each component may have collateral properties. Thus, a collateral may have multiple values for the same collateral attribute. In some embodiments, multiple values of a collateral attribute may be combined to generate one value for each attribute. Certain collateral attributes may only apply to certain portions of the collateral. Some collateral attributes, even for a given component of the collateral, may have different values depending on the interested party (e.g., the party values an aspect of the collateral more than another party) and/or depending on the transaction type (e.g., the collateral may be more valuable or appropriate for a first type of loan than for a second type of loan). Certain attributes associated with a collateral may not be collateral attributes described herein, depending on the purpose of the collateral attributes herein. For example, a product may be rated as durable relative to a similar product; however, if the life of a product is well below the term of a particular loan under consideration, the durability of the product may be rated differently (e.g., not durable) or not (e.g., the product's current inventory is used as a collateral and is expected to change over the term of the loan). Thus, the benefits of the present disclosure may apply to a variety of attributes, and any such attributes may be considered herein as collateral attributes, while in certain embodiments, a given attribute may not be considered herein as a collateral attribute. Those skilled in the art, having the benefit of the disclosure herein and knowledge of the expected collateral properties that are generally available, can readily determine which aspects of the disclosure will benefit a particular collateral property. Certain considerations of those skilled in the art in determining whether the desired attribute refers to a collateral attribute and/or whether aspects of the present disclosure may benefit or enhance the desired system include, but are not limited to: sources of attributes and attribute values (e.g., whether attributes and attribute values are from reputable sources), volatility of attributes (e.g., whether attribute values of a collateral fluctuate, whether the attribute is a new attribute of the collateral), relative differences in attribute values of similar collateral, special attribute values (e.g., certain attribute values may be high (e.g., in the 98 th percentile) or very low (e.g., in the 2 nd percentile) compared to similar categories of collateral), substitutability of collateral, transaction types related to collateral, and/or the purpose of using collateral for a particular party or transaction. Although specific examples of collateral properties and considerations are described herein for illustrative purposes, any system that would benefit from the disclosure herein, as well as any considerations understood by one of ordinary skill in the art having the benefit of the disclosure herein, are specifically contemplated within the scope of the present disclosure.
The term "blockchain service" (and similar terms) as used herein should be broadly understood. Without being limited to any other aspect or description of the disclosure, blockchain services include any service related to the processing, recording, and/or updating of blockchains, and may include services for processing blocks, computing hash values, generating new blocks in blockchains, appending blocks to blockchains, creating splits in blockchains, merging splits in blockchains, verifying previous computations, updating shared ledgers, updating distributed ledgers, generating encryption keys, verifying transactions, maintaining blockchains, updating blockchains, verifying blockchains, generating random numbers. These services may be performed by executing computer-readable instructions on a local computer and/or by a remote server and computer. Some services may not be considered blockchain services alone, but may be based on the end use of the service and/or considered blockchain services in particular embodiments-e.g., hash value calculations may be performed in contexts outside of the blockchain (e.g., in the context of secure communications). Some initial services may be invoked without first applying to the blockchain, but further actions or services in conjunction with the initial services may associate the initial services with aspects of the blockchain. For example, random numbers may be generated periodically and stored in memory; these random numbers may not have been originally generated for blockchain purposes, but may be used for blockchains. Thus, the benefits of the present disclosure may apply to a variety of services, and any such service may be considered herein as a blockchain service, while in certain embodiments a given service may not be considered herein as a blockchain service. Persons of ordinary skill in the art, with the benefit of the disclosure herein and with knowledge of the expected blockchain services that are generally available, can readily determine which aspects of the present disclosure may be used to implement and/or will benefit a particular blockchain service. Certain considerations of those skilled in the art in determining whether a prospective service refers to a blockchain service and/or whether aspects of the present disclosure may benefit or enhance a prospective system include, but are not limited to: the application of the service, the source of the service (e.g., if the service is associated with a known or verifiable blockchain service provider), the responsiveness of the service (e.g., certain blockchain services may have an expected completion time, and/or may be determined by utilization), the cost of the service, the amount of data requested for the service, and/or the amount of data generated by the service (the blocks of the blockchain or the keys associated with the blockchain may be of a particular size or a particular size range). Although specific examples of blockchain services and considerations are described herein for illustrative purposes, any system that would benefit from the disclosure herein and any considerations understood by one of ordinary skill in the art having the benefit of the disclosure herein are specifically contemplated within the scope of the present disclosure.
The term "blockchain" (and variations such as cryptocurrency ledgers) as used herein may be broadly construed as a cryptocurrency ledger that describes recording, managing, or otherwise processing online transactions. The blockchain may be public, proprietary, or a combination thereof, but is not limited thereto. The blockchain may also be used to represent a set of digital transactions, agreements, terms, or other digital values. Without being limited to any other aspect or description of the present disclosure, in the former case, the blockchain may also be used in conjunction with investment applications, token transaction applications, and/or digital/cryptocurrency based markets. Blockchains may also be associated with providing value, such as providing goods, services, goods, fees, access to restricted areas or events, data, or other valuable benefits. Various forms of blockchains may be included in discussing units of value, collateral, currency, cryptocurrency, or any other form of value. The value symbolized or represented by a blockchain can be readily determined by one of ordinary skill in the art, given the benefit of the disclosure herein and knowing the expected systems that are generally available. Although specific examples of blockchains are described herein for illustrative purposes, any embodiments that benefit from the disclosure herein, as well as any considerations understood by those skilled in the art to benefit from the disclosure herein, are specifically contemplated within the scope of the present disclosure.
The terms "ledger" and "distributed ledger" (and similar terms) as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, a ledger may be a document, file, computer file, database, book, etc. that maintains a record of transactions. Ledgers can be physical or digital. Ledgers may include records related to sales, accounts, purchases, transactions, assets, liabilities, incomes, expenses, capital, and the like. The ledger may provide a transaction history associated with time. The ledger can be centralized or decentralized/distributed. A centralized ledger can be a document that is controlled, updated or viewed by one or more selected entities or clearinghouses, where changes or updates to the ledger are managed or controlled by the entity or clearinghouse. A distributed ledger can be a ledger distributed across multiple entities, participants, or areas that can update or modify their ledger copies independently, simultaneously, or in concert. Ledgers and distributed ledgers may include security and encryption functions for signing, hiding, or verifying content. In the case of a distributed ledger, blockchain techniques can be used. In the case of a distributed ledger implemented using blockchains, the ledger can be a merkel tree composed of linked lists of nodes, where each node contains hashed or encrypted transaction data of the previous node. Some transaction records may not be considered ledgers. A file, computer file, database, or book may or may not be a ledger, depending on the data it stores, the manner in which the data is organized, maintained, or protected. For example, a transaction list may not be considered a ledger if the transaction list cannot be trusted or verified, and/or is based on inconsistent, fraudulent, or incomplete data. The data in the ledger can be organized in any format, such as tables, lists, binary data streams, etc., according to convenience, data source, data type, environment, application, etc. The ledger shared between different entities may not be a distributed ledger, but the differentiation of distributed ledgers may be based on which entities have authority to make changes to the ledger and/or how changes are shared and handled between different entities. Thus, the benefits of the present disclosure may apply to a variety of data, and any such data may be considered herein as a ledger, while in certain embodiments, given data may not be considered herein as a ledger. With the benefit of the disclosure herein and with knowledge of commonly available prospective ledgers and distributed ledgers, one skilled in the art can readily determine which aspects of the present disclosure can be used to implement and/or will benefit a particular ledger. In determining whether the intended data refers to a ledger and/or whether aspects of the present disclosure can benefit or enhance an intended ledger, certain considerations for one skilled in the art include, but are not limited to: security of data in the ledger (whether data can be tampered with or modified), time associated with making changes to data in the ledger, cost of making changes (computing and currency), details of data, organization of data (whether data needs to be processed for use in an application), who controls the ledger (whether the ledger can be trusted or relied upon by the event person to manage the ledger), confidentiality of data (who can view or track data in the ledger), size of infrastructure, communication requirements (distributed ledgers may require communication interfaces or specific infrastructure), resiliency. Although specific examples of blockchain services and considerations are described herein for illustrative purposes, any systems that benefit from the disclosure herein, as well as any considerations understood by those of ordinary skill in the art having the benefit of the disclosure herein, are specifically contemplated within the scope of the present disclosure.
The term "loan" (and similar terms) as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, the loan may be an agreement related to the property borrowed and expected to be returned in real-life (e.g., the money borrowed and the money returned) or as an agreed transaction (e.g., the first good or service is borrowed and the money returned, the second good or service, or a combination of both). An asset may be money, property, time, physical, virtual, service, rights (e.g., tickets, licenses, or other rights), depreciation amounts, deduction amounts (e.g., tax deduction amounts, discharge deduction amounts, etc.), risk or liability commitments for an appointment, and/or any combination thereof. The loan may be based on a formal or informal agreement between the borrower and the borrower, where the borrower may offer assets to the borrower at predetermined times, for variable periods of time, or for an indefinite period of time. The borrower and borrower may be individuals, entities, companies, governments, groups, organizations, etc. The loan types may include mortgage loans, personal loans, secured loans, unsecured loans, preferential loans, commercial loans, micropayments, and the like. The agreement between the borrower and the borrower may specify the terms of the loan. The borrower may be required to return the asset or be refunded with a different asset than the borrowed asset. In some cases, the loan may require repayment of interest on the borrowed property. The borrower and the lender may be intermediaries between other entities and may never own or use the property. In some embodiments, the loan may not be associated with the direct transfer of the good, but may be associated with usage rights or shared usage rights. In some embodiments, the agreement between the borrower and the borrower may be performed between the borrower and the borrower, and/or between intermediaries (e.g., beneficiaries of loan rights, such as by selling loans). In some embodiments, the agreement between the borrower and the borrower may be performed by a service herein, such as an intelligent contract service that determines at least a portion of the terms and conditions of the loan, and in some embodiments, the borrower and/or the borrower may comply with the terms of the agreement, which may be an intelligent contract. In some embodiments, the intelligent contract service may fill in the terms of the agreement and present it to the borrower and/or the borrower for execution. In some embodiments, the intelligent contractual service may automatically cause one of the borrower or the borrower to comply with the terms (at least as an offer) and may present the offer to the other of the borrower or the borrower for execution. In some embodiments, the loan agreement may include multiple borrowers and/or multiple borrowers, for example, where a group of loans includes multiple payment beneficiaries of the group of loans and/or multiple borrowers of the group of loans. In some embodiments, the risk and/or debt of the set of loans may be individual (e.g., each borrower and/or borrower is associated with a particular loan of the set of loans), apportioned (e.g., a particular loan default has associated losses apportioned among the borrowers), and/or combinations of these (e.g., one or more subsets of the set of loans are processed and/or apportioned individually).
Some agreements may not be considered loans. Depending on the property being transferred, the manner in which the property is transferred, or the parties involved, the agreement to transfer or borrow the property may not be considered a loan. For example, in some cases, the transfer of assets may be indefinite and may be considered a sale of assets or a permanent transfer. Likewise, a property may not be considered a loan in some cases if it is borrowed or transferred without explicit or clear terms or lack of consensus between the borrower and borrower. Even if the formal agreement is not directly incorporated into the written agreement, the agreement may be considered a loan as long as the party voluntarily and privately agrees to the arrangement, and/or the convention (e.g., a particular industry) may consider the transaction as a loan. Thus, the benefits of the present disclosure may apply to a variety of protocols, and any such protocol may be considered a loan herein, while in some embodiments a given protocol may not be considered a loan herein. Persons of ordinary skill in the art, with the benefit of the disclosure herein and with an understanding of expected loans that are generally available, may readily determine which aspects of the disclosure implement loans, utilize loans, or benefit a particular loan transaction. In determining whether the expected data is a loan and/or whether aspects of the disclosure may benefit or enhance an expected loan, certain considerations of those skilled in the art include, but are not limited to: the value of the property in question, the borrower's ability to return or repay the loan, the type of property in question (e.g., whether the property is consumed through use), the payoff period associated with the loan, the interest in the loan, the arrangement of the loan agreement, the form of the agreement, the details of the loan agreement, the collateral attributes associated with the loan, and/or the general business expectations of any of the above in particular circumstances. Although specific examples of loans and considerations are described herein for illustrative purposes, any system that would benefit from the disclosure herein and any considerations understood by one of ordinary skill in the art having the benefit of the disclosure herein are specifically contemplated within the scope of the present disclosure.
The term "loan-related events" (and similar terms, including loan-related events) as used herein should be broadly construed. Without being limited to any other aspect or description of the disclosure, a loan-related event may include any event related to the terms of the loan or an event triggered by an agreement associated with the loan. Loan-related events may include loan default, performance, repayment, payment, interest change, late line assessment, refund assessment, distribution, and the like. Loan-related events may be triggered by explicit terms of the agreement; for example, the agreement may specify that interest rates are rising for a period of time after the loan begins; the agreement-induced interest rate increase may be a loan-related event. The loan-related event may be implicitly triggered by the relevant loan agreement terms. In some embodiments, any occurrence that may be considered to be related to an assumption of a loan agreement and/or the expectations of the parties to the loan agreement may be considered an event occurrence. For example, if a mortgage of the loan is expected to be replaceable (e.g., as inventory for the mortgage), a change in the level of inventory may be considered an occurrence of a loan-related event. In another example, if review and/or confirmation of a collateral is expected, the absence of access to the collateral, failure or malfunction of a monitoring sensor, etc. may be considered the occurrence of a loan-related event. In some embodiments, circuitry, a controller, or other devices described herein may automatically trigger the determination of a loan-related event. In some embodiments, a loan-related event may be triggered by an entity that manages a loan or loan-related contract. The loan-related event may be conditionally triggered based on one or more conditions in the loan agreement. The loan-related event may be related to a task or requirement that the borrower, or third party needs to complete. Certain events may be considered loan-related events in certain embodiments and/or certain contexts, but may not be considered loan-related events in another embodiment or context. Many events may be related to the loan, but may be caused by an external trigger unrelated to the loan. However, in some embodiments, the external trigger event (e.g., a price change for a good associated with a mortgage) may be a loan-related event in some embodiments. For example, a borrower-initiated loan term renegotiation may not be considered a loan-related event if the terms and/or performance of an existing loan agreement do not trigger a renegotiation. Thus, the benefits of the present disclosure may apply to a variety of events, and any such event may be considered herein a loan-related event, while in some embodiments a given event may not be considered herein a loan-related event. Persons of ordinary skill in the art, with the benefit of the disclosure herein and with knowledge of the intended systems that are generally available, may readily determine which aspects of the disclosure may be considered loan-related events for the intended system and/or the particular transactions supported by the system. In determining whether the prospective data is a loan-related event and/or whether aspects of the disclosure may benefit or enhance the prospective trading system, certain considerations of those skilled in the art include, but are not limited to: the impact of the related event on the loan (the event that caused the loan to default or terminate may have a higher impact), the cost associated with the event (capital and/or operations), the cost associated with monitoring the occurrence of the event (capital and/or operations costs), the entity responsible for responding to the event, the time period and/or response time associated with the event (e.g., the time required to complete the event and the time allotted from the event trigger to the time required to process or detect the event), the entity responsible for the event, the data required to process the event (e.g., confidential information may have different protective measures or restrictions), mitigating measures that may be taken when an undetected event occurs, and/or remedial measures that may be taken by parties at risk when an undetected event occurs. Although specific examples of loan related events and considerations are described herein for illustrative purposes, any system that would benefit from the disclosure herein, as well as any consideration understood by those skilled in the art having the benefit of the disclosure herein, is specifically contemplated within the scope of the present disclosure.
The term "loan-related activities" (and similar terms) as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, the loan-related activities may include activities related to the generation, maintenance, termination, receipt, execution, service, billing, marketing, fulfillment capabilities, or negotiation of loans. Loan-related activities may include activities related to signing a loan agreement or a book slip, reviewing loan documents, processing payments, evaluating mortgages, evaluating borrowers or lenders' compliance with terms of a loan, renegotiating terms, perfecting loan guarantees or mortgages, and/or canceling terms. The loan-related activity may relate to an event associated with the loan, such as an activity associated with an initial negotiation, before a formal agreement is reached on the terms. Loan-related activities may be related to the duration of the loan and to events after the loan has terminated. The loan-related activity may be performed by the borrower, or third party. Certain activities may not be considered loan-related activities alone, but may be considered loan-related activities based on the specificity of the activity to the loan period — for example, invoicing or invoicing related to outstanding loans may be considered loan-related activities, whereas invoicing or invoicing may not be considered loan-related activities when combined with invoicing or invoicing of non-loan-related elements. Whether or not the loan is related to a property, some activities may be related to the property; in these cases, the activity may not be considered a loan-related activity. For example, a periodic audit may occur in connection with a property, whether or not the property is related to a loan, or may not be considered a loan-related activity. In another example, a periodic audit related to a property may be required by a loan agreement and will not normally occur unless related to a loan, in which case the activity may be considered a loan-related activity. In some embodiments, if activity does not occur where the loan is not active or not present, the activity may be considered loan-related activity, but in some cases (e.g., if the audit normally occurs, but the borrower is not able to perform or review the audit, the audit may be considered loan-related activity even if the audit has otherwise occurred). Thus, the benefits of the present disclosure may apply to a variety of events, and any such event may be considered herein a loan-related event, while in some embodiments a given event may not be considered herein a loan-related event. One skilled in the art, with the benefit of the disclosure herein and understanding of the intended systems generally available, can readily determine loan-related activities for the intended system purposes. In determining whether the expected data is a loan-related activity and/or whether aspects of the disclosure may benefit or enhance the expected loan, certain considerations of those skilled in the art include, but are not limited to: the necessity of the loan activity (whether the loan agreement or terms can be met without the activity), the cost of the activity, the specificity of the activity on the loan (whether the activity is similar or identical to other industries), the time involved in the activity, the effect of the activity on the loan period, the entity that developed the activity, the amount of data required for the activity (whether the activity requires confidential information related to the loan or personal information related to the entity), and/or the ability of the party to perform and/or review the activity. Although specific examples of loan-related events and considerations are described herein for illustrative purposes, any system that would benefit from the disclosure herein, as well as any considerations understood by those of ordinary skill in the art having the benefit of the disclosure herein, are specifically contemplated within the scope of the present disclosure.
The terms "loan terms," "terms and conditions," and the like, as used herein, are to be construed broadly ("loan terms"). Without being limited to any other aspect or description of the disclosure, the terms of the loan may relate to conditions, rules, restrictions, contractual obligations, etc., related to the times, repayments, initiations, and other executable conditions agreed upon by the borrower and the borrower of the loan. The terms of the loan may be specified in a formal contract between the borrower and the borrower. The loan terms may specify interest rates, collateral, redemption conditions, debt consequences, payment options, payment plans, contracts, and the like. The terms of the loan may be negotiated or may change during the duration of the loan. The terms of the loan may change or be affected by external parameters such as market price, bond price, conditions associated with the borrower or borrower, etc. Some aspects of the loan may not be considered loan terms. In some embodiments, loan aspects that have not been formally agreed upon between the borrower and/or aspects of the loan that are not normally understood in the business process (and/or a particular industry) may not be considered loan terms. Some aspects of the loan may be preliminary or informal before formal agreement or confirmation in a contract or an official agreement. Certain aspects of a loan may not be considered loan terms alone, but may not be based on the particularities of a particular loan aspect. Certain aspects of a loan may not be considered loan terms at a particular time during the loan, but may be considered loan terms at another time during the loan (e.g., obligations and/or exemptions that may occur when a party performs and/or the loan terms expire). For example, interest rates are not generally considered loan terms until they are defined as being related to the loan and as being calculated in a multiple interest (yearly, monthly), etc. If an aspect of the loan is indeterminate or unexecutable, it may not be considered a term. Some aspects may be a representation of or related to the terms of the loan, but may not be the terms of the loan itself. For example, the loan term is the repayment period of the loan, e.g., one year. The terms may not specify how the loan is repayed within a year. Loans may be reimbursed 12 months or a year. In this case, the monthly payment plan may not be considered a loan term because it is simply one or more repayment options that are not directly specified in the loan. Thus, the benefits of the present disclosure may apply to various loan aspects, and any such aspect may be considered herein as loan terms, while in certain embodiments, a given aspect may not be considered herein as loan terms. Those skilled in the art, having the benefit of the disclosure herein and knowledge of the intended system that is generally available, can readily determine which aspects of the disclosure are loan terms of the intended system.
Certain considerations of those skilled in the art in determining whether the expected data is a term of a loan and/or whether aspects of the disclosure may benefit or enhance an expected loan include, but are not limited to: enforceability of a term (whether a condition may be enforced by a borrower or borrower), enforcement cost of a term (time or effort required to ensure adherence to a term), complexity of a term (how easily a involved party adheres to or understands a term, whether a term is prone to error or misleading), entity responsible for a term, fairness of terms, stability of terms (frequency of terms change), observability of terms (whether a term may be verifiable by another party), profitability of a term to one party (whether a term is beneficial to a borrower or borrower), risk associated with a loan (the term may depend on the probability that a loan may not be repairable), characteristics of a borrower or borrower (its ability to satisfy a term), and/or general expectations of the loan and/or related industries.
Although specific examples of loan terms are described herein for illustrative purposes, any system that would benefit from the disclosure herein, as well as any consideration understood by those skilled in the art to benefit from the disclosure herein, is specifically contemplated within the scope of the present disclosure.
The terms "loan conditions", "terms and conditions", and the like, as used herein, are to be construed broadly as ("loan conditions"). Without being limited to any other aspect or description of the disclosure, the loan conditions may relate to rules, restrictions, and/or obligations associated with the loan. The loan terms may relate to rules or necessary obligations to obtain a loan, maintain a loan, apply for a loan, assign a loan, and so on. The loan conditions may include the principal amount of the debt, the balance of the debt, a fixed interest rate, a variable interest rate, a payment amount, a payment plan, an end-most grand payback plan, collateral description, collateral substitutability description, collateral processing, collateral usage rights, parties, insured persons, guarantors, collateral, personal guaranties, liens, terms, contracts, redemption conditions, default conditions, conditions related to other debts of the borrower, and default consequences.
Some aspects of the loan may not be considered a loan condition. Loan aspects that have not been formally agreed upon between the borrower and/or aspects of the loan that are not normally understood in the business process (and/or a particular industry) may not be considered loan terms. Some aspects of the loan may be preliminary or informal before formal agreement or confirmation in a contract or an official agreement. Certain aspects of a loan may not be considered loan conditions alone, but may also be considered loan conditions based on the particularities of a particular loan aspect. Certain aspects of a loan may not be considered loan conditions at a particular time during the loan, but may be considered loan conditions at another time during the loan (e.g., obligations and/or exemptions that may occur when a principal performs and/or the loan conditions expire). Thus, the benefits of the present disclosure may be applied to various loan aspects, and any such aspect may be considered herein as loan conditions, while in some embodiments a given aspect may not be considered herein as loan conditions. Those skilled in the art, with the benefit of the disclosure herein and knowledge of the intended system that is generally available, can readily determine which aspects of the disclosure are loan conditions for the intended system. In determining whether the expected data is loan conditions and/or whether aspects of the disclosure may benefit or enhance the expected loan, certain considerations of those skilled in the art include, but are not limited to: the enforceability of a condition (whether a condition may be enforced by a borrower or borrower), the cost of enforcement of a condition (the amount of time or work required to ensure that a condition is respected), the complexity of a condition (how easily a involved party is respecting or understanding a condition, whether a condition is prone to error or misinterpretation), the entity responsible for a condition, the fairness of a condition, the observability of a condition (whether a condition can be verified by another party), the interest of a term for one party (whether a condition is favorable to a borrower or borrower), the risk associated with a loan (the condition may depend on the probability that the loan may not be repatriable), and/or the general expectation of the loan and/or related industries.
Although specific examples of loan conditions are described herein for illustrative purposes, any system that would benefit from the disclosure herein, as well as any consideration understood by those skilled in the art to benefit from the disclosure herein, is specifically contemplated within the scope of the present disclosure.
The terms "mortgage," "mortgage," and the like as used herein should be broadly construed. Without being limited to any other aspect or description of the disclosure, a loan collateral may refer to any property or property that the borrower promises to the borrower in exchange for a loan and/or as a loan guarantee. A collateral may be any item of value that is accepted in the form of an alternative repayment in the event of a loan breach. The collateral can include any number of items or virtual items, such as vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, groups of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property. The collateral may include a plurality of items or types of items.
A mortgage may describe an asset, property, value, or other item defined as a loan or transaction guarantee. A set of collateral may be defined and substitution, removal or addition of collateral may be implemented within the set of collateral. For example, a collateral may be, but is not limited to: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property. If one or more groups of collateral are defined, substitution, removal or addition of collateral may be implemented, for example, substitution, removal or addition of collateral in a group of collateral. Without being limited to any other aspect or description of the disclosure, a collateral or a group of collateral may also be used in conjunction with other terms of an agreement or loan, such as statements, guarantees, indemnities, contracts, balances of debts, fixed interest rates, variable interest rates, payment amounts, payment plans, end-most payback plans, collateral statements, collateral substitutability statements, collateral, personal guaranties, liens, deadlines, redemption conditions, default conditions, and default consequences. In some embodiments, the smart contract may calculate whether a borrower meets a condition or contract, and in the event that the borrower does not meet such a condition or contract, may enable automatic actions or trigger other conditions or terms that may affect the status, ownership, or transfer of collateral, or initiate the replacement, removal, or addition of collateral from a set of loan collateral. Given the disclosure herein and the understanding of the collateral, one of ordinary skill in the art can readily determine the purpose and use of the collateral, including substitutions, removal, and additions, in the various embodiments and contexts disclosed herein.
Although specific examples of loan mortgages are described herein for illustrative purposes, any system that would benefit from the disclosure herein, as well as any consideration understood by those of ordinary skill in the art having the benefit of the disclosure herein, is specifically contemplated within the scope of the present disclosure.
The term "smart contract service" (and similar terms) as used herein should be construed broadly. Without being limited to any other aspect or description of the present disclosure, an intelligent contract service includes any service or application that manages an intelligent contract or an intelligent loan contract. For example, the intelligent contract service may specify terms and conditions of the intelligent contract (e.g., in a rules database), or process output from a set of valuation services and assign collateral sufficient to provide a loan guarantee. The intelligent contract service may automatically execute a set of rules or conditions embodying an intelligent contract, where execution may be based on or utilize collected data. The intelligent contract service may automatically initiate a demand for loan payment, automatically initiate a redemption-stop process, automatically initiate an action to request replacement or alternate collateral or transfer collateral ownership, automatically initiate an clearing process, automatically change collateral-based payments or interest rate deadlines, and may also configure intelligent contracts to automatically take loan-related actions. The intelligent contract may manage at least one of loan terms and conditions, loan-related events, and loan-related activities. An intelligent contract may be a protocol encoded as a computer protocol and may facilitate, verify, or enforce negotiation or fulfillment of the intelligent contract. The smart contracts may or may not be one or more of partially or fully automatically executed, or partially or fully automatically enforced.
Certain processes may not be considered individually as being related to a smart contract, but may be considered in an aggregation system as being related to a smart contract-for example, in one instance, automatically taking loan-related actions may not be related to a smart contract, but in another instance, may be governed by the terms of a smart contract. Thus, the benefits of the present disclosure may apply to a variety of process systems, and any such process or system may be considered herein as a smart contract or smart contract service, while in certain embodiments a given service may not be considered herein as a smart contract service.
Given the disclosure herein and an understanding of commonly available prospective systems, one skilled in the art can readily determine which aspects of the disclosure will benefit a particular system and how to combine the processes and systems of the present disclosure to implement intelligent contract services and/or enhance the operation of a prospective system. Certain considerations of those skilled in the art in determining whether a prospective system includes a smart contract service or a smart contract and/or whether aspects of the present disclosure may benefit or enhance the prospective system include, but are not limited to: the ability to automatically transfer mortgage ownership in response to an event; automatic actions that may be taken when a contract is found to be compliant (or not); whether the collateral is suitable for clustering, rebalancing, assigning, adding, replacing, and removing items of the collateral; an aspect of the loan may be responsive to a modification parameter of the event (e.g., time, complexity, applicability of the loan type, etc.); the complexity of the terms and conditions of the system loan, including the benefits of quickly determining and/or predicting changes in entities related to the loan (e.g., collateral, party financial conditions, counteracting collateral, and/or industry related to the party); automatic generation of terms and conditions and/or execution of terms and conditions may be appropriate for the type of loan expected by the system, the availability of the party and/or industry, etc. Although specific examples of intelligent contract services and considerations are described herein for illustrative purposes, any system that would benefit from the disclosure herein and any considerations understood by one of ordinary skill in the art having the benefit of the disclosure herein are specifically contemplated within the scope of the present disclosure.
The term "internet of things system" (and similar terms) as used herein should be broadly construed. Without being limited to any other aspect or description of the disclosure, an IoT system includes any system comprised of uniquely identified and related computing devices, mechanical and digital machines, sensors, and objects capable of transmitting data over a network without intervention. Certain components may not be considered IoT systems alone, but may be considered IoT systems in an aggregated system — for example, a single networked sensor, smart speaker, and/or medical device may not be an IoT system, but may be part of a larger system and/or aggregated with multiple other similar components to be considered an IoT system and/or part of an IoT system. In some embodiments, for some purposes but not others, the system may be considered an IoT system-e.g., the smart speakers may be considered part of the IoT system for some operations (e.g., for providing surround sound, etc.), but not part of the IoT system for other operations (e.g., transmitting content directly from a single local network source). Additionally, in certain embodiments, other similarly looking systems may be distinguished when determining whether and/or what type of IoT system such a system is. For example, at a given time, one group of medical devices may not share to an aggregated HER database, while another group of medical devices may share data to an aggregated HER for clinical research purposes, and thus one group of medical devices may be an IoT system, while another group of medical devices may not. Thus, the benefits of the present disclosure may apply to a variety of systems, and any such system may be considered herein as an IoT system, while in certain embodiments, a given system may not be considered herein as an IoT system. Given the benefit of the disclosure herein and knowing the intended systems that are generally available, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit the particular systems and how to combine the processes and systems in this disclosure to enhance the operation of the intended systems and/or which circuits, controllers, and/or devices comprise the IoT systems for the intended systems. Certain considerations for those skilled in the art in determining whether a prospective system is an IoT system and/or whether aspects of the present disclosure may benefit or enhance the prospective system include, but are not limited to: the transmission environment of the system (e.g., availability of low power, inter-device networking); a shared data store for a set of devices; establishing a geofence over a set of devices; as a service of a blockchain node; performance of asset, collateral, or entity monitoring; relaying data between devices; the ability to aggregate data from multiple sensors or monitoring devices, etc. Although specific examples of IoT systems and considerations are described herein for illustrative purposes, any system that would benefit from the disclosure herein and any considerations understood by one of ordinary skill in the art having the benefit of the disclosure herein are specifically contemplated within the scope of the present disclosure.
The term "data collection service" (and similar terms) as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, a data collection service includes any service that collects data or information, including any circuit, controller, device, or application that may store, transmit, share, process, organize, compare, report, and/or aggregate data. The data collection service may include a data collection device (e.g., a sensor) and/or may be in communication with the data collection device. The data collection service may monitor the entities to identify data or information for collection. The data collection service may be event driven, run periodically, or retrieve data from the application at specific points in the execution of the application. Some processes may not be considered a data collection service alone, but may be considered a data collection service in an aggregation system — for example, a networked storage device may be a component of a data collection service in one instance, but may have independent functionality in another instance. Thus, the benefits of the present disclosure may be applied to a variety of process systems, and any such process or system may be considered herein a data collection service, while in certain embodiments a given service may not be considered herein a data collection service. Given the disclosure herein and an understanding of commonly available prospective systems, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit a particular system and how to combine the processes and systems of the present disclosure to implement a data collection service and/or enhance the operation of a prospective system. Certain considerations of those skilled in the art in determining whether a prospective system is a data collection service and/or whether aspects of the present disclosure may benefit or enhance the prospective system include, but are not limited to: the ability to dynamically modify business rules and change data collection protocols; monitoring the event in real time; connecting a data collection device to a monitoring infrastructure, executing computer readable instructions, causing a processor to record or track events; using an automated inspection system; sales at a networked point of sale; data from one or more distributed sensors or cameras, etc. Although specific examples of data collection services and considerations are described herein for illustrative purposes, any systems that benefit from the disclosure herein, as well as any considerations understood by those of ordinary skill in the art having the benefit of the disclosure herein, are specifically contemplated within the scope of the present disclosure.
The term "data integration service" (and similar terms) as used herein should be construed broadly. Without being limited to any other aspects or descriptions of the present disclosure, a data integration service includes any service that integrates data or information, including any device or application that can extract, transform, load, normalize, compress, decompress, encode, decode, and otherwise process data packets, signals, and other information. The data integration service may monitor the entities to identify data or information for integration. The data integration service may integrate data without regard to the frequency, communication protocol, or business rules required by the complex integration model. Thus, the benefits of the present disclosure may be applied to a variety of process systems, and any such process or system may be considered herein as a data integration service, while in certain embodiments a given service may not be considered herein as a data integration service. Given the disclosure herein and an understanding of commonly available prospective systems, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit a particular system and how to combine the processes and systems of the present disclosure to implement a data integration service and/or enhance the operation of a prospective system. Certain considerations of those skilled in the art in determining whether a prospective system is a data integration service and/or whether aspects of the present disclosure may benefit or enhance the prospective system include, but are not limited to: the ability to dynamically modify business rules and change data integration protocols; pull-in data is integrated by communicating with a third party database; synchronizing data across different platforms; connecting to a central data repository; data storage capacity, processing capacity and/or communication capacity distributed throughout the system; connecting independent automated workflows, etc. Although specific examples of data integration services and considerations are described herein for illustrative purposes, any systems that benefit from the disclosure herein and any considerations understood by those of ordinary skill in the art that benefit from the disclosure herein are specifically contemplated within the scope of the present disclosure.
The term "computing service" (and similar terms) as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, a computing service may be included as part of one or more services, platforms, or microservices, such as a blockchain service, a data collection service, a data integration service, a valuation service, an intelligent contract service, a data monitoring service, data mining, and/or any service that facilitates data collection, access, processing, transformation, analysis, storage, visualization, or sharing. Some processes may not be considered computing services. For example, a process may not be considered a computing service, depending on the kind of rules governing the service, the end product of the service, or the intent of the service. Thus, the benefits of the present disclosure may apply to a variety of process systems, and any such process or system may be considered a computing service herein, while in certain embodiments a given service may not be considered a computing service herein. Given the disclosure herein and an understanding of commonly available prospective systems, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit from a particular system and how to combine the processes and systems of the present disclosure to achieve one or more computing services and/or enhance the operation of the prospective system. In determining whether a prospective system is a computing service and/or whether aspects of the present disclosure may benefit or enhance the prospective system, certain considerations by those skilled in the art include, but are not limited to: accessing a service based on a protocol; coordinating the exchange between different services; providing on-demand computing power to a Web service; monitoring, collecting, accessing, processing, converting, analyzing, storing, integrating, visualizing, mining, or sharing one or more data is accomplished. Although specific examples of computing services and considerations are described herein for illustrative purposes, any systems that benefit from the disclosure herein, as well as any considerations understood by those of ordinary skill in the art having the benefit of the disclosure herein, are specifically contemplated within the scope of the present disclosure.
The term "sensor" as used herein should be understood broadly. Without being limited to any other aspect or description of the disclosure, a sensor may be a device, module, machine, or subsystem that detects or measures a physical quality, event, or change. In embodiments, the detection or measurement may be recorded, indicated, communicated, or otherwise responded to. Examples of sensors may be sensors for sensing movement of an entity, sensors for sensing temperature, pressure, or other attributes about an entity or its environment, cameras that capture still or video images of an entity, sensors that collect data about collateral or assets (e.g., regarding location, condition (health, physical, or other), quality, security, possession, etc.). In an embodiment, the sensor may be sensitive to the property to be measured, but not affect it, but not to other properties. The sensors may be analog or digital. The sensor may include a processor, transmitter, transceiver, memory, power source, sensing circuitry, electrochemical reservoir, light source, and the like. Further examples of sensors contemplated for use in the system include: a biosensor, a chemical sensor, a black silicon sensor, an infrared sensor, an acoustic sensor, an inductive sensor, a motion sensor, an optical sensor, an opacity sensor, a proximity sensor, an inductive sensor, an eddy current sensor, a passive infrared proximity sensor, radar, a capacitive sensor, a capacitive displacement sensor, a hall effect sensor, a magnetic sensor, a GPS sensor, a thermal imaging sensor, a thermocouple, a thermistor, a photoelectric sensor, an ultrasonic sensor, an infrared laser sensor, an inertial motion sensor, a MEMS internal motion sensor, an ultrasonic three-dimensional motion sensor, an accelerometer, an inclinometer, a force sensor, a piezoelectric sensor, a rotary encoder, a linear encoder, an ozone sensor, a smoke sensor, a heat sensor, a magnetometer, a carbon dioxide detector, a carbon monoxide detector, an oxygen sensor, a glucose sensor, a smoke detector, a metal detector, a rainfall sensor, a heart rate meter, GPS, outdoor detection, environmental detection, activity detection, a target detector (e.g., a collateral), a marker detector (e.g., a geo-location marker), a laser range finder, a sonar, a capacitance, an optical response, a heart rate sensor, or a micro power pulse radio (MIR) sensor. In some embodiments, the sensor may be a virtual sensor-e.g., determining an interest parameter as a result of a calculation based on other sensed parameters in the system. In some embodiments, the sensor may be a smart sensor-e.g., reporting the sensed value as abstract communication (e.g., as network communication) of the sensed value. In some embodiments, the sensor may provide the sensed value directly (e.g., as a voltage level, frequency parameter, etc.) to a circuit, controller, or other device in the system. Those skilled in the art, having the benefit of the disclosure herein and understanding the intended systems available, can readily determine which aspects of the present disclosure will benefit from sensors. In determining whether the intended device is a sensor and/or whether aspects of the present disclosure may benefit or be enhanced by the intended sensor, certain considerations of those skilled in the art include, but are not limited to: adjusting activation/deactivation of the system based on the environmental quality; converting the electrical output into a measurement; an ability to implement geofencing; automatically modify the loan in response to changes in the collateral, etc. Although specific examples of sensors and considerations are described herein for illustrative purposes, any system that would benefit from the disclosure herein, as well as any considerations understood by one of ordinary skill in the art having the benefit of the disclosure herein, are specifically contemplated within the scope of the present disclosure.
The term "storage condition" and similar terms as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, storage conditions include an environment, physical location, environmental quality, exposure level, security measures, maintenance descriptions, accessibility descriptions, etc. associated with storing assets, mortgages or entities specified and monitored in a contract, loan, or agreement, or assets, mortgages or entities, etc. that warrant a contract, loan, or other agreement. Based on the storage conditions of the collateral, the asset or the entity, actions may be taken to maintain, improve and/or confirm the condition of the asset or use the asset as collateral. Based on the storage conditions, actions may be taken to change the terms or conditions of the loan or bond. The storage conditions may be classified according to various rules, thresholds, conditional procedures, workflows, model parameters, etc., and may be based on data from a report or from internet of things devices (IoT data), data from a set of environmental condition sensors, data from a set of social network analytics services, and a set of algorithms for querying network domains, social media data, crowd sourced data, etc. The storage conditions may relate to collateral, publishers, borrowers, fund distribution, or other geographic locations. Examples of IoT data may include images, sensor data, location data, and the like. Examples of social media data or crowd-sourced data may include the behavior of a loan party, the financial status of a party, the compliance of a party to terms or conditions of a loan or bond, and so forth. The lending parties may include bond issuers, related entities, borrowers, and debt-related third parties. The storage conditions may relate to asset or collateral types, such as: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, merchandise, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property. The storage condition may comprise an environment, wherein the environment may comprise an environment selected from a municipal environment, a business environment, a securities trading environment, a real estate environment, a commercial facility, a warehousing facility, a transportation environment, a manufacturing environment, a storage environment, a house, and a vehicle. Actions based on collateral, property, or entity storage conditions may include managing, reporting, altering, joining, consolidating, terminating, maintaining, modifying terms and/or conditions, stopping redemption, or otherwise processing a loan, contract, or agreement. Those skilled in the art, having the benefit of the disclosure herein and knowledge of expected storage conditions, can readily determine which aspects of the present disclosure will benefit a particular application of storage conditions. Certain considerations of those skilled in the art or of embodiments of the present disclosure include, but are not limited to, when selecting appropriate storage conditions for management and/or monitoring: the validity of the conditions of a given trading jurisdiction, the available data for a given collateral, the type of expected transaction (loan, bond, or debt), the particular type of collateral, the ratio of loan to value, the ratio of collateral to loan, the total transaction/loan amount, the credit scores of borrowers and lenders, industry practice, and other considerations. Although specific examples of storage conditions are described herein for illustrative purposes, any embodiment that would benefit from the disclosure herein, as well as any consideration understood by one skilled in the art to benefit from the disclosure herein, is specifically contemplated within the scope of the present disclosure.
The term "geographic location" and similar terms as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, the geographic location includes identifying or estimating a real-world geographic location of the object, including generating a set of geographic coordinates (e.g., latitude and longitude) and/or a street address. Based on the geographic location of the collateral, asset or entity, actions may be taken to maintain or improve the condition of the asset or to use the asset as collateral. Based on the geographic location, actions may be taken to change the terms or conditions of the loan or bond. Based on geographic location, determinations or predictions related to transactions may be made based on weather, terrain, and/or local disasters (e.g., earthquakes, floods, tornadoes, hurricanes, industrial accidents, etc.). The geographic location may be determined according to various rules, thresholds, conditional procedures, workflows, model parameters, etc., and may be based on data from a report or from an internet of things device, data from a set of environmental condition sensors, data from a set of social network analysis services, and a set of algorithms for querying network domains, social media data, crowd-sourced data, etc. Examples of geographic location data may include GPS coordinates, images, sensor data, street addresses, and the like. The geographic location data may be quantitative (e.g., longitude/latitude, relative to a platform map, etc.) and/or qualitative (e.g., categorical, such as "coastal," "rural," etc.; "within new york city," etc.). The geographic location data may be absolute (e.g., GPS location) or relative (e.g., within 100 codes of the expected location). Examples of social media data or crowd-sourced data may include the behavior of a party to a loan inferred from a geographic location, the financial status of a party inferred from a geographic location, the adherence of a party to terms or conditions of a loan or bond, and the like. The geographic location may be determined for the following asset or collateral types, for example: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, consumables, edible items, beverages, precious metals, jewelry, gemstones, antiques, fixtures, furniture, equipment, tools, machinery, and personal property. The geographic location may be determined for the following entities, for example: a principal, a third party (e.g., an inventory service, a maintenance service, a cleaning service, etc., associated with the transaction), or any other entity associated with the transaction. The geographic location may include an environment selected from a municipal environment, a business environment, a stock exchange environment, a real estate environment, a commercial facility, a warehousing facility, a transportation environment, a manufacturing environment, a storage environment, a house, and a vehicle. Actions based on the mortgage, asset, or physical geographic location may include managing, reporting, altering, federating, merging, terminating, maintaining, modifying terms and/or conditions, redeeming, or otherwise processing the loan, contract, or agreement. With the benefit of the disclosure herein and an understanding of the intended system, one of ordinary skill in the art can readily determine which aspects of the present disclosure will benefit from a particular application of geographic location and which location aspect of an item is the geographic location of the intended system. In selecting an appropriate geographic location for management, certain considerations by those skilled in the art or by embodiments of the present disclosure include, but are not limited to: the legitimacy of the geographic location of a given transaction jurisdiction, the available data for a given collateral, the type of expected transaction (loan, bond, or debt), the particular type of collateral, the ratio of loan to value, the ratio of collateral to loan, the total transaction/loan amount, the frequency of borrowers traveling to certain jurisdictions and other considerations, the liquidity of collateral, and/or the likelihood of occurrence of a particular location event related to the transaction (e.g., weather, location of related industrial facilities, availability of related services, etc.). Although specific examples of geographic locations are described herein for illustrative purposes, any embodiments that benefit from the disclosure herein, as well as any considerations understood by those skilled in the art to benefit from the disclosure herein, are specifically contemplated within the scope of the present disclosure.
The term "jurisdiction" and similar terms as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, a jurisdiction refers to the legal and legal authorities that manage the lending entity. The jurisdiction location may be based on the geographic location of the entity, the registered location of the entity (e.g., flag country of ship, enterprise registered country, etc.), the awarded country of certain rights (e.g., intellectual property priority), etc. In some embodiments, the jurisdiction may be one or more geographic locations of entities in the system. In some embodiments, the jurisdiction may not be the same geographic location as any entity in the system (e.g., the protocol specifies some other jurisdiction). In some embodiments, the jurisdiction may be different for entities in the system (e.g., borrowers at a, borrowers at B, mortgages at C, obligations at D, etc.). In some embodiments, the jurisdiction of a given entity may differ during operation of the system (e.g., due to movement of collateral, changes in relevant data, terms, and conditions, etc.). In some embodiments, a given entity of the system may have multiple jurisdictions (e.g., due to the operation of relevant laws and/or options available to one or more parties), and/or may have different jurisdictions for different purposes. The jurisdiction of a collateral, asset, entity or action may indicate certain terms or conditions of a loan or bond, and/or may indicate different obligations to a party to issue notifications, to stop redemption and/or to perform default, to collateral and/or debt warranty processing, and/or to various data processing within the system. Although specific examples of jurisdictions are described herein for illustrative purposes, any embodiment that would benefit from the present disclosure and any consideration that would be understood by one of ordinary skill in the art having the benefit of the present disclosure is specifically contemplated within the scope of the present disclosure.
Variations of the terms "value token", "token", and cryptocurrency tokens used herein in the context of value increments may be broadly construed to describe: (a) Currency or cryptocurrency units (e.g., cryptocurrency tokens) and (b) may also be used to represent credentials that may be exchanged for goods, services, data, or other valuable consideration (e.g., value tokens). Without being limited to any other aspect or description of the present disclosure, in the former case, tokens may also be used in conjunction with investment applications, token trading applications, and token-based markets. Tokens may also be associated with offering value, such as offering goods, services, items, fees, access to restricted areas or events, data, or other valuable benefits. Tokens may or may not be present (e.g., or have an access token). For example, value tokens may be exchanged for accommodations (e.g., hotel rooms), food and drink goods and services, spaces (e.g., shared spaces, work spaces, meeting spaces, etc.), fitness/health goods or services, event tickets or tickets, travel, airline or other transportation, digital content, virtual goods, license keys, or other valuable goods, services, data, or consideration. In discussing units of value, collateral, or value, various forms of tokens may be included, whether currency, cryptocurrency, or any other form of value of a good, service, data, or other benefit. One of ordinary skill in the art, with the benefit of the disclosure herein and knowledge of tokens, can readily determine the value symbolized or represented by a token, whether currency, cryptocurrency, goods, services, data, or other value. Although specific examples of tokens are described herein for illustrative purposes, any embodiment that would benefit from the disclosure herein, as well as any consideration understood by one of ordinary skill in the art having the benefit of the disclosure herein, is specifically contemplated within the scope of the present disclosure.
The term "pricing data" as used herein may be broadly understood to describe the amount of information, such as the price or cost, of one or more items in the market. Without being limited to any other aspect or description of the present disclosure, pricing data may also be used in connection with spot market pricing, forward market pricing, pricing discount information, promotional pricing, and other information related to cost or price of an item. The pricing data may satisfy one or more conditions or may trigger one or more rules for applying the intelligent contracts. Pricing data can be used in conjunction with other forms of data, such as market value data, accounting data, access data, asset and facility data, worker data, event data, underwriting data, claims data, or other forms of data. Pricing data can be adjusted for the context of the value item (e.g., condition, liquidity, location, etc.) and/or for the context of a particular party. Given the disclosure herein and the knowledge of pricing data, one of ordinary skill in the art can readily determine the purpose and use of pricing data in the various embodiments and contexts disclosed herein.
Without being limited to any other aspect or description of the disclosure, tokens include, but are not limited to, value tokens, such as mortgages, assets, rewards, such as in tokens that are representations of value, such as may be exchanged for value holding vouchers for goods or services. Certain components may not be considered tokens alone, but may be considered tokens in an aggregation system — for example, value placed on an asset may not be a token itself, but asset value may be placed in a value token, e.g., for storage, exchange, transaction, etc. For example, in a non-limiting example, the blockchain circuit may be configured to provide a mechanism for lenders to store asset value, where the value attributed to tokens is stored in a distributed ledger of the blockchain circuit, but tokens that have assigned value may themselves be exchanged or traded through the token market. In some embodiments, a token may be considered a token for some purposes, but not for other purposes — for example, a token may be used to represent ownership of an asset, but such use of a token may not be traded for value that a token that includes the value of the asset may have. Thus, the benefits of the present disclosure may be applied to a variety of systems, and any such system may be considered a token herein, while in certain embodiments, a given system may not be considered a token herein. Given the disclosure herein and an understanding of commonly available prospective systems, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit from a particular system and/or how to combine the processes and systems of the present disclosure to enhance the operation of a prospective system. Certain considerations of those skilled in the art in determining whether a prospective system is a token and/or whether aspects of the present disclosure may benefit or enhance a prospective system include, but are not limited to: access data, such as data relating to access rights, tickets and tokens; for investment applications such as investment shares, equity and tokens; a token transaction application; a token-based marketplace; value forms, such as monetary rewards and tokens; converting the value of the resource using tokens; encrypting the currency token; ownership indications, such as identity information, event information, and token information; trading blockchain based in marketplace applications; pricing applications, such as pricing for setting and monitoring or having access, basic access, tokens and fees; a transaction application, e.g. for a transaction or exchange or having access or potential access or tokens; access token tokens are created and stored on the blockchain for generating ownership or access rights (e.g., tickets), and the like.
The term "financial data" as used herein may be broadly understood to describe a collection of financial information about an asset, collateral, or other item. Financial data may include revenue, expenditure, assets, liabilities, equity, bond ratings, default, return On Asset (ROA), return On Investment (ROI), past performance, expected future performance, earnings Per Share (EPS), internal earnings (IRR), income bulletins, ratios, statistical analysis (e.g., moving averages) of any of the foregoing, and the like. Without being limited to any other aspect or description of the disclosure, financial data may also be used in conjunction with pricing data and market value data. The financial data may satisfy one or more conditions or may trigger one or more rules for applying the intelligent contract. Financial data may be used in conjunction with other forms of data, such as market value data, pricing data, accounting data, access data, asset and facility data, worker data, event data, underwriting data, claims data, or other forms of data. The purpose and use of pricing data in the various embodiments and contexts disclosed herein can be readily determined by those skilled in the art, given the benefit of the disclosure herein and knowledge of financial data.
The term "contract" as used herein may be broadly construed to describe a term, agreement, or commitment, e.g., to fulfill some role or role. For example, the contract may relate to the behavior of the principal or the legal status of the principal. Without being limited to any other aspect or description of the disclosure, the contract may also be used in conjunction with other related terms of an agreement or loan, such as statements, guarantees, indemnities, balances of debts, fixed interest rates, variable interest rates, payment amounts, payment plans, top-of-line payback plans, collateral statements, collateral substitutability statements, parties, insureds, guarantors, collateral, personal guaranties, liens, terms, redemption conditions, default conditions, and default consequences. The contract or non-fulfillment of the contract may satisfy one or more conditions, or may trigger a collection, a default, or other terms and conditions. In some embodiments, the intelligent contract may calculate whether the contract is satisfied, and in the event that the contract is not satisfied, an automatic action may be enabled or other conditions or terms may be triggered. The purpose and use of the contracts in the various embodiments and contexts disclosed herein can be readily determined by those skilled in the art, given the benefit of the disclosure herein and an understanding of the contracts.
The term "entity" as used herein may be broadly understood to describe a party, a third party (e.g., an auditor, a regulatory body, a service provider, etc.), and/or an identifiable related object, such as a collateral associated with a transaction. Example entities include individuals, partnerships, companies, limited liability companies, or other legal organizations. Other exemplary entities include identifiable mortgages, cancellation mortgages, potential mortgages, and the like. For example, an entity may be a given party to a agreement or loan, such as a person. Data or other terms herein may be characterized as having a context associated with an entity, such as entity-oriented data. An entity may be characterized using a particular context or application, such as, but not limited to, a human entity, a physical entity, a transactional entity, or a financial entity. An entity may have a representative that represents its actions. Without being limited to any other aspect or description of the disclosure, the entity may also be used in conjunction with other related entities or terms of an agreement or loan, such as statements, guarantees, indemnities, contracts, balances of debts, fixed interest rates, variable interest rates, payment amounts, payment plans, top-end grand payback plans, collateral statements, collateral substitutability statements, parties, insureds, guaranties, collateral, personal guaranties, liens, deadlines, conditions of redemption, conditions of default, and consequences of default. An entity may have a set of attributes, such as, but not limited to: public valuations, a set of properties owned by an entity as indicated by a public record, valuations of a set of properties owned by an entity, bankruptcy status, redemption-stop status, contract breach status, violation status, crime status, export regulation status, contraband status, tariff status, tax status, credit reports, credit ratings, website ratings, a set of customer reviews of the product of an entity, a social network rating, a set of credentials, a set of referrals, a set of proofs, a set of behaviors, a location, and a geographic location. In some embodiments, the intelligent contract may calculate whether an entity satisfies a condition or contract, and in the event that the entity does not satisfy such a condition or contract, an automatic action may be enabled or other conditions or terms may be triggered. The purpose and use of the entities in the various embodiments and contexts disclosed herein can be readily determined by those skilled in the art, given the benefit of the disclosure herein and an understanding of the entities.
The term "principal" as used herein may be broadly understood to describe a member of an agreement, such as a person, a partner enterprise, a company, a limited liability company or other legal organization. For example, the party may be a primary borrower, a secondary borrower, a lending bank, a corporate borrower, a government borrower, a bank borrower, a secured borrower, a bond issuer, a bond purchaser, an unsecured lender, a secured person, a secured provider, a borrower, a debtor, an underwriter, an inspector, an evaluator, an auditor, an assessment professional, a government official, an accountant, or other entity having rights or obligations to an agreement, transaction, or loan. The parties may characterize different terms such as, but not limited to, a transaction in the term "multiple parties transaction," where multiple parties participate in the transaction, and the like. A principal may have a representative acting on its behalf. In some embodiments, the term "principal" may refer to a potential principal or prospective principal that may not have committed an actual agreement during interaction with the system, such as a prospective borrower or borrower that interacts with the system. Without being limited to any other aspect or description of the disclosure, a party may also be used in conjunction with other related parties or terms of an agreement or loan, such as statements, guarantees, indemnities, contracts, balances of debts, fixed interest rates, variable interest rates, payment amounts, payment plans, top-end grand payback plans, collateral statements, collateral substitutability statements, entities, insureds, guarantors, collateral, personal guaranties, liens, deadlines, redemption conditions, default conditions, and consequences of the default. A principal may have a set of attributes such as, but not limited to: identity, reputation, activity, behavior, business practices, contract performance status, accounts receivable information, accounts payable information, collateral value information, and other types of information. In some embodiments, the intelligent contract may calculate whether a party satisfies a condition or contract, and in the event that the party does not satisfy such a condition or contract, an automatic action may be enabled or other conditions or terms may be triggered. Given the benefit of the disclosure herein and an understanding of the parties, one of ordinary skill in the art can readily determine the purposes and uses of the parties in the various embodiments and contexts disclosed herein.
The terms "principal attributes," "entity attributes," or "principal/entity attributes" as used herein may be broadly understood to describe a value, characteristic, or state of a principal or entity. For example, attributes of a principal or entity may be, but are not limited to: value, quality, location, net worth, price, physical condition, health condition, warranty, security, ownership, identity, reputation, activity, behavior, business practices, contract performance status, accounts receivable information, accounts payable information, collateral value information, and other types of information, and the like. In some embodiments, an intelligent contract may calculate a value, state, or condition associated with an attribute of a party or entity, and may enable automatic actions or trigger other conditions or terms in the event that the party or entity does not satisfy such conditions or contracts. Given the disclosure herein and an understanding of principal or entity attributes, one of ordinary skill in the art can readily determine the purpose and use of these attributes in the various embodiments and contexts disclosed herein.
The term "borrower" as used herein may be broadly understood to describe a party in an agreement to offer to loan a property or loan revenue, and may include a person, a partner, a company, a limited liability company, or other legal organization. For example, the borrower may be, but is not limited to: a primary borrower, a secondary borrower, a lending bank, a corporate borrower, a government borrower, a bank borrower, a secured borrower, an unsecured lender, or other party with rights or obligations to provide a loan to a borrower for an agreement, transaction, or loan. The borrower may have a representative on whose behalf the borrower acts. Without being limited to any other aspect or description of the disclosure, a party may also be used in conjunction with other related parties or terms of an agreement or loan, such as borrowers, guarantors, statements, guarantees, indemnities, contracts, balances of debts, fixed interest rates, variable interest rates, payment amounts, payment plans, end-most payback plans, collateral statements, collateral substitutability statements, collateral, personal guaranties, liens, terms, redemption conditions, default conditions, and default outcomes. In some embodiments, the intelligent contract may calculate whether the borrower satisfies a condition or contract, and in the event that the borrower does not satisfy such a condition or contract, automatic actions, notifications or warnings may be enabled or other conditions or terms may be triggered. The borrower's intent and use in the various embodiments and contexts disclosed herein may be readily determined by those skilled in the art, given the benefit of the disclosure herein and an understanding of the borrower.
The term "crowdsourcing service" as used herein may be broadly understood to describe a service provided or presented in connection with a crowdsourcing model or transaction, where a large number of people or entities provide contributions to meet the needs of the transaction, such as a loan. The crowdsourcing service may be provided by a platform or system, but is not so limited. A crowdsourcing request may be communicated to a group of information providers, and responses to the request may be collected and processed by the group of information providers to provide rewards to at least one successful information provider. The request and parameters may be used to obtain information relating to the status of a set of mortgages. A crowdsourcing request may be issued. In some embodiments, but not limited to, the crowdsourcing service may be performed by a smart contract, wherein rewards are managed by the smart contract, which processes responses to crowdsourcing requests and automatically assigns rewards to information that satisfies a set of parameters configured for the crowdsourcing requests. The purpose and use of crowdsourcing services in the context and various embodiments disclosed herein can be readily determined by one skilled in the art, given the benefit of the disclosure herein and knowledge of crowdsourcing services.
The term "publishing service" as used herein may be understood to describe a set of services that publish crowdsourcing requests. The publication service may be provided by a platform or system, but is not limited thereto. In some embodiments, but not limited to, the publication service may be performed by a smart contract, where the crowdsourcing request is published by the smart contract or a publication initiated by the smart contract. Given the disclosure herein and the knowledge of the publication service, one of ordinary skill in the art can readily determine the purpose and use of the publication service in the various embodiments and contexts disclosed herein.
The term "interface" as used herein may be broadly interpreted as describing a component, such as a computer, which may be embodied as software, hardware, or a combination thereof, that enables interaction or communication. For example, the interface may serve many different purposes or for different applications or contexts, such as but not limited to: an application programming interface, a graphical user interface, a software interface, a marketplace interface, a demand aggregation interface, a crowdsourcing interface, a security access control interface, a network interface, a data integration interface, or a cloud computing interface, or a combination thereof. The interface may be used as a way to input, receive, or display data in the range of, but not limited to, loan, refinance, collection, consolidation, warranty, proxy, or redemption. An interface may serve as an interface to another interface. Without being limited to any other aspect or description of the disclosure, an interface may be used in conjunction with or as part of an application, process, module, service, layer, device, component, machine, product, subsystem, interface, or connection. In certain embodiments, the interface may be embodied as software, hardware, or a combination thereof, and stored in a medium or memory. The purpose and use of the interfaces in the context and various embodiments disclosed herein may be readily determined by one of ordinary skill in the art, given the benefit of this disclosure and understanding of the interfaces.
The term "graphical user interface" as used herein may be understood to mean an interface that allows a user to interact with a system, computer, or other interface, where the interaction or communication is accomplished through a graphical device or representation. The graphical user interface may be a component of a computer that may be embodied as computer readable instructions, hardware, or a combination thereof. The graphical user interface may serve a variety of different purposes or for different applications or environments. Such an interface may serve as a way to receive or display data using visual representations, stimuli, or interactive data, but is not so limited. The graphical user interface may serve as an interface to another graphical user interface or other interfaces. Without being limited to any other aspect or description of the disclosure, the graphical user interface may be used in conjunction with or as part of an application, process, module, service, layer, device, component, machine, product, subsystem, interface, or connection. In certain embodiments, the graphical user interface may be embodied as computer readable instructions, hardware, or a combination thereof, and stored in a medium or memory. The graphical user interface may be for any input type, including keyboard, mouse, touch screen, etc. The graphical user interface may be used in any desired user interaction environment including, for example, a dedicated application program, a web page interface, or a combination thereof. Given the disclosure herein and an understanding of a graphical user interface, one of ordinary skill in the art can readily determine the purpose and use of the graphical user interface in the context and various embodiments disclosed herein.
The term "user interface" as used herein may be understood as an interface that allows a user to interact with a system, computer or other device, where the interaction or communication is accomplished through a graphical device or representation. The user interface may be a component of a computer, which may be embodied as software, hardware, or a combination thereof. The user interface may be stored on a medium or in memory. The user interface may include drop down menus, forms, etc. with default, templated, recommended, or preconfigured conditions. In some embodiments, the user interface may include voice interaction. Without being limited to any other aspect or description of the disclosure, the user interface may be used in conjunction with or as part of an application, circuit, controller, process, module, service, layer, device, component, machine, product, subsystem, interface, or connection. The user interface may serve a variety of different purposes or for different applications or environments. For example, the borrower end user interface may include features to view multiple customer profiles, but may restrict certain changes from being made. The debtor end user interface may include features to view details and make changes to the user account. Third-party-neutral interfaces (e.g., third parties who do not benefit in the underlying transaction, such as regulatory bodies, auditors, etc.) may have features that enable viewing of corporate supervised and anonymous user data without manipulating any data, and may schedule access according to the third party and access objectives. A third-party stakeholder-side interface (e.g., a third party that may benefit in a base transaction, such as a payee, debtor concierge, investigator, partial owner, etc.) may include features that allow viewing of particular user data and restrict changes from being made. Further features of these user interfaces may be used to implement embodiments of the systems and/or processes described throughout this disclosure. Thus, the benefits of the present disclosure may be applied in a variety of processes and systems, and any such process or system may be considered a service herein. Given the disclosure herein and an understanding of the user interface, one of ordinary skill in the art can readily determine the purpose and use of the user interface in the various embodiments and contexts disclosed herein. In determining whether a prospective interface is a user interface and/or whether aspects of the disclosure may benefit or enhance a prospective system, certain considerations by those skilled in the art include, but are not limited to: configurable views, ability to limit manipulation or viewing, reporting functions, ability to manipulate user profiles and data, implement regulatory requirements, provide desired user characteristics for borrowers, and third parties, and the like.
The interfaces and control panels used herein may be further understood broadly to describe components that enable interaction or communication, such as components of a computer, which may be embodied as software, hardware, or a combination thereof. The interface and control panel may acquire, receive, present, or otherwise manage items, services, offers, or other aspects of a transaction or loan. For example, the interface and control panel may serve many different purposes or for different applications or contexts, such as but not limited to: an application programming interface, a graphical user interface, a software interface, a marketplace interface, a demand aggregation interface, a crowdsourcing interface, a security access control interface, a network interface, a data integration interface, or a cloud computing interface, or a combination thereof. The interface or control panel may serve as a way to receive or display data in the context of, but not limited to, loan, refinance, collection, consolidation, warranty, proxy, or redemption. The interface or control panel may serve as an interface or control panel for another interface or control panel. Without being limited to any other aspect or description of the disclosure, an interface may be used in conjunction with or as part of an application, circuit, controller, process, module, service, layer, device, component, machine, article, subsystem, interface, or connection. In certain embodiments, the interface or control panel may be embodied as computer readable instructions, hardware, or a combination thereof, and stored in a medium or memory. The purpose and use of the interface and/or control panel in the various embodiments and contexts disclosed herein can be readily determined by one of ordinary skill in the art, given the benefit of the disclosure herein and knowing the anticipated systems that are generally available.
The term "domain" as used herein may be broadly understood to describe the scope or context of a transaction and/or communications related to a transaction. For example, a domain may serve many different purposes or for different applications or contexts, such as but not limited to: a domain for execution, a domain for digital assets, a domain to which a request is to be published, a domain to which a social network data collection and monitoring service is to be applied, a domain to which an internet of things data collection and monitoring service is to be applied, a network domain, a geo-location domain, a jurisdiction domain, and a time domain. Without being limited to any other aspect or description of the disclosure, one or more domains may be used with respect to or as part of any application, circuit, controller, process, module, service, layer, device, component, machine, product, subsystem, interface, or connection. In certain embodiments, the domains may be embodied as computer readable instructions, hardware, or a combination thereof, and stored in a medium or memory. The purpose and use of the various embodiments and contexts disclosed herein can be readily determined by those skilled in the art, given the benefit of this disclosure and the understanding of the scope.
The term "request" (and variations) as used herein may be broadly interpreted as describing an action or instance of initiating or requesting something to be provided (e.g., information, a response, an object, etc.). A particular type of request may also be used for a variety of different purposes or configured for different applications or contexts, such as but not limited to: a formal law request (e.g., a citation), a re-financing request (e.g., a loan), or a crowdsourcing request. The system may be used to execute requests and satisfy requests. Various forms of requests may be included in discussing legal proceedings, loan re-financing, or crowdsourcing services, but are not limited to such. One of ordinary skill in the art, with the benefit of the disclosure herein and understanding of the intended systems, can readily ascertain the value of the requests effected in the embodiments. Although specific examples of the requests are described herein for illustrative purposes, any embodiments that benefit from the disclosure herein, as well as any considerations understood by those skilled in the art to benefit from the disclosure herein, are specifically contemplated within the scope of the present disclosure.
The term "reward" (and variations) as used herein may be broadly construed to describe something or consideration that is received or provided in response to an action or stimulus. The reward may be of a financial type or a non-financial type, but is not limited thereto. Certain types of rewards may also serve a variety of different purposes or for different applications or environments, such as but not limited to: reward events, reward claim, monetary reward, reward acquired as a data set, reward points, and other forms of reward. Rewards may be triggered, distributed, generated for innovation, used to submit evidence, request, offer, selection, implementation, management, configuration, distribution, communication, identification, but are not limited to other actions. The system may be used to perform the actions described above. Various forms of rewards may be included, but are not limited to, when discussing a particular behavior or encouraging a particular behavior. In some embodiments herein, the reward may be used as a specific incentive (e.g., to reward a particular person in response to a crowdsourcing request) or a general incentive (e.g., to provide a reward in response to a successful crowdsourcing request, in addition to or in place of the reward to the particular person in response). Those skilled in the art, having the benefit of the disclosure herein and knowledge of the rewards, can readily determine the value of the rewards implemented in the embodiments. Although specific examples of rewards are described herein for illustrative purposes, any embodiments that benefit from the disclosure herein and any considerations understood by those skilled in the art to benefit from the disclosure herein are specifically contemplated within the scope of the present disclosure.
The term "robotic process automation system" as used herein may be broadly understood to describe a system capable of performing tasks or providing requirements for the system of the present disclosure. For example, robotic process automation systems may be used to: negotiating a set of loan terms and conditions; negotiating and financing loan; b, loan collection; merging a group of loans; managing a warranty loan; a mortgage loan is proxied; training an redemption-stopping negotiation; configuring a crowdsourcing request based on a set of loan attributes; setting a reward; determining a set of domains to which the request is to be issued; configuring the content of the request; configuring data collection and monitoring actions based on a set of loan attributes; determining a set of domains to which the internet of things data collection and monitoring service is to be applied; and iterative training and improvement based on a set of results, but is not so limited. A robotic process automation system may include: a set of data collection and monitoring services, an artificial intelligence system, and another robotic process automation system that is a component of an advanced robotic process automation system. A robotic process automation system may include: at least one of a set of mortgage activities and a set of mortgage interactions includes the following activities: a marketing campaign; identifying a group of potential borrowers; identifying property; identifying a collateral; determining the acquirement qualification of the borrower; searching for property rights; verifying the property right; evaluating the property; checking property; evaluating the property; verifying income; performing a demographic analysis on the borrower; identifying the patron; determining an available interest rate; determining available payment terms and conditions; analyzing the existing mortgage; performing a comparative analysis of existing mortgage terms and new mortgage terms; completing the application workflow; filling in an application field; compiling a mortgage protocol; completing the collateral protocol attached table; negotiating mortgage terms and conditions with the patron; negotiating mortgage terms and conditions with the borrower; transferring property rights; setting a lien right; and reaching a mortgage agreement. Exemplary and non-limiting robotic process automation systems may include one or more user interfaces, interfaces to provide, request, and/or share data with circuits and/or controllers in the overall system, and/or one or more artificial intelligence circuits to iteratively improve one or more operations of robotic process automation. Given the disclosure herein and the knowledge of commonly available prospective robotic process automation systems, one of ordinary skill in the art can readily determine the circuitry, controllers, and/or devices to include to implement a robotic process automation system that performs selected functions of the prospective system. Although specific examples of robotic process automation systems are described herein for illustrative purposes, any embodiment that benefits from the disclosure herein and any considerations that benefit from understanding.
The term "loan-related action" (and other related terms such as loan-related events and loan-related activities) as used herein may be broadly understood to describe one or more actions, events or activities related to a transaction that includes a loan in a transaction. The action, event or activity may occur in many different contexts of loan, such as, but not limited to, lending, refinancing, consolidation, warranty, brokering, redemption, management, negotiation, collection, purchasing, enforcement, and data processing (e.g., data collection), or a combination thereof. The loan-related action may be used in the form of a noun (e.g., a notice of default has been communicated to the borrower through formal notice, which may be considered a loan-related action). Loan-related actions, events, or activities may refer to a single instance or may describe a set of actions, events, and activities. For example, a single action of providing a specific notification of an overdue payment to a borrower may be considered a loan-related action. Similarly, a set of actions related to a default from start to finish may also be considered a single loan-related action. The evaluation, inventory, financing, and record (but not limited to) may also be considered a loan-related action that has occurred, as well as a loan-related event, and possibly a loan-related event. Similarly, these activities that accomplish these actions may also be considered loan-related activities (e.g., evaluation, inventory, financing, recording, etc.), but are not so limited. In some embodiments, an intelligent contract or robotic process automation system may perform loan-related actions, loan-related events, or loan-related activities for one or more parties, and process the appropriate tasks to accomplish these tasks. In some cases, the smart contracts or robotic process automation systems may not complete loan-related actions, and depending on such results, this may enable automatic actions or trigger other conditions or terms. Given the benefit of the disclosure herein and an understanding of loan-related actions, events, and activities, those skilled in the art may readily determine the purpose and use of this term in the various forms and embodiments described in this disclosure.
The term "loan-related actions, events, and activities" as used herein may also be used more specifically to describe the context of loan procurement. Loan claim is an action by which a borrower may request that a loan be repaid, typically triggered by other conditions or terms, such as a delinquent payment. For example, when a borrower makes three consecutive delinquent payments, loan-related actions may occur that lead to serious delinquent in the loan repayment plan and the loan entering a default state. In such a situation, the borrower may initiate loan-related actions for the loan to protect his rights. In such a situation, the borrower may pay a payment to cover the default and fine, which may also be considered a loan-related action for which the loan is intended. In some cases, a smart contract or robotic process automation system may initiate, manage, or process loan-related actions for the taking of a loan, including, but not limited to, providing notifications, research and collection history, or other tasks performed as part of the taking of a loan. Those skilled in the art, having the benefit of the disclosure herein and understanding loan-related actions for loans or other forms of the term and its various forms, may readily ascertain the purpose and use of the term in the event or in various other embodiments and contexts disclosed herein.
As described herein, the term "loan-related actions, events, and activities" may also be used more specifically to describe the context of loan payment. Typically, in a transaction involving a loan, but not limited to, the loan is repayed according to a payment plan. Various actions may be taken to provide information to the borrower for repayment of the loan, as well as actions by the borrower to receive payment for the loan. For example, if the borrower is, a loan-related action of loan payment may occur. Repayment of loans without limitation, such payment may include several actions related to loan payment, such as: payment submitted to the borrower; a loan ledger or accounting reflecting paid; a payment receipt provided to the borrower; and the next payment requested by the borrower. In some cases, smart contracts or robotic process automation systems may initiate, manage, or process such loan-related actions for loan payments, including but not limited to: providing a notification to the borrower; research and collect payment history; providing a receipt to the borrower; providing a notification to the borrower of the next due payment; or other action associated with the loan payment. The purpose and use of the term in the event or in the various other embodiments and contexts disclosed herein may be readily determined by those skilled in the art, given the benefit of the disclosure herein and understanding the loan-related actions of loan payments or other forms of the term and its various forms.
As described herein, the term "loan-related actions, events, and activities" may also be used more specifically to describe the context of a payment plan or alternative payment plan. Typically, in transactions involving loans, but not limited to, the loans are repayed according to a payment plan, which may be modified over time. Alternatively, one such payment plan may be made and alternative payment plans agreed upon in the alternative. Various actions may be taken in the context of the borrower's or borrower's payment plan or alternate payment plan, such as: the amount of such payment, the expiration time of such payment, fines or fees that may be added to delay payment, or other terms. For example, if the borrower repays the loan in advance, loan-related actions may occur for the loan repayment plan and the alternative loan repayment plan; in this case, the payment is applied as a principal, and the periodic payment is still unexpired. Without limitation, the loan-related actions of the loan repayment plan and the alternative loan repayment plan may include several actions related to loan payment, such as: payment submitted to the borrower; a loan ledger or accounting reflecting paid; a payment receipt provided to the borrower; calculation of the time to attach or due for any charges; and the next payment requested by the borrower. In some embodiments, the activity that determines the payment plan or the alternative payment plan may be a loan-related action, event, or activity. In some embodiments, the activity communicating the payment plan or an alternative payment plan (e.g., to the borrower, or third party) may be a loan-related action, event, or activity. In some cases, smart contract circuitry or robotic process automation systems may initiate, manage, or process such loan-related actions for payment plans and alternative payment plans, which may include, but are not limited to: providing a notification to the borrower; research and collect payment history; providing a receipt to the borrower; calculating a next due date; calculating a final payment amount and date; providing a notification to the borrower of the next due payment; determining a payment plan or an alternative payment plan; convey a payment plan or alternative payment plan or other action associated with the loan payment. Given the benefit of the disclosure herein and understanding loan-related actions for payment plans and alternative payment plans, or other forms of the term and its various forms, those skilled in the art can readily determine the purpose and use of the term in the event or in other various embodiments and contexts disclosed herein.
The term "regulatory notification requirements" (and any derivatives thereof) as used herein may be broadly construed to describe an obligation or condition to convey a notification or message to another party or entity. The regulatory notification requirements may be required under one or more conditions of a trigger or general requirement. For example, the borrower may have a regulatory notice requirement that the borrower be provided with a loan default, a change in the interest rate of the loan, or other notice related to the transaction or loan. The regulatory aspects of the term may be attributable to laws, rules, or regulations of a particular jurisdiction that require the fulfillment of certain communication obligations. In some embodiments, the policy instructions may be considered regulatory notification requirements-for example, the borrower's internal notification policy may exceed the regulatory requirements of one or more jurisdictional sites associated with the transaction. The notification aspect generally relates to formal communications that may take many different forms, but may be specified as a particular form of notification, such as a registered letter, facsimile, e-mail transmission, or other physical or electronic form, notification content, and/or time requirements associated with the notification. The requiring aspect relates to the fact that the party must fulfill his obligations, comply with laws, rules, guidelines, policies, standard practices or agreements, or terms of the loan. In some embodiments, the intelligent contract may process or trigger regulatory notification requirements and provide appropriate notifications to the borrower. This may be based on the location of at least one of: the borrower, funds provided through the loan, loan repayment and loan collateral, or other locations specified by the terms of the loan, transaction, or agreement. In the event that a party or entity does not meet such regulatory notification requirements, certain changes in rights or obligations between the parties may be triggered-for example, in the event that a borrower provides a non-compliance notification to a borrower, automatic actions or triggers based on the terms and conditions of the loan and/or based on external information (e.g., regulatory provisions, the borrower's internal policies) may be implemented by intelligent contract circuitry and/or a robotic process automation system may be implemented. Given the disclosure herein and an understanding of the anticipated systems that are generally available, one of ordinary skill in the art can readily determine that regulatory notices require the purpose and use in the various embodiments and contexts disclosed herein.
The term "regulatory notification requirements" as used herein may also describe obligations or conditions to convey a notification or message to another party or entity based on general or specific policies, rather than based on laws, rules, or regulations of a particular jurisdiction or a particular location (e.g., perhaps jurisdiction-specific regulatory notification requirements). Regulatory notification requirements may be prudent or advised, rather than mandatory or necessary, under one or more conditions of a trigger or general requirement. For example, the borrower may have a policy-based regulatory notice requirement that the borrower be provided with a notice of a new information website, or a notice of a future change in loan interest rate, or other notice related to the transaction or loan that is advisory or helpful, rather than mandatory (although mandatory notices may also be policy-based). Thus, in the policy-based usage regulatory notification requirement clause, the intelligent contract circuitry may process or trigger the regulatory notification requirement and provide the borrower with an appropriate notification, which may or may not be required by the laws, rules, or regulations. The basis of the notification or communication may be due to caution, politeness, habit, or obligation.
The term "administrative notification" as used herein may also describe an obligation or condition to convey a notification or message to another party or entity (e.g., a borrower or borrower). The administrative notification may be specific to any one principal or entity, or may be specific to a group of principals or entities. For example, it may be suggested or required to provide a particular notification or communication to the borrower, such as a particular notification or communication regarding a situation where the borrower fails to pay the loan on due, resulting in a default. Thus, such regulatory notices for a particular user (e.g., a borrower or borrower) may be the result of jurisdiction-specific or policy-based regulatory notice requirements. Thus, in some cases, a smart contract may process or trigger regulatory notifications and provide appropriate notifications to a particular party (e.g., borrower), which may or may not be required by laws, rules, or regulations, but may be provided for caution, politeness, or habit. In the event that a principal or entity does not satisfy such regulatory notification requirements for a particular principal, it may create an environment that may be exempt from certain rights by one or more of the principals or entities, or may enable automatic actions or trigger other conditions or terms. Given the disclosure herein and an understanding of the anticipated systems that are generally available, one of ordinary skill in the art can readily determine the purpose and use of regulatory notification requirements based on the various embodiments and contexts disclosed herein.
The term "regulatory redemption-stopping requirement" (and any derivatives) as used herein may be broadly construed to describe an obligation or condition to trigger, handle or complete a loan breach, mortgage redemption or redemption, or other related redemption-stopping action. Under one or more conditions of a trigger or general demand, a redemption-stop demand may need to be regulated. For example, the borrower may have a regulatory redemption-stopping requirement that the borrower be provided with a notification of a loan breach prior to redemption, or other notification related to the loan breach. The regulatory aspects of the term may be attributable to jurisdiction-specific laws, rules, or regulations that require the fulfillment of certain communication obligations. The redemption aspect typically involves a specific remedial action to the redemption, or the withdrawal of mortgage property and loan default, which may take many different forms, but may also be specified in the terms of the loan. The required aspect relates to the fact that the party must perform his obligation, comply or fulfill a law, rule, regulation or agreement or loan terms. In some embodiments, the intelligent contract circuitry may process or trigger regulatory redemption-outing requirements and process appropriate tasks related to such redemption-outing actions. The redemption-stopping action may be based on a place of jurisdiction of at least one of: the borrower, funds provided over the loan, loan repayment and loan collateral, or other jurisdiction as specified by the terms of the loan, transaction, or agreement. In the event that a party or entity does not meet such regulatory redemption requirements, the party or entity (e.g., borrower) may be exempt from certain rights, or such failure to meet regulatory notice requirements may enable automatic action or trigger other conditions or terms. Given the disclosure herein and an understanding of the anticipated systems that are generally available, one of ordinary skill in the art can readily determine that regulatory notices require the purpose and use in the various embodiments and contexts disclosed herein.
The term "regulatory redemption-claim" as used herein may also describe an obligation to trigger, handle or complete a loan breach, mortgage redemption or other related redemption-stopping action based on a general or specific policy, rather than based on laws, rules or regulations in a particular jurisdiction or location (e.g., perhaps a jurisdiction-specific regulatory redemption-claim). Under one or more conditions of triggering or general demand, regulatory redemption requirements may be prudent or advised, rather than mandatory or necessary. For example, the borrower may have a policy-based regulatory redemption requirement that the borrower be provided with notification of a loan breach, or other notification related to the transaction or loan, which is advisory or helpful, rather than mandatory (although mandatory notification may also be a policy basis). Thus, in the policy-based usage regulatory notification requirement clause, the intelligent contract may process or trigger a regulatory redemption-stopping requirement and provide the borrower with an appropriate notification, which may or may not be required by the laws, rules, or regulations. The basis of the notification or communication may be due to caution, politeness, habit, industry practice, or obligation.
The term "regulatory redemption requirements" as used herein may also describe obligations or conditions fulfilled for a particular user (e.g., borrower or borrower). The administrative notification may be specific to any one principal or entity, or may be specific to a group of principals or entities. For example, it may be suggested or required to provide a particular notification or communication to the borrower, such as a particular notification or communication regarding a situation where the borrower fails to pay the loan on due, resulting in a default. Thus, such regulatory redemption-stopping requirements are specific to a particular user (e.g., borrower or borrower), and may be the result of jurisdiction-specific or policy-based regulatory redemption-stopping requirements. For example, the redemption requirements may be associated with a particular entity involved in the transaction (e.g., the current borrower has been the customer for 30 years, and thus has acquired a particular deal), or with a class of entities (e.g., "priority" borrowers or "first default" borrowers). Thus, in some cases, the intelligent contract circuitry may handle or trigger obligations or actions that must be taken upon redemption, either to or from a particular party, such as a borrower or borrower, which may or may not be required by laws, rules, or regulations, but may be provided for caution, politeness, or custom. In some embodiments, the obligations or conditions to be fulfilled for a particular user may form part of the terms and conditions, or otherwise be known to the particular user to which they apply (e.g., an insurance company or bank publicizes specific practices for a particular category of customers, such as first default customers, first incident customers, etc.), and in some embodiments, the obligations or conditions to be performed for a particular user may be unknown to the particular user to which they apply (e.g., a bank has policies related to the category of users to which the particular user belongs, but the particular user does not know the classification).
The terms "value," "valuation," and "valuation model" (and similar terms) as used herein should be broadly understood to describe methods of evaluating and determining the estimated value of a collateral. Without being limited to any other aspect or description of the disclosure, the valuation model can be used in conjunction with: mortgages (e.g., secured property), artificial intelligence services (e.g., to improve valuation models), data collection and monitoring services (e.g., to set valuation amounts), valuation services (e.g., notification, use, and/or process of improving valuation models), and/or results related to mortgage transactions (e.g., as a basis for improving valuation models). A "jurisdiction-specific valuation model" is also used as a valuation model for a particular geography/jurisdiction or region; wherein the jurisdiction may be a particular jurisdiction of a borrower, funding, loan payment, or loan mortgage, or a combination thereof. In some embodiments, the jurisdiction-specific valuation model considers jurisdiction impacts on collateral valuation, including at least: rights and obligations of borrowers and lenders in the relevant jurisdiction; jurisdictional impact on the ability to transfer, import, export, replace and/or clear collateral; the effects of the breach of collateral and the administration of time between the redemption or collection; and/or jurisdictional effects on volatility and/or sensitivity of collateral value determination. In some embodiments, the geographic location-specific valuation model considers geographic location impacts on collateral valuations, which may include a series of similar relative jurisdictional impact considerations (although jurisdiction locations may differ from geographic locations), but may also include additional impacts, such as: weather-related effects; the distance of the collateral from the monitoring, maintenance or sequestration service; and/or proximity risk phenomena (e.g., faulty lines, industrial locations, nuclear power plants, etc.). The valuation model can utilize valuations that offset collateral (e.g., general values like collateral, market values like or alternative collateral, and/or item values related to collateral value) as part of collateral valuation. In some embodiments, the artificial intelligence circuitry includes one or more machine learning and/or artificial intelligence algorithms to improve the valuation model, including, for example, iteratively improving the valuation model using information relating to changes over time between transactions that are similar or offset to a collateral, and/or using resulting information from the same or other transactions (e.g., a loan transaction completed successfully or unsuccessfully, and/or in response to a collateral mortgage or clearing event evidencing a real-world collateral valuation determination). In some embodiments, the artificial intelligence circuit is trained based on the collateral valuation data set, such as previously determined valuations and/or by interacting with a trainer (e.g., human, accounting valuation, and/or other valuation data). In some embodiments, the valuation model and/or parameters of the valuation model (e.g., assumptions, calibrations, etc.) may be determined and/or negotiated as part of the terms and conditions of the transaction (e.g., a loan, a set of loans, and/or a subset of the set of loans). Given the disclosure herein and an understanding of expected systems that are generally available, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit a particular application of valuation models and how to select or combine valuation models to achieve a particular example of a valuation model. Some considerations for those skilled in the art or embodiments of the present disclosure in selecting an appropriate valuation model include, but are not limited to: giving legal considerations that warrant a valuation model of the jurisdiction; available data for a given collateral; expected transaction/loan type; a particular type of collateral; loan to value ratio; the ratio of mortgages to loans; total transaction/loan amount; credit rating of the borrower; loan type and/or accounting practices of the related industry; uncertainty associated with any of the above; and/or a sensitivity associated with any of the above. Although specific examples of valuation models and considerations are described herein for illustrative purposes, any embodiment that benefits from the disclosure herein, as well as any considerations that would be understood by one of ordinary skill in the art having the benefit of the disclosure herein, are specifically contemplated within the scope of the present disclosure.
The term "market value data" or "market information" (as well as other forms or variations) as used herein may be broadly understood to describe data or information relating to the valuation of properties, assets, mortgages or other items of value that may be used as a loan, mortgage or trade target. Market value data or market information may change from time to time and may be estimated, calculated, or objectively or subjectively determined from a variety of sources of information. Market value data or market information may be directly related to a collateral or cancellation collateral. Market value data or market information may include financial data, market ratings, product ratings, customer data, market research to understand customer needs or preferences, competitive intelligence. Competitors, suppliers, etc., entity sales, transactions, customer acquisition costs, customer life-long value, brand awareness, attrition rates, etc. The term may occur in many different contexts of contracts or loans, such as, but not limited to, lending, refinancing, merging, policying, brokering, redemption stopping, and data processing (e.g., data collection), or a combination thereof. Market value data or market information may be used as a noun to identify a single number or multiple numbers or data. For example, the borrower may utilize market value data or market information to determine whether a property or asset will serve as a collateral for a secured loan, or, if the loan is in default, may alternatively be used to determine the redemption, but is not limited to those instances where the term is used. Market value data or market information may also be used to determine the number or calculation of the loan versus value. In certain embodiments, the collection service, smart contract circuitry, and/or robotic process automation system may estimate or calculate market value data or market information from one or more data or information sources. In some cases, market data value or market information (depending on the data/information contained therein) may enable automatic actions or trigger other conditions or terms. Given the disclosure herein and the generally available knowledge of contemplated systems and relevant market information available, one of ordinary skill in the art can readily determine the purpose and use of the term in the various forms, embodiments, and contexts disclosed herein.
As used herein, the terms "collateral-like," "offset collateral," and other forms or variations may be broadly construed to describe properties, assets, or items of value that are similar in nature to collateral (e.g., items of value held in a collateral) related to a loan or other transaction. Similar collateral objects may refer to property, assets, collateral objects or other items of value, which may be aggregated with, replaced by or otherwise used in conjunction with other collateral objects, whether or not the similarity is in the form of a common attribute, such as the type of collateral object, the category of collateral object, the age of collateral object, the condition of collateral object, the history of collateral object, ownership of collateral object, manager of collateral object, security of collateral object, condition of owner of collateral object, lien right of collateral object, storage condition of collateral object, geographic location of collateral object, jurisdiction place of collateral object, etc. In some embodiments, the offset collateral references items that have value-related relationships with the collateral — for example, the offset collateral may exhibit similar price variations, volatility, storage requirements, and the like. In some embodiments, similar mortgages may be aggregated to form a larger secured interest or mortgage for additional loans, distribution, or transactions. In some embodiments, the cancellation collateral may be used to inform the collateral of the valuation. In some embodiments, the smart contract circuit or robotic process automation system may estimate or calculate numbers, data, or information related to similar collateral objects, or may perform functions related to aggregating similar collateral objects. The purpose and use of similar mortgages, counteracting mortgages or related terms related to mortgages in the various forms, embodiments and contexts disclosed herein can be readily determined by those skilled in the art, given the benefit of the disclosure herein and the knowledge of the intended systems that are generally available.
The term "restructuring" (as well as other forms of restructuring, etc.) as used herein may be broadly understood to describe the modification of terms or conditions, property, mortgage, or other considerations that affect a loan or transaction. Reassembly may result in successful results with modified terms or conditions between the two parties, or may result in unsuccessful results without modification or reassembly, but is not limited thereto. Reorganization may occur in many contexts of contracts or loans, such as, but not limited to, applying for, loans, refinancing, collecting, consolidating, maintaining, brokering, stopping redemption, and combinations thereof. The debt may also be reconciled, which may indicate that the debt owed to the party has changed in time, amount, collateral, or other terms. For example, the borrower may reorganize the loan obligations to accommodate changes in financial conditions, or the borrower may provide the borrower with a reorganization of obligations as needed or prudent. In some embodiments, the smart contract circuit or robotic process automation system may automatically or manually reorganize debts based on monitored conditions, or create options for reorganizing debts, manage the negotiation or implemented process of debt reorganization, or other actions related to reorganizing or modifying the terms of a loan or transaction. Given the disclosure herein and the generally available knowledge of the intended system, one of ordinary skill in the art can readily determine the purpose and use of the term in the various embodiments and contexts disclosed herein, whether in the context of a debt or in other contexts.
The terms "social network data collection," "social network monitoring service," and "social network data collection and monitoring service" (and various forms or derivatives thereof) as used herein may be broadly understood to describe services relating to the acquisition, organization, observation, or otherwise operation of data or information originating from one or more social networks. The social network data collection and monitoring service may be a system of related services or a set of independent services. The social network data collection and monitoring service may be provided by a platform or system, but is not limited to such. The social network data collection and monitoring service may be used in a variety of situations such as, but not limited to, lending, refinancing, negotiating, collecting, consolidating, warranting, brokering, stopping redemption, and combinations thereof. Requesting social network data collection and monitoring using configuration parameters may be requested by other services, automatically initiated, or automatically triggered to occur based on an occurring condition or situation. The interface may be used to configure, initiate, display, or otherwise interact with the social network data collection and monitoring service. Social networks, as used herein, refers to any mass platform where data and communications occur between individuals and/or entities, where the data and communications are at least partially accessible by an embodiment system. In some embodiments, the social networking data includes information that is publicly available (e.g., accessible without any authorization). In some embodiments, social network data includes information that is suitably accessible by an embodiment system, but may include subscription access or otherwise access to information that is not made available to the public but is accessible (e.g., in compliance with privacy policies of the social network and its users). Social networks may be primarily social in nature, but may additionally or alternatively include professional networks, alumni networks, industry-related networks, academic-oriented networks, and the like. In some embodiments, the social network may be a crowdsourcing platform, such as a platform for accepting queries or requests for users (and/or subsets of users, potentially meeting specified criteria), where users may be aware that certain communications are to be shared and accessed by requesters, at least a portion of the users of the platform, and/or are publicly available. In certain embodiments, but not limited thereto, the social network data collection and monitoring service may be performed by smart contract circuitry or a robotic process automation system. Given the benefit of the disclosure herein and understanding the anticipated systems that are generally available, one of ordinary skill in the art can readily determine the purpose and use of social network data collection and monitoring services in the various embodiments and contexts disclosed herein.
The term "crowdsourcing and social network information" as used herein may be further broadly understood to describe information obtained or provided in connection with a crowdsourcing model or transaction, or information obtained or provided on or in connection with a social network. Crowd-sourced and social networking information may be provided by a platform or system, but is not so limited. Crowd-sourced and social network information may be obtained, provided or communicated to or from a group of information providers, and responses to requests collected and processed by these information providers. Crowd-sourced and social network information may provide information, conditions, or factors related to a loan or agreement. Crowd-sourced and social network information may be private or public, or a combination thereof, but is not so limited. In some embodiments, but not limited to, crowd-sourced and social network information may be acquired, provided, organized, or processed by intelligent contract circuitry, where the crowd-sourced and social network information may be managed by the intelligent contract circuitry, which processes the information to satisfy a set of configuration parameters. The purpose and use of the term in the various embodiments and contexts disclosed herein can be readily determined by one of ordinary skill in the art, given the benefit of the disclosure herein and understanding the intended system generally available.
The term "negotiation" (as well as other forms) as used herein may be broadly understood to describe a discussion or communication that achieves or obtains a compromise, result or agreement between parties or entities. The negotiation may result in, but is not limited to, successful results of the parties agreeing to the terms, or unsuccessful results of the parties not agreeing to the particular terms or combination thereof. The negotiation may be successful on one hand or for a specific purpose and unsuccessful on the other hand or for another purpose. Negotiation may occur in many contexts of contracts or loans, such as, but not limited to, lending, refinancing, collecting, consolidating, managing, brokering, stopping redemption, and combinations thereof. For example, the borrower may negotiate interest rates or loan terms with the borrower. In another example, the default borrower may negotiate an alternative solution with the borrower to avoid redemption. In some embodiments, the intelligent contract circuit or robotic process automation system may negotiate for one or more parties and process the appropriate tasks for completing or attempting to complete the term negotiation. In some cases, the negotiation of the smart contracts or robotic process automation systems may not be complete or successful. The negotiation success may enable automatic actions or trigger other conditions or terms to be implemented by the smart contract circuit or the robotic process automation system. Those skilled in the art, having the benefit of the disclosure herein and understanding the intended systems generally available, can readily determine the purpose and use of negotiations in the various embodiments and contexts disclosed herein.
The various forms of the term "negotiation" may be used more specifically in the text in verb form (e.g., to negotiate) or noun form (e.g., negotiate) or other forms to describe the context of the mutual discussion that results in the results. For example, the robotic process automation system may negotiate terms and conditions on behalf of the principal that will be used as verb clauses. In another example, the robotic process automation system may negotiate terms and conditions for modifying the loan, or negotiate a consolidated offer or other terms. As a noun clause, negotiations (e.g., events) may be performed by a robotic process automation system. Thus, in some cases, the smart contract circuit or robotic process automation system may negotiate (e.g., as a verb clause) terms and conditions, or the description of doing so may be considered a negotiation (e.g., as a noun clause). Those skilled in the art, having the benefit of the disclosure herein and understanding negotiations or other forms thereof, may readily ascertain the purpose and use of this term in the various embodiments and contexts disclosed herein.
The term "negotiation" in its various forms may also be used specifically to describe the results, e.g. resulting in mutual compromise or completion of the negotiation of the results. For example, with a robotic process automation system or otherwise, the loan may be considered a successful result of the negotiation, an agreement is reached between the two parties, and the negotiation has been completed. Thus, in some cases, the smart contract circuit or robotic process automation system may have negotiated to complete a set of terms and conditions, or negotiated a loan. Given the benefit of the disclosure herein and understanding the intended systems that are generally available, one of ordinary skill in the art can readily ascertain the purpose and use of the term in the various embodiments and contexts disclosed herein as it relates to mutually agreed upon results achieved through completion of negotiations.
The term "negotiate" in its various forms may also be used specifically to describe an event, such as a negotiation event or event negotiation, including the agreement of a set of terms between parties. An event requiring a principal to agree or compromise may be considered a negotiation event, but is not limited thereto. For example, in a loan procurement process, the process of achieving a set of mutually accepted terms and conditions between parties may be considered a negotiation event. Thus, in some cases, the intelligent contract circuitry or robotic process automation system may adapt to communications, actions, or behaviors of the parties negotiating the event.
The term "payment" (and other forms) as used herein may be broadly understood to describe obtaining a tangible (e.g., physical), intangible (e.g., data, licenses, or rights), or monetary (e.g., payment) item or other obligation or asset from a source. The term generally refers to the entire anticipated procurement or complete completion of an item procurement of such items from an early stage related task to a later stage related task. The collection may produce a successful result if the item is submitted to the principal, or may produce an unsuccessful result if the item is not submitted to the principal or the principal does not obtain the item, or a combination thereof (e.g., a delayed or otherwise flawed submission of the item), but is not so limited. Collection may occur in many different contexts of contracts or loans, such as, but not limited to, lending, refinancing, merging, warranty, brokering, redemption stopping, and data processing (e.g., data collection), or a combination thereof. Collections may be used in the form of nouns (e.g., data collection or overdue payment collection, referring to events or descriptive events), as nouns to various items (e.g., mortgage collections referring to multiple items in a transaction), or as verbs (e.g., collecting to a borrower). For example, the borrower may receive the overdue payment from the borrower through an online payment, or may successfully receive the overdue payment through a customer service telephone call. In some embodiments, the smart contract circuit or robotic process automation system may perform collection for one or more parties and process appropriate tasks for completing or attempting collection (e.g., overdue payment) for one or more items. In some cases, the negotiation of the smart contracts or robotic process automation systems may not be complete or successful, and depending on such results, this may enable automatic actions or trigger other conditions or terms. The purpose and use of payment in the various embodiments and contexts disclosed herein can be readily determined by one of ordinary skill in the art, given the benefit of the disclosure herein and an understanding of the intended systems generally available.
The various forms of the term "collecting" may also be used herein more specifically in the noun form to describe the context of an event or thing, such as a collection event or collection. For example, a collection event may refer to a communication with a party or other activity that relates to, but is not limited to, acquiring an item in such an activity. For example, the payment may relate to an amount that the borrower pays the borrower through a payment process or through a checkout department. While not limited to overdue, delinquent, or default loans, collections may describe events, payments or departments or other terms related to a transaction or loan as a remedy for an overdue thing. Thus, in some cases, the smart contract circuit or robotic process automation system may collect payment or installment from the borrower, and the activity of doing so may be considered a collection event, but is not limited to such.
The term "payment" in its various forms may also be used herein, more specifically in adjectives or other forms, to describe context relevant to litigation, such as the outcome of a payment litigation (e.g., a litigation regarding overdue or default payment for a loan). For example, the outcome of a collect litigation may relate to delinquent items owed by the borrower or other party, and the collection associated with these delinquent items may be litigated by the party. Thus, in some cases, smart contract circuits or robotic process automation systems may receive, determine, or otherwise manage the results of a lawsuit.
The term "payment" in its various forms may also be used herein, more specifically in adjectives or other forms, to describe context relevant to an acquisition action, such as a payment action (e.g., an action that prompts an overdue payment or a default payment for a loan or other debt to be offered or obtained). The terms "rate of return for collection", "financial rate of return for collection" and/or "financial rate of return for collection" may be used. The result of such a collection action may or may not be a financial benefit. For example, a collect action may result in repayment of one or more outstanding funds on the loan, which may result in financial benefits to another party (e.g., the borrower). Thus, in some cases, the intelligent contract circuit or robotic process automation system may derive financial benefits from, or otherwise manage or somehow assist, the collection action. In an embodiment, the act of collecting may include the need to collect a litigation.
The various forms of the term "payment" (payment ROI, payment activity ROI, etc.) may also be used herein to more particularly describe the context associated with an action that receives value, such as a payment action (e.g., an action that prompts overdue or default payment of a loan or other debt to be offered or obtained) where there is a Return On Investment (ROI). The result of such a collect action may or may not have an ROI, whether with respect to the collect action itself (as the ROI of the collect action) or as the ROI of a more extensive loan or transaction by the subject of the collect action. For example, in the case of a default loan, the ROI of the collection action may be discreet, but not limited, depending on whether the ROI is provided to the principal, such as a borrower. The predicted payee ROI may be estimated or may be calculated based on the actual events that occur. In some cases, the smart contract circuit or robotic process automation system may present an estimated ROI of a collect action or collect event, or may calculate an ROI of an actual event occurring in a collect action or collect event, but is not limited thereto. In embodiments, such ROIs may be positive or negative numbers, whether estimated or actual.
The terms "reputation," "reputation measure," "borrower reputation," "entity reputation," and the like may include general, widely held beliefs, opinions, and/or opinions about individuals, entities, mortgages, and the like. Reputation metrics may be determined based on social data, including likes/dislikes, reviews of entities or products and services offered by entities, ranks of companies or products, current and historical market and financial data, including prices, forecasts, business recommendations, financial news about entities, competitors, and partners. Reputation may be cumulative in that product reputation and reputation of company leaders or chief scientists may affect the overall reputation of an entity. The reputation of an entity may be affected by the reputation of an organization associated with the entity (e.g., a school that the student has read). In some cases, smart contract circuitry or a robotic process automation system may collect or initiate collection of data related to the above and determine a reputation metric or ranking. The intelligent contract circuit or robotic process automation system may use the reputation metrics or rankings of the entities to determine whether to enter into an agreement with the entity, to determine terms and conditions of the loan, interest rate, etc. In some embodiments, the reputation-determined indicia may be correlated with the results of one or more transactions (e.g., a comparison of "likes" on a particular social media data set to a result index, such as successful payments, successful negotiations of results, ability to liquidate a particular type of collateral, etc.) to determine a reputation measure or ranking of the entity. Given the benefit of the disclosure herein and knowing the intended systems that are generally available, one of ordinary skill in the art can readily determine a "reputation," "reputation measure or ranking," and/or "use of a reputation in negotiations" a purpose and use in determining terms and conditions, determining whether to proceed with a transaction, and in other various embodiments and contexts disclosed herein.
Various forms of the term "collect" (e.g., payee) as used herein may also describe a party or entity that causes, manages, or facilitates a collection action, collection event, or other collection-related context. Objective, subjective, or historical metrics or data may be used to estimate or calculate the reputation of an interested party (e.g., payee) in the checkout process. For example, a payee may participate in a payee action, and the payee's reputation may be used to determine a decision, action, or condition. Similarly, collection may also be used to describe objective, subjective, or historical metrics or data to measure the reputation of the interested party (e.g., borrower, or debtor). In some cases, the smart contract circuit or robotic process automation system may provide a payee or metric in the context of a transaction or loan, or implement a payee.
The terms "collect" and "data collection" in their various forms (including data collection systems) may also be used herein more specifically to describe context related to the acquisition, organization, or processing of data, or a combination thereof, but are not limited thereto. The results of such data collection may be related to, but not limited to, item collection (e.g., grouping items physically or logically) or actions taken for delinquent payments (e.g., collateral, debt, etc.), or not at all. For example, data collection may be performed by a data collection system, where data is obtained, organized, or processed for decision-making, monitoring, or other purposes for prospective or actual trading or loans. In some cases, a smart contract or robotic process automation system may include a data collection or data collection system to perform some or all of the tasks of data collection, but is not limited to such. The purpose and use in the context of collecting data or information used herein can be readily determined and differentiated by those skilled in the art, given the benefit of the disclosure herein and knowing the intended system that is generally available.
As used herein, the terms "re-financing," "re-financing activity," "re-financing interaction," "re-financing results," and similar terms should be construed broadly. Without being limited to any other aspect or description of the present disclosure, the refinancing and refinancing activities include replacing existing mortgages, loans, bonds, debt transactions, etc. with new mortgages, loans, bonds, or debt transactions that repay or end a previous financial arrangement. In some embodiments, any modification to the terms and conditions of the loan and/or any substantial modification to the conditions and terms of the loan may be considered a re-financing activity. In some embodiments, the refinancing campaign is considered merely a modification to the loan agreement that effects a different financial outcome of the loan agreement. Typically, a new loan should be beneficial to the borrower or the issuer and/or agreed upon by both parties (e.g., to improve one party's original financial results, another party's warranty or other results). Refinancing may be performed to reduce interest rates, reduce periodic payments, change loan terms, change mortgages associated with loans, consolidate debts into a single loan, restructure debts, change loan types (e.g., variable interest rate to fixed interest rate), repay expired loans in response to credit score increases, expand loans, and/or in response to market condition changes (e.g., interest rate, mortgage value, etc.).
The re-financing activities may include: initiating a re-financing offer; initiating a re-financing request; configuring a re-financing rate; configuring a re-financing payment plan; configuring a refinancing balance in response to the amount or terms of the refinancing loan; collateral configured for refinancing (including variations in collateral used, variations in collateral terms and conditions, variations in collateral amounts, etc.); managing the use of re-financing revenue; canceling or setting the lien of different mortgages as appropriate according to changes in the re-financing terms and conditions; verifying ownership of a new collateral or an existing collateral used to secure the refinancing loan; an inspection process for managing property rights for securing new mortgages or existing mortgages for refinancing a loan; filling loan repayment application; negotiating terms and conditions for the refinancing loan; and completing the re-financing. The refinancing and refinancing activities may be disclosed in the context of data collection and monitoring services that collect a training set of interactions between entities for a set of loan refinancing activity. The refinancing and refinancing activities may be disclosed in the context of an artificial intelligence system that is trained using an interactive training set that includes the refinancing activities and the collection of results. The trained artificial intelligence can then be used to recommend refinancing campaigns, evaluate refinancing campaigns, make predictions around expected outcomes of refinancing campaigns, and the like. The re-financing and re-financing activities may be disclosed in the context of an intelligent contract system that may automate a subset of the re-financing interactions and activities. In one example, the intelligent contract system may automatically adjust the interest rate of the loan based on information collected via at least one of the internet of things system, the crowdsourcing system 120, a set of social network analysis services, and a set of data collection and monitoring services. Interest rates may be adjusted based on rules, thresholds, model parameters that determine or suggest loan refinancing rates based on the rates provided by the secondary borrower to the borrower, the borrower's risk factors (including predicted risk based on one or more predictive models using artificial intelligence), market factors (e.g., competitive rates provided by other borrowers), and so on. The results and events of the re-financing activity may be recorded in a distributed ledger. Based on the results of the refinancing campaign, the intelligent contracts for the refinancing loan may be automatically reconfigured to define the terms and conditions of the new loan, such as principal amount of the debt, balance of the debt, fixed interest rate, variable interest rate, payment amount, payment plan, top-end up line payoff plan, collateral statement, collateral substitutability statement, party, insured, guarantor, personal guaranty, lien, term, contract, redemption condition, default condition, and default outcome.
Those skilled in the art, having the benefit of the disclosure herein and understanding the intended systems generally available, can readily determine which aspects of the present disclosure will benefit from a particular application of a refinancing campaign, how to select or merge refinancing campaigns, how to implement a system, service, or circuit to automatically perform one or more (or all) aspects of a refinancing campaign, and the like. In selecting an appropriate set of interactive training sets, certain considerations of one skilled in the art or of embodiments of the present disclosure: training artificial intelligence to take action, suggest or predict the results of certain re-financing activities. Although specific examples of re-financing and re-financing activities are described herein for illustrative purposes, any embodiments that benefit from the disclosure herein, as well as any considerations understood by those skilled in the art having the benefit of the disclosure herein, are specifically contemplated within the scope of the present disclosure.
The terms "merge," "merge campaign," "loan merge," "debt merge," "merge plan," and similar terms as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, the merging, merging activities, loan merging, debt merging, merging plan may relate to repaying several smaller loans using a single large loan, and/or to repaying at least a portion of one or more of a second set of loans using one or more of a set of loans. In an embodiment, the loan merge may be secured (i.e., secured by the collateral) or unsecured. Loans may be consolidated to achieve a lower interest rate than one or more current loans, to reduce the monthly loan repayment total, and/or to allow debtors to comply with consolidated loans or other debtor obligations of the debtor. Loans that may be categorized as merge candidates may be determined according to a model that processes the attributes of entities involved in the set of loans, including the identity of the party, interest rates, payment margins, payment terms, payment plans, loan types, collateral types, financial conditions of the party, payment status, collateral conditions, and collateral values. Merging activities may include managing at least one of: identifying loans in a set of candidate loans; compiling a combined offer; compiling a merging plan; compiling content for the delivery of the consolidated offer; arranging for a combined offer; transmitting the combined offer; negotiating a merge offer modification; compiling a merging protocol; executing a merge protocol; modifying a collateral for a group of loans; processing a merged application workflow; managing and checking; management evaluation; setting interest rate; a deferred payment requirement; setting up a payment plan or reaching a merge agreement. In embodiments, there may be systems, circuits, and/or services for creating, configuring (e.g., using one or more templates or libraries), modifying, setting, or otherwise processing (e.g., in a user interface) various rules, thresholds, conditional processes, workflows, model parameters, etc., to determine or recommend a combined action or plan for a loan transaction or a set of loans based on one or more events, conditions, states, actions, etc. In embodiments, the consolidated plan may be based on various factors, such as payment status, interest rates of a set of loans, interest rates prevailing in a platform market or an external market, status of borrowers of a set of loans, status of collateral or assets, borrowers, risk factors of one or more insurers, market risk factors, and so forth. The merging and merging activities may be disclosed in the context of a data collection and monitoring service that collects a training set of interactions between entities for a set of loan merging activities. The merging and merging activities may be disclosed in the context of an artificial intelligence system that is trained using a collected interactive training set that includes the merging activities and results associated with those activities. Trained artificial intelligence can then be used to recommend a consolidated campaign, evaluate the consolidated campaign, make predictions about the expected outcome of the consolidated campaign, and based on similar models, including debt status, status of collateral or assets used to secure or support a set of loans, status of a business or business operations (e.g., accounts receivable, accounts payable, etc.), status of parties (e.g., net worth, wealth, debt, location, and other status), behavior of parties (e.g., behavior indicating preferences, behavior indicating debt preferences), and so forth. The debt merger, loan merger, and related merger activities may be disclosed in the context of an intelligent contract system that may automate a subset of the merged interactions and activities. In an embodiment, the merging may include: combining multiple sets of terms and conditions of the loan; selecting an appropriate loan; configuring payment terms of the consolidated loan; configuring a payment plan of the existing loan; communication encourages mergers, etc. In embodiments, the artificial intelligence of the smart contract may automatically recommend or set rules, thresholds, actions, parameters, etc. (optionally by learning to perform such operations based on a training set of results over time), resulting in a recommended consolidated plan that may specify a series of actions required to complete a recommended or desired consolidated result (e.g., within a range of acceptable results), which may be automated, and which may involve conditional execution of steps based on monitored conditions and/or smart contract terms that may be created, configured, and/or considered by the consolidated plan. The merge plan may be determined and executed based on market factors (e.g., competitive interest rates provided by other borrowers, value of mortgages, etc.) and at least a portion of regulatory and/or compliance factors. The merge plan may be generated and/or executed for the creation of a new merged loan, for a secondary loan associated with the merged loan, for a modification of an existing loan associated with the merge, for the terms of refinancing of the merged loan, for a redemption scenario (e.g., changing from a guaranteed loan interest rate to an unsecured loan interest rate), for a bankruptcy or inability scenario, for a scenario involving a market change (e.g., a change in an existing interest rate), and so forth.
Some activities related to loans, mortgages, entities, etc. may or may not be applicable to various loans, or may not be explicitly applicable to consolidated activities. The classification of the activity as a consolidated activity may be based on the context of the loan in which the activity occurred. However, those skilled in the art, having the benefit of the disclosure herein and understanding the intended systems that are generally available, may readily determine which aspects of the present disclosure will benefit from a particular application of the consolidation activities, how to select or combine consolidation activities, how to implement selected services, circuits, and/or systems described herein to perform certain loan consolidation operations, and the like. Although specific examples of combining and merging activities are described herein for illustrative purposes, any embodiment that would benefit from the disclosure herein, as well as any consideration understood by one of ordinary skill in the art having the benefit of the disclosure herein, is specifically contemplated within the scope of the present disclosure.
The terms "warranty loan," "warranty loan transaction," "warranty factor," "warranty loan interaction," "warranty property," or "groups of properties for warranty" and similar terms as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, the warranty may be applied to warranty assets, such as invoices, inventory, accounts receivable, etc., where the value of the item is realized in the future. For example, the value is higher after receivables are paid and the risk of breach is lower. Inventory and work-in-process (WIP) may be more valuable as an end product than as a component. References to accounts receivable should be understood to include such terms, not limiting terms. The warranty may include the sale of accounts receivable (typically cash) at a cash-out rate. The warranty may also include using the accounts receivable as collateral for the short-term loan. In both cases, the value of the receivables or invoices may be posted for a variety of reasons, including future monetary value; receivables limit (e.g., 30 days net payment and 90 days net payment); the degree of default risk of accounts receivable; an accounts receivable status; a Work In Progress (WIP) status; stock state; delivery and/or shipping status; financial status of the accounts receivable arrears; shipping and/or billing status; a payment status; a borrower status; stock state; risk factors for the borrower, and one or more of the insurers; a market risk factor; status of debt (whether there are other liens in the receivables or inventory debts); the status of the mortgage asset (e.g., inventory status — whether current or expired, whether an invoice is delinquent); status of the enterprise or enterprise operations; the status of the party to the transaction (e.g., net worth, wealth, debt, location, and other status); transaction party behavior (e.g., behavior indicating preferences, behavior indicating negotiation styles, etc.); current interest rate; any current regulatory and compliance issues related to inventory or accounts receivable (e.g., whether the product is expected to be properly approved if inventory is taken into account, and legal proceedings for borrowers and many others, including predicted risk based on one or more predictive models using artificial intelligence). A policy holder refers to an individual, business, entity, or group thereof who agrees to provide an exchange of value to obtain an invoice directly in a sale or to use the invoice as a collateral for a value loan. The loan warranty may include determining candidates for the warranty (borrowers and borrowers), a warranty plan specifying proposed accounts receivable (e.g., accounts receivable that meet all, part, or only certain criteria), and proposed discount factors, transmitting plans to potential parties, providing offers and receiving offers, verifying the quality of accounts receivable, processing conditions for accounts receivable within the loan terms. Although specific examples of warranties and warranty activities are described herein for illustrative purposes, any embodiments that benefit from the disclosure herein, as well as any considerations understood by those skilled in the art having the benefit of the disclosure herein, are specifically contemplated within the scope of the present disclosure.
The terms "mortgage," "proxy mortgage," "mortgage," and/or "mortgage-related activity" as used herein should be broadly construed. Without being limited to any other aspect or description of the disclosure, a mortgage is an interactive process in which a borrower provides the property or right to set aside a property of a valuable item (typically property) to the borrower as a guarantee in exchange for money or other valuable items, typically in conjunction with interest compensation, to the borrower. The exchange includes conditions under which the property is returned to the borrower and/or the property lien is removed after the loan is repaid. Proxy mortgages may include determining potential property, borrowers, and other lending parties, and arranging or negotiating mortgage terms. Certain components or activities may not be considered individually as related to a mortgage, but may be considered as related to a mortgage when used in conjunction with a mortgage, taking an action in accordance with the mortgage, an entity or party to the mortgage, and the like. For example, an agent may be adapted to offer various loans, including unsecured loans, direct property sales, and the like. The mortgage activity and mortgage interaction may include a mortgage marketing campaign: identifying a group of potential borrowers; identifying mortgage property; identifying mortgage warranty property; ensuring that the borrower obtains qualification; searching for and/or verifying property rights against the potential mortgage property; evaluating, evaluating or valuating property against the potential mortgage property; verifying revenue; performing a demographic analysis on the borrower; identifying a patron; determining an available interest rate; determining available payment terms and conditions; analyzing the existing mortgage; performing comparative analysis on the existing mortgage terms and the new mortgage terms; completing the application workflow (e.g., keeping the application forward by appropriately initiating subsequent steps in the flow); filling in an application field; compiling a mortgage protocol; completing the collateral protocol attached table; negotiating mortgage terms and conditions with the patron; negotiating mortgage terms and conditions with the borrower; transferring property rights; setting a mortgage property lien right; and to arrive at a mortgage agreement, and similar terms used herein should be construed broadly. Although specific examples of mortgages and mortgages are described herein for illustrative purposes, any embodiment that benefits from the disclosure herein, as well as any consideration understood by those of ordinary skill in the art having the benefit of the disclosure herein, is specifically contemplated within the scope of the present disclosure.
The terms "liability management", "liability transaction", "liability action", "liability terms and conditions", "joint liability", "merged liability" and/or "liability combination" as used herein should be broadly construed. Without being limited to any other aspect or description of the disclosure, the debt includes an item of monetary value owed to another party. The loan typically results in the borrower holding debt (e.g., money that must be paid in accordance with the terms of the loan, which may include interest). The consolidation of debts includes the use of a new single loan to repay multiple loans (or various other configurations of the debt structure described herein and understood by those skilled in the art). In general, a new loan may have better terms or a lower interest rate. A debt portfolio includes many parts or groupings of debts, often with different characteristics, including terms, risks, etc. Debt portfolio management may involve decisions about the quantity and quality of debts held and how to best balance the various debts to achieve a desired risk/return condition, based on: investment policy, individual debt or risk return for a group of debts. A debt may be a joint loan where multiple borrowers offer a single loan (or a group of loans) to a borrower. The debt combination may be sold to a third party (e.g., at a discount rate). Liability compliance includes various measures taken to ensure that liabilities are paid out. Proving compliance may include taking a record of actions taken to pay off debts
The debt-related transaction (debt transaction) and the debt-related action (debt action) may include: an offer debt transaction; underwriting debt transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; completing the transaction; setting terms and conditions of the transaction; providing a notification that the providing is required; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; a joint debt; and/or consolidate debts. The debt terms and conditions may include the balance of the debt, the principal amount of the debt, the fixed interest rate, the variable interest rate, the payment amount, the payment plan, the endmost grand hold plan, the guaranteed asset description of the debt, the asset substitutability description, the party, the issuer, the purchaser, the insured, the guarantor, the collateral, the personal guaranty, the lien, the term, the obligation, the redemption hold, the default condition, and the consequences of the breach. Although specific examples of liability management and liability management activities are described herein for illustrative purposes, any embodiment that benefits from the disclosure herein, as well as any consideration understood by those skilled in the art that benefits from the disclosure herein, is specifically contemplated within the scope of the present disclosure.
The terms "condition," "condition classification," "classification model," "condition management," and similar terms as used herein are to be construed broadly. Without being limited to any other aspect or description of the present disclosure, condition classification, classification model, and condition management include classifying or determining the terms or conditions of a property, issuer, borrower, loan, debt, bond, regulatory status, bond, loan or debt transaction, etc., specified and monitored in a contract. Based on the classified condition of the asset, condition management may include actions to maintain or improve the condition of the asset or to use the asset as a collateral. Based on the classified conditions of the issuer, borrower, party regulatory status, etc., condition management may include actions to change the terms or conditions of the loan or bond. The condition classification may include various rules, thresholds, condition programs, workflows, model parameters, etc. to classify the terms or conditions of an asset, issuer, borrower, loan, debt, bond, regulatory status, bond, loan or debt transaction, etc., based on data from a report or from an internet of things device, data from a set of environmental condition sensors, data from a set of social network analysis services, and a set of algorithms for querying network domains, social media data, crowd-sourced data, etc. Condition classification can include grouping or tagging entities or clustering entities according to similar positioning relative to certain aspects of the classified condition (e.g., risk, quality, ROI, likelihood of recovery, likelihood of default, or some other aspect of a related debt).
Where various classification models are disclosed, the classifications and classification models may relate to collateral, publishers, borrowers, fund distribution, or other geographic locations. In the case of open classification and classification models, artificial intelligence is used to improve the classification model (e.g., refine the model by refining using artificial intelligence data). Thus, in some cases, artificial intelligence may be considered part of the classification model, and vice versa. In the case of public classification and classification models, social media data, crowd-sourced data, or IoT data is used as input to the refinement model, or as input to the classification model. Examples of IoT data may include images, sensor data, location data, and the like. Examples of social media data or crowd-sourced data may include the behavior of a loan party, the financial status of a party, the compliance of a party to terms or conditions of a loan or bond, and so forth. The lending parties may include bond issuers, related entities, borrowers, and debt-related third parties. Condition management may be discussed in conjunction with intelligent contract services, which may include condition classification, data collection and monitoring, and bond, loan and debt transaction management. The data collection and monitoring service is also discussed in connection with classification and classification models that are relevant when classifying the issuer of a bond issuer, the assets or collateral assets associated with the bond, the collateral assets providing a guarantee for the bond, the parties to the bond, and the sets of bonds. In some embodiments, a classification model may be included when discussing bond types. Specific steps, factors or refinements may be considered as part of the classification model. In various embodiments, the classification model may vary in one embodiment or in the same embodiment as is relevant to a particular jurisdiction. Different classification models may use different data sets (e.g., based on issuer, borrower, mortgage property, bond type, loan type, etc.), and multiple classification models may be used in a single classification. For example, one type of bond (e.g., a municipal bond) may allow a classification model to be based on bond data from similarly sized and economically prosperous municipalities, while another classification model may emphasize data from IoT sensors associated with mortgage assets. Thus, depending on the embodiment and particulars of the bond, loan or debt transaction, different classification models will provide benefits or risks over other classification models. The classification model includes methods or concepts for classification. The classified conditions of the bond, loan or bond transaction may include principal amount of the bond, balance of the bond, fixed interest rate, variable interest rate, payment amount, payment plan, top-end grand payback plan, guaranteed asset description of the bond, loan or bond transaction, asset substitutability description, party, issuer, purchaser, insured person, guarantor, collateral, personal guaranty, lien, term, contract, redemption-out condition, default condition, and default consequence. The classified conditions may include types of bond issuers, such as municipalities, companies, contractors, government entities, non-government entities, and non-profit entities. An entity may include a set of publishers, a set of bonds, a set of parties, and/or a set of assets. The classified conditions may include conditions of the entity (e.g., net worth, wealth, debt, location, and other conditions), behavior of the principal (e.g., behavior indicating a preference for a debt), and so on. The classified conditions may include asset or collateral types, such as: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a set of inventory, goods, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contract rights, antiques, fixtures, furniture, equipment, tools, machinery, and conditions under which personal property is classified may include bond types, where bond types may include municipal bonds, government bonds, treasury bonds, asset security bonds, and corporate bonds. The classified conditions may include default conditions, redemption-out conditions, conditions indicative of a breach of a contract, financial risk conditions, behavioral risk conditions, policy risk conditions, financial health conditions, physical defect conditions, physical health conditions, entity risk conditions, and entity health conditions. The classified conditions may include an environment, wherein the environment may include an environment selected from a municipal environment, a business environment, a securities trading environment, a real estate environment, a commercial facility, a warehousing facility, a transportation environment, a manufacturing environment, a storage environment, a house, and a vehicle. Actions based on the status of assets, issuers, borrowers, loans, debts, bonds, regulatory status, etc. may include managing, reporting, integrating, consolidating, or otherwise processing a set of bonds (e.g., municipal bonds, corporate bonds, performance bonds, etc.), a set of loans (subsidized and non-subsidized, bond transactions, etc.), monitoring, categorizing, predicting, or otherwise processing reliability, quality, status, health, financial status, physical status, or other information about an insured person, a set of collateral supported for an insured person, assets supported for an insured person, etc. Bond transaction activities responsive to bond conditions can include: an offer debt transaction; underwriting debt transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; completing the transaction; setting terms and conditions of the transaction; providing a notification that the providing is required; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; a joint debt; and/or consolidate debts.
Given the disclosure herein and an understanding of expected systems that are generally available, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit from a particular application of the classification model, how to select or combine classification models to achieve conditions, and/or calculate the value of a collateral based on desired data. In selecting appropriate conditions to manage, certain considerations for one skilled in the art or an embodiment of the invention include, but are not limited to: the validity of the conditions of a given trading jurisdiction, the available data for a given collateral, the type of expected transaction (loan, bond or debt), the particular type of collateral, the ratio of loan to value, the ratio of collateral to loan, the total transaction/loan amount, the credit scores of the borrower and borrower, and other considerations. Although specific examples of conditions, condition classifications, classification models, and condition management are described herein for illustrative purposes, any embodiment that would benefit from the disclosure herein, as well as any consideration understood by one of ordinary skill in the art having the benefit of the disclosure herein, is specifically contemplated within the scope of the present disclosure.
The term "categorizing" (and similar terms) as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, classifying a condition or item may include the act of classifying the condition or item into a group or category based on some aspect, attribute, or feature of the condition or item, where the condition or item is common or similar to all items placed in the category, although the categories or categories based on other aspects or conditions at the time are different. Classification may include identifying one or more parameters, features, characteristics, or phenomena associated with conditions or parameters of an item, entity, person, process, project, financial structure, or the like. The conditions classified by the condition classification system may include default conditions, redemption-stop conditions, conditions indicative of a breach of a contract, financial risk conditions, behavioral risk conditions, contract performance conditions, policy risk conditions, financial health conditions, physical defect conditions, physical health conditions, entity risk conditions, and/or entity health conditions. The classification model may automatically classify or categorize items, entities, processes, projects, financial structures, etc. based on data received from various sources. The classification model may classify items based on a single attribute or a combination of attributes, and/or may utilize data about the items and models to be classified. The classification model may classify individual or groups of items, entities, financial structures. The bonds may be classified based on bond type (e.g., municipal bonds, corporate bonds, performance bonds, etc.), rate of return, bond rating (a third party indicator of bond quality indicating the financial strength of the issuer on the bond and/or the ability to pay the bond principal and interest), and the like. The borrower or bond issuer may be classified based on the type of borrower or issuer, the licensing attributes (e.g., based on income, wealth, location (domestic or foreign), various risk factors, the issuer's condition, etc.). The borrower may be categorized based on licensing attributes (e.g., income, wealth, total assets, location, credit history), risk factors, current status (e.g., employment, students), the behavior of the party (e.g., behavior indicating preferences, reliability, etc.), and the like. The situation classification system may classify the student receiving the loan based on: the progress of the student in the academic degree, the achievement or ranking of the student in the class, the status of the student at school (admission, trial reading, etc.), the participation of the student in non-profit activities, the postponed status of the student, and the participation of the student in public welfare activities. The conditions classified by the condition classification system may include the status of a set of mortgages of the loan or the status of an entity associated with the loan guarantee. The conditions classified by the condition classification system may include medical conditions of borrowers, guarantors, subsidizers, and the like. The condition classified by the condition classification system may include compliance with at least one of laws, regulations, or policies associated with the loan transaction or the loan institution. The conditions classified by the condition classification system may include the condition of the bond issuer, the condition of the bond, the rating of the loan-related entity, and the like. The condition classified by the condition classification system may include an identification of a machine, component, or mode of operation. The conditions classified by the condition classification system may include a state or context (e.g., a state of a machine, a process, a workflow, a market, a storage system, a network, a data collector, etc.). The condition classification system may classify processes related to a state or context (e.g., data storage processes, network coding processes, network selection processes, data market processes, power generation processes, manufacturing processes, refining processes, mining processes, boring processes, and/or other processes described herein). The condition classification system may classify a set of loan refinancing conditions based on a prediction of a set of loan refinancing actions. The condition classification system may classify a set of loans as merging candidate loans based on the following attributes: the identity of the party, interest rate, payment balance, payment terms, payment plan, loan type, collateral type, financial status of the party, payment status, collateral value. The situation classification system may classify entities involved in a set of warranty loans, bond issuing campaigns, mortgage loans, and the like. The situation classification system may classify a set of entities based on the prediction results from various loan management activities. The situation classification system may classify the situation of a set of publishers based on information from an internet of things data collection and monitoring service, a set of parameters associated with the publishers, a set of social network monitoring and analysis services, and/or the like. The situation classification system may classify a set of loan receipt actions, loan merge actions, loan negotiation actions, loan re-financing actions, etc., based on a set of predictions for these activities and entities.
The term "subsidized loan" (and similar terms) as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, a subsidized loan is a loan of currency or an item of value, in which interest payment for the value of the loan may be delayed, deferred, or delayed, including or excluding accrued interest, such as when the borrower is school, unemployed, ill, or the like. In an embodiment, the loan may be subsidized when a portion or subset of the loan's payment interest is borne or guaranteed by a person other than the borrower. Examples of subsidy loans may include municipal subsidy loans, government subsidy loans, school-aid loans, property guarantee subsidy loans, and corporate subsidy loans. Examples of subsidized assisted loans may include assisted loans that may be subsidized by the government and may or may not accumulate interest based on the progress of the student making the degree, the student engaging in non-profit activities, the deferred status of the student, and the student engaging in public welfare activities. Examples of government subsidized house loans may include government subsidies that may exempt the borrower from paying delivery costs, first mortgage loan repayment, etc. Such conditions for subsidy loans may include the location of the property (rural or urban), the income of the borrower, the identity of the borrower's soldiers, the ability of the purchased house to meet health and safety standards, profit limits earned in selling the house, etc. Some uses of the term "loan" may not apply to subsidized loans, but to regular loans. Those skilled in the art, with the benefit of the disclosure herein and understanding of the intended systems generally available, can readily determine which aspects of the present disclosure will benefit from consideration of a subsidized loan (e.g., determining the value of the loan, negotiation related to the loan, terms and conditions related to the loan, etc.), where the borrower may exempt from some common loan obligations for non-subsidized loans, where subsidization may include exemption, delay or postponement of interest in the loan, or payment of interest by a third party. Subsidies may include payment of delivery costs, including points, first payments, etc., by individuals or entities other than the borrower, and/or how to incorporate the processes and systems of the present disclosure to enhance or benefit from title verification.
The term "subsidy loan management" (and similar terms) as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, subsidized loan management may include a number of activities and solutions for managing or responding to one or more events related to the subsidized loan, where the events may include: applying for subsidy loan; a loan is to be subsidized; accepting a subsidy loan; providing underwriting information for the subsidy loan; providing a credit report of the borrower applying for the subsidy loan; the required payment is made as part of a deferred payment for the loan patch; setting an interest rate for a subsidy loan where a lower interest rate may be part of the subsidy; deferring the payment request as part of the loan patch; identifying a collateral for the loan; verifying the property rights of the loan mortgage or guarantee; recording changes to property rights; evaluating the value of the loan collateral or guaranty; checking the property involved in the loan; identifying a change in a status of an entity associated with the loan; a change in value of an entity associated with the loan; the working state of the borrower changes, and the financial rating of the borrower changes; a change in financial value of an item provided as a warranty; providing loan insurance, providing evidence of property insurance associated with the loan; providing evidence of loan eligibility; identifying a loan warranty; an underwriting loan; paying a loan; defaulting the loan; the loan is collected; settlement loan; setting the terms and conditions of the loan; the redemption of property subject to loan restrictions; modifying the terms and conditions of the loan; terms and conditions for setting up the loan (e.g., principal amount of the debt, balance of the debt, fixed interest rate, variable interest rate, payment amount, payment plan, last-minute hold plan, collateral description, collateral substitutability description, party, insured person, guarantor, collateral, personal guaranty, lien, term, contract, redemption condition, default condition, and default outcome); or managing loan-related activities (e.g., without limitation, finding parties interested in participating in a loan transaction, processing a loan application, underwriting a loan, making a loan legal contract, monitoring loan fulfillment, paying a loan, recombining or modifying a loan, settling a loan, monitoring a loan mortgage, building a loan bank, stopping a loan, withdrawing a loan, merging loans, analyzing loan fulfillment, processing a loan default, transferring ownership of a property or mortgage, and completing a loan transaction), etc. In an embodiment, a system for processing a subsidy loan may include classifying a set of parameters for a set of subsidies based on data related to parameters obtained from an internet of things data collection and monitoring service. The classification of the set of parameters for the set of subsidized loans may also be based on data obtained from one or more configurable data collection and monitoring services that utilize social network analysis services, crowdsourcing services, or the like to obtain parameter data (e.g., determining that a person or entity is eligible for a subsidized loan, determining a social value to provide a subsidized loan or to remove a subsidy from a loan, determining that a subsidizing entity is legal, determining appropriate terms of the subsidy based on characteristics of the buyer and/or the subsidizer, etc.).
The terms "redemption" and "redemption conditions" and "default redemption collateral" (and similar terms) as used herein are to be construed broadly. Without being limited to any other aspect or description of the disclosure, the redemption condition, default, etc. describes that the borrower fails to satisfy the loan terms. Without being limited to any other aspect or description of the disclosure, redemption includes the process of a borrower attempting to withdraw a loan balance from a borrower in a redemption or default condition or redeem a mortgage as a loan guarantee in lieu of the borrower's rights. Failure to satisfy the terms of the loan may include failure to pay a specified payment, failure to comply with the payment plan, failure to make a final hold payment, failure to properly warrantMortgages, failure to maintain the mortgage in a particular condition (e.g., in good maintenance), obtaining a second loan, etc. Redemption may include notifying the borrower, the public, the jurisdiction, by way of a redemption auction, or the like, to forcibly sell the collateral. At the time of redemption, the collateral may be placed on an open auction website (e.g., eBay) TM Or a public auction website applicable to a particular type of property). The minimum opening price for the collateral may be set by the borrower and may cover the loan balance, loan interest, fees associated with the redemption of the loan, etc. Attempting to reclaim the loan balance may include transferring the collateral's deed in lieu of redemption (e.g., a real estate mortgage where the borrower holds the property deed as a collateral loan collateral). Redemption may include possession or withdrawal of the collateral (e.g., sports cars, yachts, etc., ATVs, skis, jewelry). Redemption may include securing collateral associated with the loan (e.g., by locking a connected device, such as a smart lock, smart container, etc. containing or securing the collateral). Redemption may include arranging for the carrier, the forwarder, etc. to ship the collateral. Redemption may include arranging for a drone, robot, or the like to transport the collateral. In embodiments, the loan may allow for alternative mortgages or transfer of liens from the mortgage originally used to secure the loan to an alternative mortgage, where the value of the alternative mortgage (to the borrower) is higher than the original mortgage, or where the borrower has more rights in the item. As a result of the alternative mortgage, the alternative mortgage can be the subject of a forced sale or a rebate when the loan is closed. Some usage of the term "breach" may not apply to the redemption of a redemption, but rather to the general or breach of the condition of the article. Given the disclosure herein and knowing the anticipated systems that are generally available, one of skill in the art can readily determine which aspects of the disclosure will benefit from redemption-out, and/or how to combine the processes and systems of the disclosure to enhance or benefit from redemption-out. Some considerations of those skilled in the art in determining the terms of redemption-up, redemption status, default, etc., refer to the borrower's failure to meet the terms of the loan and the borrower's associated attempt to withdraw the loan balance or gain ownership of the collateral.
The terms "verification of property", "property verification", "verification of property" and similar terms as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, title verification includes any work verifying or confirming an individual or entity's ownership or equity to a property item such as a vehicle, a boat, an airplane, a building, a house, real estate, undeveloped land, a farm, a crop, a municipal facility, a warehouse, a set of inventory, a commodity, a security, currency, a value token, a ticket, crypto currency, a consumable, an edible item, a beverage, a precious metal, a jewelry item, a gemstone, an intellectual property item, intellectual property, a contract right, an antique, a fixture, furniture, equipment, tools, machinery, and a personal property. The work to verify ownership may include reference to sales tickets, government documents for ownership transfer, legal willingness to transfer ownership, revocation documents for property liens, verification of transfer of intellectual property rights to proposed borrowers in appropriate jurisdictions, and the like. For real estate, validation may include reviewing deeds and records of a country, state, county, or regional court where the building, house, real estate, undeveloped land, farm, crop, municipal facility, vehicle, ship, aircraft, or warehouse is located or registered in the country, state, county, or region. Some uses of the term "authentication" may not apply to authentication of property or property authentication, but rather to whether the validation process is operating correctly, whether the person has been correctly identified using biometric data, whether the intellectual property is valid, whether the data is correct and meaningful, and so forth. Given the disclosure herein and knowing the intended systems that are generally available, one of ordinary skill in the art can readily determine which aspects of the present disclosure will benefit from title validation, and/or how to combine the processes and systems of the present disclosure to enhance or benefit from title validation. Certain considerations of those skilled in the art in determining whether the term "verify" validity is a title verification are specifically considered within the scope of the present disclosure.
Without being limited to any other aspect or description of the present disclosure, authentication includes any authentication system, including but not limited to: verifying the title of the loan collateral or guarantee, verifying the collateral condition of the guarantee or loan, verifying the status of the loan guarantee, and so on. For example, the verification service may provide a borrower with a mechanism to provide a loan with more certainty, such as by verifying the loan or warranty information components (e.g., income, employment, property rights, loan status, mortgage status, and property status). In a non-limiting example, the verification service circuitry may be configured to verify the plurality of loan information components with respect to a financial entity that determines a loan condition of the property. Certain components may not be considered separately verification systems, but may be considered verified in an aggregated system — for example, an internet of things component may not be considered a separate verification component, whereas an internet of things component for property data collection and monitoring may be considered a verification component that is applied to verify reliability parameters for a personal guarantee of a loan when the internet of things component is associated with a mortgage property. In some embodiments, other similarly appearing systems may be distinguished in determining whether these systems are used for verification. For example, a blockchain-based ledger can be used to verify identity in one instance and maintain confidential information in another instance. Thus, the benefits of the present disclosure may be applied to a variety of systems, and any such system may be considered herein to be a verification system, while in certain embodiments, a given system may not be considered herein to be a verification system. Given the disclosure herein and an understanding of commonly available prospective systems, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit from a particular system and/or how to combine the processes and systems of the present disclosure to enhance the operation of a prospective system. Certain considerations of those skilled in the art in determining whether a prospective system is a verification system and/or whether aspects of the present disclosure may benefit or enhance the prospective system include, but are not limited to: the loan platform is provided with a social network monitoring system and is used for verifying the reliability of loan guarantee; the loan platform is provided with an internet of things data collection and monitoring system and is used for verifying the reliability of loan guarantee; the lending platform is provided with a crowdsourcing and automatic classification system and is used for verifying the condition of the bond issuers; a crowdsourcing system for verifying loan mortgage quality, ownership, or other conditions; biometric authentication applications, such as using DNA or fingerprints; an IoT device to collectively verify the location and identity of capital improvements tagged by a virtual asset tag; a verification system using a voting or consensus protocol; an artificial intelligence system trained to recognize and verify events; authentication information, such as title records, video clips, photos or testimonials; validating statements, relating to actions, such as to validate the occurrence of a compliance condition, validate the occurrence of a breach condition, prevent misbehavior or false statements, reduce uncertainty or reduce information asymmetry, and the like.
The term "underwriting" (and similar terms) as used herein should be construed broadly. Without being limited to any other aspect or description of the present disclosure, underwriting includes any underwriting, including but not limited to: underwriting related to the underwriter, providing loan underwriting information, underwriting debt transactions, underwriting bond transactions, underwriting subsidy loan transactions, underwriting security transactions, and the like. The underwriting service may be provided by a financial entity, such as a bank, insurance or investment company, whereby the financial entity vouches for payment and assumes a financial risk of vouching for liability in the event that a loss condition (e.g., damage or financial loss) is determined. For example, a bank may underwrite a loan through a mechanism that performs a credit analysis that may result in determining a loan to be issued, e.g., by analyzing personal information components related to the application of a consumer loan by a personal borrower (e.g., work experience, payroll and financial statements, publicly available information, such as the borrower's credit history), analyzing business financial information components from the company requesting the business loan (e.g., tangible equity, debt to value ratios (leverage), and available liquidity (liquidity)), and so on. In a non-limiting example, the underwriting service circuit may be configured to underwrite a financial transaction that includes a plurality of financial information components relative to a financial entity for determining a financial condition of the asset. In some embodiments, the underwriting component may be considered an underwriting for some purposes but not others — for example, an artificial intelligence system for collecting and analyzing transaction data may be used in conjunction with an intelligent contract platform to monitor loan transactions, but may also be used to collect and analyze underwriting data, for example, using a model trained by a human expert underwriter. Thus, the benefits of the present disclosure may apply to a variety of systems, and any such system may be considered an underwriting herein, while in certain embodiments, a given system may not be considered an underwriting herein. Given the disclosure herein and an understanding of commonly available prospective systems, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit from a particular system and/or how to combine the processes and systems of the present disclosure to enhance the operation of a prospective system. Certain considerations of those skilled in the art in determining whether a prospective system is underwritten and/or whether aspects of the present disclosure may benefit or enhance the prospective system include, but are not limited to: a loan platform having a loan underwriting system with a set of data integration microservices including, for example, data collection and monitoring services, block chain services, artificial intelligence services, and intelligent contract services for underwriting loan entities and transactions; underwriting flows, operations and services; underwriting data, such as data relating to the identity of potential and actual parties involved in insurance and other transactions, actuarial data, data relating to the probability and/or extent of risk occurrence associated with an activity, data relating to observed activities, and other data used to underwrite or estimate risk; underwriting applications such as, but not limited to, underwriting any insurance offer, any loan or any other transaction, including detecting, describing or predicting risk potential and/or scope, underwriting or inspection procedures of an entity providing a loan solution, any application that analyzes a solution, or an asset management solution; underwriting insurance policies, loans, guarantees, or guarantees; a blockchain and intelligent contract platform for aggregating identity and behavioral information of an insurance underwriting, such as a set of events, transactions, activities, identities, facts, and other information related to the underwriting process using an optional distributed ledger; crowd-sourcing platforms, such as underwriting of various loans and guarantees; a loan underwriting system having a set of data integration microservices including data collection and monitoring services, block chain services, artificial intelligence services and intelligent contract services to underwrite loan entities and transactions; underwriting solutions to create, configure, modify, set, or otherwise process various rules, thresholds, conditional procedures, workflows, or model parameters; underwriting an action or plan to manage a set of loans of one or more given types for reclaiming, consolidating, stopping, bankrupting, bankruptcy, existing loan modifications, conditions involving market changes, stopping activities, based on one or more events, conditions, states, actions, secondary loans, or transactions that provide a guarantee for the loans; an adaptive intelligence system comprising an artificial intelligence model trained on expert-based underwriting activity training sets and/or underwriting action results to generate a set of predictions, classifications, control instructions, plans, models; the loan underwriting system is provided with a set of data integration micro services, wherein the set of data integration micro services comprise data collection and monitoring services, block chain services, artificial intelligence services and intelligent contract services and are used for underwriting loan entities and transactions and the like.
The term "application" (and similar terms) as used herein should be broadly construed. Without being limited to any other aspect or description of the present disclosure, insuring includes any insurance, including but not limited to: applying a guarantee for the loan; providing insurance proofs for loan-related assets; a first entity accepts the risk or responsibility of another entity, etc. Insuring or insurance may be a mechanism by which the insurance holder may be protected from financial loss, for example in the form of risk management for risk of accidental or indeterminate loss. The insurance mechanism may provide insurance, determine insurance requirements, determine evidence of insurance, etc., e.g., in connection with an asset, an asset transaction, an asset loan, a guarantee, etc. The entity that provides insurance may be referred to as an insurer, insurance company, insurance carrier, insurer, etc. For example, the application mechanism may provide a mechanism for the financial entity to determine evidence of insurance for the loan-related property. In a non-limiting example, the insurance service circuit may be configured to determine an insurance evidence condition for the property based on a plurality of insurance information components relative to a financial entity for determining a loan condition of the property. In some embodiments, components may be viewed as underwriting for some purposes but not others — for example, blockchains and intelligent contract platforms may be used to manage various aspects of loan transactions, such as identity and confidentiality, but may also be used to aggregate identity and behavioral information for insurance underwriting. Thus, the benefits of the present disclosure may apply to a variety of systems, and any such system may be considered an application herein, while in certain embodiments, a given system may not be considered an application herein. Given the disclosure herein and an understanding of commonly available prospective systems, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit from a particular system and/or how to combine the processes and systems of the present disclosure to enhance the operation of a prospective system. Certain considerations of those skilled in the art in determining whether a prospective system is an application and/or whether aspects of the present disclosure may benefit or enhance the prospective system include, but are not limited to: insurance facilities, such as branches, offices, storage facilities, data centers, underwriting services, and the like; insurance claims, such as for outage insurance, product liability insurance, commodity, facility or equipment insurance, flood insurance, contract-related risk insurance, and the like, as well as claim data relating to product liability, general liability, worker compensation, contract-related injuries and other liability claims and claim data, such as supply contract performance claims, product delivery claims, contract claims, damage claims, redemption points or reward claims, access rights claims, warranty claims, compensation claims, energy production claims, delivery claims, time claims, milestones, key performance indicators, and the like; insurance-related loans; insurance service, insurance broker service, life insurance service, health insurance service, retirement insurance service, property insurance service, accidental injury insurance service, financial insurance service, reinsurance service; the block chain and intelligent contract platform is used for aggregating the identity and behavior information of insurance underwriting; the identity of the insurance applicant, the identity of the party willing to provide insurance, information about the risk of possible insurance (of any type, but not limited to, for example, property, life, travel, infringement, health, housing, business liability, product liability, automobile, fire, flood, casualties, retirement, unemployment, etc.); the distributed ledger can be used to facilitate offers and underwriting of small insurance, for example, to define defined risks associated with defined activities that range less than a typical insurance policy over a defined period of time; to secure loans, to provide insurance certificates for loan-related properties, and the like.
The term "polymerization" (and similar terms) as used herein should be broadly construed. Without being limited to any other aspect or description of the present disclosure, polymerization includes any polymerization, including but not limited to: aggregating items together, such as aggregating or linking similar items together (e.g., a collateral that provides a collateral for a set of loans, a group of collateral for loans aggregated in real-time based on similarity of states of the group of collateral, etc.); collecting data (e.g., training data for storage, for communication, for analysis, as a model, etc.); aggregating the aggregated items or data into a simpler description; or any other method for creating an entirety formed by combining a plurality of (e.g., different) elements. Further, the aggregator may be any system or platform for aggregation, as described herein. Some components may not be considered separately as aggregates, but may be considered as aggregates in an aggregation system-for example, loan settlement may not be considered as an aggregation of the loan itself, but may be considered as an aggregation if the loan is settled in this way. In a non-limiting example, the aggregation circuit may be configured to provide a mechanism for a borrower to aggregate loans from multiple loans together (e.g., based on loan attributes, parameters, terms or conditions, financial entities, etc.) to become a loan aggregate. In some embodiments, aggregation may be considered aggregation for some purposes but not others — for example, aggregation of property mortgage conditions may be collected to aggregate loans together in one instance and determine default behavior in another instance. Further, in certain embodiments, other similarly appearing systems may be distinguished in determining whether such systems are aggregators and/or which type of aggregation system. For example, both a first aggregator and a second aggregator may aggregate financial entity data, where the first aggregator aggregates data to build a training set of analytical model circuits, and the second aggregator aggregates financial entity data for storage in a blockchain based distributed ledger. Thus, the benefits of the present disclosure may apply to a variety of systems, and any such systems may be considered herein as an aggregation, while in certain embodiments, a given system may not be considered herein as an aggregation. Given the disclosure herein and an understanding of commonly available prospective systems, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit from a particular system and/or how to combine the processes and systems of the present disclosure to enhance the operation of a prospective system. Certain considerations of those skilled in the art in determining whether a prospective system is an aggregate and/or whether aspects of the present disclosure may benefit or enhance a prospective system include, but are not limited to: forward market demand aggregation (e.g., blockchains and intelligent contract platforms for forward market demand aggregation, interests expressed or committed in a demand aggregation interface, blockchains for aggregating future demands related to various products and services in a forward market, handling a set of potential configurations having different parameters of a subset of configurations consistent with each other for aggregating committed demand for satisfying a sufficiently large subset of products at a profitability price, etc.); worker age, certifications, experience (including by flow type) and aggregate data (including trend information) associated with process data in which the workers participate; pre-aggregation and facilitating accommodation needs (e.g., distributed ledgers) achieved by automatically identifying conditions that satisfy pre-configured commitments represented on a blockchain; aggregated and fulfilled transportation services (e.g., with a wide range of predefined contingencies); aggregation of goods and services over blockchains (e.g., distributed ledgers for demand planning); with respect to a demand aggregation interface (e.g., presented to one or more consumers); aggregation of multiple submissions; aggregating identity and behavioral information (e.g., insurance underwriting); accumulation and aggregation of multiple parties; data aggregation of a set of collateral; aggregate value of collateral or assets (e.g., based on real-time condition monitoring, real-time market data collection and integration, etc.); the total amount of the loan; smart contract mortgages aggregated with other similar mortgages, and the like.
The term "link" (and similar terms) as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, a link includes any link, including but not limited to a link that is a relationship between two things or conditions (e.g., where one thing affects the other). For example, a subset of similar items (e.g., mortgages) are linked together to provide a mortgage for a group of loans. Some components may not be considered separately as links but may be considered in the linking process in the aggregation system-for example, the intelligent contract circuitry may be configured to operate with blockchain circuitry that is part of the loan processing platform, but if the intelligent contract circuitry does not store information through blockchain circuitry when processing contracts, the two circuits may be linked through the intelligent contract circuitry and then link financial entity information through a distributed ledger on the blockchain circuitry. In some embodiments, the links may be considered links for some purposes but not others-for example, the radio frequency links between the goods and services linked for the user and the access points are different forms of links where the goods and services linked for the user link together and the RF links are communication links between the transceivers. Further, in some embodiments, other similarly appearing systems may be distinguished in determining whether and/or what type of link such systems are. For example, linking similar data together for analysis is different from linking similar data together for mapping. Thus, the benefits of the present disclosure may apply to a variety of systems, and any such systems may be considered linked herein, while in certain embodiments a given system may not be considered linked herein. Given the benefit of the disclosure herein and knowing the intended systems that are generally available, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit from a particular system and/or how to combine the processes and systems of the present disclosure to enhance the operation of the intended system. Certain considerations of those skilled in the art in determining whether a prospective system is a link and/or whether aspects of the present disclosure may benefit or enhance the prospective system include, but are not limited to: linking a marketplace or external marketplace with a system or platform; link data (e.g., a data cluster including links and nodes); storing and retrieving data related to a local process; links in the public knowledge graph (e.g., about nodes); data related to proximity or location (e.g., assets); associated with an environment (e.g., goods, services, assets, etc.); link events (e.g., for storage, e.g., in a blockchain, for communication or analysis); link ownership or access rights; link to an access token (e.g., link to a travel product of the access token); links to one or more resources (e.g., protected by encryption or other techniques); link the message to an intelligent contract, etc.
The term "indicator of interest" (and similar terms) as used herein should be broadly construed. Without being limited to any other aspect or description of the present disclosure, the indicators of interest include any indicators of interest, including but not limited to: interest indicators from a user or users or parties related to a transaction (e.g., parties interested in participating in a loan transaction), etc.; recording or storing such interests (e.g., circuitry for recording interest inputs from users, entities, circuits, systems, etc.); an analyze interest-related data and set interest indicator circuit (e.g., a circuit that sets or communicates an indicator based on circuit input, e.g., from a user, party, entity, system, circuit, etc.); a model trained to determine an interest indicator for input data related to interest via one of a plurality of inputs from a user, party, financial entity, or the like. Some components may not be considered solely interest indicators, but may be considered interest indicators in an aggregation system-for example, a party may seek information related to a transaction, such as a translation market in which the party is interested in finding information, but this may not be considered an interest indicator for a transaction. However, when the party declares a particular interest (e.g., through a user interface having control inputs for indicating interest), the party's interest may be recorded (e.g., in storage circuitry, in blockchain circuitry), analyzed (e.g., via analysis circuitry, data collection circuitry), monitored (e.g., by monitoring circuitry), and so forth. In a non-limiting example, interest metrics for a product, service, etc. can be recorded (e.g., in a blockchain through a distributed ledger) from a set of parties, such as metrics defining parameters for which the parties are willing to commit to purchasing the product or service. In some embodiments, the interest indicators may be considered interest indicators for some purposes but not other purposes-for example, the user may indicate an interest in a loan transaction, but this does not necessarily mean that the user indicates an interest in providing mortgage types related to the loan transaction. For example, the data collection circuit may record an interest indicator of a transaction, but may have a separate circuit structure for determining an interest indicator of a collateral. Further, in certain embodiments, other similarly appearing systems may be distinguished in determining whether such systems are determining indicators of interest and/or what type of indicators of interest are present. For example, one circuit or system may collect data from multiple parties to determine an interest indicator in a secured loan, while a second circuit or system may collect data from multiple parties to determine an interest indicator in determining ownership associated with the loan. Thus, the benefits of the present disclosure may apply to a variety of systems, and any such system may be considered herein an indicator of interest, while in certain embodiments a given system may not be considered herein an indicator of interest. Given the benefit of the disclosure herein and knowing the intended systems that are generally available, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit from a particular system and/or how to combine the processes and systems of the present disclosure to enhance the operation of the intended system. Certain considerations of those skilled in the art in determining whether a prospective system is an indicator of interest and/or whether aspects of the present disclosure may benefit or enhance the prospective system include, but are not limited to: the party indicates an interest in participating in a transaction (e.g., a loan transaction); the party indicates an interest in protecting the product or service; recording or storing the indicators of interest (e.g., by a storage circuit or a blockchain circuit); analyzing the indicators of interest (e.g., via data collection and/or monitoring circuitry), and the like.
The term "accommodation" (and similar terms) as used herein should be understood broadly geographicallyAnd (5) solving. Without being limited to any other aspect or description of the disclosure, an accommodation includes any service, activity, event, etc., including, for example and without limitation, a room, a group of rooms, a table, a seat, a building, an event, a shared space provided by an individual (e.g., airbnb) TM Space), bed and breakfast, work spaces, conference rooms, meeting spaces, fitness facilities, health and wellness facilities, catering facilities, etc., where a person may live, stay, sit, live, participate, etc. Thus, accommodations may be purchased (e.g., tickets through a sports ticketing application), booked (e.g., booked through a hotel booking application), offered as rewards or gifts, traded or exchanged (e.g., via the marketplace), offered as access rights (e.g., offered in an aggregated demand manner), offered based on unexpected events (e.g., booking of a room depending on whether there is a nearby event), and so forth. Certain components may not be considered accommodations individually, but may be considered accommodations in the aggregation system — for example, a resource (e.g., a room in a hotel) may not itself be considered an accommodation, but a reservation for a room may be considered an accommodation. For example, a blockchain and intelligent contract platform for lodging forward market rights may provide a mechanism to provide access rights related to lodging. In a non-limiting example, blockchain circuitry can be configured to store access rights in the forward demand market, where the access rights can be stored in a distributed ledger with associated shared access to multiple executable action entities. In some embodiments, accommodation may be considered accommodation for some purposes but not others-for example, a room reservation may be an individual accommodation, but may not be an accommodation that satisfies an appointment if the appointment is not satisfied at the time of the reservation in relation to an incident. Further, in certain embodiments, other similarly appearing systems may be distinguished in determining whether such systems are relevant to an accommodation and/or which type of accommodation. For example, the accommodation product may be determined based on different systems, such as a system in which the accommodation product is determined by a system that collects data related to forward demand, and a second system in which the accommodation product is provided as a reward based on a system that processes performance parameters. Accordingly, the benefits of the present disclosure may be For various systems, and any such systems may be considered herein as being related to an accommodation, while in certain embodiments a given system may not be considered herein as being related to an accommodation. Given the disclosure herein and an understanding of commonly available prospective systems, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit from a particular system and/or how to combine the processes and systems of the present disclosure to enhance the operation of a prospective system. Certain considerations of those skilled in the art in determining whether a prospective system is accommodation and/or whether aspects of the present disclosure may benefit or enhance the prospective system include, but are not limited to: determining offered accommodation through service circuits, transaction or exchange services (e.g., through an application and/or user interface); offer as an accommodation product, e.g., with respect to a combination of products, services, and access rights (e.g., total demand for products in the forward market); through pre-booked accommodation; by advance booked accommodation (e.g., associated with prices within a given time window) when certain conditions are met, and the like.
The term "incident" (and similar terms) as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, an incident includes any incident, including but not limited to any action that relies on the second action. For example, a service may be provided according to a parameter value, such as a condition that data is collected according to an asset tag indication from the internet of things circuitry. In another example, a hotel reservation or the like may be due to whether a concert (the holding location is the hotel location and the holding time is the reservation time) is in progress. Certain components may not be considered solely related to unforeseen events, but may be considered related to unforeseen events in the aggregated system — for example, data inputs collected from the data collection service circuitry may be stored, analyzed, processed, etc., rather than being considered unforeseen events, however, the intelligent contract service circuitry may apply contract terms in accordance with the collected data. For example, the data may indicate collateral status for the loan transaction, and the intelligent contract service circuitry may apply the data to the contract terms that depend on the collateral. In some embodiments, an unexpected event may be considered an unexpected event for some purpose but not others-for example, delivery of unexpected access rights for a future event may depend on satisfaction of loan conditions, but the loan conditions themselves may not be considered an unexpected event if there is no accidental link between the loan conditions and the access rights. Further, in certain embodiments, other similarly appearing systems may be distinguished in determining whether such systems are associated with an incident and/or which type of incident. For example, both algorithms may create a forward market event access token, but with the first algorithm creating a token suitable for use in the absence of contingencies and the second algorithm creating a token suitable for use in the presence of contingencies to deliver the token. Thus, the benefits of the present disclosure may be applied in a variety of systems, and any such system may be considered herein as an incident, while in certain embodiments, a given system may not be considered herein as an incident. Given the benefit of the disclosure herein and knowing the intended systems that are generally available, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit from a particular system and/or how to combine the processes and systems of the present disclosure to enhance the operation of the intended system. Certain considerations of those skilled in the art in determining whether a prospective system is an accident and/or whether aspects of the present disclosure may benefit or enhance the prospective system include, but are not limited to: the forward market operating within or by the platform may be or have a forward market, e.g., a forward market that grants, triggers, or arises future rights based on event occurrences, condition fulfillment, etc.; blockchains are used to create or market in any form of event or access token by securely storing access rights on a distributed ledger; setting and monitoring or pricing of access rights, basic access rights, tokens, fees, etc.; optimizing products, time, pricing, etc. to identify and predict patterns, establish rules and incidents; exchange or have access or base access or token access token and/or have access token; creating or having a forward market event access token, wherein the token may be created and stored on a blockchain for possible ticket ownership or access; discovery and delivery of or access to future events; unforeseen events that affect or represent future demand, including, for example, a set of products, services, etc.; a predetermined contingency; optimizing products, time, pricing, etc. to identify and predict patterns, establish rules and incidents; create or have future offers within the control panel; or have access to, each intelligent contract that may result in ownership of the virtual good or purchase of the virtual good, etc., if the virtual good is available under specified conditions.
The term "service level" (and similar terms) as used herein should be construed broadly. Without being limited to any other aspect or description of the present disclosure, service levels include any service level, including but not limited to: any qualitative or quantitative measure of the extent to which services are provided, such as, but not limited to, first-class services and business-class services (e.g., travel reservations or mail transfers); the degree of resource availability (e.g., a service level a indicating that the resource is highly available and a service level C indicating that the resource is restricted, such as in terms of road traffic flow restrictions); the degree to which the operating parameter is being run (e.g., the system is running in a high service state and a low service state), etc. In embodiments, the service level may be multi-modal such that the service level is variable when the system or circuit provides a service rating (e.g., when the service rating is used as an input to the analysis circuit to determine a result based on the service rating). Certain components may not be considered solely related to service levels but may be considered related to service levels in an aggregation system-for example, a system for monitoring traffic flow may provide data for a current rate but not indicate a service level, but when the determined traffic flow is provided to the monitoring circuitry, the monitoring circuitry may compare the determined flow to past flows and determine a service level based on the comparison. In some embodiments, the service level may be considered a service level for some purposes but not others-for example, the availability of first class travel accommodations may be considered a service level to determine whether to purchase tickets rather than predicting future needs of flights. Further, in some embodiments, other similarly appearing systems may be distinguished in determining whether such systems utilize a service level and/or type of service level. For example, an artificial intelligence circuit can be trained based on past service levels of traffic flow patterns on a particular highway and used to predict future traffic flow patterns based on current flow, but a similar artificial intelligence circuit can predict future traffic flow patterns based on time of day. Thus, the benefits of the present disclosure may be applied to a variety of systems, and any such system may be considered herein to relate to a service level, while in certain embodiments, a given system may not be considered herein to relate to a service level. Given the disclosure herein and an understanding of commonly available prospective systems, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit from a particular system and/or how to combine the processes and systems of the present disclosure to enhance the operation of a prospective system. Certain considerations of those skilled in the art in determining whether a prospective system is a service level and/or whether aspects of the present disclosure may benefit or enhance the prospective system include, but are not limited to: traffic or accommodation products with predefined contingencies and parameters (e.g., price, service mode, and service level); warranty or warranty applications, transportation markets, etc.
The term "payment" (and similar terms) as used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, payment includes, but is not limited to, any action or process of paying (e.g., loan repayment) or being paid (e.g., insurance payment), an amount paid or payable (e.g., paying $ 1000), a repayment (e.g., a refund), a payment method (e.g., using a loyalty program, reward points, or a particular currency, including cryptocurrency), and the like. Some components may not be considered payments individually, but may be considered payments in the aggregated system-for example, submitting an amount may not be considered a payment, but when applied to a payment that meets the loan requirements, may be considered a payment (or repayment). For example, the data collection circuit may provide a mechanism for the borrower to monitor the repayment of the loan. In a non-limiting example, the data collection circuitry may be configured to monitor payment of a plurality of loan components relative to a financial loan contract used to determine a loan condition of a property. In some embodiments, payment may be considered payment for some purpose but not for other purposes-for example, payment to a financial entity may be in the amount of a repayment to repay the loan, or may be in order to satisfy mortgage obligations under conditions of loan default. Further, in some embodiments, other similarly appearing systems may be distinguished in determining whether such systems are associated with payments and/or which types of payments. For example, funds may be used to book an accommodation or to pay for a service after accommodation is satisfied. Thus, the benefits of the present disclosure may apply to a variety of systems, and any such system may be considered payment herein, while in some embodiments a given system may not be considered payment herein. Given the benefit of the disclosure herein and knowing the intended systems that are generally available, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit from a particular system and/or how to combine the processes and systems of the present disclosure to enhance the operation of the intended system. In determining whether a prospective system is paying for and/or whether aspects of the present disclosure may benefit or enhance the prospective system, certain considerations by those skilled in the art include, but are not limited to: postponing the required payment; a deferred payment requirement; repayment of the loan; a payment amount; a payment plan; a final-stage large pen clearing plan; payment fulfillment and satisfaction; payment methods, etc.
The term "location" (and similar terms) as used herein should be broadly construed. Without being limited to any other aspect or description of the disclosure, a location includes any location, including but not limited to: a particular location or position of a person, location, or item, or location information regarding the location of a person, location, or item, such as a geographic location (e.g., the geographic location of a mortgage), a storage location (e.g., the storage location of a property), the location of a person (e.g., a borrower, worker), location information related to the foregoing, and the like. Some components may not be considered location alone, but may consider location in the aggregation system — for example, the smart contract circuit may be configured to specify a requirement to store a collateral in a fixed location, but not to specify a particular location of a particular collateral. In some embodiments, the location may be considered a location for some purpose but not others-for example, in one instance, the borrower's address location may be needed to handle the loan, while in another instance, a particular location may be needed to handle the default condition. Further, in certain embodiments, other similarly appearing systems may be distinguished in determining whether such systems are locations and/or types of locations. For example, in one example, the location of a concert may need to be in a concert hall that accommodates 10,000 people, but in another example the location of the actual concert hall is specified. Thus, the benefits of the present disclosure may apply to a variety of systems, and any such systems may be considered herein to relate to location, while in certain embodiments a given system may not be considered herein to relate to location. Given the benefit of the disclosure herein and knowing the intended systems that are generally available, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit from a particular system and/or how to combine the processes and systems of the present disclosure to enhance the operation of the intended system. Certain considerations of those skilled in the art in determining whether a prospective system is a location and/or whether aspects of the present disclosure may benefit or enhance the prospective system include, but are not limited to: the geographic location of the item or collateral; a storage location of an item or asset; location information; the location of the borrower or borrower; a location-based product or service location application; a location-based fraud detection application; indoor location monitoring systems (e.g., cameras, IR systems, motion detection systems); the location of the worker (including a route through the location); a location parameter; an event location; the particular location of the event, etc.
The term "route" (and similar terms) as used herein should be broadly construed. Without being limited to any other aspect or description of the present disclosure, routes include any route, including but not limited to: from an origin to a destination, a road or route to be sent or guided along a specified route, etc. Certain components may not be considered individually to relate to routes, but may be considered to be routes in the aggregation system-for example, a mobile data collector may specify route requirements for collecting data based on input from the monitoring circuitry, but only upon receiving the input does the mobile data collector determine what route to take and begin traveling along the route. In some embodiments, a route may be considered a route for some purposes and not others-for example, a possible route through a road system may be considered different from a particular route from one location to another. Further, in some embodiments, other similarly appearing systems may be distinguished when determining whether such systems are specified for a location and/or which types of locations. For example, a route depicted on a map may indicate a possible route or an actual route taken by an individual. Thus, the benefits of the present disclosure may apply to a variety of systems, and any such systems may be considered herein to relate to routes, while in certain embodiments a given system may not be considered herein to relate to routes. Given the disclosure herein and an understanding of commonly available prospective systems, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit from a particular system and/or how to combine the processes and systems of the present disclosure to enhance the operation of a prospective system. Certain considerations of those skilled in the art in determining whether a prospective system is a prospective system and/or whether aspects of the present disclosure may benefit or enhance a prospective system include, but are not limited to: a delivery route; a route through the location; a heatmap showing a route traveled by a customer or worker within the environment; determining what resources to deploy to what route or travel type; a direct route or multi-stop route, such as from the consumer's destination to a particular location or anywhere where an event occurs; the route of the mobile data collector, etc.
The term "future offer" (and similar terms) as used herein should be construed broadly. Without being limited to any other aspect or description of the present disclosure, a future offer includes an offer for any future goods or services, including but not limited to: providing a future offer for the goods or services; a future offer regarding a proposed purchase; future offers made through a forward market platform; future contracts determined by the smart contract circuit, etc. Further, the future offer may be or have a future offer or an offer based on conditions that cause the offer to be a future offer, such as a future offer that is dependent on or has imposed conditions with predetermined conditions (e.g., a security may be purchased at $ 1000 on a set future date based on a predetermined status of the market indicator). Some components may not be considered future offers alone, but may be considered future offers in an aggregated system — for example, a loan offer may not be considered a future offer if the offer is not authorized by a collective agreement between multiple parties associated with the offer, but may be considered a future offer once votes are collected and stored by a distributed ledger (e.g., by blockchain circuitry). In some embodiments, the future offer may be considered a future offer for some purpose but not others-e.g., the future offer may depend on a condition that is met in the future, and thus, the future offer may not be considered a future offer until the condition is met. Further, in certain embodiments, similarly appearing systems may be distinguished in determining whether and/or what type of future offer such systems are. For example, two vouching offers may be determined as offers made at a future time, but one of them may have an immediate contingency that needs to be satisfied, and thus may not be considered a future offer, but rather an immediate offer with a future statement. Thus, the benefits of the present disclosure may apply to a variety of systems, and any such system may be considered herein to be associated with a future offer, while in certain embodiments, a given system may not be considered herein to be associated with a future offer. Given the benefit of the disclosure herein and knowing the intended systems that are generally available, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit from a particular system and/or how to combine the processes and systems of the present disclosure to enhance the operation of the intended system. In determining whether a prospective system is a future offer and/or whether aspects of the present disclosure may benefit or enhance the prospective system, certain considerations by those skilled in the art include, but are not limited to: a future offer, or a future offer, a future offer in a forward market platform (e.g., for creating a future offer or a future offer associated with offer data identifying a market or an external market operated by the platform); regarding future offers to sign smart contracts (e.g., by performing an indication of a commitment to purchase, participate in, or otherwise consume the future offers), and so forth.
The term "access rights" (and derivatives or variants) as used herein may be broadly construed to describe the right to acquire or own property, item or other item of value. Or the condition of having access may be that a trigger or condition is satisfied before such access is granted, or counter-acted. The access rights or access rights may also be used for specific purposes or configured for different applications or contexts, such as but not limited to loan-related actions or any service or offer. Without limitation, it may be desirable to notify the property, item, or owner of the item of value before such access is granted or has access. Various forms of access and or access may be included in discussing legal proceedings, delinquent or default loans or agreements, or other situations in which a borrower may seek remediation, but are not so limited. The value of such rights to be realized in the embodiments can be readily determined by those skilled in the art, given the benefit of the present disclosure and understanding the intended systems generally available. Although specific examples of and or having access rights are described herein for illustrative purposes, any embodiments that benefit from the disclosure herein, as well as any considerations understood by those skilled in the art to benefit from the disclosure herein, are specifically contemplated within the scope of the present disclosure.
The term "smart contract" (as well as other forms or variations) as used herein may be broadly construed to describe a method, system, connected resource, or wide area network that provides one or more resources that may be used to assist in developing or performing an action, task, or thing through embodiments disclosed herein. An intelligent contract may be a set of steps or processes used to negotiate, manage, restructure, or enforce an agreement or loan between parties. The smart contracts may also be implemented as an application, web site, FTP site, server, appliance or other connected component or internet related system that provides resources to negotiate, manage, restructure or enforce agreements or loans between parties. The smart contracts may be self-contained systems or may be part of a larger system or component (which may also be a smart contract). For example, a smart contract may refer to the loan or agreement itself, conditions or terms, and may also refer to the system implementing such a loan or agreement. In some embodiments, smart contract circuits or robotic process automation systems may incorporate or be incorporated into automated robotic process automation to perform one or more purposes or tasks, whether or not a loan or a portion of a transaction process. Given the benefit of the disclosure herein and understanding the intended systems that are generally available, one skilled in the art can readily ascertain the purpose and use of the term in the various forms, embodiments, and contexts disclosed herein as relating to smart contracts.
The term "reward distribution" (and variants) as used herein may be broadly construed to describe something or consideration that is distributed or offered as consideration or offered for some purpose. The allocation of the reward may be of a financial type or a non-financial type, but is not limited thereto. A particular type of reward distribution may also serve a variety of different purposes or for different applications or environments, such as, but not limited to: reward events, reward claim, monetary reward, reward acquired as a data set, reward points, and other forms of reward. Thus, the allocation of the reward may be provided as a consideration of the loan or agreement. The system may be utilized to distribute rewards. Various forms of reward distribution may be included, but are not limited to, when discussing a particular behavior or encouraging a particular behavior. The allocation of the reward may include the actual allocation of the reward and/or a record of the reward. The distribution of the reward may be performed by smart contract circuitry or a robotic process automation system. The value of the reward distribution in an embodiment can be readily determined by one skilled in the art, given the benefit of the disclosure herein and knowing the expected systems that are generally available. Although specific examples of reward distribution are described herein for illustrative purposes, any embodiments that benefit from the disclosure herein, as well as any considerations understood by those skilled in the art having the benefit of the disclosure herein, are specifically contemplated within the scope of the present disclosure.
The term "satisfaction of a parameter or condition" (as well as other derivatives, forms, or variants) used herein can be broadly interpreted as describing the completion, presence, or proof of a parameter or condition that has been satisfied. The term may generally relate to a process of determining such satisfaction of a parameter or condition, or may relate to completing such a process with a result, but is not limited thereto. Satisfaction may result in successful results of other trigger conditions or terms that may take effect, but is not limited to such. Satisfaction of parameters or conditions may occur in many different contexts of contracts or loans, such as, but not limited to, lending, refinancing, merging, warranty, brokering, redemption cessation, and data processing (e.g., data collection), or a combination thereof. Satisfaction of a parameter or condition may be used in the form of a noun (e.g., satisfaction of debt repayment) or an verb to describe the process of determining the outcome of the parameter or condition. For example, the borrower may satisfy the parameter by paying a certain amount of money on time, or may satisfy a condition for allowing the owner to gain access in the event of a loan default, but is not limited thereto. In some embodiments, an intelligent contract or robotic process automation system may perform or determine that parameters or conditions of one or more parties are satisfied and process the appropriate tasks to satisfy the parameters or conditions. In some cases, the satisfaction of parameters or conditions by the smart contracts or robotic process automation systems may not be complete or successful, and depending on such results, this may enable automatic actions or trigger other conditions or terms. The purpose and use of the terms in the various forms, embodiments, and contexts disclosed herein can be readily ascertained by one of ordinary skill in the art, given the benefit of the present disclosure and understanding the intended systems generally available.
The term "information" (as well as other forms) used herein may be broadly understood in various contexts relating to agreements or loans. The term may generally relate to a larger context, such as information about an agreement or loan, or may specifically relate to limited information (such as specific details of an event occurring on a particular date). Thus, information may appear in many different contexts of contracts or loans, and may be used in these contexts, without limitation, evidence, transactions, visits, and the like. Alternatively, but not limited to, information may be used in conjunction with various stages of an agreement or transaction, such as lending, refinancing, consolidation, warranty, agency, redemption, and information processing (e.g., data or information collection), or a combination thereof. For example, information as evidence, transactions, visits, etc. may be used in the form of nouns (e.g., information obtained from the borrower), or may refer to various items of information as nouns (e.g., information about the loan may be found in a smart contract), or may be used in the form of adjectives (e.g., the borrower is providing an information submission file). For example, the borrower may receive the overdue payment from the borrower through an online payment, or may successfully receive the overdue payment through a customer service telephone call. In some embodiments, the smart contract circuit or robotic process automation system may perform collection, management, computation, provisioning, or other tasks for one or more parties and process appropriate tasks related to the information (e.g., providing overdue payment notifications). In some cases, the information of the smart contract circuit or robotic process automation system may be incomplete, and depending on such results, this may enable automatic actions or trigger other conditions or terms. Given the disclosure herein and the knowledge of commonly available prospective systems, one of ordinary skill in the art can readily ascertain the purpose and use of evidence, transactions, access, etc. of information in the various forms, embodiments, and contexts disclosed herein.
The information may be linked to external information (e.g., an external source). More specifically, the term may relate to, but is not limited to, obtaining, parsing, receiving, or other relationship to an external source. Thus, information associated with external information or sources may be used in conjunction with various stages of an agreement or transaction, such as lending, refinancing, merging, policying, brokering, redemption, and information processing (e.g., data or information collection), or a combination thereof. For example, the information associated with the external information may vary as the external information varies, such as based on the borrower credit score of the external source. In certain embodiments, the intelligent contract circuit or robotic process automation system may perform acquisition, management, computation, reception, updating, provision, or other tasks for one or more parties and process appropriate tasks related to information linked to external information. In some cases, the information that the intelligent contracts or robotic process automation systems link to external information may not be complete, and depending on such results, this may enable automatic actions or trigger other conditions or terms. The purpose and use of the terms in the various forms, embodiments, and contexts disclosed herein can be readily ascertained by one of ordinary skill in the art, given the benefit of the present disclosure and understanding the intended systems generally available.
The information that is part of the loan or agreement may be separate from the information presented in the access location. More particularly, the term may relate to the feature that information may be distributed, split, limited, or otherwise separated from other information in the context of a loan or agreement. Thus, the information presented or received at the visiting location is not necessarily all of the information available for a given context. For example, the information provided to the borrower may be different information that the borrower receives from an external source and may be different than the information received or presented from the access location. In some embodiments, the smart contract circuit or robotic process automation system may perform information separation or other tasks for one or more principals and process the appropriate tasks. The purpose and use of the term in the various forms, embodiments and contexts disclosed herein can be readily determined by those skilled in the art, given the benefit of the disclosure herein and understanding the intended system as it is generally available.
The term "information encryption and access control" (as well as other related terms) as used herein may be broadly understood to describe whether one or more parties may view or possess certain information, actions, events or activities related to a transaction or loan. Encryption of information may be used to prevent a party from accessing, viewing or receiving information, or alternatively may be used to prevent individuals other than a transaction or loan from being able to access, view and receive confidential (or other) information. Control of information acquisition involves determining whether a party is authorized to acquire information. Information encryption or access control may occur in many different contexts of loans, such as, but not limited to, lending, refinancing, consolidating, warranting, brokering, stopping redemption, managing, negotiating, collecting, purchasing, enforcing, and data processing (e.g., data collection), or a combination thereof. Encryption of information or control over access to information may refer to a single instance, or may describe a larger amount of information, action, event, or activity, but is not limited to such. For example, a borrower or lender may have access to information about a loan, but parties outside of the loan or agreement may not have access to the loan information because of the encryption of the information or access control to the loan details. In certain embodiments, the intelligent contract circuitry or robotic process automation system may perform information encryption or information access control for one or more parties and process the appropriate tasks for information access encryption or control. The purpose and use of the terms in the various forms, embodiments, and contexts disclosed herein can be readily ascertained by one of ordinary skill in the art, given the benefit of the present disclosure and understanding the intended systems generally available.
The term "list of potential visiting parties" (and other related terms) as used herein may be broadly understood to describe whether one or more parties observe or possess certain information, actions, events or activities related to a transaction or loan. The list of potential accessing parties may be used to authorize one or more parties to access, observe, or receive information, or alternatively to prevent the parties from being able to do so. The potential accessing principal list information involves determining whether a principal (on the potential accessing principal list or not) has access to the information. The list of potential accessing parties may appear in many different contexts of loans, such as, but not limited to, lending, refinancing, consolidating, warranting, brokering, stopping, managing, negotiating, collecting, purchasing, enforcing, and data processing (e.g., data collection), or a combination thereof. The list of potential access principals may refer to a single instance or may describe a greater amount of respective persons or information, actions, events or activities, but is not limited thereto. For example, the list of potential accessing parties may grant (or deny) access to information regarding the loan, but other parties outside the list of potential accessing parties may not be able to (or may be granted) access to the loan information. In certain embodiments, the intelligent contract circuit or robotic process automation system may perform management or enforcement of potential access principal lists for one or more principals and handle appropriate tasks for encrypting or controlling information access. The purpose and use of the terms in the various forms, embodiments, and contexts disclosed herein can be readily ascertained by one of ordinary skill in the art, given the benefit of the present disclosure and understanding the intended systems generally available.
The terms "offer," "make offer," and similar terms used herein should be construed broadly. Without being limited to any other aspect or description of the disclosure, an offer includes an offer for any item or service, including but not limited to: insurance offers, vouching offers, offers to provide goods or services, offers on proposed purchases, offers made through forward market platforms, future offers, or offers related to loans (e.g., lending, refinancing, collecting, consolidating, policing, brokering, stopping redemption), offers determined by intelligent contract circuitry, offers for customers/debtors, offers for providers/borrowers, third party offers (e.g., regulatory agencies, auditors, partial owners, tiered service providers), and the like. The offer may include physical goods, virtual goods, software, physical services, access rights, entertainment content, lodging or many other items, services, solutions or considerations. In one example, the third party offer may be to arrange for a band, rather than just provide a sales ticket. Further, the offer may be based on a predetermined condition or incident. Some components may not be considered offers alone, but may be considered offers in an aggregated system — for example, an insurance offer may not be considered an offer if the offer is not approved by one or more parties related to the offer; however, once approved, it may be considered an offer. Thus, the benefits of the present disclosure may apply to a variety of systems, and any such system may be considered herein to be associated with an offer, while in certain embodiments, a given system may not be considered herein to be associated with an offer. Given the disclosure herein and an understanding of commonly available prospective systems, one of ordinary skill in the art can readily determine which aspects of the disclosure will benefit from a particular system and/or how to combine the processes and systems of the present disclosure to enhance the operation of a prospective system. Certain considerations of those skilled in the art in determining whether a prospective system is an offer and/or whether aspects of the present disclosure may benefit or enhance the prospective system include, but are not limited to: an item or service to offer, an contingency related to the offer, a manner of tracking whether the contingency or condition has been met, approval of the offer, performance of an offer price exchange, and the like.
The term "Artificial Intelligence (AI) solution" as used herein should be construed broadly. Without being limited to any other aspect of the disclosure, an AI solution includes a set of coordinated AI-related aspects to perform one or more tasks or operations throughout the disclosure. One example AI solution includes one or more AI components, including any of the AI components described herein (including at least neural networks, expert systems, and/or machine learning components). As one aspect, an example AI solution may include types of components of the solution, such as heuristic AI components, model-based AI components, neural networks of selected types (e.g., recursive, convolutional, perceptron, etc.), and/or any type of AI component with selected processing capabilities (e.g., signal processing, frequency component analysis, auditory processing, visual processing, speech processing, text recognition, etc.). Without being limited to any other aspect of the disclosure, a given AI solution may be formed by the number and type of AI components of the AI solution, the connectivity of the AI components (e.g., connected to each other, to system inputs from and/or to system outputs from and/or with the AI solution). A given AI solution can also be formed by connections between AI components within the AI solution and boundary elements (e.g., inputs, outputs, stored intermediate data, etc.) that communicate with the AI solution. A given AI solution may also be formed from a configuration of each AI component of the AI solution, where the configuration may include the following: model calibration of the AI component; connectivity and/or flow between AI components (e.g., serial and/or parallel coupling, feedback loops, logical connections, etc.); the quantity of AI component inputs, selected input data and/or input data processing; the depth and/or complexity of the neural network or other components; a training data description of the AI component (e.g., training data parameters such as content, amount of training data, statistical description of valid training data, etc.); and/or selection and/or mix descriptions of AI component types. AI solutions include selection of AI elements, flow connectivity of the AI elements, and/or configuration of the AI elements.
One of ordinary skill in the art, with the benefit of this disclosure, can readily determine the AI solution for a given system and/or configure operations to perform the selection and/or configuration operations for the AI solution for the given system. Some considerations in determining an AI solution and/or configuration operation to perform the selection and/or setting operation of an AI solution include, but are not limited to: availability of AI components and/or component types for a given implementation; availability of support infrastructure to implement a given AI component (e.g., available data input values including data quality, service level, resolution, sampling rate, etc.; availability of suitable training data for a given AI solution; availability of expert input, such as for expert systems and/or development of model training data sets; regulatory and/or policy-based considerations, including allowing actions to be taken by AI solutions; requiring acquisition and/or retention of sensitive data; data that is difficult to obtain; and/or data that is costly); operational considerations of the system including or interacting with the AI solution, including response time specifications, safety considerations, liability considerations, and the like; available computing resources such as processing power, network communication power, and/or memory storage power (e.g., supporting initial data, training data, input data (e.g., buffered, or stored input data), iterative improvement state data, output data (e.g., buffered, and stored output data), and/or intermediate data storage (e.g., data used to support ongoing computation, historical data, and/or accumulated data)); the type of tasks to be performed by the AI solution, the applicability of AI components to these tasks, the sensitivity of AI components performing the tasks (e.g., variability in the amount of interference in the output space relative to the input space); interaction of AI components throughout an AI solution (e.g., a low-capability rationality AI component can be coupled with a high-capability AI component that can provide a high sensitivity and/or infinite response to input); and/or model implementation considerations (e.g., recalibration requirements, model aging constraints, etc.).
The selected and/or configured AI solution may be used with any of the systems, procedures, and/or aspects of the embodiments set forth in this disclosure. For example, a system utilizing an expert system may include the expert system as all or part of a selected, configured AI solution. In another example, a system utilizing a neural network and/or a combination of neural networks may include a neural network as all or part of a selected, configured AI solution. The described aspects of the AI solution, including the selection and configuration of the AI solution, are non-limiting illustrations.
Referring to fig. 1, an embodiment 100 of a financial, trading, and marketplace support system is shown in which a loan support platform 100 is enabled, and a platform-oriented marketplace 132 may include a loan application 144. The loan support platform 100 may comprise a set of systems, applications, processes, modules, services, layers, devices, components, machines, products, subsystems, interfaces, connections, and other elements (collectively referred to as "platforms," "loan platforms," "systems," and the like in the alternative unless the context dictates otherwise) that work in concert (e.g., through data integration and organization in a service-oriented architecture) to enable intelligent management of a set of entities 198 that may exist, run, transact, and the like, or own, run, support, or otherwise be physically present within, or within one or more applications, services, solutions, programs, and the like of the loan application 144 or the external marketplace 188 Now the loan application 144 or one or more applications, services, solutions, programs, etc. of an external marketplace 188 that relates to the loan transaction or loan-related entity, or that may be part of, integrated with, linked to, or run by the loan support platform 100. Unless the context indicates otherwise, references herein to a set of services should be understood to refer to these and various other systems, applications, procedures, modules, services, layers, devices, components, machines, articles, subsystems, interfaces, connections, and other types of elements. Fig. 1 includes an administration application platform 126 that includes a lending application 144, an adaptive intelligence system 158, a monitoring system 164, a data collection system 166, and a data storage system 186, all of which are coupled to a data processing layer 168. FIG. 1 also shows the disclosed system having process and application outputs and results 151 and communicating with entity 198. The components of the loan application 144 may include underwriting 103, risk management 122, analysis 130, pricing 131, tax 124, crowdsourcing system 120, intelligent contracts 134, blockchains 136, loan model 108, trust and custody 150, platform market 132, fraud prevention 138, administration 142, payment 146, and security 148. A group of entities may include multiple members or a single member. The adaptive intelligence system 158 may include an opportunity mining program 153, a Robotic Process Automation (RPA) 154, artificial intelligence 156, artificial intelligence storage 157, and clusters 104. The monitoring system 164 and the data collection system 166 may include software interaction observation 160, functional imaging 161, and physical process observation 162. The data storage system 186 may include access data 170, pricing data 178, asset and facility data 172, claims data 180, worker data 174, accounting data 182, event data 176, and underwriting data 184. Entities 198 may include an external marketplace 188, a collateral 102, a facility 190, a collaboration robot 193, a worker 194, a wearable/portable device 195, a process 196, and a machine 197. Like other embodiments, the loan support platform 100 may have various data processing layers, with various components, modules, systems, services, components, functions, and other elements described in connection with other embodiments described in the present disclosure and documents incorporated by reference herein. This may include a variety of The adaptive intelligence system 158, the monitoring system 164, the data collection system 166, and the data storage system 186, as well as a set of interfaces 187 of each of these systems and/or various other elements of the loan support platform 100, connecting these systems and/or elements, and/or between these systems and/or elements. In an embodiment, the interface 187 may include: an application programming interface 112; data integration techniques for extracting, converting, cleansing, normalizing, deduplication, loading, etc., while moving data between various services using various protocols and formats (collectively referred to as ETL systems 114); and various ports, portals, connectors, gateways, wired connections, sockets, virtual private networks, containers, secure channels, and other connections (collectively referred to as ports 118) configured on a one-to-one, one-to-many, or many-to-one basis between elements in unicast, broadcast, multicast transmissions, and the like. The interface 187 may include a real-time operating system (RTOS) 110 (e.g., freeRTOS) TM An operating system), enabled by, integrated with, or interfaced with, the real-time operating system has a deterministic execution mode, wherein a user can define the execution mode, e.g., based on a priority assignment for each execution thread. Instances of the RTOS110 may be embedded on a microcontroller or the like of the internet of things device, such as a microcontroller used to monitor various entities 198. The RTOS110 may provide real-time scheduling (e.g., scheduling data transmissions to the monitoring system 164 and the data collection system 166, scheduling inter-task communications between various service elements, and other timing and synchronization elements). In embodiments, the interface 187 may use or include a set of libraries that enable secure connections between small low-power edge devices, such as internet of things devices for monitoring various entities 198, various cloud deployment services for the loan support platform 100, and a set of edge devices and systems that enable these devices, such as running awgsio greenrass TM And/or AWSLArambda TM Functions, etc. local data processing and devices of the computing system to allow local computation, data communication configuration, execution of machine learning models (e.g., for prediction or classification), synchronization of device or device data, and communication between devices and services. This may include using local device resources, such as serial port, GPU, pass-throughSensor and camera. In an embodiment, data may be encrypted for secure end-to-end communication.
In the context of the loan support platform 100 and the set of loan applications 144, the various entities 198 may include any of the various assets, systems, devices, machines, facilities, individuals, or other entities mentioned in this disclosure or in the documents incorporated by reference herein, such as, but not limited to: machine 197 and its components (e.g., machines that are the subject of the loan or the mortgage of the loan, such as various vehicles and equipment, as well as machines for conducting loan transactions, such as automated teller machines, point of sale machines, vending machines, self-service terminals, smart card enabled machines, and many other machines, including machines for supporting small loans, payday loans, and the like); financial and transaction flow 196 (e.g., loan flow, verification flow, collateral tracking flow, valuation flow, credit investigation flow, creditworthiness flow, association flow, interest rate setting flow, software flow (including applications, programs, services, etc.), production flow, collection flow, banking flow (e.g., loan flow, underwriting flow, investment flow, etc.), financial services flow, diagnosis flow, security flow, assessment flow, payment flow, valuation flow, issuance flow, warranty flow, merger flow, association flow, collection flow, redemption flow, property transfer flow, property verification flow, collateral monitoring flow, etc.); wearable and portable devices 195 (e.g., mobile phones, tablets, dedicated portable devices for financial applications, data collectors (including mobile data collectors), sensor-based devices, watches, glasses, audible wear devices, head-worn devices, garment-made devices, armpieces, bracelets, neck-worn devices, AR/VR devices, headphones, etc.); workers 194 (e.g., bank workers, loan officers, financial services personnel, dealers, inspectors, brokers (e.g., mortgage brokers), lawyers, insurers, supervisors, evaluators, appraisers, process supervisors, security personnel, etc.); a robotic system 192 (e.g., physical robots, collaborative robots (e.g., "cobots"), software robots, etc.); in embodiments, various entities 198 may include external markets 188 such as finance, commerce, e-commerce, advertising, and other external markets 188 as well as other external markets 188 (including current and futures markets) in which various goods and services are transacted, such as external markets in which various goods and services are transacted, such that monitoring of external markets 188 and various entities 198 within them may provide loan-related information, such as information about the price or value of the item, the fluidity of the item, the characteristics of the item, the depreciation rate of the item, and the like, for example, for various entities that may include collateral 102 or assets for which the asset is to be credited, the monitoring system 164 may not only monitor the mobility of the item, the characteristics of the item, the availability of the item, or the like by a camera, sensor, or other monitoring system 164, but also may collect data about the age of the asset, such as by a system 102, or other system that may be adapted by collecting data about the age of the collateral 102, such as by using a camera, sensor, or other monitoring system that may also collect data about the availability of the collateral, such as by other systems that may include information about the loan 102, such as a system that may be adapted to collect data about the loan, such as a system that may collect data about the loan of a loan, such as a loan, or the like, by collecting data about the loan of a loan on the loan of a loan, such as a loan, or the loan of a loan, or the like, the circuitry that groups or clusters various entities 198, including assets, etc., such as a k-means clustering system, an ad hoc mapping system, or other systems described herein and in documents incorporated by reference herein. For example, the clustering system may manage a collection of mortgages, assets, parties, and loans such that they may be monitored and analyzed based on common attributes such that the performance of a subset of transactions may be used to predict the performance of other transactions, which in turn may be used for underwriting 122, pricing 131, fraud prevention applications 138, or other applications, including any of the services, solutions, or applications described in connection with fig. 1 and 2 or elsewhere in this disclosure or documents incorporated by reference herein. In an embodiment, condition information about the collateral 102 or asset is continuously monitored by the monitoring system 164 (e.g., a set of sensors on the collateral 102 or asset, a set of sensors or cameras in the collateral 102 or asset environment, etc.) and market information is collected by the data collection system 166 in real-time, so that the condition and market information can be time-ranked and relied upon for real-time estimation of the collateral or asset value and prospective prediction of the collateral or asset future value. The present and predicted values of a collateral 102 or a property may be based on a model that may be accessed and used (e.g., in a smart contract) to enable automatic or machine-assisted lending of the collateral or property, such as underwriting or issuance of a small loan of the collateral 102 or property. Data aggregation of a set of mortgages 102 or a set of assets (e.g., a collection or group of mortgages 102, or a group of assets owned by an entity 198) may enable real-time portfolio valuation and larger-scale lending, including valuation and lending by intelligent contracts that automatically adjust interest rates and other terms and conditions based on real-time condition monitoring and real-time market data collection and integration based on individual or aggregated values of the mortgages 102 or assets. Transactions, party information, title transfers, terms and condition changes, and other information may be stored in blockchain 136, including loan transactions and information about mortgages 102 or properties (e.g., market data and condition information for mortgages 102 or properties). The smart contracts may be used to require the parties to confirm status information and/or market value information, such as statements and assurances that are supported or verified by the monitoring system 164 (which may mark fraud in the fraud prevention application 138). The loan model 108 may be used to value the collateral 102 or assets, determine loan qualifications based on the condition and/or value of the collateral 102 or assets, set pricing (e.g., interest rates), adjust terms and conditions, and the like. The loan model 108 may be created by a set of experts, for example, using computational analysis 130 of past loan transactions. The lending model 108 may be populated with data from the monitoring system 164 and the data collection system 166, may retrieve data from the data storage system 186, and the like. The lending model 108 may be used to configure parameters of the intelligent contract such that the terms and conditions of the intelligent contract are automatically adjusted according to the adjustments in the lending model 108. The lending model 108 may be used to improve through artificial intelligence 156, for example by training it on a set of outcomes, such as the outcome of a lending transaction (e.g., payment outcome, default outcome, fulfillment outcome, etc.), the outcome on collateral 102 or assets (e.g., price or value pattern of collateral or assets over time), the outcome on an entity (e.g., default, redemption, fulfillment outcome, on-time payment, overdue payment, bankruptcy, etc.), and so forth. Training may be used to adjust and improve model parameters and performance, including classification for collateral or assets (e.g., automatic classification of types and/or conditions, such as using vision-based classification from camera-based monitoring system 164), value prediction, default prediction, performance prediction, etc. of collateral 102 or assets. In an embodiment, the configuration or processing of a smart contract for collateral 102 or asset lending may be learned and automatically performed in a Robotic Process Automation (RPA) system 154, such as by training the RPA system 154 to create a smart contract, configuring parameters of a smart contract, confirming the property rights of the collateral 102 or asset, setting terms and conditions of a smart contract, initiating a vouching interest for collateral 102, monitoring the state or performance of a smart contract, terminating or initiating termination for smart contract default, terminating a smart contract, canceling a redemption of collateral 102 or asset, transferring property rights, etc., such as by monitoring an expert entity 198 (e.g., human manager) using a monitoring system 164 because they employ similar training sets of tasks and actions in the creation, configuration, property rights confirmation, initiating a vouching interest, monitoring, terminating, stopping, redemption, etc. of a training set of a smart contract. Once the RPA system 154 is trained, it can efficiently create the ability to provide large-scale lending among various entities and assets (that can serve as collateral 102) that can provide guarantees or assurances, etc., making the loan easier to use for a wider range of situations, entities 198 and collateral 102. The RPA system 154 itself may be improved by artificial intelligence 156, for example, by continuously adjusting model parameters, weights, configurations, etc. based on results of loan fulfillment results, collateral valuation results, default outcomes, closing interest rate results, profitability results, return on investment results, etc. Intelligent contracts may include or be used for direct loans, banking loans and secondary loans contracts, personal loans or aggregate batch loans, and the like.
In embodiments, the lending application 144 of the administration application platform 128 may, in alternative embodiments, include, be integrated with, or interact with a set of applications (e.g., in other embodiments of the lending support platform), such as applications by which one or more elements of a loan, such as an operator or owner of a borrower, insurer, transaction or financial entity, or other user may manage, monitor, control, analyze, or otherwise interact with the loan (e.g., as a principal of the loan, a collateral for the loan, or otherwise an entity 198 associated with the loan). This may include any of the elements described above in connection with fig. 1. The set of applications may include loan applications 144 (e.g., without limitation, for personal loans, business loans, mortgage loans, low-volume loans, point-to-point loans, insurance-related loans, asset security loans, guaranteed debt loans, corporate debt loans, assisted loans, subsidized loans, mortgage loans, municipal loans, main right debts, automobile loans, payday loans, loans mortgage with accounts payable, warranty transactions, loans mortgage with guaranteed or guaranteed payments (e.g., refunds, annuals, etc.), and the like). The lending application 144 may include, integrate or link one or more of a variety of other types of applications that may be related to lending, such as investment applications (e.g., without limitation, for investing in batch loans, corporate debts, bonds, banking loans, municipal debts, staple debts or other types of debt-related securities); asset management applications (such as, but not limited to, for managing assets that may be the subject of a loan, loan collateral, assets that provide a guarantee for the loan, loan collateral or creditworthiness proofs, bond-related assets, investment assets, real estate, fixtures, personal property, real estate, equipment, intellectual property, vehicles, and other assets); risk management solutions 122 (e.g., without limitation, for managing risks or liability related to the loan principal, the loan party, or activities related to loan fulfillment, such as products, assets, people, houses, vehicles, equipment items, components, information technology systems, security events, network security systems, property items, health conditions, mortality, fires, floods, weather, disabilities, outages, injuries, property losses, business damage, default, etc.); marketing application 202 (such as, but not limited to, an application for marketing loans or partial loans, a customer relationship management application for loans, a search engine optimization application for attracting interested parties, a sales management application, an advertising web application, a behavior tracking application, a marketing analytics application, a location-based product or service targeting application, a collaborative filtering application, a recommendation engine for loan-related products or services, etc.); a trading application (such as, but not limited to, an application for trading a loan or loan portion, a portion of a loan, loan-related interest, etc., such as a purchase application, a sales application, a bid application, an auction application, a reverse auction application, a deal matching application, etc.); a tax application 262 (e.g., without limitation, for managing, calculating, reporting, optimizing, or otherwise processing data, events, workflows, or other factors related to the tax-related impact of the loan); an anti-fraud application 138 (such as, but not limited to, one or more of an authentication application, a biometric authentication application, a transaction mode-based fraud detection application, a location-based fraud detection application, a user behavior-based fraud detection application, a network address-based fraud detection application, a blacklist application, a whitelist application, a content inspection-based fraud detection application, or other fraud detection applications); security applications, solutions, or services (referred to herein as security applications 148, such as, but not limited to, any of the above-described fraud prevention applications 138, as well as physical security systems (e.g., for access control systems (e.g., using biometric access controls, fingerprints, retinal scans, passwords, and other access controls), safes, vaults, net cages, safe rooms, etc.)), monitoring systems (e.g., using cameras, motion sensors, infrared sensors, and other sensors), network security systems (e.g., for virus detection and remediation, intrusion detection and remediation, spam detection and remediation, phishing detection and remediation, social engineering detection and remediation, network attack detection and remediation, packet detection, traffic detection, DNS attack remediation and detection, etc.), or other security applications); an underwriting application 122 (such as, but not limited to, any application for underwriting any loan, guarantee, or other loan-related transaction or obligation, including for detecting, characterizing, or predicting the likelihood and/or scope of risk, including underwriting based on any data source, event, or entity described in this disclosure or documents incorporated by reference); a blockchain application for storing information as blockchain 136 (e.g., without limitation, a distributed ledger that captures a series of transactions, such as debits or credits, purchases or sales, physical value exchanges, smart contract events, etc., cryptocurrency applications, or other blockchain-based applications); real estate applications (such as, but not limited to, real estate brokerage applications, real estate valuation applications, real estate mortgage or loan applications, real estate assessment applications, and the like); regulatory and/or compliance solutions 142 (e.g., without limitation, applications for regulating loan terms and conditions, such as licensor, licensed collateral, licensed repayment period, licensed interest rate, required disclosure, required underwriting process, joint conditions, etc.); a platform-oriented market 500, such as a market application, solution, or service (abbreviated market application, such as, but not limited to, a loan association market, a blockchain-based market, a crypto currency market, a token-based market, a market for items used as mortgages, or other market); a warranty or guarantee application (e.g., without limitation, a related warranty or guarantee application for an item that is a subject of a loan, a mortgage of a loan, etc., such as a product, service, offer, solution, physical product, software, service level, quality of service, financial instrument, debt, mortgage item, service performance, or other item); an analysis application 130 (e.g., without limitation, an analysis application of any data type, application, event, workflow, or entity described in relation to the present disclosure and in the documents incorporated by reference herein, such as a big data application, a user behavior application, a forecasting application, a classification application, a control panel, a pattern recognition application, a metered economics application, a financial revenue application, a return on investment application, a scenario planning application, a decision support application, etc.); a pricing application 131 (e.g., without limitation, for pricing interest rates of loans and other terms and conditions). Thus, the administration application platform 128 can host and enable interaction between a variety of different applications (which term includes the above and other financial or transactional applications, services, solutions, etc.) such that any pair-wise or greater combination or permutation of these services can be improved over the same type of standalone application, with shared microservices, shared data infrastructure, and shared intelligence.
In embodiments, the data collection system 166 and monitoring system 164 may monitor one or more events related to loans, debts, bonds, warranty agreements, or other loan transactions, such as events related to: applying for loan; offer loan; receiving a loan; providing underwriting information for the loan; providing a credit report; postponing the required payment; setting loan interest rate; a deferred payment requirement; determining a collateral or property of the loan; verifying the property rights of the loan mortgage or guarantee; recording property right changes of property; evaluating the value of the loan collateral or guaranty; checking property related to the loan, status change of entity related to the loan, value change of entity related to the loan, working state change of borrower, financial rating change of borrower, and economic value change of goods provided as guarantee; providing loan insurance; providing evidence of property insurance associated with the loan; providing loan qualification evidence; determining a loan guarantee; underwriting the loan; repayment of the loan; defaulting the loan; withdrawing the loan; settlement loan; setting the terms and conditions of the loan; canceling property redemption rights subject to loan restrictions; the terms and conditions of the loan are modified.
Micro-service lending platform with data mobile phone service, block chain and intelligent contract
In embodiments, a platform is provided herein that includes various services, components, modules, programs, systems, devices, algorithms, and other elements for lending. In an embodiment, the platform or system includes a set of microservices having a set of application programming interfaces that enable connections between and with microservices through programs external to the platform, wherein the microservices include: (a) A multimodal data collection service set that collects information about loan transactions and monitors entities related to loan transactions; (b) A set of blockchain services for maintaining a security history ledger for events related to the loan, the blockchain services having access control features to manage access rights for a set of parties involved in the loan; (c) A set of application programming interfaces, data integration services, data processing workflows, and user interfaces for processing loan-related events and loan-related activities; and (d) a set of intelligent contract services for specifying terms and conditions of an intelligent contract governing at least one of loan terms and conditions, loan-related events, and loan-related activities.
In an embodiment, the loan-related entities include a group of entities selected from the group consisting of borrowers, insurers, equipment, goods, systems, fixtures, buildings, storage facilities, and mortgages.
In an embodiment, a collateral is monitored and the collateral is selected from: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, the multimodal data collection service set includes services selected from: a set of systems of things for monitoring an entity; a set of cameras monitoring the entity; a set of software services that extract information related to the entity from a publicly available information site; a set of mobile services that report information related to an entity; a set of wearable devices worn by a human entity; a set of user interfaces through which the entity provides information about the entity; and a set of crowdsourcing services for requesting and reporting information related to the entity.
In an embodiment, the loan-related event is selected from: applying for loan; offer loan; receiving a loan; providing underwriting information for the loan; providing a credit report; postponing the required payment; setting loan interest rate; a deferred payment requirement; determining a collateral for the loan; verifying the property rights of the loan mortgage or guarantee; recording property right changes of property; evaluating the value of the loan collateral or guaranty; checking property related to the loan, status change of entity related to the loan, value change of entity related to the loan, working state change of borrower, financial rating change of borrower, and economic value change of goods provided as guarantee; providing loan insurance; providing property insurance certificates associated with the loans; providing a loan qualification certificate; determining a loan guarantee; underwriting the loan; repayment of the loan; defaulting the loan; withdrawing the loan; settlement loan; setting the terms and conditions of the loan; canceling property redemption rights subject to loan restrictions; the terms and conditions of the loan are modified.
In an embodiment, the set of terms and conditions of the loan specified and managed by the set of intelligent contract services is selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line return plan, collateral description, collateral substitutability description, party, insured person, collateral, personal guaranty, lien, term, contract, redemption condition, default condition, and default outcome.
In an embodiment, the set of parties to the loan is selected from: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, and accountants.
In an embodiment, the loan-related activity comprises an activity selected from the group consisting of: searching for a party interested in participating in the loan transaction; applying for loan; underwriting the loan; forming a legal contract for the loan; monitoring loan fulfillment; repayment of the loan; restructuring or modifying the loan; settling the loan; monitoring the loan mortgage; building a loan bank; canceling the mortgage redemption right of the loan; and completing the loan transaction.
In an embodiment, the loan is of at least one of the following types: the system comprises an automobile loan, an inventory loan, a capital equipment loan, a performance bond, a capital improvement loan, a construction loan, an account receivable guarantee loan, an invoice financing arrangement, a warranty arrangement, a payday loan, a refund expected loan, an academic loan, a banking loan, a property loan, a housing loan, a risk debt loan, an intellectual property loan, a contractual right loan, a floating fund loan, a small business loan, an agricultural loan, a municipal bond, and a subsidy loan.
In an embodiment, the intelligent contract service configures at least one intelligent contract to automatically perform loan-related actions based on information collected by the multimodal data collection service set.
In an embodiment, the loan-related action is selected from: offer loan; receiving a loan; underwriting loan; setting interest rate of the loan; a deferred payment requirement; modifying interest rate of the loan; verifying the property rights of the mortgage; recording the change of property rights; evaluating the value of the collateral; initiating a check for collateral; the loan is collected; settlement loan; setting the terms and conditions of the loan; providing a notification to be provided to the borrower; the redemption of loan assets; and modifying the terms and conditions of the loan.
In embodiments, the platform or system may also include an automated agent that processes events related to at least one of the value, status, and ownership of a mortgage and takes actions related to a loan to which the mortgage belongs.
In an embodiment, the loan-related action is selected from: offer a loan; accepting the loan; an underwriting loan; setting interest rate of loan; a deferred payment requirement; modifying interest rate of the loan; verifying the property rights of the mortgage; recording the change of property rights; evaluating the value of the collateral; initiating a check for collateral; the loan is collected; settlement loan; setting the terms and conditions of the loan; providing a notification to be provided to the borrower; the redemption of loan assets; and modifying the terms and conditions of the loan.
Referring to fig. 2, there are depicted additional applications, solutions, programs, systems, services, etc. that may be present in the lending application 144, which may be included in the administration application platform 128 interchangeably with other elements described in connection with fig. 1, elsewhere in this disclosure, and in documents incorporated by reference herein. Additional entities 198 are also depicted in the figure, which should be understood to be interchangeable with other entities 198 described in connection with the various embodiments described herein. In addition to the elements already mentioned above, the lending application 144 may include: a set of applications, solutions, programs, systems, services, etc. that include one or more social network analysis applications 204 that can find and analyze information described in one or more social networks about various entities 198 (e.g., without limitation, information about parties, party behaviors, asset conditions, events related to parties or assets, facility conditions, locations of collateral 102 or assets, etc.), for example, by allowing a user to configure queries that can be initiated and managed between a set of social network sites using data collection system 166 and monitoring system 164; a crowdsourcing solution 250; <xnotran> 149 (, ( : ; ; ; ; ; ; ; ; ; ; ; ; , , , , , ; ; ; ; ; ; ; ; ; ; ; ; ), (, , , , , , , , , , , , , , , , , , , ), ( : ; ; ; ; ; ; ; ; </xnotran> An agent; building a loan bank; canceling the mortgage redemption right of the loan; withdrawing the loan; merging a set of loans; analyzing loan fulfillment; processing the loan default; transferring property rights for assets or collateral; and completing the loan transaction)); a rating solution 2102 (e.g., for rating an entity 198 (e.g., principal 210, collateral 102, asset 218, etc.), such as a rating relating to reputation, financial status, actual, status, value, presence of defects, quality, or other attributes); regulatory and/or compliance solutions 142 (e.g., for implementing regulations, applications, and/or monitoring of one or more policies, rules, regulations, procedures, agreements, processes, etc., such as policies, rules, regulations, procedures, agreements, processes, etc., relating to the terms and conditions of a loan transaction, steps required to form a loan transaction, steps required to perform a loan transaction, steps required with respect to a collateral or collateral, steps required for underwriting, steps required to set prices, interest rates, etc., steps required to provide necessary legal disclosure and notifications (e.g., to present percent annual interest rates), etc.); a custody solution or set of custody solutions 1802 (e.g., for custody of a set of assets 218, mortgages 102, etc. (including cryptocurrency, currency, securities, stocks, bonds, agreements certifying ownership rights, etc.), e.g., representing a principal 210, customer or other entity 198 in need of assistance in maintaining the security of an item, or intended to provide assurance, support or assurance of a debt, such as a debt related to a loan transaction); a loan marketing solution 2002 (e.g., to enable a borrower to sell a loan to a set of potential borrowers, to target a set of borrowers that are eligible for a transaction type, to configure marketing or promotional messages (including placement and duration of messages), to configure advertising and promotional channels for loan transactions, to configure promotional or loyalty program parameters, etc.); an agent solution 244 (e.g., for acting a set of loan transactions, such as mortgage loans, among a set of parties) that may allow a user to configure a set of preferences, profiles, parameters, etc., to find a set of prospective counterparties to the loan transaction; a bond management solution 234, e.g., for managing, reporting, joining, consolidating, or otherwise handling a set of bonds (e.g., municipal bonds, corporate bonds, performance bonds, etc.); a collateral and/or collateral monitoring solution 230, for example, for monitoring, classifying, predicting, or otherwise processing reliability, quality, status, health, financial status, physical condition, or other information about a collateral, a guarantor, a set of collateral in support of the collateral, a set of assets in support of the collateral, or the like; negotiation solutions 232, such as a set of terms and conditions for assisting, monitoring, reporting, facilitating and/or automatically negotiating a loan transaction (e.g., without limitation, principal amount of a debt, balance of a debt, fixed interest rate, variable interest rate, payment amount, payment plan, last line payback plan, collateral statement, collateral substitutability statement, party, insured person, guaranty, personal guaranty, lien, deadline, contract, redemption-out condition, default condition, and default outcome), which may include a set of user interfaces for configuring negotiation parameters, profiles, preferences, etc., such as a user interface that is automated using or provided information from the loan model 108, and a user interface that is automated using, provided information from, or facilitated by the Robot Process Automation (RPA) system 154 or other adaptive intelligence system 158; a collection solution 238 for reclaiming loans, which may optionally be automated by or with the assistance of a set of artificial intelligence 156 services and systems, provided information by or automated by the robotic process automation system 154 or other adaptive intelligence system 158, such as based on monitoring the status or condition of various entities 198 with the monitoring system 164 and data collection system 166 to trigger collection of collections, such as when one or more contracts are not met, the condition of a mortgage is poor, when a person's financial condition is below a threshold, etc.; a consolidation solution 240 for consolidating a set of loans, for example using a loan model 108 configured to model a set of consolidated loans and to implement automation using or by one or more adaptive intelligent systems 158; custody solution 258; a warranty solution 242, e.g., for monitoring, managing, automatically executing, or otherwise processing a set of warranty transactions, e.g., using a loan model 108 configured to model and automate the warranty transactions using or implemented by one or more adaptive intelligent systems 158; liability restructuring solution 228, e.g., for restructuring a set of loans or liabilities, e.g., using a loan model 108 that is configured to model alternative scenarios for restructuring a set of loans or liabilities and that uses or is automated by one or more adaptive intelligent systems 158; and/or an interest rate automation solution 224, such as a set of rules or models for setting or configuring a set of interest rates for a set of loan transactions, or for automatically setting interest rate settings based on information collected by the data collection system 166 or the monitoring system 164 (such as information about conditions, status, health, location, geographic location, storage conditions, or other relevant information about any entity 198) that may set interest rates or facilitate interest rate settings for a set of loans, such as using an interest rate model 108 configured to model interest rate scenarios for a set of loans and to implement automation using or by one or more adaptive intelligent systems 158. As with the solution referenced in connection with fig. 1, the various solutions may share the adaptive intelligence system 158, the monitoring system 164, the data collection system 166, and the data storage system 186, for example, by integrating into the loan support platform 100 in a microservice architecture with various appropriate data integration services, APIs 112, and interfaces.
Like entity 198 described in connection with fig. 2, entity 198 may also include a series of entities involved in loans, debt transactions, bonds, warranty agreements, and other loan transactions, such as: mortgages 102 and assets 218 (e.g., vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, facilities 190 (e.g., municipal facilities, factories, warehouses, storage facilities, processing facilities, plants, etc.), systems, a set of inventories, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property, contractual rights, legal rights, antiques, fixtures, equipment, furniture, tools, machinery, and personal property) used to secure, guarantee, or support payment obligations; a set of parties 210 (e.g., one or more primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured persons, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, agents, lawyers, valuation professionals, government officers, and/or accountants); a set of lending agreements 220 (e.g., loans, bonds 212, lending agreements, corporate debt agreements, subsidized loan agreements, warranty agreements, merger agreements, warranty agreements, underwriting agreements, etc., which may include a set of terms and conditions such as interest rates, payment schedules, payment amounts, principal, statements and warranties, indemnities, contracts, and other terms and conditions that may be searched, collected, monitored, modified, or otherwise processed by the lending support platform 100); a set of guarantees 214 (e.g., provided by personal insurers, enterprise insurers, government insurers, municipal insurers, and others to guarantee or support payment obligations or other obligations of the loan protocol 220); a set of fulfillment activities 222 (e.g., paying principal and/or interest, reserving required insurance, reserving property rights, meeting contracts, maintaining the status of collateral 102 or assets 218, conducting business according to agreed requirements, etc.); and a device 252 (e.g., an internet of things device that may be disposed on or in a good, device, or other item, such as a device for supporting collateral 102 or assets 218 for payment obligations or meeting contractual or other requirements, or a device that may be disposed on or in a package of goods, as well as a device disposed in other environments where the facility 190 or entity 198 may be located). In embodiments, the lending agreement 220 may be for bonds, warranty agreements, joint agreements, merger agreements, settlement agreements, or loans, such as one or more of the following: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
As mentioned elsewhere herein and in documents incorporated by reference herein, artificial intelligence (e.g., any of the techniques or systems described in this disclosure) can be employed in conjunction with various trading and marketing entities 198 and related processes and applications to facilitate the following: (a) Optimization, automation, and/or control of various functions, workflows, applications, features, resource utilization, and other factors; (b) Identification or diagnosis of various states, entities, patterns, events, contexts, behaviors, or other elements; and/or (c) predicting various states, events, contexts, or other factors. As artificial intelligence has increased, a large number of domain-specific and/or general artificial intelligence systems have become available and may continue to proliferate. As developers seek solutions to domain-specific problems, such as those associated with the entities 198 and applications of the platform 126 described by the present disclosure, they face challenges in selecting artificial intelligence models (e.g., which neural networks, machine learning systems, expert systems, etc. to select) and in discovering and selecting which inputs can effectively and efficiently use artificial intelligence for a given problem. As described above, opportunity mining program 153 may help find opportunities to improve automation and intelligence; however, once opportunities are discovered, the selection and configuration of artificial intelligence solutions remains a significant challenge that may continue to grow as artificial intelligence solutions proliferate.
One set of solutions to these challenges is an artificial intelligence storage 157 that is used to enable the collection, organization, recommendation, and presentation of relevant groups of artificial intelligence systems based on one or more attributes of the domain and/or domain-related issues. In embodiments, artificial intelligence storage 157 may include a set of interfaces to artificial intelligence systems, e.g., to enable downloading of relevant artificial intelligence applications, establishing links or other connections to artificial intelligence systems (e.g., links to cloud-deployed artificial intelligence systems through APIs, ports, connectors, or other interfaces), and so forth. The artificial intelligence storage 157 may include descriptive content about each of the various artificial intelligence systems, such as metadata or other descriptive material indicating the applicability of the system to solve a particular type of problem (e.g., prediction, NLP, image recognition, pattern recognition, motion detection, route optimization, or many other problems) and/or to operate on inputs, data, or other entities in a particular domain. In embodiments, artificial intelligence storage 157 may be organized by categories such as domain, input type, processing type, output type, computing requirements and capabilities, cost, energy usage, and other factors. In embodiments, the interface to the application memory 157 may obtain input from a developer and/or from a platform (e.g., from the opportunity mining program 153) indicating one or more attributes of a problem that may be resolved through artificial intelligence, and may provide a set of recommendations for a subset of artificial intelligence solutions that may represent favorable candidates based on the developer's domain-specific problem, such as via an artificial intelligence attribute search engine.
In an embodiment, the criteria for determining the recommendation may include an expected level of manual supervision. This may include: the level and type of decision committed to human workers (e.g., decision to purchase securities, make market decisions, obtain intellectual property licenses, financial limitations on actions and orders (e.g., whether the RPA can order or promise transactions below a certain dollar amount above which transactions are human participation)), the level and type of anticipated manual supervision of robotic process automation operations, the anticipated level of manual supervision and/or management of model training and training data set selection. Other considerations may include the level and type of expected human involvement in the management of the model version (e.g., determining historical break points at which input data should be discarded), and so forth.
In embodiments, criteria for determining recommendations may include security considerations, such as resistance training and complex environments such as network attacks, viruses, and so forth. Other security considerations may include security and management of historical training data sets, including audit trails. Safety considerations may include traceability and accuracy of the model-the manner in which the model or control parameters are updated, the personnel who have the authority to update the model, the manner in which the updates are recorded, the manner in which the results are associated with the model updates, etc. The manner in which versioning is implemented and recorded. Another safety consideration is to record AI results for audit trails, including financial and performance results.
In embodiments, the criteria for determining recommendations may include the availability of different AI types, models, algorithms, or systems (including heuristic/model-based AI, neural networks, etc.). Availability may be limited by the computing environment that the user intends to use, such as a given cloud platform, local IT system or network (edge or other network), etc., and whether a given type, model or algorithm is running in a client environment. In embodiments, computational factors and configurations may be used as criteria. For example, the types of available processors for running an AI solution in a client environment may be a factor, including: number and architecture of chipset, module, device, cloud component, processor types (e.g., multi-core processor availability, GPU availability, CPU availability, FPGA availability, custom ASIC availability, etc.), and the like. Further, the computing factors that may be represented as the minimum capability criteria may include available processing capabilities for solution training (e.g., utilizing cloud computing resources) and solution operator deployment environments/capabilities (e.g., ioT, in-vehicle network, edge network, mesh network, in-house IT solutions, standalone or other deployment environments). Additional standards may include software and interface standards, such as software environments like operating systems (Linux, mac, PC, etc.), languages and protocols to access input data sources for solution training and APIs to access runtime data, data integration and output.
In embodiments, the criteria may include various network factors such as available network type, available network bandwidth (input and output) for AI solutions and AI operations, network uptime, network redundancy, variability in delivery times (ordering of data may vary), and any other network and network criteria described herein.
In embodiments, the criteria may include absolute performance or quality of service factors, or performance or quality of service factors relative to other AI and/or non-AI solutions (e.g., traditional models or rule-based solutions). The criteria may include speed/delay, training/configuration time and AI solution, time that the AI solution provides the operating condition results, accuracy, reliability (e.g., ability to resolve the results), consistency, unbiased, result-based quality metrics such as Return On Investment (ROI), profitability (e.g., operational output of AI management), profitability, revenue and other economic metrics, safety measure performance, energy consumption (e.g., overall consumption, time-based consumption (e.g., ability to shift processing from peak time to off-peak time)), ability to acquire renewable or low carbon energy for model training and/or operation, cost management of new model training plans (power cost, delay and validation of new models), and so forth.
In embodiments, the criteria may include the ability of the client to access a given type or model due to license requirements and restrictions, client policy (as described elsewhere herein), regulations (including within the jurisdiction of the client), the jurisdiction of the data source (e.g., european data privacy and security harbor), the jurisdiction that manages a particular model, algorithm, etc. (e.g., export control of the technology), permissions (e.g., training data or operational data), etc. Further, recommendations may be influenced by the type of problem to be solved and whether there is a specific algorithm or method optimized for that type of problem (e.g., a quantum-annealing-based traveler solver, or even a classical heuristic that provides reasonable baseline results).
In embodiments, the criteria may include compliance or adherence to regulatory principles and policies. There may be policies regarding which input data sources are available for training the AI solution. There may be policies regarding which input sources may be used during operation. For example, input data sources may be reviewed for potential deviations, appropriate representations (demographic or problem space representations), scopes, and the like. There may be standards regarding the certification or approval of the solution by regulatory agencies, certification organizations, internal IT audits, and the like. There may be policies and procedures that must be deployed or enforced in terms of security (e.g., physical security of the system, network security, etc.), security requirements (e.g., user security, security of the output product, etc.), and so forth.
In embodiments, the criteria for recommending an AI solution may include criteria regarding data availability, such as availability of data sources of sufficient size, granularity, quality, reliability, location, time zone, accuracy, etc. for efficient model training. Additional criteria regarding data availability may include data costs of: input of model training, input of model operation. Additional criteria may include data availability for operation of the AI solution, and the like. The criteria for AI selection may also include upstream data processing requirements, primary data management considerations such as dimensional cleaning and data validation, and the like.
In an embodiment, criteria for solution selection may include the applicability of a model or solution to a given task or workflow of a "problem". The criteria may include benchmark performance of a given model relative to other models that perform known task types (e.g., convolutional neural networks for 2D object classification, gated recurrent neural networks for tasks prone to explosive errors, etc.). In embodiments, the selection of a solution may be based on a solution having a similar configuration as how a biological brain addresses similar tasks (e.g., where a sequence of neural network models is arranged to simulate a sequence or stream that may include series elements, parallel elements, feedback loops, conditional logical connections, graphics-driven elements, and other stream features), for example a stream of modular or quasi-modular processes, such as a stream involving a human or other species of brain, such as for visual or auditory processing, language recognition, speech, motion tracking, image recognition, face recognition, motion coordination, haptic recognition, spatial orientation, and so forth. The criteria may include applying an AI-like heuristic as a guard rail or operation affecting smaller areas.
In embodiments, the criteria may include model deployment considerations such as model update requirements (e.g., frequency and requirements of model decommissioning), management of historical models and maintenance of historical decision engines, likelihood of distributed decision capability, model management rules (e.g., how long a model or input data is deemed to be effective for training), and so forth.
In embodiments, search results or recommendations may be based at least in part on collaborative filtering, such as by requiring developers to indicate or select elements of favorable models, and by clustering, such as by using similarity matrices, k-means clustering, or other clustering techniques that associate similar developers, similar domain-specific problems, and/or similar artificial intelligence solutions. Artificial intelligence storage 157 may include e-commerce features such as ratings, reviews, links to related content, and mechanisms for provisioning, licensing, delivery, and payment (including distribution of payment to branches and/or contributors), including mechanisms that operate using intelligent contracts and/or blockchain features to automatically perform purchasing, licensing, payment tracking, transaction settlement, or other functions.
In an embodiment, upon selection or recommendation of a solution, the solution must be configured for the particular client and problem to be solved. The configuration may include, but is not limited to, any of the factors mentioned above in connection with the solution model selection. It is important to configure a set of neural network types (e.g., modules) in a flow (with options of series elements, parallel elements, feedback loops, conditional logical connections, graph-driven flow, etc.) to identify the relative strengths and weaknesses (based on any or selected factors described above) of each AI solution for the particular task involved in the flow. In an illustrative and non-limiting example of flow, a) identify something by visual classification (e.g., with CNN), b) predict its future state (e.g., with gated RNN), c) optimize the future state (using feed-forward neural networks). The configuration options include: selecting one or more neural network types (including a mixture of different neural networks and/or other model types in the various streams described above); selecting an input model type; setting an initial model weight; setting a model size (e.g., number of layers in a deep neural network); selecting a computing deployment environment; selecting an input data source for training; selecting an input data source for operation; selecting a feedback function/outcome metric; selecting one or more data integration languages for input and output; configuring an API for model training; configuring an API for model input; configuring an API for output; configuring access controls (role based, user based, policy based, etc.); configuring security parameters; configuring a network protocol; configuring storage parameters (type, location, deadline); configuration economics factors (e.g., admission pricing, cost allocation, etc.), and the like. Additional configuration options may include: configuring a data stream (e.g., a stream from a plurality of stock exchanges into a centralized decision engine); configuring high availability, fault tolerant environments (e.g., requiring transaction system failure to reach an operational state that meets service level requirements), price based data acquisition policies (e.g., detailed financial data may require additional expenditure); combining with a heuristic method; coordinating massively parallel decision environments (e.g., distributed vision systems), and the like. If there are areas that need further consideration (e.g., pushing decisions to edges to monitor specific events), additional configuration may include building decision models.
In an embodiment, another set of solutions that may be deployed alone or with other elements of the platform (including the artificial intelligence memory 157) may include a set of functional imaging capabilities 161, which may include a monitoring system 164 and a data collection system 166, and in some cases may include a physical process viewing system 162 and/or a software interaction viewing system 160, for example, for monitoring various trading and marketing entities 198. In an embodiment, the functional imaging system 161 may provide considerable insight to in-depth analyze the type of artificial intelligence that may be most effective in most effectively solving a particular type of problem. As noted elsewhere in this disclosure and in the documents incorporated by reference herein, as the size, complexity, and interconnections of computing and networking systems grow, they exhibit information overload, noise, network congestion, energy waste, and many other problems. As the internet of things evolves into hundreds of billions of devices, and indeed a myriad of potential interconnections, optimization becomes very difficult. One source of insight is the human brain, which faces similar challenges, and reasonable solutions have been developed over thousands of years, solving a series of very difficult optimization problems. The human brain operates using a large number of neural networks organized into interconnected modular systems, each modular system having a degree of adaptability to address specific problems, ranging from regulation of biological systems and maintenance of homeostasis, to detection of a wide range of static and dynamic patterns, to identification of threats and opportunities, and the like.
Establishing a Robotic Process Automation (RPA) system includes selecting an optimal AI solution and configuration. There may be goals in training an RPA system, typically with respect to human interaction with software and/or hardware (e.g., tools) and use of the system in operation, both of which may be enhanced by understanding the manner in which the human brain operates in solving a problem. In a single neural network solution (using one network to solve a problem in a single step, such as a single step conversion), the process may involve setting initial weights for the inputs, selecting the input data source, selecting the network type (e.g., convolutional or non-convolutional, gated or non-gated, deep or non-deep network, etc.), the number of layers, and the type of inputs provided thereto (and outputs provided thereto if complex outputs are present). The idea is to select inputs and weights that the human brain tends to use to solve the same problem. For a mixture of multiple AI modules/systems and/or a combination of AI with more traditional software systems (e.g., control systems, analytical models, rule-based systems, conditional logic systems, etc.), the value may be the above value plus a perceptual configuration to the time series of processing, such as to reflect brain activity patterns in the following cases: visual, auditory, haptic, and other sensory information is processed to identify conditions, context, motion, objects, etc., and then other areas (that behave differently) perform a number of things such as solving logical problems, calculating, following algorithms, expanding possibilities, etc. For these, "Lego blocks" (each composed of a different neural network or other AI type) can be ordered, set in parallel, linked through conditional logic, etc. to achieve a solution that automates the process.
In embodiments, identification information of inference type and/or processing type may be provided by performing brain imaging such as functional MRI or other magnetic imaging, electroencephalography (EEG), or other imaging, for example by identifying extensive brain activity (e.g., activity bands such as delta waves, theta waves, alpha waves, and gamma waves), by identifying a set of brain regions activated and/or in an inactive state during user set interaction for training an intelligent agent (e.g., neocortical regions such as Fp1 (participation judgment and decision), F7 (participation imagination and emulation), F3 (participation analytic inference), T3 (participation in speech), C3 (participation in fact storage), T5 (participation in mediation and sympathy), P3 (participation in tactical navigation), O1 (participation in visual engineering), fp2 (participation in process management), F8 (participation in belief systems), F4 (participation in expert classification), T4 (participation in listening and intuition), C4 (participation in artistic creation), T6 (participation in prediction), P4 (participation in games), O2 (strategic participation in abstract games), and/or other combinations of these, by which intelligent agents may be able to solve certain types of mental tasks or similar intelligent agents in learning processes. In an embodiment, the intelligent agent may be configured with a neural network type or combination of types selected to replicate or simulate processing activities similar to brain region activities of a human expert who is performing a set of activities for which the intelligent agent is to be trained. As one of many possible examples, the trader may be shown to use the visual processing area O1 and the strategic play area P4 of the neocortex when making a successful trade, and the neural network may be configured with a convolutional neural network for providing efficient replication of visual pattern recognition and a gated recurrent neural network for replicating strategic play. In an embodiment, a neural network repository representing a combination of neural network types that mimic or simulate neocortical activity may be configured to allow selection and implementation of modules that replicate the combination of activities used by human experts to conduct as the subject of intelligent agent development, e.g., relating to robotic process automation. In an embodiment, the various neural network types from the library may be in a series and/or parallel configuration to represent a processing flow that may be arranged to mimic or replicate the processing flow in the brain, for example based on spatiotemporal imaging of the brain as it relates to activity as an automated object. In embodiments, an intelligent software agent for agent development may be trained, for example using any of the training techniques described herein, to select a set of neural network resource types, arrange the neural network resource types according to a process flow, configure input data sources for the set of neural network resources, and/or automatically deploy the set of neural network types on available computing resources to initiate training of the configured set of neural network resources to perform a desired intelligent agent/automated workflow. In an embodiment, an intelligent software agent for agent development operates on an input dataset of spatiotemporal imaging data of the human brain (e.g., an expert who is performing a workflow that is the subject of further development) and uses the spatiotemporal imaging data to automatically select and configure the selection and arrangement of the set of neural network types to begin learning. Thus, a system for developing intelligent agents may be configured to (optionally automatically) select a neural network type and/or arrangement based on spatio-temporal neocortical activity patterns of human users involved in a workflow for which the agent is trained. Once developed, the resulting intelligent agent/process automation system may be trained as described in this disclosure.
In an embodiment, a system for developing intelligent agents, including the agents for developing intelligent agents described above, may use information from brain imaging of a human user to (optionally automatically) infer which data sources should be selected as inputs to the intelligent agents. For example, for a process in which the neocortical region O1 is in a highly active state (involving visual processing), visual input (e.g., available information from a camera, or a visual representation of information such as price patterns, etc.) may be selected as a favorable data source. Similarly, for processes involving area C3 (involving the storage and retrieval of facts), a data source (e.g., a blockchain-based distributed ledger) may be selected that provides reliable fact information. Thus, the system for developing intelligent agents may be configured to (optionally automatically) select input data types and input data sources based on spatio-temporal neocortical activity patterns of human users involved in the workflow for which the agent is trained.
Functional imaging 161, such as functional magnetic resonance imaging (fMRI), electroencephalography (EEG), computed Tomography (CT), and other brain imaging systems have been developed that can recognize patterns of brain activity in real-time and temporally correlate with other information, such as behavior, stimulation information, environmental condition data, gestures, eye movements, etc., so that through the functional imaging 161, the platform can determine and classify brain modules, operations, systems, and/or functions used during the performance of a set of tasks or activities, such as tasks or activities involving software interactive viewing system 160, physical process viewing 162, or a combination thereof, alone or in conjunction with other information collected by monitoring system 164. Such classification may help select and/or configure a set of artificial intelligence solutions, such as a set of artificial intelligence solutions from artificial intelligence storage 157, that includes a set of capabilities and/or functions similar to the modules and functional groups of the human brain in performing an activity, such as Robotic Process Automation (RPA) system 154 for initially configuring a task to automatically perform a task performed by an expert human.
In embodiments, the system may receive and/or monitor a set of inputs related to the user, including image/video feeds, audio feeds, motion sensors, heartbeat monitors, other related biosensors, and so forth. In an embodiment, the system may also receive and be monitoredAn input related to an action taken by the user is measured, such as an input to the computing device or an action taken with respect to the physical environment in which the user is working. In an embodiment, all of the collected data is time stamped, such that, for example, a video feed may capture a series of images of the user as the user performs a task, and may simultaneously capture eye movements of the user (e.g., gaze tracking) to determine items of interest to the user (e.g., what the user sees on the screen). During this time, the system may also track the user's heart rate or other biosensor measurements to determine whether the user is engaged in a task that requires attention or is less demanding of attention. The system may also track actions taken and may further determine the time spent between these actions. The RPA solution may then allocate processing (e.g., heavier, more computationally intensive activities) to an AI solution on a cloud platform (e.g., deep neural network with multiple layers) and use a more compact model (e.g., tinyML: (a) (b)) TM ) Models) place less computationally intensive tasks (e.g., tasks for which humans quickly make decisions on minimal input data) on the edge or IoT device platform.
In an embodiment, the system may determine the relative time spent between these actions such that a long period of no action may indicate that the user is engaged in work requiring a large amount of thought, while a short period of no action may indicate that the user is engaged in work requiring less thought, more action. The system may also monitor the audio feed and/or status of the computing device being used by the user when the period of inactivity occurs, which may indicate that the user is distracted rather than focused. Assuming that the user is working actively and not showing distraction, the system may generate a feature vector relating to the work the user is performing, the feature vector indicating the time-stamped data entries, which may then be fed into the machine learning model. In an embodiment, the machine learning model may determine a brain region (or regions) from a set of brain regions that are likely to participate during work. In an embodiment, the machine learning model may be trained using a training data set (including labeled training vectors), where the label of each training vector indicates the brain region (or regions) in which the subject participated in generating the training vector. For example, each training vector may be labeled using one or more of: fp1 (participation in judgment and decision), F7 (participation in imagination and simulation), F3 (participation in analytical reasoning), T3 (participation in speech), C3 (participation in fact storage), T5 (participation in mediation and sympathy), P3 (participation in tactical navigation), O1 (participation in visual engineering), fp2 (participation in process management), F8 (participation in belief system), F4 (participation in expert classification), T4 (participation in listening and intuition), C4 (participation in artistic creation), T6 (participation in forecasting), P4 (participation in strategic game), O2 (participation in abstraction). In some embodiments, the training vector may indicate additional data, such as the type of task being performed, whether the subject successfully completed the task, or other suitable information.
In embodiments, these machine learning models may be trained for different types of work tasks, such as negotiating, drafting, data entry, replying to emails, analyzing data, reviewing documents, and so forth. Further, in some embodiments, such a machine learning model may be trained by one principal but used by other principals. In these embodiments, the machine learning model (and/or training data vector) may be purchased and sold by the marketplace. Such machine learning models may be used in a wider range of RPA systems, such that the output of the model may be used as a specific signal in the RPA learning process.
Typically, data from an organization is used to predict the organization's location in the marketplace and to adjust the flow within the organization accordingly. In an exemplary embodiment, robotic imaging may be used to capture data of users (e.g., employees or workers) within an organization as they complete various tasks and processes, while also correlating this information with the completion of those tasks/processes. Various analyses (e.g., efficiencies) are obtained regarding successful completion of the task. Data obtained from the tracking/monitoring users is then used to determine which factors indicate that certain users are more successful in completing the task than others (e.g., based on the user's physical activity in correctly performing the task, the active brain region, the user's physical strength, etc.). This may be based on scanning/monitoring of the user as they complete the task. In some exemplary embodiments, a system is used to separate the following two types of data: data relating to users who successfully completed the task, and data relating to users who completed less successfully. The system may analyze biological data of workers to determine why one worker was more successful than the other workers. In some exemplary embodiments, the analysis may also be combined with data from the machine to determine whether the worker is accurately/efficiently using the machine. These biological data from the workers may also be used to determine if more workers are needed to improve efficiency. Historical data and results of process competition are used to see if improvements should be made by training, selecting employees that perform better than others in performing certain tasks, and the like. For example, the resulting analysis and the contribution to the results may be used as a feedback function for weighting the values of specific capabilities used to design an AI solution intended to perform the same or similar tasks. In some exemplary embodiments, various data and analyses as described above may be used to determine whether improvements made based on the analysis also improve the market position of the organization.
An operator skilled in performing a task may establish a firm memory connection with muscle function, i.e. muscle memory, which translates into easily accomplished actions that would otherwise be difficult to accomplish or at least require repeated attempts, slow operation, etc. A system that can distinguish between actions done using muscle memory and other actions can better identify which actions are worth following/repeating/learning.
Understanding the mechanisms of muscle memory, such as learning the path of travel of muscle memory from cognitive (visual, auditory, etc.) inputs, may be the basis for understanding how human action automation is achieved. This may involve repeating types of actions, a similarity-based association of one type of action with another type of action, such as body posture, expected result (throwing the hammer into a holster, etc.).
Another value might be to know how two people develop a muscle memory that enables them to "enter a rhythm", for example when exchanging physical goods. What the clues they exchange are, visually recognizable actions (hand placement/orientation), and how to interpret these actions.
In embodiments, the imaging system may analyze brain images of multiple members of a team for a set of tasks or workflows involving different types of expertise. Team performance may be tracked and the AI solution may be configured to replicate the types of neural processing performed by different team members, such as motion tracking and coordination performed by one team member and performance decisions made by another team member.
In an embodiment, the imaging system may analyze brain images of a plurality of members of a simulated trial or negotiation practice session to conduct a set of verbal communications or the like regarding negotiation points, point-by-point counts, or the like. In addition to brain images, biological indicators of audio capture and response to communication may be obtained to increase the range of multidimensional data that is useful for learning how to automate human behavior related to successful negotiations and the like.
Given the degree of abstraction that humans use to trigger actions, e.g. identifying an alarm tone or identifying a colleague's action, we may not be so abstract in machine-machine communication, e.g. the input triggering an alarm tone may trigger direct machine-machine communication, or if the colleagues are machines, they may indicate their location in daily work to indicate that they are ready to hand over work. This is similar to the way in which less intelligent robots implement automation, even with simple macros, extracting "intelligence" from the process to make it more robust, and there are strategies and methods that can be applied to these biological types of inputs that are more abstract than necessary. This reduction in complexity can be trained in the system itself, as they recognize that a myriad of "soft" triggers (e.g., image recognition) may turn into "hard" triggers.
By using systems of Fp1 (engage in judgment and decision), P3 (engage in tactical navigation), O1 (engage in visual engineering), fp2 (engage in process management), F8 (engage in belief systems), and T4 (engage in listening and intuition), etc., in some embodiments, the training vector may indicate a system that mixes audio and visual concepts. The system may use an expert system to monitor a set of inputs and reconfigure the inputs to monitor assets including image feeds at various electromagnetic frequencies (e.g., visible light, heat, UV, etc.) as well as audio feeds from those frequencies to determine usage, sound used, and sounds that may be of interest. When examples include fixed assets (non-movable assets), environmental measurements of the environment and signatures of product use or non-use, such as lack of motion, hot stamping, or lack of product, may be measured. Contact with assets by the changing environment, user or other fixture within the room may result in reconfiguration of the sensors to seek space. When secured within a room, such systems may determine that environmental conditions may be harmful to the asset, such as high intensity exterior lighting (UV content too high) versus more appropriate lighting. Additionally, sensing usage movement is also included. In more mobile assets, detection and resolution of benign motion (rather than motion that may have a greater tendency to age or damage the asset) may be recorded and may be described as an aggregate feed.
Risk management-combination of F3 (analytical reasoning) and Fp1 (judgment and decision) -analysis and decision in the human brain is informative by experience and knowledge, which may be incomplete, limited, negative, positive, factual, emotional, etc. The AI can identify situations (sensors, image recognition, proximity, text and dialog analysis, etc.) and apply better risk management in decisions using fact-based stored results of similar situations. This can be used to make better purchasing and financial decisions for the consumer. In other applications, it may be applied to emergency responses, police action, and the like.
In embodiments, the AI solution may be configured as a companion risk manager that primarily operates the AI solution, e.g., sharing common inputs and resources, but with emphasis on identifying risks, externalities, and other factors that the core process automation does not need but may improve abatement, safety, emergency response, and other aspects.
In embodiments, the AI solution may be configured as a companion risk manager that primarily operates the AI solution, e.g., sharing common inputs and resources, but with emphasis on identifying risks, externalities, and other factors that the core process automation does not need but may improve abatement, safety, emergency response, and other aspects.
Thus, the platform may include a system that acquires input from a functional imaging system to optionally configure a set of artificial intelligence capabilities for the robotic process automation system based on attribute matching between one or more biological systems (e.g., brain systems) and one or more artificial intelligence systems. The selection and configuration may also include selecting inputs for robotic process automation and/or artificial intelligence that are configured based at least in part on functional imaging of the brain while the worker performs tasks, such as selecting visual inputs for brain-vision system high activation (e.g., images from a camera), selecting acoustic inputs for brain-hearing system high activation, selecting chemical inputs for brain-olfactory system high activation (e.g., chemical sensors), and so forth. Thus, an improved way of a bio-aware robotic process automation system is to automate initial configuration or iterative improvements or to guide under developer control through imaging derived information collected while workers perform expert tasks that may benefit from automation.
With functional imaging, one can understand tasks that involve serial processing and parallel processing, and understand the types of AI solutions that may be best suited for similar tasks (e.g., whether it is best to receive speech and visual data/input simultaneously (in parallel) or sequentially). Is there an order in which the user receives data that may suggest the best performance ranking? Analysis of the functional images can identify which computational tasks are processed most quickly by visual input relative to text (language processing) and can improve the matching of tasks to optimal input/stimuli.
With functional imaging, the efficiency resulting from pairing or multiple combinations of stimuli (e.g., whether tasks/commands are most efficiently delivered by providing multiple different inputs at once and/or whether it is preferable to omit certain stimuli from the inputs/commands) can be determined.
With functional imaging, tasks or events to be performed/resolved may be ordered based on probabilistic improvement in performance of subsequent tasks (where a task may be a computational or actual action performed by the device based on data/stimulus input).
With functional imaging, the negative impact on performance/computation can be measured based on "noise", which can be unwanted data, irrelevant data, or overwhelming data size, similar to determining "negative stimuli" (in a human environment, this may be environmental noise that distinguishes human sounds in a cascade of auditory inputs, or environmental lighting in image recognition, or motion when objects in the computation region, etc.).
As one of many possible examples, the market host may be shown as using the forecast region T6 and the judgment and decision region Fp1 when configuring a new market, for example, to forecast favorable market configuration parameters (e.g., to optimize market efficiency, profitability, and/or fairness) and generate decisions related to the market parameters, and the neural network may be configured with a neural network for providing efficient replication of the forecast and a neural network for replicating the decisions. Market configuration parameters may include, but are not limited to, assets, asset types, asset descriptions, ownership verification methods, delivery of traded goods, market forecasts, marketing methods, market control methods, regulatory limits, data sources, insider transaction detection techniques, liquidity requirements, admission requirements (e.g., whether a dealer-to-dealer transaction is conducted, a dealer-to-customer transaction, or a customer-to-customer transaction is conducted), anonymity (e.g., whether a counterparty identity is revealed), continuity of order processing (e.g., continuous or periodic order processing), interaction (e.g., bilateral or multilateral), price discovery, pricing drivers (e.g., order-driven pricing or quote-driven pricing), price formation (e.g., consolidated or dispersed price formation), custody requirements, types of orders allowed (e.g., limit, stop-run, market, and non-market), types of markets supported (e.g., dealer market, auction market, absolute auction market, minimum bid auction market, reverse auction market, closed auction market, dutch auction market, multi-step auction market (e.g., two steps, three steps, n steps, etc.)), forward market, futures market, secondary market, derivatives market, emergency market, total market (e.g., common fund), etc.), trading rules (e.g., minimum bid unit, trade pause, open/close time, custody requirements, liquidity requirements, geo-location rules, jurisdictional rules, show rules, insider trade ban, benefit conflict rules, etc.) Temporal rules (e.g., related to spot market transactions, futures transactions, etc.), asset listing requirements (e.g., financial reporting requirements, auditing requirements, minimum capital requirements), minimum savings amount, minimum transaction amount, validation rules, commission rules, charging rules, market lifetime rules (e.g., long-term market versus short-term market with temporal restrictions), and transparency (e.g., amount and scope of information disseminated).
The RPA system can perform tasks related to visual algorithms using AI systems related to biological brain functions F3 (participating in analytical reasoning) and O1 (participating in visual engineering) in combination. For example, tasks related to visual algorithms may include processing image sensor data by an O1 vision engineering system to determine what the RPA system "observes" and how to interpret, classify, identify, etc. what is "observed". The F3 analytic inference system may then perform: 1) Inference to determine factors that lead to a current state of "observed" content, and 2) prediction to determine a future state of "observed" content based on the current state of visual data. The RPA system may use the T6 prediction function to help perform such predictions. These inferences may be useful in determining the cause of problems, inefficiencies, or problems in the system to be analyzed. The prediction may help determine a solution to the problem and/or potential efficiency improvements. The AI system using F3, O1, and/or T6 may then also be used to select a machine learning model suitable for performing problem solving and/or efficiency boosting. For example, in a manufacturing environment, the RPA system and the AI system may obtain data from a plurality of visual IoT sensors, which are from one or more locations in a manufacturing plant. The O1 vision engineering system may determine and/or classify what the visual data observes, such as one or more machines, products, assembly lines, and so forth. The F3 analytic inference system may determine whether one or more machines, products, assembly lines, etc., indicate a problem or inefficiency. The T6 system may then make the prediction and forward the prediction to an appropriate machine learning model to determine a solution to the problem and/or an efficiency boost.
IoT and onboard sensor platform for monitoring mortgages
In embodiments, a platform is provided herein that includes various services, components, modules, programs, systems, devices, algorithms, and other elements for monitoring a loan mortgage. In an embodiment, the platform or system comprises: (a) A set of internet of things services for monitoring the environment of a collateral; a set of sensors disposed on at least one of the collateral, the collateral container, the collateral package, the set of sensors for associating sensor information sensed by the set of sensors with a unique identifier of the collateral; and a set of blockchain services for obtaining information from the set of internet of things services and the set of sensors and storing the information in blockchains, wherein access to the blockchains is provided through the secure access control interface for secured borrowers of loans for which the mortgage is restricted.
In an embodiment, the loan is of at least one of the following types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
In embodiments, the collateral is selected from: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, the set of internet of things services monitors an environment selected from a real estate environment, a commercial facility, a warehousing facility, a transportation environment, a manufacturing environment, a storage environment, a house, and a vehicle.
In an embodiment, the set of sensors is selected from the group consisting of: image, temperature, pressure, humidity, velocity, acceleration, rotation, torque, weight, chemical, magnetic, electric, and position sensors.
In an embodiment, the platform or system may further include a set of services for reporting events related to at least one of value, status, and ownership of the collateral.
In embodiments, the platform or system may also include an automated agent that processes events related to at least one of the value, status, and ownership of a collateral and takes actions related to loans for which the collateral is restricted.
In an embodiment, the loan-related action is selected from: offer loan; receiving a loan; underwriting loan; setting interest rate of the loan; a deferred payment requirement; modifying interest rate of the loan; verifying the property rights of the mortgage; recording the change of property rights; evaluating the value of the collateral; initiating a check for collateral; the loan is collected; settlement loan; setting the terms and conditions of the loan; providing a notification to be provided to the borrower; the redemption of loan assets; and modifying the terms and conditions of the loan.
In embodiments, the platform or system may also include a market value data collection service that monitors and reports market information related to the value of a collateral. In embodiments, the collateral is selected from: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, merchandise, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, the market value data collection service monitors pricing or financial data of items similar to the collateral in at least one public market.
In an embodiment, a set of similar items for valuing a collateral is constructed using a similarity clustering algorithm based on attributes of the collateral. In an embodiment, the attributes are selected from: the type of collateral object, the age of the collateral object, the condition of the collateral object, the history of the collateral object, the storage conditions of the collateral object, and the geographic location of the collateral object.
In an embodiment, the platform or system may also include a set of intelligent contract services for managing intelligent contracts for loans. In an embodiment, the intelligent contract service sets the terms and conditions of the loan. In an embodiment, the set of terms and conditions of the loan specified and managed by the set of intelligent contract services is selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line return plan, collateral description, collateral substitutability description, party, insured person, collateral, personal guaranty, lien, term, contract, redemption condition, default condition, and default outcome.
Allocating collateral for loans using distributed ledgers and intelligent contracts
In an embodiment, a system for processing a loan with a set of computing services is provided herein. In an embodiment, the platform or system comprises: (a) A set of blockchain services for supporting a distributed ledger; (b) A set of data collection and monitoring services for monitoring a set of items providing collateral for the loan; (c) A set of valuation services that use valuation models to set the value of collateral based on information from the data collection and monitoring services; and (d) a set of intelligent contract services for determining intelligent loan contracts, wherein the intelligent contract services process output from the set of valuation services and assign mortgages sufficient to warrant the loan to the loan on the distributed ledger where the loan-related events are recorded.
In an embodiment, the set of intelligent contract services further includes services for specifying terms and conditions of an intelligent contract governing at least one of loan terms and conditions, loan-related events, and loan-related activities.
In an embodiment, the loan is of at least one of the following types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
In an embodiment, the set of terms and conditions of the loan specified and managed by the set of intelligent contract services is selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line return plan, collateral description, collateral substitutability description, party, insured person, collateral, personal guaranty, lien, term, contract, redemption condition, default condition, and default outcome.
In embodiments, the collateral is selected from: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, a set of data collection and monitoring services includes the following: a set of internet of things systems for monitoring entities; a set of cameras for monitoring the entity; a set of software services for obtaining information related to an entity from an open information website; a set of mobile devices for reporting information related to an entity; a set of wearable devices for wearing by a human entity; a set of user interfaces through which entities provide information about the entities; and a set of crowdsourcing services for requesting and reporting information related to the entity.
In an embodiment, the valuation service includes an artificial intelligence service that iteratively refines the valuation model based on result data related to the collateral transactions.
In an embodiment, the valuation service also includes a set of market value data collection services that monitor and report market information related to the value of the collateral.
In an embodiment, a set of market value data collection services monitor pricing or financial data for items similar to the collateral in at least one public market.
In an embodiment, a set of similar items for valuing a collateral is constructed using a similarity clustering algorithm based on attributes of the collateral.
In an embodiment, the attributes are selected from: the type of collateral object, the age of the collateral object, the condition of the collateral object, the history of the collateral object, the storage conditions of the collateral object, and the geographic location of the collateral object. Intelligent contracts for setting primary and secondary priorities for borrowers of the same mortgage
In an embodiment, a system for processing a loan with a set of computing services is provided herein. In an embodiment, the platform or system comprises: (a) A set of blockchain services for supporting a distributed ledger; (b) A set of data collection and monitoring services for monitoring a set of items providing collateral for the loan; and (c) a set of intelligent contract services for determining intelligent lending contracts, wherein the intelligent contract services assign mortgages to loans on a distributed ledger that records loan-related events, and record priorities for the mortgages among a set of lending entities.
In an embodiment, the set of intelligent contract services further includes services for specifying terms and conditions of an intelligent contract governing at least one of loan terms and conditions, loan-related events, and loan-related activities.
In an embodiment, the loan is of at least one of the following types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
In an embodiment, the set of terms and conditions of the loan specified and managed by the set of intelligent contract services is selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line return plan, collateral description, collateral substitutability description, party, insured person, collateral, personal guaranty, lien, term, contract, redemption condition, default condition, and default outcome.
In an embodiment, the set of collateral is selected from the following: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, the platform or system may also include a set of valuation services that use a valuation model to set the value of a collateral based on information from a set of data collection and monitoring services that monitor the collateral.
In an embodiment, the valuation service includes an artificial intelligence service that iteratively refines the valuation model based on result data related to the collateral transactions.
In an embodiment, the valuation service also includes a set of market value data collection services that monitor and report market information related to the value of the collateral.
In an embodiment, a set of market value data collection services monitor pricing or financial data for items similar to the collateral in at least one public market.
In an embodiment, a set of similar items for valuing a collateral is constructed using a similarity clustering algorithm based on attributes of the collateral.
In an embodiment, the attributes are selected from: the type of collateral object, the age of the collateral object, the condition of the collateral object, the history of the collateral object, the storage conditions of the collateral object, and the geographic location of the collateral object.
In an embodiment, the intelligent contract service uses the output from the set of valuation services to distribute the value of mortgages among a set of borrowers.
In an embodiment, the allocation of value is based on the borrower's priority information recorded in the distributed ledger.
Referring to fig. 3, in an embodiment, the device 252 may be a connecting device that connects (e.g., through any of a variety of interfaces 187) to an internet of things (IoT) data collection service 208, which may be part of or integrated with the data collection system 166 and the monitoring system 164 of the loan support platform 100. The interface 187 can include a network interface, API, SDK, port, proxy, connector, gateway, cellular network appliance, data integration interface, data migration system, cloud computing interface (including interfaces including computing capabilities, such as awgiotgreengrass TM 、Amazon TM Lambda TM And the like) and the like. For example, ioT data collection service 208 may be used to obtain data from a set of edge data collection devices in the internet of things, such as low power sensor devices (e.g., to sense movement of an entity, to sense temperature, pressure, or other attributes of entity 198 or its environment, etc.), cameras that capture still or video images of entity 198, more fully enabled edge devices (e.g., raspberypi TM Or other computing devices, unix TM Apparatus and operationDevices of an embedded system, e.g., including microcontrollers, FPGAs, ASICs, etc.), etc. In an embodiment, the IoT data collection service 208 may collect data about the collateral 102 or assets 218, such as data about location, condition (health, physical condition, etc.), quality, security, ownership, and the like. For example, personal property such as gems, vehicles, art, etc. may be monitored by motion sensors and/or cameras having known locations (or locations confirmed by GPS or other positioning systems). The camera may provide evidence that the item remains undamaged and owned by the principal 210, e.g., indicating that it is still an appropriate and sufficient collateral 102 for the loan. In embodiments, this may include mortgages for small loans, such as clothing, collectibles, and other items.
In an embodiment, the loan support platform 100 has a set of data integration microservices including a data collection service 166, a monitoring service 164, a blockchain service for storing data as blockchain 136, and an intelligent contract service 134 for processing loan entities and transactions. The intelligent contract service 134 may obtain data from the data collection system 166 and the monitoring system 164 (e.g., from IoT devices) and automatically execute a set of rules or conditions embodying an intelligent contract based on the collected data. For example, upon identifying that the collateral 102 of the loan has been compromised (e.g., as evidenced by a camera or sensor), the smart contract service 134 may automatically initiate a loan payment request, automatically initiate a redemption-stop process, automatically initiate actions requiring replacement or backup of the collateral, automatically initiate a check process, automatically alter collateral-based payments or interest rate terms (e.g., set an interest rate to a level of unsecured loan instead of secured loan), and so forth. The smart contract events may be recorded by the blockchain service on the blockchain 136, such as in a distributed ledger. Automatically monitoring mortgages 102 and assets 218 and processing the loan through the smart contract service 134 may facilitate lending to a greater range of parties 210 and lending based on mortgages 102 and assets 218 that are more extensive than traditional loans, as the borrower may have greater certainty as to the status of the mortgages. The monitoring system 164 and the data collection system 166 may also monitor and collect data from Data from an external market 188 or a market operating with the loan support platform 100 to maintain knowledge of the value of the collateral 102 and assets 218 to ensure that the items remain of sufficient value and liquidity to warrant repayment of the loan. For example, eBay may be monitored TM Etc. to confirm that the type and condition of the personal property may be a readily disposable type and condition for the borrower in a high liquidity public market, such that the borrower is certain to receive payment in the event of a default by the borrower. In this manner, loans may be issued and managed for various personal properties that are generally difficult to use as mortgages. In an embodiment, an automatic redemption process may be initiated by a smart contract, which upon the occurrence of a default condition that permits redemption (e.g., an outstanding condition is not processed), may include the following processes: at a common auction site (e.g., eBay) TM Or an auction website suitable for a particular type of property), automatically initiate placement of a collateral item, automatically provide assurance for the collateral item (e.g., by locking a connected device containing or providing assurance for the collateral item, such as a smart lock, smart container, etc.), automatically configure a set of instructions for shipping the collateral item for a carrier, forwarder, etc., automatically configure a set of instructions for transporting the collateral item for a drone, robot, etc.
In an embodiment, a system is provided for facilitating the redemption of collateral. The system may include: a set of data collection and monitoring services for monitoring at least one condition of a loan agreement; a set of intelligent contract services for determining terms and conditions of a loan agreement, the terms and conditions including redemption-stopping terms and conditions for at least one article providing collateral for securing a repayment obligation for the loan agreement; wherein the set of intelligent contract services automatically initiates a redemption process for the collateral upon detection of a breach based on data collected by the data collection and monitoring service. In an embodiment, the set of smart contract services initiates a signal to at least one of a smart lock and a smart container to lock the collateral. In an embodiment, the set of smart contract services configure and initiate a listing of collateral on a common auction website. In an embodiment, the set of intelligent contract services configures and provides a transportation instruction set for the collateral. In an embodiment, the set of smart contract services configure the drone with a set of instructions to transport the collateral. In an embodiment, the set of smart contract services configure the robot with a set of instructions to transport the collateral. In an embodiment, the set of intelligent contract services initiates a process for automatically replacing a set of substitute mortgages. In an embodiment, the set of intelligent contract services initiates a message to the borrower to initiate a negotiation for redemption. In an embodiment, the negotiation is managed by a robotic process automation system that is trained based on a training set of redemption-stop negotiations. In an embodiment, the negotiation involves modifying at least one of interest rates, payment terms, and collateral for the loan transaction.
Referring to fig. 4, in an embodiment, a loan support platform 100 is provided having an internet of things (IoT) data collection service 208 (with various IoT devices and edge devices described throughout this disclosure) for monitoring at least one of a set of assets 218 and a set of collateral 102 for a loan, bond, or debt transaction. The lending support platform 100 may include a vouching and/or collateral monitoring solution 230 for monitoring the assets 218 and/or collateral 102 based on data collected by the IoT data collection service 208, such as where the vouching and/or collateral monitoring solution 230 uses various adaptive intelligent systems 158, such as a system that may use models (that may adjust, reinforce, train, etc., e.g., using artificial intelligence 156) that determine the condition or value of an item based on images, sensor data, location data, or other types of data collected by the IoT data collection service 208. Monitoring may include monitoring the location of the collateral 102 or assets 218, the behavior of the principal 210, the financial status of the principal 210, and the like. The collateral and/or collateral monitoring solution 230 may include a set of interfaces through which a user may configure parameters for monitoring, such as rules or thresholds regarding conditions, behaviors, attributes, financial value, location, etc., in order to obtain alerts regarding the collateral 102 or asset 218. For example, the user may set rules by which mortgages must be retained in a given jurisdiction, thresholds for mortgages as a percentage of the loan balance, minimum status conditions (e.g., no damage or defects), and the like. The configured parameters may be used to provide alerts to persons responsible for monitoring loan compliance and/or used or embodied in one or more intelligent contracts that may take input from the interface of the underwriting and/or collateral monitoring solution 230 to configure conditions for redemption stop, conditions for interest rate change, conditions for accelerated payment, and the like. The loan support platform 100 may have a loan management solution 248 that allows a loan manager to access information from the IoT data collection service 208 and/or the collateral and/or collateral monitoring solution 230 so that a user can manage various actions (of the types described herein, such as setting interest rates, stopping redemption, sending notifications, etc.) on a loan based on the status of the mortgage 102 or asset 218, based on events involving the entity 198, based on behavior, based on loan-related actions (e.g., payments), and other factors. The loan management solution 248 may include a set of interfaces, workflows, models (including the adaptive intelligence system 158) that are configured for a particular type of loan (of the various types described herein) and that allow a user to configure parameters, set rules, set thresholds, design workflows, configure intelligent contract services, configure blockchain services, etc., in order to facilitate automated or assisted management of the loan, e.g., to enable automated processing of loan actions by intelligent contracts in response to data collected from the IoT data collection service 208 or to enable generation of a set of recommended actions for a human user based on the data.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing ownership of a set of collateral and at least one of a set of events associated with the set of collateral. For example, a set of smart contract services 134 may transfer ownership of a collateral 102 or other asset 218 upon identifying an event such as unpaid or other default behavior, the occurrence of a redemption condition (e.g., failure to meet a contract or fail to fulfill a obligation), etc., where ownership transfers and related events are recorded in a distributed ledger by a set of blockchain services, such as a distributed ledger that provides a secure record of the property 218 or the title of the collateral 102. For example, a loan contract included in a smart contract may require that the value of the collateral 102 exceed a minimum proportion (or multiple) of the loan balance. Based on the collected data regarding collateral value (e.g., by monitoring one or more of the external markets 188 or the markets of the loan support platform 100), the intelligent contract may calculate whether the contract is satisfied and record the result on the blockchain. If the contract is not satisfied, such as where market factors indicate that the type of collateral has decreased while the loan balance is still high, the smart contract may initiate redemption, including recording ownership transfers on the distributed ledger through blockchain services. The intelligent contract may also handle events related to entity 198 (e.g., principal 210). For example, a loan obligation may require a party to maintain a debt level below a threshold or a certain rate to maintain a income level, a profit level, or the like. The monitoring system 164 or data collection system 166 may provide data used by the intelligent contract service 134 to determine compliance with contracts and to perform automatic actions, including recording redemption and ownership transfer events on a distributed ledger. In another example, the contract may relate to the behavior of principal 210 or the legal status of principal 210, such as requiring the principal not to take a particular action on property. For example, a contract may require that a principal comply with partition provisions that prohibit certain real estate uses. The IoT data collection service 208 may be used to monitor principals 210, property, or other items, to determine compliance with contracts, or to trigger alarms or automatic actions in the event of non-compliance.
Automatic redemption-stopping intelligent contract based on collateral price value lower than contract requirement
In an embodiment, a system for processing a loan with a set of computing services is provided herein. In an embodiment, the platform or system comprises: (a) A set of data collection and monitoring services for monitoring a set of items providing collateral for the loan; (b) A set of valuation services that use valuation models to set the value of collateral based on information from the data collection and monitoring services; and (c) a set of intelligent contract services for managing intelligent lending contracts, wherein the set of intelligent contract services processes output from the set of valuation services, compares the output to a loan contract specified in the intelligent contract, and automatically initiates at least one of a breach notice and a redemption-stopping action when the value of the collateral is insufficient to satisfy the contract.
In an embodiment, the set of intelligent contract services further includes services for specifying terms and conditions of an intelligent contract governing at least one of loan terms and conditions, loan-related events, and loan-related activities.
In an embodiment, the loan is of at least one of the following types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
In an embodiment, the set of terms and conditions of the loan specified and managed by the set of intelligent contract services is selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line return plan, collateral description, collateral substitutability description, party, insured person, collateral, personal guaranty, lien, term, contract, redemption condition, default condition, and default outcome.
In an embodiment, a set of collateral is selected from: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, a set of data collection and monitoring services includes the following: a set of internet of things systems for monitoring entities; a set of cameras for monitoring the entity; a set of software services for obtaining information related to an entity from an open information website; a set of mobile devices for reporting information related to an entity; a set of wearable devices for wearing by a human entity; a set of user interfaces through which entities provide information about the entities; and a set of crowdsourcing services for requesting and reporting information related to the entity.
In an embodiment, a set of valuation services includes an artificial intelligence service that iteratively refines a valuation model based on result data related to a collateral transaction.
In an embodiment, the set of valuation services also includes a set of market value data collection services that monitor and report market information related to the value of the collateral.
In an embodiment, a set of market value data collection services monitor pricing or financial data for items similar to the collateral in at least one public market.
In an embodiment, a set of similar items for valuing a collateral is constructed using a similarity clustering algorithm based on attributes of the collateral.
In an embodiment, the attributes are selected from: the type of collateral object, the age of the collateral object, the condition of the collateral object, the history of the collateral object, the storage conditions of the collateral object, and the geographic location of the collateral object.
Smart contract mortgages aggregated with other similar mortgages
In an embodiment, an intelligent contract system is provided herein for processing a loan having a set of computing services. In an embodiment, the platform or system comprises: (a) A set of data collection and monitoring services for determining a set of items that provide collateral for a set of loans and collecting information about the collateral; (b) A set of clustering services for grouping the collateral based on similarity of collateral attributes; and (c) a set of intelligent contract services for managing intelligent loan contracts, wherein the set of intelligent contract services process outputs from the set of clustering services and aggregate and link subsets of similar mortgages to provide mortgages for a set of loans. The clustering circuit 104 may be part of the adaptive intelligence system 158 and may use any of a variety of clustering models and techniques, such as models and techniques based on attributes of the entities 198 collected by the monitoring system 164 or the data collection system 166 and/or stored in the data storage system 186.
In an embodiment, the loan of the aggregate mortgage may be any of the following: automobile loans, inventory loans, capital equipment loans, performance bonds, fixed capital improvement loans, construction loans, accounts receivable warranty loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, title loans, house loans, risk debt loans, intellectual property loans, contractual claim loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
In an embodiment, a set of collateral is selected from: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, clustering of the collateral is performed by a clustering algorithm that groups the collateral based on attributes collected by the data collection and monitoring service.
In an embodiment, the attributes for the grouping are selected from the following: the type of the item, the category of the item, the description of the item, the product feature set of the item, the model of the item, the brand of the item, the manufacturer of the item, the state of the item, the environment of the item, the condition of the item, the value of the item, the storage location of the item, the geographic location of the item, the age of the item, the maintenance history of the item, the usage history of the item, the accident history of the item, the failure history of the item, the ownership history of the item, the price of the item type, the value of the item type, the evaluation of the item, and the valuation of the item.
In an embodiment, the set of smart contract services allocate a set of similar items as collateral in a set of loans between different parties, thereby dispersing the risk of the loans.
In an embodiment, the platform or system may also include a set of valuation services that use valuation models to set the value of a collateral based on information from the data collection and monitoring services, wherein the set of smart contract services automatically rebalance the collateral into a set of loans based on the value of the collateral.
In an embodiment, a group of similar mortgages for a group of loans is aggregated in real-time based on similarity of the state of the group of items.
In an embodiment, the similarity of states is based on items transported during a defined time period.
In an embodiment, a set of collateral is selected from: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, the set of intelligent contract services further includes services for specifying terms and conditions of an intelligent contract governing at least one of loan terms and conditions, loan-related events, and loan-related activities.
In an embodiment, the set of terms and conditions of the loan specified and managed by the set of intelligent contract services is selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line return plan, collateral description, collateral substitutability description, party, insured person, collateral, personal guaranty, lien, term, contract, redemption condition, default condition, and default outcome.
Intelligent contracts for managing property liens in blockchains and distributed ledgers based on loan status of properties as collateral
In an embodiment, an intelligent contract system is provided herein for managing the lien of a mortgage for a loan having a set of computing services. In an embodiment, the platform or system comprises: (a) A set of data collection and monitoring services for monitoring the status of the loan and a set of related mortgages for the loan; (b) A set of blockchain services for maintaining a security history ledger for events related to the loan, the blockchain services having access control features to manage access rights for a set of parties involved in the loan; and (c) a set of intelligent contract services for managing intelligent loan contracts, wherein the set of intelligent contract services process information from the set of data collection and monitoring services and automatically initiate and terminate lien on at least one item in the set of collateral based on the status of the loan, wherein actions regarding lien are stored in a distributed ledger of the loan.
In an embodiment, a set of data collection and monitoring services includes the following: a set of internet of things systems for monitoring entities; a set of cameras for monitoring the entity; a set of software services for obtaining information related to an entity from an open information website; a set of mobile devices for reporting information related to an entity; a set of wearable devices for wearing by a human entity; a set of user interfaces through which entities provide information about the entities; and a set of crowdsourcing services for requesting and reporting information related to the entity.
In an embodiment, the loan is of at least one of the following types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
In an embodiment, the status of the loan is determined based on the status of at least one entity associated with the loan and the fulfillment status of the conditions of the loan.
In an embodiment, fulfillment of the condition is related to at least one of payment fulfillment and satisfaction of the contract.
In an embodiment, a set of data collection and monitoring services monitor entities to determine compliance with a contract.
In an embodiment, the entity is a principal and a set of data collection and monitoring services monitor the financial status of the entity as the principal of the loan.
In an embodiment, the financial condition is determined based on a set of attributes of the entity from among: a public valuation of an entity, a set of properties owned by the entity as indicated by a public record, a valuation of a set of properties owned by the entity, a bankruptcy condition of the entity, a redemption-out status of the entity, a contract breach status of the entity, a violation status of the entity, a criminal status of the entity, an export regulation status of the entity, a contraband status of the entity, a duty status of the entity, a tax status of the entity, a credit report of the entity, a credit rating of the entity, a website rating of the entity, a set of customer reviews of products of the entity, a social network rating of the entity, a set of credentials of the entity, a set of referrals of the entity, a set of proofs of the entity, a set of behaviors of the entity, a location of the entity, and a geographic location of the entity.
In an embodiment, the principal is selected from: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, and accountants.
In an embodiment, the entity is a set of mortgages for a loan, and the set of data collection and monitoring services monitor the status of the mortgages.
In an embodiment, a set of collateral is selected from: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In embodiments, the platform or system may also include a set of valuation services that use valuation models to set the value of a set of collateral based on information from the data collection and monitoring services.
In an embodiment, a set of collateral is selected from: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, a set of valuation services includes an artificial intelligence service that iteratively refines a valuation model based on result data related to a collateral transaction.
In an embodiment, the set of valuation services also includes a set of market value data collection services that monitor and report market information related to the value of the collateral.
In an embodiment, a set of market value data collection services monitor pricing or financial data for items similar to the collateral in at least one public market.
In an embodiment, a set of similar items for valuing a collateral is constructed using a similarity clustering algorithm based on attributes of the collateral.
In an embodiment, the attributes are selected from: the type of collateral object, the age of the collateral object, the condition of the collateral object, the history of the collateral object, the storage conditions of the collateral object, and the geographic location of the collateral object.
In an embodiment, the terms and conditions of the loan specified and managed by the set of intelligent contract services are selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line return plan, collateral description, collateral substitutability description, party, insured person, collateral, personal guaranty, lien, term, contract, redemption condition, default condition, and default outcome.
In an embodiment, the set of intelligent contract services further includes services for specifying terms and conditions of an intelligent contract governing at least one of loan terms and conditions, loan-related events, and loan-related activities.
In an embodiment, the loan is of at least one of the following types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
In an embodiment, the set of terms and conditions of the loan specified and managed by the set of intelligent contract services is selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line return plan, collateral description, collateral substitutability description, party, insured person, collateral, personal guaranty, lien, term, contract, redemption condition, default condition, and default outcome.
Intelligent contract/blockchain that allows for the replacement of a mortgage based on verification information (ownership, status, value) about the mortgage
In an embodiment, an intelligent contract system is provided herein for managing mortgages of a loan with a set of computing services. In an embodiment, the platform or system comprises: (a) A set of data collection and monitoring services for monitoring the status of the loan and a set of related mortgages for the loan; (b) A set of blockchain services for maintaining a security history ledger for events related to the loan, the blockchain services having access control features to manage access rights for a set of parties involved in the loan; and (c) a set of intelligent contract services for managing intelligent loan contracts, wherein the set of intelligent contract services processes information from the set of data collection and monitoring services and automatically initiates at least one of replacement, removal, or addition of a set of items to a set of loan collateral based on the results of the processing, wherein alterations to the set of collateral are recorded in a distributed ledger of the loan.
In an embodiment, a set of data collection and monitoring services includes the following: a set of internet of things systems for monitoring entities; a set of cameras for monitoring the entity; a set of software services for obtaining information related to an entity from an open information website; a set of mobile devices for reporting information related to an entity; a set of wearable devices for wearing by a human entity; a set of user interfaces through which entities provide information about the entities; and a set of crowdsourcing services for requesting and reporting information related to the entity.
In an embodiment, the loan is of at least one of the following types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
In an embodiment, the status of the loan is determined based on the status of at least one entity associated with the loan and the fulfillment status of the conditions of the loan.
In an embodiment, fulfillment of the condition is related to at least one of payment fulfillment and satisfaction of the contract.
In an embodiment, a set of data collection and monitoring services monitor entities to determine compliance with a contract.
In an embodiment, the entity is a principal and a set of data collection and monitoring services monitor the financial status of the entity as the principal of the loan.
In an embodiment, the financial condition is determined based on a set of attributes of the entity from among: a public valuation of an entity, a set of properties owned by the entity as indicated by a public record, a valuation of a set of properties owned by the entity, a bankruptcy condition of the entity, a redemption-out status of the entity, a contract breach status of the entity, a violation status of the entity, a criminal status of the entity, an export regulation status of the entity, a contraband status of the entity, a duty status of the entity, a tax status of the entity, a credit report of the entity, a credit rating of the entity, a website rating of the entity, a set of customer reviews of products of the entity, a social network rating of the entity, a set of credentials of the entity, a set of referrals of the entity, a set of proofs of the entity, a set of behaviors of the entity, a location of the entity, and a geographic location of the entity.
In an embodiment, the principal is selected from: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, and accountants.
In an embodiment, the entity is a set of mortgages for a loan, and the set of data collection and monitoring services monitor the status of the mortgages.
In an embodiment, a set of collateral is selected from: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, merchandise, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In embodiments, the platform or system may also include a set of valuation services that use valuation models to set the value of a set of collateral based on information from the data collection and monitoring services.
In an embodiment, a smart contract initiates a mortgage substitution, removal, or addition to a set of mortgages of a loan to maintain the value of the mortgage within a specified range.
In an embodiment, a set of collateral is selected from: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, a set of valuation services includes an artificial intelligence service that iteratively refines a valuation model based on result data related to a collateral transaction.
In an embodiment, the set of valuation services also includes a set of market value data collection services that monitor and report market information related to the value of the collateral.
In an embodiment, a set of market value data collection services monitor pricing or financial data for items similar to the collateral in at least one public market.
In an embodiment, a set of similar items for evaluating a collateral is constructed using a similarity clustering algorithm based on attributes of the collateral.
In an embodiment, the attribute is selected from: the type of collateral object, the age of the collateral object, the condition of the collateral object, the history of the collateral object, the storage conditions of the collateral object, and the geographic location of the collateral object.
In an embodiment, the terms and conditions of the loan specified and managed by the set of intelligent contract services are selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line return plan, collateral description, collateral substitutability description, party, insured person, collateral, personal guaranty, lien, term, contract, redemption condition, default condition, and default outcome.
In an embodiment, the set of intelligent contract services further includes services for specifying terms and conditions of an intelligent contract governing at least one of loan terms and conditions, loan-related events, and loan-related activities.
In an embodiment, the set of terms and conditions of the loan specified and managed by the set of intelligent contract services is selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line return plan, collateral description, collateral substitutability description, party, insured person, collateral, personal guaranty, lien, term, contract, redemption condition, default condition, and default outcome.
In an embodiment, a lending platform is provided having an intelligent contract that automatically adjusts the interest rate of a loan based on at least one of regulatory factors and market factors of a particular jurisdiction.
Referring to fig. 55, in an embodiment, a lending platform is provided having a crowd sourcing system for obtaining information regarding at least one of a status of a set of mortgages of a loan and a status of an entity associated with a guarantee of the loan. Thus, in an embodiment, a platform is provided herein having systems, methods, processes, services, components, and other elements for enabling a platform 500 for blockchain and intelligent contracts for crowdsourcing loan-related information. As with other embodiments described above in connection with purchasing innovations, product requirements, etc., the blockchain 136 (e.g., optionally embodying a distributed ledger) may be configured with a set of intelligent contracts to manage rewards 512 for submitting loan information 518, such as evidence of property ownership, proof of property, information about collateral ownership, information about collateral status, information about collateral location, information about party identity, information about party reputation, information about party activity or behavior, information about party business practices, information about contract performance, information about accounts receivable, information about accounts payable, information about collateral value, and many other types of information. In an embodiment, blockchain 136 (e.g., optionally distributed in a distributed ledger) may be used to configure a request for information 518 and terms and conditions 510 related to the information, such as a reward 512 to submit information 518, a set of terms and conditions 510 related to the use of information 518, and various parameters 508, such as timing parameters, the nature of the information required (e.g., independently verified information, such as title records, video clips, photographs, witness statements, etc.), and other parameters 508.
In embodiments, the information may relate to fact collection or data collection of various applications and solutions that may be supported by the loan support platform 100, including the crowdsourcing platform 500, including for underwriting solutions 103 (e.g., various types of loans, guarantees, and other items), risk management solutions 122 (e.g., managing various risks described in this disclosure, such as risks associated with personal loans, batch loans, and the like), lending applications 144 (e.g., evidence of ownership and/or value of collateral, evidence of stated authenticity, evidence of fulfillment or adherence to a loan contract, and the like), regulatory and/or compliance solutions 142 (e.g., adherence to various types of regulations regarding the processes, behaviors, or activities performed by the manageable entities 198 and entities 198 or thereof), and fraud prevention applications 138 (e.g., for detecting fraud, inappropriate statements, defamation, fluent statements, and the like). For example, a building's capital loan may include contracts for property purposes, such as allowing certain uses and disallowing other uses, allowing a given right to occupy, etc., and the crowdsourcing platform 500 may request and consider compliance information about the building (e.g., requesting people to confirm that the building is actually being used for the intended use allowed by regional regulations). The crowdsourcing information may be combined with information from the monitoring system 164. In an embodiment, for example, the adaptive intelligence system 158 may continuously monitor the property, collateral 102, or other entity 198 and upon identifying (e.g., by an AI system such as a neural network classifier) a suspicious event (e.g., an event that may indicate a violation of a loan obligation), the adaptive intelligence system 158 may provide a signal to the crowd-sourcing system 520 indicating that a crowd-sourcing process should be initiated to verify whether a violation exists. In an embodiment, this may include using a machine classifier to classify contract-related conditions, provide classification, and identify data about the entity, and automatically configure a crowdsourcing request based on a model or a set of rules, etc., that identifies requested information content related to the entity 198 and provided rewards 512. In embodiments, the reward 512 may be configured by experts, the reward 512 may be based on a set of rules (e.g., terms and conditions for a loan parameter, a contract in a smart contract (e.g., loan value, remaining term, etc.), the value of the collateral 102, etc.), and/or the reward 512 may be set by the Robotic Process Automation (RPA) system 154, e.g., the RPA system 154 is trained based on a set of expert activity training sets that set the reward in various cases that collectively show which rewards are appropriate in a given case. The reward configured Robotic Process Automation (RPA) 154 may be continuously improved by artificial intelligence 156, for example, based on continuous feedback of crowd-sourced outcomes, such as successful outcomes (e.g., verifying contract violations, generating outcomes, etc.).
Information collection may include information collection about an entity 198 and its identity, assertions, actions, or behaviors, among many other factors, and may be accomplished by crowd sourcing in platform 500 or by data collection system 166 and monitoring system 164, optionally through automation by Robotic Process Automation (RPA) 154 and adaptive intelligence (e.g., using artificial intelligence system 156).
Referring to fig. 6, the various support capabilities of the loan support platform 100 described in this disclosure may be used to configure a platform operated market crowdsourcing system 500, for example in a crowdsourcing control panel interface 618 or other user interface of the operator of the platform operated market crowdsourcing system 500. The operator may take a series of steps to execute or employ an algorithm using the user interface or control panel 514 to create the crowdsourcing request for information 518 described in connection with fig. 5. In an embodiment, one or more steps of an algorithm for creating the reward 512 within the control panel 514 may include: in step 602, potential rewards 512 are identified, such as which information 518 may have value in a given situation (e.g., as may be indicated by a stakeholder or representative of the entity (e.g., an individual or business such as a lawyer, an agent, an investigator, a party, an auditor, a spy, an insurer, an inspector, etc.) through various communication channels).
The control panel 514 may be configured with a crowdsourcing control panel interface 618, e.g., with elements (including application programming elements, data integration elements, messaging elements, etc.) that allow management of crowdsourcing requests in the platform marketplace 500 and/or one or more external marketplaces 188. At control panel 514, in step 604, a user may configure one or more parameters 508 or conditions 510, such as conditions (of the type described herein) that include or describe a crowdsourcing request, such as by defining a set of conditions 510 that trigger a reward 512 and determining an assignment of reward 512 to a set of information submitters 518. The user interface of the control panel 514 (which may include or be associated with the crowdsourcing control panel interface 620) may include a set of drop-down menus, forms, etc., with default, templated, recommended, or preconfigured conditions, parameters 508, conditions 510, etc. (e.g., conditions suitable for various types of crowdsourcing requests). Once the conditions and other parameters of the request are configured, the intelligent contract and blockchain 136 may be used to maintain (e.g., via a ledger) the required data to provision, distribute, and exchange data related to the request and submit information 518 in step 608. The smart contracts and blockchains 136 may be used to identify information 518, transaction information (e.g., for information exchange), technical information, other evidence data of the type described in connection with fig. 5, including any data, testimonials, photographs, video content, or other information that may be relevant to submitting the information 518 or the conditions 510 to obtain the reward 512. In step 610, the smart contract may be used to embody the conditions 510 that have been configured in step 604, operate on the blockchain 136 that has been created in step 608, and operate on other data, such as data (e.g., data related to the submission information 518) indicating facts, conditions, events, etc. in the platform operated marketplace 500 and/or the external marketplace 188 or other information sites or resources (e.g., sites indicating the results of legal cases or partial cases, sites reporting surveys, etc.). In step 610, the smart contract may be used to apply one or more rules to evidence data 518, data indicating that parameters 508 or conditions 510 are satisfied, and data such as identity data, transaction data, timing data, and other data, perform one or more conditional operations, and the like. Upon completing the configuration of one or more blockchains 136 and one or more intelligent contracts, in step 612, blockchains 136 and intelligent contracts may be deployed in a marketplace 500, external marketplace 188, or other site or environment in which the platform operates, such as for interaction by one or more submitters or other users who may sign intelligent contracts in a crowd-sourced control panel interface 620 (e.g., a website, an application, etc.) or the like, such as by submitting information 518 and requesting rewards 512, at which time platform 500 (e.g., using adaptive intelligence system 158 or other capabilities) may correlate data, such as the identity data of one or more parties submitting data 518, signing intelligent contracts on blockchains 136, or otherwise on platform 500. In step 614, once the smart contract is executed, the platform 500 may monitor the marketplace 500 and/or one or more external marketplaces 188 or other sites operated by the platform, through a layer of the monitoring system 164 or the like, for submission data 518, event data 176, or other data that may satisfy or indicate the satisfaction of one or more conditions 510 or the application of one or more rules that trigger the smart contract, for example to trigger the reward 512.
In step 616, when condition 510 is satisfied, the smart contract may be settled, executed, or the like, to update or otherwise operate on blockchain 136, such as by transferring consideration (e.g., via a payment system) and transferring access to information 518. Thus, through the above steps, an operator of the market 500 operated by the platform may discover, configure, deploy, and have executed a set of intelligent contracts that crowd-source loan-related information (e.g., information about the value or condition of the collateral 102, contractual compliance, fraud or false statements, etc.) and that are cryptographically protected and transmitted from the information-collecting parties to the respective parties seeking the information over the blockchain 136. In an embodiment, layers of the adaptive intelligence system 158 may be used to monitor the steps of the above-described algorithm, and one or more artificial intelligence systems may be used to automatically perform the entire process, one or more sub-steps, or sub-algorithms, such as through Robotic Process Automation (RPA) 154. This may occur as described above, for example, by having the artificial intelligence system 156 learn a training data set obtained by observation, such as monitoring human users' software interactions as they perform the steps described above. After training, the layers of the adaptive intelligence system 158 may thus enable the loan support platform 100 to provide a fully automated platform for crowd sourcing loan information.
Crowd-sourcing system for verifying loan mortgage quality, property, or other conditions
In an embodiment, a crowdsourcing system for verifying the condition of a mortgage 102 or asset 218 of a loan is provided herein. In an embodiment, the platform or system comprises: (a) A set of crowdsourcing services through which crowdsourcing requests are communicated to a set of information providers and through which responses to the requests are collected and processed to provide rewards to at least one successful information provider; (b) A set of interfaces to a crowdsourcing service that enable configuration of parameters of the request, wherein the request and parameters are used to obtain information relating to a condition of a set of mortgages of the loan; and (c) a set of publishing services for publishing crowdsourcing requests.
In an embodiment, rewards are managed by a smart contract that processes responses to crowdsourcing requests and automatically assigns rewards to information that satisfies a set of parameters configured for crowdsourcing requests.
In an embodiment, the loan is of at least one of the following types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
In an embodiment, a set of collateral is selected from: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, the condition of the collateral 102 or asset 218 includes a condition attribute selected from a group consisting of: the quality of the mortgage, the condition of the mortgage, the property status of the mortgage, the occupation status of the mortgage, the lien status of the mortgage, the brand new status or use status of the item, the type of the item, the category of the item, the description of the item, the product feature set of the item, the model of the item, the brand of the item, the manufacturer of the item, the condition of the item, the environment of the item, the status of the item, the value of the item, the storage location of the item, the geographic location of the item, the age of the item, the maintenance history of the item, the use history of the item, the accident history of the item, the failure history of the item, the ownership history of the item, the price of the type of the item, the evaluation of the item, and the valuation of the item.
In an embodiment, the platform or system may further include a set of blockchain services that record information and parameters identifying the request, a response to the crowdsourcing request, and an award in a distributed ledger of the crowdsourcing request.
In an embodiment, the interface is a graphical user interface for enabling a workflow through which a human user enters parameters to establish a crowdsourcing request.
In an embodiment, the parameters include the type of information requested, the reward, and the conditions under which the reward is received.
In an embodiment, the parameter is a reward, and the reward is selected from: a physical reward, a token, a ticket, a contract right, a cryptocurrency, a set of reward points, a currency, a product or service discount, and an access right.
In an embodiment, the platform or system may also include a set of intelligent contract services 134 that manage intelligent lending contracts, where the intelligent contract services 134 process information from the set of crowd-sourcing services and automatically take actions related to the loan.
In an embodiment, the action is at least one of a redemption action, a lien management action, an interest rate setting action, a default origination action, a collateral replacement, and a claim for loan.
In an embodiment, the platform or system may also include a Robotic Process Automation (RPA) system 154 that trains based on a training set of human user interactions with the interface of the set of crowdsourcing services to configure crowdsourcing requests based on a set of attributes of the loan. In an embodiment, the attributes of the loan are obtained from a set of intelligent contract services that manage the loan. In an embodiment, a robotic process automation system is used to iteratively train and improve based on a set of results from a set of crowdsourcing requests. In an embodiment, training includes training the robotic process automation system to set the reward. In an embodiment, training includes training the robotic process automation system to determine a set of domains to which requests are to be issued. In an embodiment, training includes training the robotic process automation system to configure the requested content.
Crowdsourcing system for verifying personal loan warranty quality
In an embodiment, a crowdsourcing system 520 is provided herein for verifying the condition of a mortgage 102 or asset 218 of a loan. In an embodiment, the platform or system comprises: (a) A set of crowdsourcing services through which crowdsourcing requests are communicated to a set of information providers and through which responses to the requests are collected and processed to provide rewards to at least one successful information provider; (b) A set of crowdsourcing service interfaces capable of configuring parameters of the request, wherein the request and parameters are used to obtain information relating to a condition of the loan guarantor; (c) a set of publishing services for publishing crowdsourcing requests.
In an embodiment, the set of crowdsourcing systems 520 obtains information regarding the financial status of an entity that is a loan guarantor.
In an embodiment, the financial condition is based at least in part on entity-related information selected from: a public valuation of an entity, a set of properties owned by the entity as indicated by a public record, a valuation of a set of properties owned by the entity, a bankruptcy status of the entity, a redemption-out status of the entity, a contract breach status of the entity, a violation status of the entity, a criminal status of the entity, an export regulation status of the entity, a contraband status of the entity, a duty status of the entity, a tax status of the entity, a credit report of the entity, a credit rating of the entity, a website rating of the entity, a set of customer reviews of products of the entity, a social network rating of the entity, a set of credentials of the entity, a set of referrals of the entity, a set of proofs of the entity, a set of behaviors of the entity, a location of the entity, and a geographic location of the entity.
In an embodiment, rewards are managed by a smart contract that processes responses to crowdsourcing requests and automatically assigns rewards to information that satisfies a set of parameters configured for crowdsourcing requests.
In an embodiment, the loan is of at least one of the following types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
In an embodiment, the platform or system may also include an interface for a crowdsourcing service. In an embodiment, a request is made for information regarding the status of a set of collateral for the loan, where the set of collateral is selected from the following: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, the condition of the mortgage includes a condition attribute from the following set of condition attributes: the quality of the mortgage, the condition of the mortgage, the property status of the mortgage, the occupancy status of the mortgage, the lien status of the mortgage, the brand new or use status of the item, the type of the item, the category of the item, the description of the item, the product feature set of the item, the model of the item, the brand of the item, the manufacturer of the item, the condition of the item, the value of the item, the storage location of the item, the geographic location of the item, the age of the item, the maintenance history of the item, the use history of the item, the accident history of the item, the failure history of the item, the ownership history of the item, the price of the type of the item, the evaluation of the item, and the valuation of the item.
In an embodiment, the platform or system may further include a set of blockchain services that record information and parameters identifying the request, a response to the crowdsourcing request, and an award in a distributed ledger of the crowdsourcing request.
In an embodiment, the interface is a graphical user interface for enabling a workflow through which a human user enters parameters to establish a crowdsourcing request.
In an embodiment, the parameters include the type of information requested, the reward, and the conditions under which the reward is received.
In an embodiment, the parameter is a reward, and the reward is selected from: a physical reward, a token, a ticket, a contract right, a cryptocurrency, a set of reward points, a currency, a product or service discount, and an access right.
In an embodiment, the platform or system may further include a set of intelligent contract services that manage intelligent loan contracts, wherein the intelligent contract services process information from the set of crowd-sourced services and automatically take loan-related actions.
In an embodiment, the action is at least one of a redemption action, a lien management action, an interest rate setting action, a default origination action, a collateral replacement, and a claim for loan.
In an embodiment, the platform or system may further include a robotic process automation system that trains based on a training set of human user interactions with the set of crowdsourcing service's interfaces to configure crowdsourcing requests based on a set of attributes of the loan.
In an embodiment, the attributes of the loan are obtained from a set of intelligent contract services that manage the loan.
In an embodiment, a robotic process automation system is used to iteratively train and improve based on a set of results from a set of crowdsourcing requests.
In embodiments, training includes training the robotic process automation system to set rewards, determine a set of domains to which requests will be issued, or configure the content of requests.
Referring to fig. 7, in an embodiment, a lending platform is provided having an intelligent contract service 134 that automatically adjusts the interest rate of a loan based on information collected through at least one of an internet of things system, a crowd sourcing system, a set of social network analysis services, and a set of data collection and monitoring services. The loan support platform 100 may include an interest rate automation solution 224 that may include a set of interfaces, workflows and models (which may include, use or be enabled by various adaptive intelligent systems 158) and other components for automating the setting of interest rates based on a set of conditions that may include the terms and conditions of an intelligent contract, market conditions (of the platform market and/or the external market 188), conditions monitored by the monitoring system 164 and the data collection system 166, etc. (e.g., conditions of the entity 198 including, but not limited to, conditions of the principal 210, collateral 102, assets 218, etc.). For example, the user of the interest rate automation solution 224 may set (e.g., in a user interface) rules, thresholds, model parameters, etc. that determine or recommend the interest rate of the loan based on the above, such as based on the interest rate available to the borrower from the secondary borrower, the borrower's risk factors (including the risk predicted based on one or more predictive models using the artificial intelligence 156), or the system may automatically recommend or set such rules, thresholds, parameters, etc. (optionally recommended or set by learning a training set based on results over a period of time). The interest rate may be determined based on market factors (e.g., competitive interest rates offered by other borrowers). Interest rates may be calculated for new loans, modifications to existing loans, re-financing, redemption situations (e.g., changing from a guaranteed loan interest rate to an unsecured loan interest rate), and the like.
In an embodiment, an intelligent contract system for modifying a loan with a set of computing services is provided herein. In an embodiment, the platform or system comprises: (a) A set of data collection and monitoring services for monitoring a set of entities involved in the loan; (b) A set of intelligent contract services for managing intelligent loan contracts, wherein the set of intelligent contract services process information from the set of data collection and monitoring services and automatically initiate a change in loan rates based on the information.
In an embodiment, the change in interest rate is based on a condition of a set of collateral of the loan monitored by a set of data collection and monitoring services.
In an embodiment, the change in interest rate is based on attributes of the parties monitored by a set of data collection and monitoring services.
In an embodiment, the set of intelligent contract services further includes services for specifying terms and conditions of an intelligent contract governing at least one of loan terms and conditions, loan-related events, and loan-related activities.
In an embodiment, the loan is of at least one of the following types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
In an embodiment, the set of terms and conditions of the loan specified and managed by the set of intelligent contract services is selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line return plan, collateral description, collateral substitutability description, party, insured person, collateral, personal guaranty, lien, term, contract, redemption condition, default condition, and default outcome.
In an embodiment, a set of data collection and monitoring services includes the following: a set of internet of things systems for monitoring entities; a set of cameras for monitoring the entity; a set of software services for obtaining information related to an entity from an open information website; a set of mobile devices for reporting information related to an entity; a set of wearable devices for wearing by a human entity; a set of user interfaces through which entities provide information about the entities; and a set of crowdsourcing services for requesting and reporting information related to the entity.
In embodiments, the platform or system may also include a set of valuation services that use valuation models to set the value of a set of collateral based on information from the data collection and monitoring service.
In an embodiment, the change in interest rate is based on a valuation of a set of collateral for the loan, the set of collateral monitored by the set of data collection and monitoring services.
In an embodiment, a set of collateral is selected from: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, merchandise, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, a set of valuation services includes an artificial intelligence service that iteratively refines a valuation model based on result data related to a collateral transaction.
In an embodiment, the set of valuation services also includes a set of market value data collection services that monitor and report market information related to the value of the collateral.
In an embodiment, a set of market value data collection services monitor pricing or financial data for items similar to the collateral in at least one public market.
In an embodiment, a set of similar items for valuing a collateral is constructed using a similarity clustering algorithm based on attributes of the collateral.
In an embodiment, the attribute is selected from: the type of collateral object, the age of the collateral object, the condition of the collateral object, the history of the collateral object, the storage conditions of the collateral object, and the geographic location of the collateral object.
In an embodiment, an intelligent contract system for modifying a loan with a set of computing services is provided herein. In an embodiment, the platform or system comprises: (a) A set of data collection and monitoring services for monitoring common information sources of a set of entities involved in the loan, wherein the common information sources are selected from website information, news article information, social networking information, and crowd-sourced information; and (b) a set of intelligent contract services for managing intelligent loan contracts, wherein the set of intelligent contract services process information from the set of data collection and monitoring services and automatically initiate a change in loan interest rate based on the information.
In an embodiment, the group data collection and monitoring service monitors the financial status of the entity acting as the principal of the loan.
In an embodiment, the loan is of at least one of the following types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
In an embodiment, the financial condition is determined based on a set of attributes of the entity from among: a public valuation of an entity, a set of properties owned by the entity as indicated by a public record, a valuation of a set of properties owned by the entity, a bankruptcy condition of the entity, a redemption-out status of the entity, a contract breach status of the entity, a violation status of the entity, a criminal status of the entity, an export regulation status of the entity, a contraband status of the entity, a duty status of the entity, a tax status of the entity, a credit report of the entity, a credit rating of the entity, a website rating of the entity, a set of customer reviews of products of the entity, a social network rating of the entity, a set of credentials of the entity, a set of referrals of the entity, a set of proofs of the entity, a set of behaviors of the entity, a location of the entity, and a geographic location of the entity.
In an embodiment, the principal is selected from: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, and accountants.
In embodiments, the platform or system may also include an automated agent that processes events related to at least one of the value, status, and ownership of a mortgage and takes actions related to a loan to which the mortgage belongs.
In an embodiment, the loan-related action is selected from: offer loan; receiving a loan; underwriting loan; setting interest rate of the loan; a deferred payment requirement; modifying interest rate of the loan; verifying the property rights of the mortgage; recording the change of property rights; evaluating the value of the collateral; initiating a check for collateral; the loan is collected; settlement loan; setting the terms and conditions of the loan; providing a notification to be provided to the borrower; redeeming the loan asset; and modifying the terms and conditions of the loan.
In an embodiment, the set of intelligent contract services further includes services for specifying terms and conditions of an intelligent contract governing at least one of loan terms and conditions, loan-related events, and loan-related activities.
In an embodiment, the set of terms and conditions of the loan specified and managed by the set of intelligent contract services is selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line return plan, collateral description, collateral substitutability description, party, insured person, collateral, personal guaranty, lien, term, contract, redemption condition, default condition, and default outcome.
In an embodiment, the monitored entity is a set of collateral selected from: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, an intelligent contract system for modifying a loan is provided herein having a set of computing services. In an embodiment, the platform or system comprises: (a) A set of data collection and monitoring services for monitoring a set of entities involved in the loan, which in embodiments are located in a plurality of different jurisdictions; (b) A set of intelligent contract services for managing intelligent loan contracts, wherein the set of intelligent contract services process information about entities from the set of data collection and monitoring services and automatically take loan-related actions for the loan based at least in part on the location information.
In an embodiment, the loan-related action is selected from: offer loan; receiving a loan; underwriting loan; setting interest rate of the loan; a deferred payment requirement; modifying interest rate of the loan; verifying the property rights of the mortgage; recording the change of property rights; evaluating the value of the collateral; initiating a check for collateral; the loan is collected; settlement loan; setting the terms and conditions of the loan; providing a notification to be provided to the borrower; the redemption of loan assets; and modifying the terms and conditions of the loan.
In an embodiment, the intelligent contract is used to process a set of jurisdiction-specific regulatory notification requirements and provide appropriate notifications to the borrower based on the location of at least one of the borrower and the borrower, the funds provided over the loan, the repayment of the loan, and the collateral for the loan.
In an embodiment, the intelligent contract is for processing a set of jurisdiction-specific regulatory redemption-stopping requirements and providing an appropriate redemption-stopping notification to the borrower based on the jurisdiction of at least one of the borrower and the borrower, the funds provided over the loan, the repayment of the loan, and the collateral for the loan.
In an embodiment, the intelligent contract is for processing a set of jurisdiction-specific rules that set the terms and conditions of the loan, and the intelligent contract is configured based on the location of at least one of the borrowers, the funds provided over the loan, the repayment of the loan, and the collateral for the loan.
In an embodiment, the intelligent contract is used to set the interest rate of the loan so that the loan meets the maximum interest rate limit applicable to the jurisdiction.
In an embodiment, the change in interest rate is based on the condition of a set of mortgages of the loan monitored by a set of data collection and monitoring services.
In an embodiment, the change in interest rate is based on attributes of the parties monitored by a set of data collection and monitoring services.
In an embodiment, the set of intelligent contract services further includes services for specifying terms and conditions of an intelligent contract governing at least one of loan terms and conditions, loan-related events, and loan-related activities.
In an embodiment, the loan is of at least one of the following types: the system comprises an automobile loan, an inventory loan, a capital equipment loan, a performance bond, a capital improvement loan, a construction loan, an account receivable guarantee loan, an invoice financing arrangement, a warranty arrangement, a payday loan, a refund expected loan, an academic loan, a banking loan, a property loan, a housing loan, a risk debt loan, an intellectual property loan, a contractual right loan, a floating fund loan, a small business loan, an agricultural loan, a municipal bond, and a subsidy loan.
In an embodiment, the set of terms and conditions of the loan specified and managed by the set of intelligent contract services is selected from the group consisting of: principal amount of the debt, balance of the debt, fixed interest rate, variable interest rate, payment amount, payment plan, endmost big payback plan, collateral description, collateral substitutability description, party, insured person, guarantor, collateral, personal guaranty, lien, deadline, contract, redemption condition, default condition, and default consequence.
In an embodiment, a set of data collection and monitoring services includes the following: a set of internet of things systems for monitoring entities; a set of cameras for monitoring the entity; a set of software services for obtaining information related to an entity from an open information website; a set of mobile devices for reporting information related to an entity; a set of wearable devices for wearing by a human entity; a set of user interfaces through which entities provide information about the entities; and a set of crowdsourcing services for requesting and reporting information related to the entity.
In embodiments, the platform or system may also include a set of valuation services that use valuation models to set the value of a set of collateral based on information from the data collection and monitoring services.
In an embodiment, the valuation model is based on a jurisdiction of at least one of the borrower and the borrower, a funding provided over the loan, a repayment of the loan, and a jurisdiction-specific valuation model of a mortgage of the loan.
In an embodiment, at least one of the terms and conditions of the loan is based on a valuation of a set of mortgages of the loan, the set of mortgages monitored by the set of data collection and monitoring services.
In an embodiment, a set of collateral is selected from: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, a set of valuation services includes an artificial intelligence service that iteratively refines a valuation model based on result data related to a collateral transaction.
In an embodiment, the set of valuation services also includes a set of market value data collection services that monitor and report market information related to the value of the collateral.
In an embodiment, a set of market value data collection services monitor pricing or financial data for items similar to the collateral in at least one public market.
In an embodiment, a set of similar items for valuing a collateral is constructed using a similarity clustering algorithm based on attributes of the collateral.
In an embodiment, the attributes are selected from: the type of collateral object, the age of the collateral object, the condition of the collateral object, the history of the collateral object, the storage conditions of the collateral object, and the geographic location of the collateral object.
Referring to fig. 8, in an embodiment, a lending platform is provided with intelligent contracts that automatically reorganize debts based on monitored conditions. The lending support platform 100 may include a liability recomposition solution 228 that may include a set of interfaces, workflows and models (which may include, use or be enabled by various adaptive intelligent systems 158) and other components for automating the recomposition of liabilities based on a set of conditions that may include the terms and conditions of intelligent contracts, market conditions (of the platform market and/or the external market 188), conditions monitored by the monitoring system 164 and the data collection system 166, and the like (e.g., conditions of the entity 198 including, but not limited to, conditions of the principal 210, collateral 102, assets 218, and the like). For example, the user of the debt reorganization solution 228 may create, configure (e.g., using one or more templates or libraries), modify, set, or otherwise process (e.g., in a user interface of the debt reorganization solution 228) various rules, thresholds, processes, workflows, model parameters, etc., that determine or recommend a debt reorganization action for the loan based on one or more events, conditions, states, actions, etc., where the reorganization may be based on various factors, such as current market interest rate, interest rate that the borrower may obtain from a secondary borrower, risk factors for the borrower (including risk predicted by the human intelligence 156 based on one or more predictive models), the status of other debts (e.g., the borrower's new debt, the borrower's debt reimbursement, etc.), the status of the collateral 102 or 218 used to provide a guarantee or support for the loan, the status of the enterprise or enterprise's assets (e.g., the operating status of the accounts payable, etc.), and so on the like. The reorganization may include a change in interest rate, a change in a sponsor's priority, a change in collateral 102 or assets 218 used to provide support or guarantee for a debt, a change in a party, a change in a guarantor, a change in a payment plan, a change in a principal amount (e.g., including a grace or accelerated payment), etc. In an embodiment, the debt reorganization solution 228 may automatically recommend or set such rules, thresholds, actions, parameters, etc. (optionally recommended or set by learning a training set based on results over a period of time) to produce a recommended reorganization plan that may specify a series of actions required to complete the reorganization of the recommendation, which actions may be performed automatically and involve conditional execution of steps based on monitored conditions and/or intelligent contract terms, which may be created, configured, and/or accounted for by the debt reorganization plan. The repacking plan may be determined and executed based at least in part on marketing factors (e.g., competitive interest rates provided by other borrowers, value of mortgages, etc.) as well as regulatory and/or compliance factors. A repayment plan may be generated and/or executed for modification of an existing loan, refinancing, redemption situations (e.g., changing from a guaranteed loan interest rate to an unsecured loan interest rate), bankruptcy or non-liability situations, situations involving market changes (e.g., changes in current interest rate), and the like. In an embodiment, an adaptive intelligence system 158 including artificial intelligence 156 may be trained based on the results of the reformulation actions and/or by an expert based on a training set of reformulation activities to generate a set of predictions, classifications, control instructions, plans, models, etc. to automatically create, manage, and/or execute one or more aspects of a reformulation plan.
In an embodiment, an intelligent contract system for modifying a loan is provided herein having a set of computing services. In an embodiment, the platform or system comprises: (a) A set of data collection and monitoring services for monitoring a set of entities involved in the loan; (b) A set of intelligent contract services for managing intelligent loan contracts, wherein the set of intelligent contract services processes information from the set of data collection and monitoring services and automatically reorganizes debt based on the monitored conditions.
In an embodiment, the status of a set of mortgages based on the loan, the set of mortgages monitored by the set of data collection and monitoring services, is reorganized.
In an embodiment, the restructuring is performed according to a set of rules based on the loan obligation, wherein the restructuring occurs at an event determined for at least one monitoring entity associated with the obligation.
In an embodiment, the event is that the collateral for the loan fails to exceed the desired point value for the balance of the loan.
In an embodiment, the event is a violation of the loan obligation by the buyer.
In an embodiment, the reorganization is based on attributes of the parties monitored by the set of data collection and monitoring services.
In an embodiment, the set of intelligent contract services further includes services for specifying terms and conditions of an intelligent contract governing at least one of loan terms and conditions, loan-related events, and loan-related activities.
In an embodiment, the loan is of at least one of the following types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
In an embodiment, the set of terms and conditions of the loan specified and managed by the set of intelligent contract services is selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line return plan, collateral description, collateral substitutability description, party, insured person, collateral, personal guaranty, lien, term, contract, redemption condition, default condition, and default outcome.
In an embodiment, a set of data collection and monitoring services includes the following: a set of internet of things systems for monitoring entities; a set of cameras for monitoring the entity; a set of software services for obtaining information related to an entity from an open information website; a set of mobile devices for reporting information related to an entity; a set of wearable devices for wearing by a human entity; a set of user interfaces through which entities provide information about the entities; and a set of crowdsourcing services for requesting and reporting information related to the entity.
In embodiments, the platform or system may also include a set of valuation services that use valuation models to set the value of a set of collateral based on information from the data collection and monitoring services.
In an embodiment, the reorganization of the debt is based on the valuation of a set of collateral for the loan, the set of collateral monitored by the set of data collection and monitoring services.
In an embodiment, a set of collateral is selected from: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, merchandise, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, a set of valuation services includes an artificial intelligence service that iteratively refines a valuation model based on result data related to a collateral transaction.
In an embodiment, the set of valuation services also includes a set of market value data collection services that monitor and report market information related to the value of the collateral.
In an embodiment, a set of market value data collection services monitor pricing or financial data for items similar to the collateral in at least one public market.
In an embodiment, a set of similar items for valuing a collateral is constructed using a similarity clustering algorithm based on attributes of the collateral.
In an embodiment, the attributes are selected from: the type of collateral object, the age of the collateral object, the condition of the collateral object, the history of the collateral object, the storage conditions of the collateral object, and the geographic location of the collateral object.
Referring to FIG. 9, in an embodiment, a loan support platform 100 is provided having a social network analysis application 204 for monitoring social media, collecting data, and determining an analysis for verifying the reliability of a loan guarantee. The loan support platform 100 may include a collateral and/or collateral monitoring solution 230 that may include a set of interfaces, workflows and models (which may include, be enabled by, or use various adaptive intelligent systems 158) and other components for enabling the monitoring of the collateral and/or guarantee of a loan transaction based on a set of conditions that may include the terms and conditions of an intelligent contract, market conditions (of the platform market and/or the external market 188), conditions monitored by the monitoring system 164 and the data collection system 166, and the like (e.g., conditions of the entity 198 including, but not limited to, conditions of the principal 210, collateral 102, asset 218, and the like). For example, a user of the collateral and/or collateral monitoring solution 230 may set (e.g., in a user interface) rules, thresholds, model parameters, etc. that determine or recommend a monitoring plan for the loan transaction based on the borrower's risk factors, the market risk factors, and/or the collateral 102 or asset 218's risk factors (including the risk predicted based on one or more predictive models using the artificial intelligence 156), or the loan support platform 100 may automatically recommend or set such rules, thresholds, parameters, etc. (optionally by learning a training set based on results over a period of time). The collateral and/or collateral monitoring solution 230 may configure a set of social network analysis services 204 and/or other monitoring systems 164 and/or data collection systems 166 to search, parse, extract, and process data from one or more social networks, websites, etc., such as data that may contain information about the collateral 102 or assets 218 (e.g., a photograph showing the vehicle, ship, or other personal property of the party 210, a photograph of a house or other real property, a photograph or text describing the activities of the party 210 (including photographs or text indicating financial risks, physical risks, health risks, or other risks that may be related to the quality of the collateral 210 and/or the ability of the collateral to pay for the collateral and/or the borrower to pay back a loan).
Thus, in an embodiment, a social network monitoring system is provided herein for verifying loan guarantee conditions. In an embodiment, the platform or system comprises: (a) A set of social networking data collection and monitoring services whereby data is collected via a set of algorithms for monitoring social networking information about entities involved in the loan; and (b) an interface to the set of social networking services that enables configuration of parameters of the social networking data collection and monitoring service to obtain information related to the warranty terms.
In an embodiment, the set of social network data collection and monitoring services obtain information about financial status of an entity that is a loan guarantor.
In an embodiment, the financial status is based at least in part on entity-related information contained in the social network selected from: a public valuation of an entity, a set of properties owned by the entity as indicated by a public record, a valuation of a set of properties owned by the entity, a bankruptcy status of the entity, a redemption-out status of the entity, a contract breach status of the entity, a violation status of the entity, a criminal status of the entity, an export regulation status of the entity, a contraband status of the entity, a duty status of the entity, a tax status of the entity, a credit report of the entity, a credit rating of the entity, a website rating of the entity, a set of customer reviews of products of the entity, a social network rating of the entity, a set of credentials of the entity, a set of referrals of the entity, a set of proofs of the entity, a set of behaviors of the entity, a location of the entity, and a geographic location of the entity.
In an embodiment, the loan is of at least one of the following types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
In an embodiment, the platform or system may also include an interface to a social network data collection and monitoring service. In an embodiment, the data collection and monitoring service is used to obtain information about the status of a set of mortgages of the loan, wherein the set of mortgages is selected from the following: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, the condition of the mortgage includes a condition attribute from the following set of condition attributes: the quality of the mortgage, the condition of the mortgage, the property status of the mortgage, the occupancy status of the mortgage, the lien status of the mortgage, the brand new or use status of the item, the type of the item, the category of the item, the description of the item, the product feature set of the item, the model of the item, the brand of the item, the manufacturer of the item, the condition of the item, the value of the item, the storage location of the item, the geographic location of the item, the age of the item, the maintenance history of the item, the use history of the item, the accident history of the item, the failure history of the item, the ownership history of the item, the price of the type of the item, the evaluation of the item, and the valuation of the item.
In an embodiment, the interface is a graphical user interface for enabling a workflow by which a human user enters parameters to establish a social network data collection and monitoring request.
In an embodiment, the platform or system may further include a set of intelligent contract services that manage intelligent loan contracts, wherein the intelligent contract services process information from the set of social network data collection and monitoring services and automatically take loan-related actions.
In an embodiment, the action is at least one of a redemption action, a lien management action, an interest rate setting action, a default origination action, a collateral replacement, and a claim for loan.
In an embodiment, the platform or system may further include a robotic process automation system that trains based on a training set of human user interactions with interfaces of the set of social network data collection and monitoring services to configure data collection and monitoring actions based on a set of attributes of the loan.
In an embodiment, the attributes of the loan are obtained from a set of intelligent contract services that manage the loan.
In an embodiment, a robotic process automation system is used to iteratively train and improve based on a set of results from a set of social network data collection and monitoring requests.
In an embodiment, training includes training the robotic process automation system to determine a set of domains for which the social network data collection and monitoring service is applicable.
In an embodiment, training includes training the robotic process automation system to configure social network data collection and monitor the content of the search.
Still referring to fig. 9, in an embodiment, a lending platform is provided having an internet of things data collection and monitoring system for verifying the reliability of a loan guarantee. The vouching and/or collateral monitoring solution 230 may include using and configuring collection activities from a set of internet of things services 208, which may include the various IoT devices, edge computing and processing capabilities, etc., described in connection with various embodiments, such as services that monitor the various entities 198 and their environments involved in loan transactions.
In an embodiment, a monitoring system for verifying the condition of a loan guarantee is provided herein. In embodiments, a set of algorithms may be used to initiate data collection, manage data collection, etc. over an IoT device, e.g., based on the above-described conditions, including conditions related to risk factors of the borrower or borrower, market risk factors, physical risk factors, etc. For example, an IoT system may be used to capture videos or images of a house during inclement weather, such as to determine whether the house is at risk of flooding, wind damage, etc., to confirm whether the house can predict enough collateral for a house loan, credit line, or other loan transaction
In an embodiment, the platform or system comprises: (a) A set of internet of things data collection and monitoring services whereby data is collected via a set of algorithms for monitoring internet of things information collected from entities involved in the loan and internet of things information about the entities; and (b) an interface to the set of internet of things data collection and monitoring services capable of configuring parameters of the social network data collection and monitoring services to obtain information related to the warranty terms.
In an embodiment, the set of internet of things data collection and monitoring services obtain information about the financial status of an entity that is a loan guarantor.
In an embodiment, the financial status is based at least in part on entity-related information collected by the internet of things device selected from: a public valuation of an entity, a set of properties owned by the entity as indicated by a public record, a valuation of a set of properties owned by the entity, a bankruptcy status of the entity, a redemption-out status of the entity, a contract breach status of the entity, a violation status of the entity, a criminal status of the entity, an export regulation status of the entity, a contraband status of the entity, a duty status of the entity, a tax status of the entity, a credit report of the entity, a credit rating of the entity, a website rating of the entity, a set of customer reviews of products of the entity, a social network rating of the entity, a set of credentials of the entity, a set of referrals of the entity, a set of proofs of the entity, a set of behaviors of the entity, a location of the entity, and a geographic location of the entity.
In an embodiment, the loan is of at least one of the following types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
In an embodiment, the platform or system may further include a set of interfaces for internet of things data collection and monitoring services. In an embodiment, the set of social network data collection and monitoring services is used to obtain information about a set of collateral conditions for the loan, wherein the set of collateral is selected from the following: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, the condition of the mortgage includes a condition attribute from the following set of condition attributes: the quality of the mortgage, the condition of the mortgage, the property status of the mortgage, the occupancy status of the mortgage, the lien status of the mortgage, the brand new or use status of the item, the type of the item, the category of the item, the description of the item, the product feature set of the item, the model of the item, the brand of the item, the manufacturer of the item, the condition of the item, the value of the item, the storage location of the item, the geographic location of the item, the age of the item, the maintenance history of the item, the use history of the item, the accident history of the item, the failure history of the item, the ownership history of the item, the price of the type of the item, the evaluation of the item, and the valuation of the item.
In an embodiment, the interface is a graphical user interface for enabling a workflow by which a human user inputs parameters to determine monitoring actions of the internet of things data collection and monitoring service.
In an embodiment, the platform or system may further include a set of intelligent contract services that manage intelligent loan contracts, wherein the set of intelligent contract services process information from the set of internet-of-things data collection and monitoring services and automatically take loan-related actions.
In an embodiment, the action is at least one of a redemption action, a lien management action, an interest rate setting action, a default origination action, a collateral replacement, and an underwriting action.
In an embodiment, the platform or system may further include a robotic process automation system that trains based on a training set of human user interactions with interfaces of the set of internet of things data collection and monitoring services to configure data collection and monitoring actions based on a set of attributes of the loan.
In an embodiment, the attributes of the loan are obtained from a set of intelligent contract services that manage the loan.
In an embodiment, a robotic process automation system is used to iteratively train and improve based on a set of results from a set of internet of things data collection and monitoring service activities.
In an embodiment, training includes training the robotic process automation system to determine a set of domains for which the internet of things data collection and monitoring service is applicable.
In an embodiment, training includes training the robotic process automation system to configure content of the internet of things data collection and monitoring service activities.
Referring to fig. 10, in an embodiment, a lending platform is provided having a Robotic Process Automation (RPA) system 154 for negotiating a set of terms and conditions for a loan. The RPA system 154 may provide automation for one or more aspects of the negotiation solution 232 that may enable automated negotiation and/or provide recommendations or plans for negotiations related to loan transactions. The negotiation solution 232 and/or the RPA system 154 for negotiation may include a set of interfaces, workflows and models (which may include, use or be enabled by various adaptive intelligent systems 158) and other components for automating the negotiation of one or more terms and conditions of a loan transaction based on a set of conditions, etc., which may include the terms and conditions of an intelligent contract, market conditions (of the platform market and/or the external market 188), conditions monitored by the monitoring system 164 and the data collection system 166, etc. (e.g., conditions of the entity 198 including, but not limited to, conditions of the principal 210, collateral 102, asset 218, etc.). For example, a user of the negotiation solution 232 may create, configure (e.g., using one or more templates or libraries), modify, set, or otherwise process (e.g., in a user interface of the negotiation solution 232 and/or the RPA system 154) various rules, thresholds, conditional flows, workflows, model parameters, etc., that determine or recommend negotiation actions or plans for loan transactions based on one or more events, conditions, states, actions, etc., where the negotiation plans may be based on various factors, such as current market interest rate, interest rate available to a borrower from a secondary borrower, risk factors for a borrower, market risk factors, etc. (including risk predicted based on one or more predictive models using the loan intelligence 156), debt status, status of collateral 102 or assets 218 for providing insurance or support for a loan, status of an enterprise or business (e.g., operational status of accounts receivable, accounts payable status, etc.), behavioral indications of financial behavior (e.g., location of the borrower, location of the loan), and/or other behavioral indications of the loan, such as financial preferences, location, and/or the like. The negotiation may include a negotiation of: debit transaction terms and conditions, debt reorganization, redemption-stopping activities, set interest rates, changes in sponsor priority, changes in collateral 102 or assets 218 used to provide support or guarantee for a debt, changes in parties, changes in a sponsor, changes in a payment plan, changes in principal amounts (e.g., including grace or accelerated payments), and many other transactions or terms and conditions. In an embodiment, the negotiation solution 232 may automatically recommend or set rules, thresholds, actions, parameters, etc. (optionally recommended or set by learning a training set based on results over a period of time) to produce a recommended negotiation plan, which may specify a series of actions required to complete the recommended or expected negotiation results (e.g., within a range of acceptable results), which actions may be automatically performed and involve conditional execution of steps based on monitored conditions and/or intelligent contract terms that may be created, configured, and/or accounted for by the negotiation plan. The negotiation plan may be determined and executed based at least in part on marketing factors (e.g., competitive interest rates provided by other borrowers, value of mortgages, etc.) as well as regulatory and/or compliance factors. A negotiation plan may be generated and/or executed for the establishment of a new loan, the establishment of a secured and guaranteed loan, a secondary loan, a modification of an existing loan, re-financing, a redemption condition (e.g., a change from a secured loan interest rate to an unsecured loan interest rate), a bankruptcy or disbond condition, a condition involving a market change (e.g., a change in an existing interest rate), and so forth. In an embodiment, the adaptive intelligence system 158, including the artificial intelligence 156, may be trained based on the results of the negotiation actions and/or a training set of negotiation activities by an expert to generate a set of predictions, classifications, control instructions, plans, models, etc. to automatically create, manage, and/or execute one or more aspects of the negotiation plans.
In an embodiment, a robotic process automation system for negotiating loans is provided herein. In an embodiment, the platform or system comprises: (a) A set of data collection and monitoring services for collecting a training set of interactions between a set of loan transaction entities; (b) An artificial intelligence system trained based on an interactive training set to classify a set of loan negotiation actions; and (c) a robotic process automation system that trains based on the set of loan transaction interactions and the set of loan transaction results to negotiate terms and conditions of the loan on behalf of the lending party.
In an embodiment, a set of data collection and monitoring services includes the following: a set of internet of things systems for monitoring entities; a set of cameras for monitoring the entity; a set of software services for obtaining information related to an entity from a public information website; a set of mobile devices for reporting information related to an entity; a set of wearable devices for wearing by a human entity; a set of user interfaces through which entities provide information about the entities; and a set of crowdsourcing services for requesting and reporting information related to the entity.
In an embodiment, the entity is a group of parties to a loan transaction.
In an embodiment, the set of principals is selected from: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, and accountants.
In an embodiment, the artificial intelligence system comprises at least one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
In an embodiment, the robotic process automation is trained based on a set of interactions of a party with a set of user interfaces involved in a set of lending processes.
In an embodiment, after the negotiation is completed, the intelligent contract for the loan is automatically configured by a set of intelligent contract services based on the negotiation results.
In an embodiment, at least one of the result of the negotiation and the negotiation event is recorded in a distributed ledger associated with the loan.
In an embodiment, the loan is one of the following types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
In an embodiment, the artificial intelligence system comprises at least one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
In an embodiment, a robotic process automation system is provided herein for negotiating loan refinancing. In an embodiment, the platform or system comprises: (a) A set of data collection and monitoring services for collecting a training set of interactions between entities of a set of loan refinancing activities; (b) An artificial intelligence system trained based on an interactive training set to classify a set of loan refinancing actions; and (c) a robotic process automation system that trains based on a set of loan refinance interactions and a set of loan refinance results to conduct loan refinance activities on behalf of the loan party.
In an embodiment, the loan refinancing activity includes initiating a refinancing offer, initiating a refinancing request, configuring refinancing rates, configuring refinancing payment schedules, configuring refinancing balances, configuring refinancing mortgages, managing the use of refinancing revenues, removing or setting liers associated with refinancing, verifying refinancing property rights, managing inspection flows, negotiating refinancing terms and conditions, and completing refinancing.
In an embodiment, a set of data collection and monitoring services includes the following: a set of internet of things systems for monitoring entities; a set of cameras for monitoring the entity; a set of software services for obtaining information related to an entity from a public information website; a set of mobile devices for reporting information related to an entity; a set of wearable devices for wearing by a human entity; a set of user interfaces through which entities provide information about the entities; and a set of crowdsourcing services for requesting and reporting information related to the entity.
In an embodiment, the entity is a group of parties to a loan transaction.
In an embodiment, the set of principals is selected from: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, and accountants.
In an embodiment, the artificial intelligence system comprises at least one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
In an embodiment, the robotic process automation trains based on a set of interactions of a principal with a set of user interfaces involved in a set of lending processes.
In an embodiment, after completion of the refinancing process, the intelligent contracts for refinancing the loan are automatically configured by a set of intelligent contract services based on the results of the refinancing campaign.
In an embodiment, at least one of the results and events of the refinancing is recorded in a distributed ledger associated with the refinancing loan.
In an embodiment, the loan is one of the following types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
In an embodiment, the artificial intelligence system comprises at least one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
Referring to fig. 11, in an embodiment, a lending platform is provided having a robotic process automation system for loan collection. RPA system 154 may provide automation for one or more aspects of collection solution 238 that may enable automated collection of funds and/or provide suggestions or plans for collection activities associated with a debit or credit transaction. The collection solution 238 and/or RPA system 154 for collecting money may include a set of interfaces, workflows and models (which may include, use or be enabled by various adaptive intelligent systems 158) and other components for automating one or more aspects of the collection action of one or more terms and conditions of the loan transaction collection flow based on a set of conditions, etc., which may include the terms and conditions of an intelligent contract, market conditions (of the platform market and/or the external market 188), conditions monitored by the monitoring system 164 and the data collection system 166, etc. (e.g., conditions of the entity 198 including, but not limited to, conditions of the principal 210, collateral 102, asset 218, etc.). For example, a user of the payment solution 238 may create, configure (e.g., using one or more templates or libraries), modify, set, or otherwise process (e.g., in a user interface of the payment solution 238 and/or the RPA system 154) various rules, thresholds, conditional flows, workflows, model parameters, etc., that determine or recommend a payment action or plan for a loan transaction or loan monitoring solution based on one or more events, conditions, states, actions, etc., where the payment plan may be based on various factors, such as payment status, borrower status, collateral 102 or asset 218 status, borrower, loan carrier, one or more collateral carrier risk factors, market risk factors, etc. (including risk factors predicted based on one or more predictive models using artificial intelligence 156), debt status, loan status, collateral status, status for collateral or asset 102 or asset 218 providing insurance or support, enterprise or operational business operational status (e.g., payable behavior, etc.), other behavioral indications such as financial behavior (e.g., monetary disposition, location, return behavior, etc.), financial behavior (e.g., financial institution preference, etc.), and other communication behavior indications such as a financial institution preference of the principal, and/or fee. The collection may include communication regarding the withdrawal of loans, encouraging payment, and the like. In an embodiment, the payment solution 238 may automatically recommend or set rules, thresholds, actions, parameters, etc. (optionally by learning a training set based on results over a period of time) to produce a recommended payment plan that may specify a series of actions required to complete the recommended or expected payment result (e.g., within a range of acceptable results), which actions may be automatically performed and involve conditional execution of steps based on monitored conditions and/or intelligent contract terms that may be created, configured, and/or accounted for by the payment plan. The collection plan may be determined and executed based at least in part on marketing factors (e.g., competitive interest rates offered by other borrowers, value of mortgages, etc.) as well as regulatory and/or compliance factors. Collection plans may be generated and/or executed for the establishment of new loans, secondary loans, modification of existing loans, refinancing, redemption situations (e.g., changing from a guaranteed loan interest rate to an unsecured loan interest rate), bankruptcy or non-liability situations, situations involving market changes (e.g., changes in the existing interest rate), and the like. In an embodiment, an adaptive intelligence system 158, including artificial intelligence 156, may be trained based on the results of the collection action and/or by an expert based on a training set of collection activities to generate a set of predictions, classifications, control instructions, plans, models, etc. to automatically create, manage, and/or execute one or more aspects of a collection plan.
In an embodiment, a robotic process automation system is provided herein for handling the withdrawal of loans. In an embodiment, the platform or system comprises: (a) A set of data collection and monitoring services for collecting a training set of interactions between entities for a set of loan transactions involving the withdrawal of a set of funds for a set of loans; (b) An artificial intelligence system trained based on an interactive training set to classify a set of loan payment actions; and (c) a robotic process automation system that trains to conduct a loan gathering activity on behalf of the lender based on the set of loan transaction interactions and the set of loan gathering results.
In an embodiment, the loan receipt action taken by the robotic process automation system is selected from: initiating a collection process; referral of the loan to an agent for collection; configuring a payment communication; scheduling a payment communication; configuring the content of the checkout communication; configuring a settlement loan offer; terminating the collection action; a deferred collection action; configuring an offer to replace the payment plan; initiating litigation; initiating redemption cessation; initiating a production-breaking process; re-owning the process; and setting collateral liens.
In an embodiment, the set of loan receipt results is selected from: a response to a collect contact event; loan repayment; a default by the loan borrower; the loan borrower is bankruptcy; collecting litigation results; financial benefits of a set of cash register actions; return on investment with respect to collection; and a reputation measure of the party involved in the collection.
In an embodiment, a set of data collection and monitoring services includes the following: a set of internet of things systems for monitoring entities; a set of cameras for monitoring the entity; a set of software services for obtaining information related to an entity from an open information website; a set of mobile devices for reporting information related to an entity; a set of wearable devices for wearing by a human entity; a set of user interfaces through which entities provide information about the entities; and a set of crowdsourcing services for requesting and reporting information related to the entity. In an embodiment, these entities are a group of parties to a loan transaction. In an embodiment, the set of principals is selected from: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, and accountants.
In an embodiment, the artificial intelligence system comprises at least one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
In an embodiment, the robotic process automation trains based on a set of interactions of a principal with a set of user interfaces involved in a set of lending processes.
In an embodiment, upon completion of the negotiation of the collection process, the intelligent contract for the loan is automatically configured by a set of intelligent contract services based on the negotiation results.
In an embodiment, at least one of the payment result and the payment event is recorded in a distributed ledger associated with the loan.
In an embodiment, the loan is one of the following types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
In an embodiment, the artificial intelligence system comprises at least one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
Referring to fig. 12, in an embodiment, a lending platform is provided having a robotic process automation system for consolidating a set of loans. The RPA system 154 may provide automation for one or more aspects of the merge solution 240 that may enable automatic merging and/or provide suggestions or plans for merge activities related to the loan transaction. The merge solution 240 and/or RPA system 154 for merging may include a set of interfaces, workflows and models (which may include, use or be enabled by various adaptive intelligent systems 158) and other components for implementing automation of one or more aspects of the merge action or merge flow of loan transactions based on a set of conditions, etc., which may include the terms and conditions of the intelligent contract, market conditions (of the platform market and/or the external market 188), conditions monitored by the monitoring system 164 and the data collection system 166, etc. (e.g., conditions of the entity 198 including, but not limited to, conditions of the principal 210, collateral 102 and assets 218, etc.). For example, a user of the consolidated solution 240 may create, configure (e.g., using one or more templates or libraries), modify, set, or otherwise process (e.g., in a user interface of the consolidated solution 240 and/or the RPA system 154) various rules, thresholds, conditional flows, workflows, model parameters, etc., that determine or recommend a consolidated action or plan for a loan transaction or set of loans based on one or more events, conditions, states, actions, etc., where the consolidated plan may be based on various factors such as payment status, interest rate of the set of loans, current interest rate in the platform market or external market, borrower status of a set of loans, status of collateral 102 or assets 218, borrower, risk factors of one or more collateral market holders, risk factors, etc. (including risk factors predicted by using artificial intelligence 156 based on one or more predictive models), debt status, operational status for providing a guarantee or hold for a loan, or other operational status of the loan, such as operational status of the loan, payback-on or other behavior (e.g., indications of the principal's (e.g., payback-on the payable behavior, status of the loan, status, etc.), and other indications of the loan. Consolidation may include consolidation of terms and conditions on a set of loans, selection of an appropriate loan, setting of payment terms for a consolidated loan, setting of repayment plans for existing loans, encouraging consolidated communication, and the like. In an embodiment, the merge solution 240 may automatically recommend or set rules, thresholds, actions, parameters, etc. (optionally by learning a training set based on results over a period of time) to produce a recommended merge plan that may specify a series of actions needed to complete a recommended or expected merged result (e.g., within a range of acceptable results), which actions may be automatically performed and involve conditional execution of steps based on monitored conditions and/or intelligent contract terms that may be created, configured, and/or accounted for by the merge plan. The merge plan may be determined and executed based on market factors (e.g., competitive interest rates provided by other borrowers, value of mortgages, etc.) and at least a portion of regulatory and/or compliance factors. The consolidated plan may be generated and/or executed for the establishment of a new consolidated loan, a secondary loan associated with the consolidated loan, a modification of an existing loan associated with the consolidation, a re-financing term of the consolidated loan, a redemption situation (e.g., a change from a guaranteed loan interest rate to an unsecured loan interest rate), a bankruptcy or disbursement situation, a situation involving a market change (e.g., a change in the existing interest rate), and so on. In an embodiment, an adaptive intelligence system 158 including artificial intelligence 156 may be trained based on the results of the merging actions and/or by an expert based on a training set of merging activities to generate a set of predictions, classifications, control instructions, plans, models, etc. to automatically create, manage, and/or execute one or more aspects of the merging plan.
In an embodiment, a robotic process automation system for merging a set of loans is provided herein. In an embodiment, the platform or system comprises: (a) A set of data collection and monitoring services for collecting information about a set of loans and for collecting a training set of interactions between a set of entities for loan merger transactions; (b) An artificial intelligence system trained based on an interactive training set to classify a group of loans as merging candidate loans; and (c) a robotic process automation system trained on a set of loan merger interactions to manage the merger of at least a subset of the set of loans on behalf of the merging party.
In an embodiment, a set of data collection and monitoring services includes the following: a set of internet of things systems for monitoring entities; a set of cameras for monitoring the entity; a set of software services for obtaining information related to an entity from an open information website; a set of mobile devices for reporting information related to an entity; a set of wearable devices for wearing by a human entity; a set of user interfaces through which entities provide information about the entities; and a set of crowdsourcing services for requesting and reporting information related to the entity.
In an embodiment, the set of loans classified as merge candidates is determined based on a model that processes attributes of entities involved in the set of loans, wherein the attributes are selected from the following: the identity of the party, interest rate, payment balance, payment terms, payment plan, loan type, collateral type, financial status of the party, payment status, collateral status, and collateral value.
In an embodiment, managing consolidation comprises managing at least one of: determining loans in a set of candidate loans, preparing a consolidated offer, preparing a consolidation plan, preparing communication content for the consolidated offer, scheduling for the consolidated offer, communicating about the consolidated offer, negotiating a modification to the consolidated offer, preparing a consolidation agreement, executing the consolidation agreement, modifying collateral for a set of loans, processing the consolidated application workflow, managing checks, managing assessments, setting interest rates, deferring payment requirements, setting a payment plan, and reaching a consolidation agreement. In an embodiment, the entity is a group of parties to a loan transaction. In an embodiment, the set of principals is selected from: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, and accountants.
In an embodiment, the artificial intelligence system comprises at least one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
In an embodiment, robotic process automation trains based on a set of interactions of a principal with a set of user interfaces involved in a set of merged flows. In an embodiment, after the negotiation is completed, the smart contract for the consolidated loan is automatically configured by a set of smart contract services based on the negotiation results. In an embodiment, at least one of the result of the negotiation and the negotiation event is recorded in a distributed ledger associated with the loan.
In an embodiment, the loan is one of the following types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
In an embodiment, the artificial intelligence system comprises at least one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
Referring to fig. 13, in an embodiment, a lending platform is provided having a robotic process automation system for managing warranty transactions. The RPA system 154 may provide automation for one or more aspects of a warranty solution 242 that may implement automated warranties and/or provide advice or plans for warranty activities related to debit transactions (e.g., transactions involving an accounts receivable warranty). The warranty solution 242 and/or the RPA system 154 for warranty may include a set of interfaces, workflows and models (which may include, use or be enabled by various adaptive intelligent systems 158) and other components for automating one or more aspects of the warranty action of one or more terms and conditions of a warranty transaction based on, among other things, a set of conditions that may include, for example, the terms and conditions of an intelligent contract, market conditions (of the platform market and/or the external market 188), conditions monitored by the monitoring system 164 and the data collection system 166, and the like (e.g., conditions of the entity 198 including, but not limited to, conditions of the principal 210, collateral 102 and assets 218, accounts receivable and inventory, and the like). For example, a user of the warranty solution 242 may create, configure (e.g., using one or more templates or libraries), modify, set, or otherwise process (e.g., in a user interface of the warranty 242 and/or the RPA system 154) various rules, thresholds, conditional flows, workflows, model parameters, etc., that determine or recommend a warranty action or plan for a warranty transaction or monitoring solution based on one or more events, conditions, states, actions, etc., where the warranty plan may be based on various factors, such as accounts receivable status, ongoing work status, inventory status, delivery and/or shipping status, payment status, borrower's status, collateral 102 or 218 status, borrower's, one or more insurer's risk factors, enterprise risk factors, etc. (including risk factors predicted based on one or more predictive models using the artificial intelligence 156), financial status, liability status, operational or held operational or financial operations 102 or debt's, financial accounts payor other indications of financial (e.g., payor financial) status, enterprise market risk factors, enterprise risk factors, such as indications of financial accounts payor other indications of financial behavior (e.g., financial status, accounts receivable status, accounts status, and/or other indications of the financial accounts payor financial or financial accounts, etc.). The warranty may include a warranty on the loan, communication to encourage payment, etc. In an embodiment, the warranty solution 242 may automatically recommend or set rules, thresholds, actions, parameters, etc. (optionally by learning a training set based on results over a period of time) to produce a recommended warranty plan that may specify a series of actions needed to complete a recommended or expected warranty result (e.g., within a range of acceptable results), which actions may be automatically performed and involve the conditional execution of steps based on monitoring conditions and/or intelligent contract terms that may be created, configured, and/or accounted for by the warranty plan. The warranty plan may be determined and executed based at least in part on market factors (e.g., competitive interest rates or other terms and conditions provided by other borrowers, values of mortgages, values of accounts receivable, interest rates, etc.), as well as regulatory and/or compliance factors. A warranty plan may be generated and/or executed for the set-up of a new warranty arrangement, the modification of an existing warranty arrangement, and the like. In an embodiment, the adaptive intelligence system 158, including the artificial intelligence 156, may be trained based on the results of the warranty action and/or by an expert based on a training set of warranty activities to generate a set of predictions, classifications, control instructions, plans, models, etc. to automatically create, manage, and/or execute one or more aspects of a warranty plan.
In an embodiment, a robotic process automation system for merging a set of loans is provided herein. In an embodiment, the platform or system comprises: (a) A set of data collection and monitoring services for collecting information about entities involved in a set of warranty loans and for collecting a training set of interactions between entities in a set of warranty loan transactions; (b) An artificial intelligence system trained based on an interactive training set to classify entities involved in the group of warranty loans; and (c) a robotic process automation system that trains to manage the warranty loan based on a set of warranty loan interactions.
In an embodiment, a set of data collection and monitoring services includes the following: a set of internet of things systems for monitoring entities; a set of cameras for monitoring the entity; a set of software services for obtaining information related to an entity from an open information website; a set of mobile devices for reporting information related to an entity; a set of wearable devices for wearing by a human entity; a set of user interfaces through which entities provide information about the entities; and a set of crowdsourcing services for requesting and reporting information related to the entity.
In embodiments, the artificial intelligence system uses a model that processes attributes of entities involved in the set of warranty loans, wherein the attributes are selected from the following: the warranty property, the identity of the party, the interest rate, the payment balance, the payment terms, the payment plan, the loan type, the collateral type, the financial status of the party, the payment status, the status of the collateral, and the value of the collateral.
In an embodiment, the warranty asset comprises a set of accounts receivable.
In an embodiment, managing the warranty loan comprises: managing at least one of a set of warranty assets; identifying a warranty loan in a set of candidate loans; compiling a warranty offer; compiling a warranty plan; communicating the content of the warranty offer; arranging a warranty offer; communicating a warranty offer; negotiating to modify a warranty offer; compiling a warranty protocol; executing a warranty protocol; modifying a set of mortgages of a warranty loan; processing a transfer of a set of accounts receivable; processing a warranty application workflow; managing and checking; managing an evaluation of a set of warranty assets; setting interest rate; a deferred payment requirement; setting a payment plan; and a process for achieving a warranty agreement.
In an embodiment, the entity is a group of parties to a loan transaction.
In an embodiment, the set of principals is selected from: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, and accountants.
In an embodiment, the artificial intelligence system comprises at least one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
In an embodiment, robotic process automation trains based on a set of interactions of a principal with a set of user interfaces involved in a set of warranty flows.
In an embodiment, after the negotiation is completed, the intelligent contract for the loan warranty is automatically configured by a set of intelligent contract services based on the negotiation results.
In an embodiment, at least one of the result of the negotiation and the negotiation event is recorded in a distributed ledger associated with the loan.
In an embodiment, the artificial intelligence system comprises at least one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
Referring to fig. 14, in an embodiment, a lending platform is provided having a robotic process automation system for brokering loans. For example, the loan may be a mortgage loan.
RPA system 154 may provide automation for one or more aspects of an agent solution 244 that may enable automatic agents and/or provide advice or plans for agent activities related to loan transactions, such as for brokering a set of mortgage loans, house loans, credit lines, automobile loans, construction loans, or other loans of any type described herein. The agent solution 244 and/or RPA system 154 for an agent may include a set of interfaces, workflows and models (which may include, use or be enabled by various adaptive intelligent systems 158) and other components for automating one or more aspects of the agent actions or agent flows of a loan transaction based on, among other things, a set of conditions that may include the terms and conditions of an intelligent contract, market conditions (of the platform market and/or the external market 188), conditions monitored by the monitoring system 164 and data collection system 166, and the like (e.g., conditions of the entity 198 including, but not limited to, conditions of the principal 210, collateral 102 and assets 218, and the like, as well as conditions of interest rates, availability terms, and the like). For example, a user of the proxy solution 244 may create, configure (e.g., using one or more templates or libraries), modify, set, or otherwise process (e.g., in a user interface of the proxy solution 244 and/or the RPA system 154) various rules, thresholds, conditional flows, workflows, model parameters, etc., that determine or recommend a proxy action or plan for a given one or more types of loan to proxy based on one or more events, conditions, states, actions, etc., where the proxy plan may be based on various factors, such as the interest rate of the set of loans available from various primary and secondary borrowers, allowable attributes of borrowers (e.g., based on income, wealth, location, etc.), current interest rate in platform markets or external markets, borrower status of a set of loans, status of collateral 102 or 218 or other attributes, borrowers, payers, one or more risk factors of the loan, market risk factors, etc. (including an indication of an intelligent or other financial model of the payable behavior for providing a more types of loan, such as a prediction of payable behavior, a payable status of the loan, a payable or other type of loan, such as a payable behavior (e.g., payable behavior) or payable status, payable by a principal, a payor other financial model of loan, a payor other type of loan, such as a payable behavior. The agent may include an agent regarding the terms and conditions of a set of loans, selection of an appropriate loan, setting of payment terms for a consolidated loan, setting of a repayment plan for an existing loan, encouraging communication by the agent, and the like. In an embodiment, the agent solution 244 may automatically recommend or set rules, thresholds, actions, parameters, etc. (optionally by learning a training set based on results over a period of time) to produce a recommended agent plan that may specify a series of actions required to complete a recommended or expected agent result (e.g., within a range of acceptable results), which actions may be performed automatically and involve conditional execution of steps based on monitored conditions and/or intelligent contract terms that may be created, configured, and/or accounted for by the agent plan. The broker plan may be determined and executed based at least in part on marketing factors (e.g., competitive interest rates provided by other borrowers, property values, borrower attributes, mortgage values, etc.) as well as regulatory and/or compliance factors. An agent plan may be generated and/or executed for the set-up of new loans, secondary loans, modification of existing loans, re-financing terms, circumstances relating to market changes (e.g., changes in the current interest rate or property value), and so forth. In an embodiment, an adaptive intelligence system 158 including artificial intelligence 156 may be trained based on the results of agent actions and/or by experts based on a training set of agent activities to generate a set of predictions, classifications, control instructions, plans, models, etc. to automatically create, manage, and/or execute one or more aspects of an agent plan.
In an embodiment, a robotic process automation system for automatically brokering mortgage loans is provided herein. In an embodiment, the platform or system comprises: (a) A set of data collection and monitoring services for collecting information about entities involved in a set of mortgage activities and for collecting a training set of interactions between entities in a set of mortgage transactions; (b) An artificial intelligence system trained based on an interactive training set to classify entities involved in the set of mortgages; and (c) a robotic process automation system trained to broker the mortgage based on at least one of the set of mortgage activities and the set of mortgage interactions.
In an embodiment, at least one of the set of mortgage activities and the set of mortgage interactions includes the following activities: marketing campaigns, determining a set of potential borrowers, determining properties, determining collateral, qualifying review of borrowers, property investigation, property verification, property assessment, property clearance, property valuation, income verification, demographic analysis of borrowers, determining payers, determining available interest rates, determining available payment terms and conditions, analyzing existing mortgages, analyzing and comparing existing mortgage terms and new mortgage terms, completing application workflows, filling application fields, preparing a mortgage loan agreement, completing a schedule for a mortgage loan agreement, negotiating terms and conditions for a mortgage loan with a lender, negotiating terms and conditions for a mortgage loan with a borrower, transferring property, setting liens, and reaching a mortgage agreement.
In an embodiment, a set of data collection and monitoring services includes the following: a set of internet of things systems for monitoring entities; a set of cameras for monitoring the entity; a set of software services for obtaining information related to an entity from an open information website; a set of mobile devices for reporting information related to an entity; a set of wearable devices for wearing by a human entity; a set of user interfaces through which entities provide information about the entities; and a set of crowdsourcing services for requesting and reporting information related to the entity.
In embodiments, the artificial intelligence system uses a model that processes attributes of entities involved in the set of mortgages, wherein the attributes are selected from the following: property restricted by mortgage, property for mortgage, identity of the party, interest rate, payment balance, payment terms, payment plan, mortgage type, property type, financial status of the party, payment status, property status, and property value.
In an embodiment, managing a mortgage loan includes managing at least one of the property limited by the mortgage loan, determining a candidate mortgage from a set of borrower conditions, preparing a mortgage offer, preparing communication content of the mortgage offer, scheduling the mortgage offer, communicating the mortgage offer, negotiating a modification to the mortgage offer, preparing a mortgage agreement, executing the mortgage agreement, modifying a mortgage of a set of mortgages, handing over lien rights, processing an application workflow, managing inspections, managing an assessment of a set of assets limited by the mortgage loan, setting an interest rate, deferring payment requirements, setting a payment plan, and reaching the mortgage agreement. In an embodiment, the entity is a group of parties to a loan transaction. In an embodiment, the set of principals is selected from: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, and accountants.
In an embodiment, the artificial intelligence system comprises at least one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
In an embodiment, robotic process automation trains based on a set of interactions of a principal with a set of user interfaces involved in a set of mortgage activities. In an embodiment, after the negotiation is completed, the intelligent contract for the mortgage is automatically configured by a set of intelligent contract services based on the negotiation results. In an embodiment, at least one of the result of the negotiation and the negotiation event is recorded in a distributed ledger associated with the loan. In an embodiment, the artificial intelligence system comprises at least one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
Referring to fig. 15, in an embodiment, a lending platform is provided having a crowd sourcing and automatic classification system for verifying the status of bond issuers. RPA system 154 may provide automation for one or more aspects of a bond management solution 234 that may enable automatic bond management and/or provide advice or plans for bond management activities related to bond transactions, such as for municipal bonds, corporate bonds, government bonds, or other bonds that may be supported by the property, collateral, or commitment of a bond issuer. The bond management solution 234 and/or RPA system 154 for bond management may include a set of interfaces, workflows and models (which may include, use or be enabled by various adaptive intelligent systems 158) and other components for automating one or more aspects of bond management actions or management flows for bond transactions based on, among other things, a set of conditions that may include the terms and conditions of intelligent contracts, market conditions (of the platform market and/or the external market 188), conditions monitored by the monitoring system 164 and data collection system 166, and the like (e.g., conditions of the entity 198 including, but not limited to, conditions of the principal 210, collateral 102, assets 218, and the like, as well as conditions of interest rates, available borrowers, available terms, and the like). For example, a user of the bond management solution 234 may create, configure (e.g., using one or more templates or libraries), modify, set, or otherwise process (e.g., in a user interface of the bond management solution 234 and/or the RPA system 154) various rules, thresholds, conditional flows, workflows, model parameters, etc., that determine or recommend bond management actions or plans for managing a given one or more types of a set of bonds based on one or more events, conditions, states, negotiation actions, etc., wherein the bond management plans may be based on various factors, such as the interest rate of the set of loans available from various primary and secondary borrowers or issuers, allowable attributes of issuers and buyers (e.g., based on income, wealth, location, etc.), current interest rate in a platform market or external market, issuer conditions of a set of bonds, conditions of collateral holders 102 or assets 218 or other attributes, issuers, conditions of one or more payers, risk factors, such as an indication of a financial balance (e.g., a risk) for providing a human contribution to the set of the bond management system, or other factors, such as a financial model or financial balance, a financial model, and/or financial balance. Bond management may include management of terms and conditions on a set of bonds, selection of appropriate bonds, communication to encourage transactions, and the like. In an embodiment, the bond management solution 234 may automatically recommend or set rules, thresholds, actions, parameters, etc. (optionally by learning a training set based on results over a period of time) to produce a recommended bond management plan that may specify a series of actions required to complete the recommended or expected bond management results (e.g., within a range of acceptable results), which actions may be automatically performed and involve conditional execution of steps based on monitored conditions and/or intelligent contract terms that may be created, configured, and/or specified by the bond management plan. The bond management plan may be determined and executed based at least in part on marketing factors (e.g., competitive interest rates provided by other publishers, property values, attributes of publishers, values of collateral or assets, etc.) and regulatory and/or compliance factors. A bond management plan may be generated and/or executed for the establishment of new bonds, secondary loans or deals that support bonds, modifications to existing bonds, situations involving market changes (e.g., changes in current interest rates or property value), and the like. In an embodiment, an adaptive intelligence system 158 including artificial intelligence 156 may be trained based on the results of the bond management actions and/or by an expert based on a training set of bond management activities to generate a set of predictions, classifications, control instructions, plans, models, etc. to automatically create, manage, and/or execute one or more aspects of a bond management plan.
In embodiments, a platform is provided herein that includes various services, components, modules, programs, systems, devices, algorithms, and other elements for monitoring the condition of a bond issuer. In an embodiment, the platform or system comprises: (a) A set of crowdsourcing systems 520 for collecting information about a set of entities involved in a set of bond transactions; and (b) a situation classification system having a model and a set of artificial intelligence services for classifying the situation of the set of publishers using information from the set of crowdsourcing services, wherein the model is trained using a training data set of results related to publishers.
In an embodiment, a set of entities includes entities from among a set of publishers, a set of bonds, a set of parties, and a set of assets.
In an embodiment, the set of distributors includes at least one of: municipalities, companies, contractors, government entities, non-government entities, and non-profit entities.
In an embodiment, the set of bonds comprises at least one of: municipal bonds, government bonds, treasury bonds, asset security bonds, and corporate bonds.
In an embodiment, the condition classified by the condition classification system is among a default condition, a redemption-suspension condition, a condition indicative of a breach of a contract, a financial risk condition, a behavioral risk condition, a policy risk condition, a financial health condition, a physical defect condition, a physical health condition, an entity risk condition, and an entity health condition.
In an embodiment, the set of crowdsourcing services enables a user interface through which a user can configure crowdsourcing requests for information related to the status of the set of publishers.
In an embodiment, the platform or system may further include a set of configurable data collection and monitoring services for monitoring publishers that includes at least one of a set of internet of things devices, a set of environmental condition sensors, a set of social network analysis services, and a set of algorithms for querying network domains.
In an embodiment, a set of configurable data collection and monitoring services monitor the following environments: municipal environments, enterprise environments, securities trading environments, real estate environments, commercial facilities, warehousing facilities, transportation environments, manufacturing environments, storage environments, houses, and vehicles.
In an embodiment, a set of bonds is secured by a set of assets.
In an embodiment, the set of assets includes the following assets: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, the platform or system may further comprise an automated agent for processing events relating to at least one of value, status and ownership of the asset and taking actions relating to the transaction of the debt to which said asset relates.
In an embodiment, the action is selected from: an offer debt transaction; underwriting debt transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notification requiring provisioning; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; joint debt and consolidated debt.
In an embodiment, the artificial intelligence service comprises at least one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
In an embodiment, the platform or system may further include an automated bond management system that manages actions related to bonds, wherein the automated bond management system is trained based on a training set of bond management activities.
In an embodiment, an automated bond management system trains based on a set of interactions of a party with a set of user interfaces involved in a set of bond transactions.
In an embodiment, the set of bond transaction activities includes the following activities: providing a debt transaction, providing an underwriting for a debt transaction, setting an interest rate, deferring a payment requirement, modifying an interest rate, verifying a property, managing an inspection, recording a property change, assessing a value of an asset, reclaiming a loan, completing a transaction, setting terms and conditions of a transaction, providing a notification that needs to be provided, canceling a redemption right of a set of assets, modifying terms and conditions, setting a rating of an entity, federating, and consolidating debts.
In an embodiment, the platform or system may further include a market value data collection service that monitors and reports market information related to the value of at least one of the issuer and the set of assets.
In an embodiment, the reporting is done for a set of assets comprising at least one of: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, the market value data collection service monitors pricing or financial data for items similar to the property in at least one public market.
In an embodiment, a set of similar items for valuing an asset is constructed using a similarity clustering algorithm based on attributes of the asset.
In an embodiment, the attributes are selected from the following: asset class, asset age, asset condition, asset history, asset storage, and asset geographic location.
In an embodiment, the platform or system may further include a set of smart contract services for managing smart contracts for bond transactions.
In an embodiment, the intelligent contract service sets the terms and conditions of the bond.
In an embodiment, the set of terms and conditions of the debt transaction specified and managed by the set of intelligent contract services is selected from the group consisting of: principal amount of the debt, balance of the debt, fixed interest rate, variable interest rate, payment amount, payment plan, top-end grand return plan, guaranteed asset description of the debt, asset substitutability description, party, issuer, purchaser, insured, guarantor, collateral, personal guaranty, lien, deadline, obligation, redemption condition, default condition, and outcome of the breach.
In an embodiment, a lending platform is provided having a social network monitoring system employing artificial intelligence for classifying a condition of a bond.
In embodiments, a platform is provided herein that includes various services, components, modules, programs, systems, devices, algorithms, and other elements for monitoring the condition of a bond issuer. In an embodiment, the platform or system comprises: (a) A set of social network analysis applications 204 for collecting information about a set of entities involved in a set of bond transactions; and (b) a situation classification system having a model and a set of artificial intelligence services for classifying a situation of the set of publishers based on information from a set of social network monitoring and analysis services, wherein the model is trained using a training data set of results related to publishers.
In an embodiment, a set of entities includes entities from among a set of publishers, a set of bonds, a set of parties, and a set of assets.
In an embodiment, the set of distributors includes at least one of: municipalities, companies, contractors, government entities, non-government entities, and non-profit entities.
In an embodiment, the set of bonds comprises at least one of: municipal bonds, government bonds, treasury bonds, asset security bonds, and corporate bonds.
In an embodiment, the condition classified by the condition classification system is among a default condition, a redemption-suspension condition, a condition indicative of a breach of a contract, a financial risk condition, a behavioral risk condition, a policy risk condition, a financial health condition, a physical defect condition, a physical health condition, an entity risk condition, and an entity health condition.
In an embodiment, the set of social network monitoring and analysis services enables a user interface through which a user may configure queries for information related to the set of entities.
In an embodiment, the platform or system may further include a set of data collection and monitoring services for monitoring the entity, including at least one of a set of internet of things devices, a set of environmental condition sensors, a set of crowdsourcing services, and a set of algorithms for querying the network domain.
In an embodiment, a set of data collection and monitoring services monitor the following environments: municipal environments, enterprise environments, securities trading environments, real estate environments, commercial facilities, warehousing facilities, transportation environments, manufacturing environments, storage environments, houses, and vehicles.
In an embodiment, a set of bonds is secured by a set of assets. In an embodiment, the set of assets includes the following assets: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, unexplored land, farms, crops, municipal facilities, warehouses, a group of inventory, goods, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, the platform or system may further comprise an automated agent for processing events related to at least one of value, status and ownership of the asset and taking actions related to bond transactions involving said asset.
In an embodiment, the action is selected from: an offer bond transaction; underwriting bond transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a request for a notice to offer, stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; a joint bond; and merging the bonds.
In an embodiment, the artificial intelligence service comprises at least one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
In an embodiment, the platform or system may further include an automated bond management system that manages actions related to bonds, wherein the automated bond management system is trained based on a training set of bond management activities.
In an embodiment, an automated bond management system trains based on a set of interactions of a party with a set of user interfaces involved in a set of bond transactions.
In an embodiment, the set of bond transaction activities includes the following activities: an offer bond transaction; underwriting bond transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notification that the providing is required; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; a joint bond; and merging the bonds.
In an embodiment, the platform or system may further include a market value data collection service for monitoring and reporting market information relating to the value of at least one of the issuer, the set of bonds, and the set of assets.
In an embodiment, a set of assets is reported, the set of assets including at least one of the following assets: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, the market value data collection service monitors pricing or financial data for items similar to the property in at least one public market.
In an embodiment, a set of similar items for valuing an asset is constructed using a similarity clustering algorithm based on attributes of the asset.
In an embodiment, the attributes are selected from the following: asset class, asset age, asset condition, asset history, asset storage, and asset geographic location.
In an embodiment, the platform or system may further include a set of smart contract services for managing smart contracts for bond transactions.
In an embodiment, the intelligent contract service sets the terms and conditions of the bond.
In an embodiment, the set of terms and conditions of the debt transaction specified and managed by the set of intelligent contract services is selected from the group consisting of: principal amount of the debt, balance of the debt, fixed interest rate, variable interest rate, payment amount, payment plan, end-most grand return plan, guaranteed asset description of the debt, asset substitutability description, party, issuer, purchaser, insured person, guarantor, collateral, personal guaranty, lien, deadline, contract, redemption hold condition, default condition, and result of default.
In an embodiment, a lending platform is provided having an internet of things data collection and monitoring system employing artificial intelligence for classifying conditions about bonds.
In embodiments, a platform is provided herein that includes various services, components, modules, programs, systems, devices, algorithms, and other elements for monitoring the condition of a bond issuer. In an embodiment, the platform or system comprises: (a) A set of internet of things data collection and monitoring services for collecting information about a set of entities involved in a set of bond transactions; and (b) a situation classification system having a model and a set of artificial intelligence services for classifying the situation of the set of publishers based on information from the IoT data collection service 208, wherein the model is trained using a training data set of results related to publishers.
In an embodiment, the set of entities includes entities from among a set of publishers, a set of bonds, a set of parties, and a set of assets.
In an embodiment, the set of distributors includes at least one of: municipalities, companies, contractors, government entities, non-government entities, and non-profit entities.
In an embodiment, the set of bonds comprises at least one of: municipal bonds, government bonds, treasury bonds, asset security bonds, and corporate bonds.
In an embodiment, the condition classified by the condition classification system is among a default condition, a redemption-suspension condition, a condition indicative of a breach of a contract, a financial risk condition, a behavioral risk condition, a policy risk condition, a financial health condition, a physical defect condition, a physical health condition, an entity risk condition, and an entity health condition.
In embodiments, a set of internet of things data collection and monitoring services support a user interface through which a user can configure queries for information about a set of entities.
In an embodiment, the platform or system may further include a set of configurable data collection and monitoring services for monitoring entities including at least one of a set of social network analysis services, a set of environmental condition sensors, a set of crowdsourcing services, and a set of algorithms for querying network domains.
In an embodiment, a set of configurable data collection and monitoring services monitor the following environments: municipal environments, enterprise environments, securities trading environments, real estate environments, commercial facilities, warehousing facilities, transportation environments, manufacturing environments, storage environments, houses, and vehicles.
In an embodiment, a set of bonds is secured by a set of assets.
In an embodiment, the set of assets includes the following assets: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In embodiments, the platform or system may further include an automated agent for processing events related to at least one of value, status, and ownership of the assets and taking actions related to bond transactions involving the assets.
In an embodiment, the action is selected from: an offer bond transaction; underwriting bond transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notice requiring the provision, stopping the redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; a joint bond; and merging the bonds.
In an embodiment, the artificial intelligence service comprises at least one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
In an embodiment, the platform or system may further comprise an automated bond management system that manages actions related to bonds, wherein the automated bond management system is trained based on a training set of bond management activities.
In an embodiment, an automated bond management system trains based on a set of interactions of a party with a set of user interfaces involved in a set of bond transactions.
In an embodiment, the set of bond transaction activities includes the following activities: an offer bond transaction; underwriting bond transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notification requiring provisioning; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; a joint bond; and merging the bonds.
In an embodiment, the platform or system may further include a market value data collection service for monitoring and reporting market information relating to the value of at least one of the issuer, the set of bonds, and the set of assets.
In an embodiment, a set of assets is reported, the set of assets including at least one of the following assets: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, the market value data collection service monitors pricing or financial data for items similar to the property in at least one public market.
In an embodiment, a set of similar items for valuing an asset is constructed using a similarity clustering algorithm based on attributes of the asset.
In an embodiment, the attributes are selected from the following: asset class, asset age, asset condition, asset history, asset storage, and asset geographic location.
In an embodiment, the platform or system may further include a set of smart contract services for managing smart contracts for bond transactions.
In an embodiment, the intelligent contract service sets the terms and conditions of the bond.
In an embodiment, the set of terms and conditions of the debt transaction specified and managed by the set of intelligent contract services is selected from the group consisting of: principal amount of the debt, balance of the debt, fixed interest rate, variable interest rate, payment amount, payment plan, end-most grand return plan, guaranteed asset description of the debt, asset substitutability description, party, issuer, purchaser, insured person, guarantor, collateral, personal guaranty, lien, deadline, contract, redemption hold condition, default condition, and result of default.
In embodiments, a platform is provided herein that includes various services, components, modules, programs, systems, devices, algorithms, and other elements for monitoring a condition of an entity and managing debts related to the entity. In an embodiment, the platform or system comprises: (a) A set of data collection and monitoring services for collecting information about entities involved in a set of debt transactions; (b) A situation classification system having a model and a set of artificial intelligence services for classifying a situation of a set of entities, wherein the model is trained using a training data set of results associated with the entities; and
(c) An automatic debt management system that manages debt related actions, wherein the automatic debt management system is trained based on a training set of debt management activities.
In an embodiment, the data collection and monitoring service includes at least one of a set of internet of things devices, a set of environmental condition sensors, a set of crowdsourcing services, a set of social network analysis services, and a set of algorithms for querying a network domain.
In an embodiment, a set of data collection and monitoring services monitor the following environments: municipal environments, enterprise environments, securities trading environments, real estate environments, commercial facilities, warehousing facilities, transportation environments, manufacturing environments, storage environments, houses, and vehicles.
In an embodiment, the debt transaction is of a type selected from: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
In an embodiment, the entities involved in the set of debt transactions include a set of parties and a set of assets.
In an embodiment, the set of assets includes the following assets: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, the platform or system may further comprise: a set of sensors disposed on at least one of the asset, the asset container, the asset packaging, the set of sensors for associating sensor information sensed by the set of sensors with a unique identifier of the asset; and a set of blockchain services for obtaining information from the data collection and monitoring services and the set of sensors and storing the information in the blockchain, wherein access to the blockchain is provided to parties to a debt transaction involving the asset through the secure access control interface.
In an embodiment, the set of sensors is selected from the group consisting of: image, temperature, pressure, humidity, velocity, acceleration, rotation, torque, weight, chemical, magnetic, electric, and position sensors.
In an embodiment, the platform or system may further comprise an automated agent for processing events relating to at least one of value, status and ownership of the asset and taking actions relating to the transaction of the debt to which said asset relates.
In an embodiment, the action is selected from: an offer debt transaction; underwriting debt transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notification that the providing is required; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; joint debt and consolidate debt.
In an embodiment, the artificial intelligence service comprises at least one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
In an embodiment, an automated debt management system trains based on a set of interactions of a party with a set of user interfaces involved in a set of debt transactions.
In an embodiment, the set of debt transaction activities includes the following activities: an offer debt transaction; underwriting debt transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; completing the transaction; setting terms and conditions of the transaction; providing a notification that needs to be provided; stopping redemption of a set of assets; modifying the terms and conditions; setting the rating and the joint debt of the entity; and merging the debts.
In an embodiment, the platform or system may also include a market value data collection service that monitors and reports market information related to the value of a set of assets.
In an embodiment, the set of assets includes the following assets: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, the market value data collection service monitors pricing or financial data for items similar to the property in at least one public market.
In an embodiment, a set of similar items for valuing an asset is constructed using a similarity clustering algorithm based on attributes of the asset.
In an embodiment, the attributes are selected from the following: asset class, asset age, asset condition, asset history, asset storage, and asset geographic location.
In an embodiment, the platform or system may further comprise a set of intelligent contract services for managing intelligent contracts for liability transactions.
In an embodiment, the intelligent contract service sets terms and conditions for the transaction.
In an embodiment, the set of terms and conditions of the debt transaction specified and managed by the set of intelligent contract services is selected from the following: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line payment plan, collateral description, collateral substitutability description, party, guaranty, personal guaranty, lien, deadline, contract, redemption condition, default condition, and result of default.
Referring to fig. 16, in an embodiment, a lending platform is provided having a system for altering the terms and conditions of a loan based on parameters monitored by the internet of things. The loan may be a subsidy loan. The RPA system 154 may provide automation for one or more aspects of a loan management solution 248 that enables automated loan management and/or provides advice or plans for loan management activities related to loan transactions, such as personal loans, corporate loans, subsidized loans, assisted loans, or other loans, including loans that may be secured with borrower's assets, collateral, or commitments. The loan management solution 248 and/or the RPA system 154 for loan management may include a set of interfaces, workflows and models (which may include, be implemented using, or by various adaptive intelligent systems 158), and other components for automating one or more aspects of the loan management actions or management process of a loan transaction, e.g., based on a set of conditions (which may include intelligent contract terms and conditions, market conditions (platform market and/or external market 188 conditions), conditions monitored by the monitoring system 164 and the data collection system 166, etc. (e.g., conditions of the entity 198, including but not limited to parties 210, collateral 102 and assets 218, etc., as well as interest rates, available borrowers, available terms, etc.). For example, a user of the loan management solution 248 may create, configure (e.g., using one or more templates or libraries), modify, set, or otherwise process (e.g., in a user interface of the loan management solution 248 and/or the RPA system 154) various rules, thresholds, conditional procedures, workflows, model parameters, etc. that determine or recommend loan management actions or plans for managing a set of given types of loans based on one or more events, conditions, states, actions, etc., where the loan management plans may be based on various factors, such as interest rates available from various primary and secondary borrowers or issuers, allowable attributes of borrowers (e.g., based on income, wealth, geographic location, etc.), current interest rates of the platform market or outside market, conditions of a set of borrowers, conditions or other attributes of the collateral 102 or 218, risk factors of the borrower, risk factors of one or more payers, risk factors of the insurance, market risk factors, etc. (including one or more of the payables based on the intellectual property 156), a set of the loan, or other predicted conditions, such as a financial preference of the loan, a set of the loan, or other predicted behavior of the loan, such as a financial preference of the loan, or a financial preference of the loan for the loan. Loan management may include management of terms and conditions for groups of loans, appropriate loan selection, communication to encourage transactions, and the like. In an embodiment, the loan management solution 248 may automatically recommend or set rules, thresholds, actions, parameters, etc. (optionally by learning to do so based on a training set of results that vary over time) to form a recommended loan management plan that may specify a series of actions required to achieve a recommended or expected loan management result (e.g., within an acceptable range of results), which may be automated, and may involve conditional execution of steps based on monitoring conditions and/or intelligent contract terms that may be created, configured, and/or accounted for in the loan management plan. The loan management plan may be determined and executed based at least in part on marketing factors (e.g., competitive interest rates provided by other issuers, property values, issuer attributes, mortgage or property values, etc.) as well as regulatory and/or compliance factors. Loan management plans may be formulated and/or executed for creating new loans, secondary loans or loan guarantee transactions, collecting, merging, stopping redemption, bankruptcy or non-liability situations, modifying existing loans, situations involving market changes (e.g., current interest rates or property value changes), and the like. In an embodiment, the adaptive intelligence system 158 (including the artificial intelligence 156) may be trained by experts based on training sets of loan management activities and/or results of loan management actions to generate a set of predictions, classifications, control instructions, plans, models, etc. for automatically creating, managing, and/or executing one or more aspects of a loan management plan.
In an embodiment, a system for automatically processing a subsidy loan is provided herein. In an embodiment, the platform or system includes (a) a set of internet of things data collection and monitoring services for collecting information about a set of entities involved in a set of subsidy loan transactions; (b) A situation classification system having a model and a set of artificial intelligence services for classifying a set of parameters of the set of subsidies involved in the transaction based on information from the set of Internet of things data collection services 208, wherein the model is trained using a training dataset of results related to the subsidy; and (c) a set of intelligent contracts for automatically modifying the terms and conditions of the subsidized loan based on a set of classification parameters from the condition classification system.
In an embodiment, the set of entities comprises the following entities: a set of subsidies, a set of parties, a set of subsidies, a set of guarantors, a set of subsidizing parties, and a set of collateral.
In an embodiment, the set of subsidizing parties includes at least one of: municipalities, companies, contractors, government entities, non-government entities, and non-profit entities.
In an embodiment, a set of subsidy loans includes at least one of: municipal subsidy loans, government subsidy loans, school-aid loans, asset guarantee subsidy loans, and corporate subsidy loans.
In an embodiment, the condition classified by the condition classification system is among a default condition, a redemption-stop condition, a condition indicative of a breach of a contract, a financial risk condition, a behavioral risk condition, a contract performance condition, a policy risk condition, a financial health condition, a physical defect condition, a physical health condition, an entity risk condition, and an entity health condition.
In an embodiment, the loan is a school-aid loan and the condition classification system classifies at least one of: the student gains academic progress, the student participates in non-profit activities and the student participates in public welfare activities.
In embodiments, a set of internet of things data collection and monitoring services support a user interface through which a user can configure queries for information about a set of entities.
In an embodiment, the platform or system may further include a set of configurable data collection and monitoring services for monitoring entities including at least one of a set of social network analysis services, a set of environmental condition sensors, a set of crowdsourcing services, and a set of algorithms for querying network domains.
In an embodiment, a set of configurable data collection and monitoring services monitor the following environments: municipal environments, educational environments, enterprise environments, securities trading environments, real estate environments, commercial facilities, warehousing facilities, transportation environments, manufacturing environments, storage environments, houses, and vehicles.
In an embodiment, a set of subsidy loans is guaranteed by a set of properties.
In an embodiment, the set of assets includes the following assets: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, unexplored land, farms, crops, municipal facilities, warehouses, a group of inventory, goods, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, the platform or system may further comprise an automated agent for processing events relating to at least one of value, status and ownership of the property and taking actions relating to the subsidy loan transaction to which the property relates.
In an embodiment, the action is selected from: a loan transaction to be tendered; underwriting subsidy loan transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a request for a notice to offer, stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; joint subsidy loans and merged subsidy loans.
In an embodiment, the artificial intelligence service comprises at least one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
In an embodiment, the platform or system may further include an automatic subsidized loan management system that manages actions related to subsidizing a loans, wherein the automatic subsidizing loan management system is trained based on a training set of subsidized loan management activities.
In an embodiment, an automated subsidy loan management system is trained based on a set of interactions of a party with a set of user interfaces involved in a set of subsidy loan transactions.
In an embodiment, a set of subsidy loan transaction activities includes the following activities: a loan transaction to be tendered; underwriting subsidy loan transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notice requiring the provision, stopping the redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; joint subsidy loans and merged subsidy loans.
In an embodiment, the platform or system may further include a set of blockchain services for recording a modified set of terms and conditions for a set of subsidized loans in the distributed ledger.
In an embodiment, the platform or system may further include a market value data collection service that monitors and reports market information related to the value of at least one of the issuer, a set of subsidized loans, and a set of properties.
In an embodiment, a set of assets is reported, the set of assets including at least one of the following assets: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, the market value data collection service monitors pricing or financial data for items similar to the property in at least one public market.
In an embodiment, a set of similar items for valuing an asset is constructed using a similarity clustering algorithm based on attributes of the asset.
In an embodiment, the attributes are selected from the following: asset class, asset age, asset condition, asset history, asset storage, and asset geographic location.
In an embodiment, the platform or system may also include a set of intelligent contract services for managing intelligent contracts for subsidizing loan transactions.
In an embodiment, the intelligent contract service sets terms and conditions for subsidizing a loan.
In an embodiment, the set of terms and conditions of the debt transaction specified and managed by the set of intelligent contract services is selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, top-end big payback plan, guaranteed property description of subsidized loan, property substitutability description, party, issuer, purchaser, insured person, collateral, personal guarantee, lien, term, contract, redemption status, default status, and default outcome.
In an embodiment, a lending platform is provided having a system that varies terms and conditions of a subsidized loan based on parameters monitored in a social network.
In an embodiment, a system for automatically processing a subsidy loan is provided herein. In an embodiment, the platform or system includes (a) a set of social network analytics data collection and monitoring services for collecting information about a set of entities involved in a set of subsidy loan transactions; (b) A situation classification system having a model and a set of artificial intelligence services for classifying a set of parameters of the set of subsidies involved in the transaction based on information from the set of social network analysis applications 204 (including data collection, monitoring and analysis), wherein the model is trained using a training dataset of results related to the subsidy loans; and (c) a set of intelligent contracts for automatically modifying the terms and conditions of the subsidized loan based on a set of classification parameters from the condition classification system.
In an embodiment, the set of entities comprises the following entities: a set of subsidies, a set of parties, a set of subsidies, a set of guarantors, a set of subsidizing parties, and a set of collateral.
In an embodiment, the set of subsidizing parties includes at least one of: municipalities, companies, contractors, government entities, non-government entities, and non-profit entities.
In an embodiment, a set of subsidy loans includes at least one of: municipal subsidy loans, government subsidy loans, school-aid loans, asset guarantee subsidy loans, and corporate subsidy loans.
In an embodiment, the condition classified by the condition classification system is among a default condition, a redemption-stop condition, a condition indicative of a breach of a contract, a financial risk condition, a behavioral risk condition, a contract performance condition, a policy risk condition, a financial health condition, a physical defect condition, a physical health condition, an entity risk condition, and an entity health condition.
In an embodiment, the loan is a school-aid loan and the condition classification system classifies at least one of: the student gains academic progress, the student participates in non-profit activities and the student participates in public welfare activities.
In an embodiment, the set of social network analytics data collection and monitoring services enable a user interface through which a user may configure a query for information about the set of entities, and the social network analytics data collection and monitoring services initiate a set of algorithms to search and retrieve data from a social network based on the query.
In an embodiment, the platform or system may further comprise a set of configurable data collection and monitoring services for monitoring entities, including at least one of a set of internet of things services, a set of environmental condition sensors, a set of crowdsourcing services, and a set of algorithms for querying a network domain.
In an embodiment, a set of configurable data collection and monitoring services monitor the following environments: municipal environments, educational environments, enterprise environments, securities trading environments, real estate environments, commercial facilities, warehousing facilities, transportation environments, manufacturing environments, storage environments, houses, and vehicles.
In an embodiment, a set of subsidy loans is guaranteed by a set of properties.
In an embodiment, the set of assets includes the following assets: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, the platform or system may further comprise an automated agent for processing events relating to at least one of value, status and ownership of the property and taking actions relating to the subsidy loan transaction to which the property relates.
In an embodiment, the action is selected from: a loan transaction to be tendered; underwriting subsidy loan transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notice requiring the provision, stopping the redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; joint subsidy loans and merged subsidy loans.
In an embodiment, the artificial intelligence service comprises at least one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
In an embodiment, the platform or system may further include an automatic subsidized loan management system that manages actions related to subsidizing a loans, wherein the automatic subsidizing loan management system is trained based on a training set of subsidized loan management activities.
In an embodiment, an automated subsidy loan management system is trained based on a set of interactions of a party with a set of user interfaces involved in a set of subsidy loan transactions.
In an embodiment, a set of subsidy loan transaction activities includes the following activities: a loan transaction to be tendered; underwriting subsidy loan transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a request for a notice to offer, stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; joint subsidy loans and merged subsidy loans.
In an embodiment, the platform or system may further include a set of blockchain services for recording a modified set of terms and conditions for a set of subsidized loans in a distributed ledger.
In an embodiment, the platform or system may further include a market value data collection service for monitoring and reporting market information relating to the value of at least one of the party, the set of subsidized loans, and the set of properties.
In an embodiment, a set of assets is reported, the set of assets including at least one of the following assets: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, unexplored land, farms, crops, municipal facilities, warehouses, a group of inventory, goods, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, the market value data collection service monitors pricing or financial data for items similar to the property in at least one public market.
In an embodiment, a set of similar items for valuing an asset is constructed using a similarity clustering algorithm based on attributes of the asset.
In an embodiment, the attributes are selected from the following: asset class, asset age, asset condition, asset history, asset storage, and asset geographic location.
In an embodiment, the platform or system may also include a set of intelligent contract services for managing intelligent contracts for subsidizing loan transactions.
In an embodiment, the intelligent contract service sets terms and conditions for subsidizing a loan.
In an embodiment, the set of terms and conditions of the debt transaction specified and managed by the set of intelligent contract services is selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, top-end big payback plan, guaranteed property description of subsidized loan, property substitutability description, party, issuer, purchaser, insured person, collateral, personal guarantee, lien, term, contract, redemption status, default status, and default outcome.
In an embodiment, a lending platform is provided having a system for altering terms and conditions of a subsidized loan based on parameters monitored by crowdsourcing.
In an embodiment, a system for automatically processing a subsidy loan is provided herein. In an embodiment, the platform or system includes (a) a set of crowdsourcing systems 520 for collecting information about a set of entities involved in a set of subsidy loan transactions; (b) A situation classification system having a model and a set of artificial intelligence services for classifying a set of parameters of the set of subsidies involved in the transaction based on information from the set of crowdsourcing services, wherein the model is trained using a training dataset of results related to the subsidy loans; and (c) a set of intelligent contracts for automatically modifying the terms and conditions of the subsidized loan based on a set of classification parameters from the condition classification system.
In an embodiment, the set of entities comprises the following entities: a set of subsidies, a set of parties, a set of subsidies, a set of guarantors, a set of subsidizing parties, and a set of collateral.
In an embodiment, the set of subsidizing parties includes at least one of: municipalities, companies, contractors, government entities, non-government entities, and non-profit entities.
In an embodiment, a set of subsidy loans includes at least one of: municipal subsidy loans, government subsidy loans, school-aid loans, asset guarantee subsidy loans, and corporate subsidy loans.
In an embodiment, the condition classified by the condition classification system is among a default condition, a redemption-stop condition, a condition indicative of a breach of a contract, a financial risk condition, a behavioral risk condition, a contract performance condition, a policy risk condition, a financial health condition, a physical defect condition, a physical health condition, an entity risk condition, and an entity health condition.
In an embodiment, the loan is a school-aid loan and the condition classification system classifies at least one of: the student gains academic progress, the student participates in non-profit activities and the student participates in public welfare activities.
In an embodiment, the set of crowdsourcing services enables a user interface through which a user can configure a query for information about the set of entities, and the set of crowdsourcing services automatically configures an initiation of a crowdsourcing request based on the query.
In embodiments, the platform or system may further include a set of configurable data collection and monitoring services for monitoring entities, including at least one of a set of internet of things services, a set of environmental condition sensors, a set of social network analysis services, and a set of algorithms for querying network domains.
In an embodiment, a set of configurable data collection and monitoring services monitor the following environments: municipal environments, educational environments, enterprise environments, securities trading environments, real estate environments, commercial facilities, warehousing facilities, transportation environments, manufacturing environments, storage environments, houses, and vehicles.
In an embodiment, a set of subsidy loans is guaranteed by a set of properties.
In an embodiment, the set of assets includes the following assets: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, the platform or system may further comprise an automated agent for processing events relating to at least one of value, status and ownership of the property and taking actions relating to the subsidy loan transaction to which the property relates.
In an embodiment, the action is selected from: a loan transaction to be tendered; underwriting subsidy loan transaction; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notice requiring the provision, stopping the redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; joint subsidy loans and merged subsidy loans.
In an embodiment, the artificial intelligence service comprises at least one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
In an embodiment, the platform or system may further include an automatic subsidy loan management system that manages actions related to subsidizing loans, wherein the automatic subsidy loan management system is trained based on a training set of subsidy loan management activities.
In an embodiment, an automated subsidy loan management system is trained based on a set of interactions of a party with a set of user interfaces involved in a set of subsidy loan transactions.
In an embodiment, a set of subsidy loan transaction activities includes the following activities: a loan transaction to be tendered; underwriting subsidy loan transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notice requiring the provision, stopping the redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; joint subsidy loans and merged subsidy loans.
In an embodiment, the platform or system may further include a set of blockchain services for recording a modified set of terms and conditions for a set of subsidized loans in the distributed ledger.
In an embodiment, the platform or system may further include a market value data collection service for monitoring and reporting market information relating to the value of at least one of the party, a set of subsidized loans, and a set of properties.
In an embodiment, a set of assets is reported, the set of assets including at least one of the following assets: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
In an embodiment, the market value data collection service monitors pricing or financial data for items similar to the property in at least one public market.
In an embodiment, a set of similar items for valuing an asset is constructed using a similarity clustering algorithm based on attributes of the asset.
In an embodiment, the attributes are selected from the following: asset class, asset age, asset condition, asset history, asset storage, and asset geographic location.
In an embodiment, the platform or system may also include a set of intelligent contract services for managing intelligent contracts for subsidizing loan transactions.
In an embodiment, the intelligent contract service sets terms and conditions for subsidizing a loan.
In an embodiment, the set of terms and conditions of the debt transaction specified and managed by the set of intelligent contract services is selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, top-end big payback plan, guaranteed property description of subsidized loan, property substitutability description, party, issuer, purchaser, insured person, collateral, personal guarantee, lien, term, contract, redemption status, default status, and default outcome.
Referring to FIG. 17, in an embodiment, a lending platform is provided having an automated blockchain retention service and scheme for managing a set of retention assets. The RPA system 154 may provide automation for one or more aspects of a retention scheme 1802 that enables automated retention management and/or provides advice or planning for retention activities associated with a set of assets, e.g., assets involved in or warranting a loan transaction or assets a customer seeks to retain for security or management purposes, e.g., any type of asset described herein, including cryptocurrency and other currencies, equity and other ownership certificates, securities, etc. The retention scenario 1802 and/or the RPA system 154 for handling retention activities may include a set of interfaces, workflows and models (which may include, be implemented using, or by various adaptive intelligent systems 158), and other components for automating one or more aspects of a retention action or management process of the trust or retention of a set of assets 218, e.g., based on a set of conditions (which may include intelligent contract terms and conditions, market conditions (conditions of the platform market and/or external market 188, conditions monitored by the monitoring system 164 and data collection system 166, etc. (e.g., conditions of the entity 198, including but not limited to the principal 210, collateral 102 and assets 218, etc.)). A user of the retention management scheme 1802 may create, configure (e.g., using one or more templates or libraries), modify, set, or otherwise process (e.g., in the retention management scheme 1802 and/or a user interface of the RPA system 154) various rules, thresholds, conditional procedures, workflows, model parameters, etc., that determine or recommend a retention action or plan for managing a set of assets of a given type based on one or more events, conditions, states, actions, conditions, etc., wherein the retention plan may be based on various factors, such as available storage options, asset retrieval criteria, asset ownership transfer criteria, etc., the status of the asset 218 requiring retention management services, the behavior of the parties (e.g., behavior indicating preferences), etc Selecting appropriate terms and conditions for trust and custody 150, selecting ownership transfer parameters, selecting and providing storage devices, selecting and providing security infrastructure for data storage, and the like. In an embodiment, the retention management scheme 1802 may automatically recommend or set rules, thresholds, actions, parameters, etc. (optionally by learning to do so based on a training set of results that vary over time) to form a recommended retention management plan that may specify a series of actions required to achieve a recommended or expected retention management service result (e.g., within an acceptable range of results), which may be automated, and may involve conditional execution of steps based on monitoring conditions and/or intelligent contract terms that may be created, configured, and/or specified in accordance with the retention management plan. Retention plans may be determined and executed based at least in part on market factors (e.g., competitive terms and conditions provided by other retainers, property values, customer attributes, collateral or asset values, physical storage costs, data storage costs, etc.), as well as regulatory and/or compliance factors. In an embodiment, the adaptive intelligence system 158 (including the artificial intelligence 156) may be trained by an expert based on a training set of custody activities and/or results of custody actions to generate a set of predictions, classifications, control instructions, plans, models, etc. for automatically creating, managing, and/or executing one or more aspects of a custody plan. In an embodiment, actions related to the custody of a set of assets may be stored in a blockchain 136, such as a distributed ledger.
In an embodiment, a system for handling trust and custody 150 of a set of assets is provided herein. The platform or system may include (a) a set of asset qualification services for qualifying a set of assets that a financial institution is responsible for custody; (b) A set of identity management services whereby the financial institution verifies the identities and credentials of a set of entities authorized to take action on the asset; and (c) a set of blockchain services, wherein at least one of the set of assets and identification information for the set of assets is stored in the blockchain, wherein events related to the set of assets are recorded in the distributed ledger.
In an embodiment, the credentials include owner credentials, broker credentials, beneficiary credentials, trustee credentials, and custodian credentials.
In an embodiment, events related to a set of assets include transferring property rights, owner death, owner disability, owner bankruptcy, redemption, setting liens, using an asset as a collateral, designating a beneficiary, lending with an asset as a collateral, providing notification about an asset, reviewing an asset, evaluating an asset, reporting an asset for tax purposes, assigning ownership of an asset, disposing of an asset, selling an asset, purchasing an asset, and designating an ownership status.
In an embodiment, the platform or system further comprises a set of data collection and monitoring services for monitoring at least one of the set of assets, a set of entities, and a set of events related to the set of assets.
In an embodiment, the set of entities includes at least one of an owner, a beneficiary, an agent, a trusted person, and a custodian.
In an embodiment, the platform or system further comprises a set of intelligent contract services for managing custody of the set of assets, wherein at least one event related to the set of assets is automatically managed by an intelligent contract based on a set of terms and conditions carried by the intelligent contract and information collected by the set of data collection and monitoring services.
In an embodiment, events related to a set of assets include transferring property rights, owner death, owner disability, owner bankruptcy, redemption, setting liens, using an asset as a collateral, designating a beneficiary, lending with an asset as a collateral, providing notification about an asset, reviewing an asset, evaluating an asset, reporting an asset for tax purposes, assigning ownership of an asset, disposing of an asset, selling an asset, purchasing an asset, and designating an ownership status.
Referring to FIG. 18, in an embodiment, a lending platform with a loan underwriting system is provided having a set of data integration microservices including data collection and monitoring services, blockchain services, artificial intelligence services, and intelligent contract services for underwriting entities and transactions. The RPA system 154 may provide automation for one or more aspects of the underwriting scheme 122 that enables automated underwriting and/or provides advice or plans for underwriting activities related to loan transactions, such as personal loans, corporate loans, subsidy loans, school loans, or other loans, including loans that may be secured with borrower's assets, collateral, or commitments. The underwriting scheme 122 and/or the RPA system 154 for underwriting may include a set of interfaces, workflows and models (which may include, be implemented using, or by various adaptive intelligent systems 158), and other components for automating one or more aspects of the underwriting action or management process of a loan transaction, for example, based on a set of conditions (which may include intelligent contract terms and conditions, market conditions (of the platform market and/or the external market 188), conditions monitored by the monitoring system 164 and the data collection system 166, and the like (e.g., conditions of the entity 198, including but not limited to parties 210, collateral 102, assets 218, and the like, as well as interest rates, available borrowers, available terms, and the like)). For example, a user of the underwriting plan 122 may create, configure (e.g., using one or more templates or libraries), modify, set, or otherwise process (e.g., in a user interface of the underwriting plan 122 and/or the RPA system 154) various rules, thresholds, conditional procedures, workflows, model parameters, etc., that determine or recommend underwriting actions or plans for managing a given set of loans based on one or more events, conditions, states, actions, etc., wherein the underwriting plans may be based on various factors, such as interest rates available from various primary and secondary borrowers or issuers, allowable attributes of the borrower (e.g., based on income, wealth, geographic location, etc.), prevailing interest rates of a platform market or an outside market, conditions of a set of borrowers, conditions or other attributes of the collateral 102 or assets 218, risk factors of the borrower, risk factors of one or more collateral holders, market risk factors, etc. (including one or more accounts receivable models 156 based on the user intelligence), expected or predicted conditions of the loan, such as a set of payable behavior of the loan, or other conditions, such as financial preferences, and/or other applicable conditions indicated by the loan. Underwriting may include management of terms and conditions for groups of loans, appropriate loan selections, communications related to the underwriting process, and the like. In embodiments, the underwriting schema 122 may automatically recommend or set rules, thresholds, actions, parameters, etc. (optionally by learning to do so based on a training set of results that vary over time) to form a recommended underwriting plan, which may specify a series of actions required to achieve a recommended or expected underwriting result (e.g., within a range of acceptable results), which may be automated, and may involve conditional execution of steps based on monitored conditions and/or intelligent contract terms that may be created, configured, and/or specified by the underwriting plan. The underwriting plan may be determined and executed based at least in part on marketing factors (e.g., competitive interest rates provided by other publishers, property values, borrower behavior, demographic trends, payment trends, publisher attributes, collateral or asset values, etc.) as well as regulatory and/or compliance factors. Underwriting plans may be formulated and/or executed for new loans, secondary loans, or loan guarantee transactions, collections, mergers, redemption shutdowns, bankruptcy or non-liability situations, modification of existing loans, situations involving market changes (e.g., current interest rates or property value changes), redemption outages, and the like. In embodiments, the adaptive intelligence system 158 (including the artificial intelligence 156) may be trained by an expert based on a training set of underwriting activities and/or results of underwriting actions to generate a set of predictions, classifications, control instructions, plans, models, etc. for automatically creating, managing, and/or executing one or more aspects of an underwriting plan. In embodiments, underwriting events and results may be recorded in blockchain 136, such as a distributed ledger, in order to authorize users for secure access and retrieval. The adaptive intelligence system 158 may, for example, improve or automate one or more aspects of the underwriting using various artificial intelligence 156 or expert systems disclosed herein and incorporated by reference in the documents herein, such as training models, neural networks, deep learning systems, etc., through training sets based on training sets of expert interactions and/or training sets of results of underwriting activities.
Referring to FIG. 19, in an embodiment, a lending platform with a loan marketing system is provided having a set of data integration microservices including a data collection and monitoring service for marketing loans to a set of potential parties, a blockchain service, an artificial intelligence service, and an intelligent contract service. The loan support platform 100 may implement one or more aspects of a loan marketing solution 2002 that enables automated loan marketing and/or provides advice or plans for loan marketing activities related to loan transactions, such as personal loans, corporate loans, subsidized loans, assisted loans, or other loans, including loans that may be secured with borrower's assets, collateral, or commitments. The marketing loan solution 2002 (which in embodiments may include or use the RPA system 154 for marketing loans) may include a set of interfaces, workflows and models (which may include, use various adaptive intelligent systems 158 or be implemented by various adaptive intelligent systems 158), and other components for facilitating the marketing loan based on, for example, a set of conditions (which may include intelligent contract terms and conditions (which may be used, for example, for a set of sales loans), capital available for lending, regulatory factors, market conditions (conditions for the platform market and/or the external market 188, conditions monitored by the monitoring system 164 and the data collection system 166, etc. (e.g., conditions for the entity 198, including but not limited to the principal 210, collateral 102 and assets 218, for example, a user of the loan marketing solution 2002 may create, configure (e.g., using one or more templates or libraries), modify, set, or otherwise process (e.g., in the user interface of the loan marketing solution 2002 and/or the RPA system 154) various rules, thresholds, conditional programs, workflows, model parameters, etc., that determine or recommend marketing actions or plans for managing a set of given types of loans based on one or more events, conditions, states, actions, etc., wherein the marketing plans may be based on various factors, such as interest rates, available terms, etc., that may be obtained from various primary and secondary borrowers or issuers), the return on capital available for the loan, the borrower's allowable or required attributes (e.g., based on income, wealth, geographic location, etc.), the current interest rate of the platform market or external market, the status of a group of parties to the loan, the status or other attributes of the collateral 102 or assets 218, the borrower's risk factors, one or more collateral risk factors, market risk factors, etc. (including predicted risk based on one or more predictive models of using artificial intelligence 156), debt status, the conditions available to vouch for a group of loans 102 or assets 218, business or business state (e.g., accounts receivable, accounts payable, etc.), the conditions of the parties 210 (e.g., equity, wealth, debt, geographic location, and other conditions), the parties ' behaviors (e.g., behaviors indicating preferences, behavior indicating debt preferences, payment preferences, or communication preferences), etc. Loan marketing may include the management of terms and conditions for groups of loans, appropriate loan selections, communications related to the loan marketing process, and the like. In an embodiment, the loan marketing solution 2002 may automatically recommend or set rules, thresholds, actions, parameters, etc. (optionally by learning to do so based on a training set of results that vary over time) to form a recommended loan marketing plan, which may specify a series of actions required to achieve a recommended or expected loan marketing result (e.g., within an acceptable range of results), which may be automated, and may involve conditional execution of steps based on monitoring conditions and/or intelligent contract terms that may be created, configured, and/or accounted for by the loan marketing plan. The loan marketing plan may be determined and executed based at least in part on marketing factors (e.g., competitive interest rates provided by other issuers, property values, borrower behavior, demographic trends, payment trends, issuer attributes, collateral or property values, etc.) as well as regulatory and/or compliance factors. Loan marketing plans may be formulated and/or executed for new loans, secondary loans or loan guarantee transactions, collections, mergers, check-out situations (e.g., check-out alternatives), bankruptcy or non-liability situations, modification of existing loans, situations involving market changes (e.g., current interest rates, available capital or property value changes), and the like. In an embodiment, the adaptive intelligence system 158 (including the artificial intelligence 156) may be trained by experts based on a training set of loan marketing activities and/or results of loan marketing actions to generate a set of predictions, classifications, control instructions, plans, models, etc. to automatically create, manage, and/or execute one or more aspects of a loan marketing plan. In an embodiment, the loan marketing event and results may be recorded in a blockchain 136, such as a distributed ledger, to authorize users for secure access and retrieval. The adaptive intelligence system 158 may, for example, improve or automate one or more aspects of the entity ratings using various artificial intelligence 156 or expert systems disclosed herein and incorporated by reference in the documents herein, such as training models, neural networks, deep learning systems, etc. through training sets based on expert interaction and/or training sets of results of the loan marketing campaign.
Referring to fig. 20, in an embodiment, a lending platform with a rating system is provided having a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a blockchain service, an artificial intelligence service, and an intelligent contract service. The loan support platform 100 may implement one or more aspects of the entity rating scheme 206 that enable automated entity rating and/or provide advice or plans for entity rating activities related to loan transactions, such as personal loans, corporate loans, subsidized loans, assisted loans, or other loans, including loans that may be secured with borrowers' assets, collateral, or commitments. The entity rating scheme 206 (which in embodiments may include or use the RPA system 154 for entity rating) may include a set of interfaces, workflows and models (which may include, use various adaptive intelligent systems 158 or be implemented by various adaptive intelligent systems 158), and other components for, for example, identifying a set of conditions, attributes, events, etc. (which may include attributes of the entity 198 (e.g., value, quality, geographic location, net worth, price, physical conditions, health conditions, security, ownership, etc.), intelligent contract terms and conditions (e.g., which may be configured or populated based on ratings of a set of rated loans), regulatory factors, market conditions (conditions of the platform market and/or the outside market 188, conditions monitored by the monitoring system 164 and the data collection system 166, etc. (e.g., conditions of the entity 198, including but not limited to parties 210, mortgages 102, and assets 218, etc., as well as interest rates, available borrowers, available terms, etc.)) automate one or more aspects of the entity rating action or rating process of a loan transaction, for example, a user of the entity rating scheme 206 may create, configure (e.g., using one or more templates or libraries), modify, set, or otherwise process (e.g., in a user interface of the entity rating scheme 206 and/or RPA system 154) various rules, thresholds, conditional programs, workflows, model parameters, etc., that determine or recommend an entity rating action or plan for rating a given set of types of loans based on one or more events, attributes, parameters, features, conditions, states, actions, etc., where the entity rating plan may be based on various factors (e.g., based on income, wealth, geographic location, etc., or the principal 210, relative to others, or based on the conditions of the collateral 102 or assets 218, etc.), the prevailing conditions of the platform market or the outside market, the conditions of the principal of a set of loans, the conditions or other attributes of the collateral 102 or assets 218, the risk factors of borrowers, the risk factors of one or more of the guarantors, market risk factors, etc. (including predicted risk based on one or more predictive models of the artificial user intelligence 156), the debt conditions, the conditions available to secure the collateral 102 or assets 218 of a set of loans, business or business operational status (e.g., accounts receivable, accounts payable, etc.), the conditions of the principal 210 (e.g., equity, wealth, debt, geographic location, and other conditions), the behavior of the principal (e.g., behavior indicative of preferences, behavior indicative of debt preferences, payment preferences, or communication preferences), and the like. Entity ratings may include management of terms and conditions of multiple sets of loans, appropriate loan selections, communications related to the entity rating process, and the like. In embodiments, the entity rating scheme 206 may automatically recommend or set rules, thresholds, actions, parameters, etc. (optionally by learning to do so based on a training set of results that vary over time) to form a recommended entity rating plan that may specify a series of actions required to achieve a recommended or expected entity rating result (e.g., within an acceptable range of results), which may be automated, and may involve conditional execution of steps based on monitored conditions and/or intelligent contract terms that may be created, configured, and/or accounted for by the entity rating plan. The entity rating plan may be determined and executed based at least in part on marketing factors (e.g., competitive interest rates provided by other publishers, property values, borrower behavior, demographic trends, payment trends, publisher attributes, collateral or asset values, etc.) as well as regulatory and/or compliance factors. Entity rating plans may be formulated and/or executed for new loans, secondary loans or loan assurance transactions, collections, mergers, check-out situations (e.g., check-out alternatives), bankruptcy or non-liability situations, modification of existing loans, situations involving market changes (e.g., current interest rates, available capital or property value changes), and the like. In embodiments, the adaptive intelligence system 158 (including the artificial intelligence 156) may be trained by an expert based on a training set of entity rating activities and/or results of entity rating actions to generate a set of predictions, classifications, control instructions, plans, models, etc. for automatically creating, managing, and/or executing one or more aspects of an entity rating plan. In embodiments, entity rating events and results may be recorded in blockchain 136, such as a distributed ledger, in order to authorize users for secure access and retrieval. The adaptive intelligence system 158 may, for example, improve or automate one or more aspects of entity ratings using various artificial intelligence 156 or expert systems disclosed herein and incorporated by reference in documents herein, such as by training models, neural networks, deep learning systems, etc., based on a training set of expert interactions and/or a training set of results of entity rating activities.
Referring to fig. 21, in an embodiment, a loan platform with a regulatory and/or compliance solution 142 is provided having a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies applicable to loan transactions. The loan support platform 100 may implement one or more aspects of a regulatory and compliance solution 142 that enables automated regulation and compliance and/or provides advice or plans for regulatory and compliance activities related to loan transactions, such as personal loans, corporate loans, subsidized loans, assisted loans, or other loans, including loans that may be secured with borrower's assets, collateral, or commitments. The administration and compliance solution 142 (which in embodiments may include or use the RPA system 154 for automating administration and compliance activities based on a training set of professional interactions in the administration and/or compliance activities) may include a set of interfaces, workflows and models (which may include, use, or be implemented by various adaptive intelligent systems 158) and other components for, for example, creating or implementing in a multiple manner a plurality of administration and/or compliance processing schemes 142, or other components for, for example, automatically implementing in a multiple manner a plurality of administration and/or compliance processing schemes 142, or a plurality of administration and/or compliance processing schemes 142, such as a plurality of administration and/or compliance processing schemes 142, a plurality of administration and/or compliance processing schemes (which may include, for example, but not limited to, a plurality of administration and/or compliance processing schemes 142) Model parameters, etc., that determine or recommend regulatory and compliance actions or plans for managing a given set of loans based on one or more events, attributes, parameters, features, conditions, states, actions, etc., wherein the regulatory and compliance plans may be based on various factors (e.g., based on allowable interest rates, required notice (e.g., on annualization percentage reports), allowed borrowers (e.g., students applying for federal subsidy for assistance loans), allowed borrowers, allowed issuers, income (e.g., low income loans), wealth (e.g., policies allow loans to be offered only to sufficiently large parties), geographic location (e.g., geographically limited loan plans, such as for municipal development), conditions of the platform market or external market (e.g., where the loan interest rate is required to not exceed a threshold calculated from the current interest rate), conditions of a group of parties to the loan, conditions or other attributes of the collateral 102 or assets 218, risk factors of the borrower, risk factors of one or more insurers, market risk factors, etc. (including predicted risk based on one or more predictive models using artificial intelligence 156), debt conditions, conditions of the collateral 102 or assets 218 that may be used to secure a group of loans, business or business operational status (e.g., accounts receivable, accounts payable, etc.), conditions of the parties 210 (e.g., equity, wealth, debt, geographic location, and other conditions), behaviors of the parties (e.g., behaviors that indicate preferences, behaviors that indicate debt preferences, business status, etc.) The behavior of payment preferences or communication preferences), etc. Administration and compliance may include management of terms and conditions for groups of loans, appropriate loan selections, notifications to be provided, underwriting policies, and communications related to the administration and compliance process. In an embodiment, the regulatory and compliance solution 142 may automatically recommend or set rules, thresholds, actions, parameters, etc. (optionally, by learning to do so based on a training set of results that vary over time) to form a recommended regulatory and compliance plan, which may specify a series of actions required to achieve a recommended or expected regulatory and compliance result (e.g., within an acceptable range of results), which may be automated, and may involve conditional execution of steps based on monitored conditions and/or intelligent contract terms that may be created, configured, and/or specified in accordance with the regulatory and compliance plan. Regulatory and compliance programs may be determined and executed based at least in part on marketing factors (e.g., competitive interest rates provided by other publishers, property values, borrower behavior, demographic trends, payment trends, publisher attributes, collateral or asset values, etc.) as well as regulatory and/or compliance factors. Regulatory and compliance programs may be formulated and/or executed for new loans, secondary loans or loan assurance transactions, collections, mergers, check-out situations (e.g., check-out alternatives), bankruptcy or non-liability situations, modification of existing loans, situations involving market changes (e.g., current interest rates, available capital or property value changes), and the like. In an embodiment, the adaptive intelligence system 158 (including the artificial intelligence 156) may be trained by an expert based on a training set of regulatory and compliance activities and/or results of regulatory and compliance actions to generate a set of predictions, classifications, control instructions, plans, models, etc. for automatically creating, managing, and/or executing one or more aspects of a regulatory and compliance program. In an embodiment, regulatory and compliance events and results may be recorded in blockchain 136, such as in a distributed ledger, in order to authorize users for secure access and retrieval. The adaptive intelligence system 158 may, for example, improve or automate one or more aspects of the oversight and compliance using various artificial intelligence 156 or expert systems disclosed herein and incorporated by reference in the documents herein, such as training models, neural networks, deep learning systems, etc. based on training sets of expert interactions and/or training sets of outcomes of oversight and compliance activities.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and has an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and has an intelligent contract and distributed ledger platform for managing ownership of a set of collateral and at least one of a set of events related to the set of collateral.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and having an intelligent contract system that automatically adjusts the loan rates based on information gathered via at least one of an internet of things system, a crowdsourcing system, a set of social network analysis services, and a set of data collection and monitoring services.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and having a crowdsourcing system for obtaining information regarding at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and has an intelligent contract that automatically adjusts the loan rate based on at least one of regulatory factors and market factors of a particular jurisdiction.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and has intelligent contracts that automatically reorganize debts based on monitored conditions.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and has a social network monitoring system for verifying the reliability of the loan guarantee.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and has an internet of things data collection and monitoring system for verifying the reliability of loan guarantees.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and has a robotic process automation system for negotiating a set of loan terms and conditions.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and has a robotic process automation system for loan gathering.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and has a robotic process automation system for merging a set of loans.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and has a robotic process automation system for managing the warranty loan.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and has a robotic process automation system for brokering mortgages.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and has a crowd-sourcing and automatic classification system for verifying the condition of the bond issuer.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and has a social network monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and has an internet of things data collection and monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by the internet of things.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored in the social network.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by crowdsourcing.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and has an automated blockchain retention service for managing a set of retention assets.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and has a loan underwriting system with a set of data integration microservices including data collection and monitoring services for underwriting lending entities and transactions, blockchain services, artificial intelligence services, and intelligent contract services.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and has a loan marketing system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for marketing loans to a set of potential parties.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a lending platform is provided having a set of data integration microservices including a data collection and monitoring service for processing lending entities and transactions, a blockchain service and an intelligent contract service; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and has an intelligent contract and distributed ledger platform for managing ownership of a set of collateral and at least one of a set of events related to the set of collateral.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and having an intelligent contract system that automatically adjusts the loan rates based on information gathered via at least one of an internet of things system, a crowdsourcing system, a set of social network analysis services, and a set of data collection and monitoring services.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and having a crowdsourcing system for obtaining information regarding at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and has an intelligent contract that automatically adjusts the loan rate based on at least one of regulatory factors and market factors of a particular jurisdiction.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and has intelligent contracts that automatically reorganize debts based on monitored conditions.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and has a social network monitoring system for verifying the reliability of the loan guarantee.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and has an internet of things data collection and monitoring system for verifying the reliability of loan guarantees.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and has a robotic process automation system for negotiating a set of loan terms and conditions.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and has a robotic process automation system for loan gathering.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and has a robotic process automation system for merging a set of loans.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and has a robotic process automation system for managing the warranty loan.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and has a robotic process automation system for brokering mortgages.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and has a crowd-sourcing and automatic classification system for verifying the condition of bond issuers.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and has a social network monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and has an internet of things data collection and monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by the internet of things.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored in the social network.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by crowdsourcing.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and has an automated blockchain retention service for managing a set of retention assets.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and has a loan underwriting system with a set of data integration microservices including data collection and monitoring services for underwriting lending entities and transactions, blockchain services, artificial intelligence services, and intelligent contract services.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and has a loan marketing system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for marketing loans to a set of potential parties.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a lending platform is provided having an internet of things and sensor platform for monitoring at least one of a set of assets and a set of collateral for a loan, bond or debt transaction; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing at least one of ownership of a set of collateral and a set of events related to the set of collateral; and having an intelligent contract system that automatically adjusts the loan rates based on information gathered via at least one of an internet of things system, a crowdsourcing system, a set of social network analysis services, and a set of data collection and monitoring services.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing at least one of ownership of a set of collateral and a set of events related to the set of collateral; and having a crowdsourcing system for obtaining information regarding at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing at least one of ownership of a set of collateral and a set of events related to the set of collateral; and has an intelligent contract that automatically adjusts the loan rate based on at least one of regulatory factors and market factors of a particular jurisdiction.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing at least one of ownership of a set of collateral and a set of events related to the set of collateral; and has intelligent contracts that automatically reorganize debts based on monitored conditions.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing at least one of ownership of a set of collateral and a set of events related to the set of collateral; and has a social network monitoring system for verifying the reliability of the loan guarantee.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing at least one of ownership of a set of collateral and a set of events related to the set of collateral; and has an internet of things data collection and monitoring system for verifying the reliability of loan guarantees.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing at least one of ownership of a set of collateral and a set of events related to the set of collateral; and has a robotic process automation system for negotiating a set of loan terms and conditions.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing at least one of ownership of a set of collateral and a set of events related to the set of collateral; and has a robotic process automation system for loan gathering.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing at least one of ownership of a set of collateral and a set of events related to the set of collateral; and has a robotic process automation system for merging a set of loans.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing at least one of ownership of a set of collateral and a set of events related to the set of collateral; and has a robotic process automation system for managing the warranty loan.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing at least one of ownership of a set of collateral and a set of events related to the set of collateral; and has a robotic process automation system for brokering mortgages.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing at least one of ownership of a set of collateral and a set of events related to the set of collateral; and has a crowd-sourcing and automatic classification system for verifying the condition of bond issuers.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing at least one of ownership of a set of collateral and a set of events related to the set of collateral; and has a social network monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing at least one of ownership of a set of collateral and a set of events related to the set of collateral; and has an internet of things data collection and monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing at least one of ownership of a set of collateral and a set of events related to the set of collateral; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by the internet of things.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing at least one of ownership of a set of collateral and a set of events related to the set of collateral; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored in the social network.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing at least one of ownership of a set of collateral and a set of events related to the set of collateral; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by crowdsourcing.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing at least one of ownership of a set of collateral and a set of events related to the set of collateral; and has an automated blockchain retention service for managing a set of retention assets.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing at least one of ownership of a set of collateral and a set of events related to the set of collateral; and has a loan underwriting system with a set of data integration microservices including data collection and monitoring services for underwriting lending entities and transactions, blockchain services, artificial intelligence services, and intelligent contract services.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing at least one of ownership of a set of collateral and a set of events related to the set of collateral; and has a loan marketing system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for marketing loans to a set of potential parties.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing at least one of ownership of a set of collateral and a set of events related to the set of collateral; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a lending platform is provided having an intelligent contract and distributed ledger platform for managing at least one of ownership of a set of collateral and a set of events related to the set of collateral; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a lending platform is provided with an intelligent contract system that automatically adjusts a loan interest rate based on information gathered via at least one of an internet of things system, a crowdsourcing system, a set of social network analytics services, and a set of data collection and monitoring services; and having a crowdsourcing system for obtaining information regarding at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance.
In an embodiment, a lending platform is provided having an intelligent contract system that automatically adjusts a loan rate based on information collected via at least one of an internet of things system, a crowdsourcing system, a set of social network analysis services, and a set of data collection and monitoring services; and has an intelligent contract that automatically adjusts the loan rate based on at least one of regulatory factors and market factors of a particular jurisdiction.
In an embodiment, a lending platform is provided having an intelligent contract system that automatically adjusts a loan rate based on information collected via at least one of an internet of things system, a crowdsourcing system, a set of social network analysis services, and a set of data collection and monitoring services; and has intelligent contracts that automatically reorganize debts based on monitored conditions.
In an embodiment, a lending platform is provided having an intelligent contract system that automatically adjusts a loan rate based on information collected via at least one of an internet of things system, a crowdsourcing system, a set of social network analysis services, and a set of data collection and monitoring services; and has a social network monitoring system for verifying the reliability of the loan guarantee.
In an embodiment, a lending platform is provided having an intelligent contract system that automatically adjusts a loan rate based on information collected via at least one of an internet of things system, a crowdsourcing system, a set of social network analysis services, and a set of data collection and monitoring services; and has an internet of things data collection and monitoring system for verifying the reliability of loan guarantees.
In an embodiment, a lending platform is provided having an intelligent contract system that automatically adjusts a loan rate based on information collected via at least one of an internet of things system, a crowdsourcing system, a set of social network analysis services, and a set of data collection and monitoring services; and has a robotic process automation system for negotiating a set of loan terms and conditions.
In an embodiment, a lending platform is provided having an intelligent contract system that automatically adjusts a loan rate based on information collected via at least one of an internet of things system, a crowdsourcing system, a set of social network analysis services, and a set of data collection and monitoring services; and has a robotic process automation system for loan gathering.
In an embodiment, a lending platform is provided having an intelligent contract system that automatically adjusts a loan rate based on information collected via at least one of an internet of things system, a crowdsourcing system, a set of social network analysis services, and a set of data collection and monitoring services; and has a robotic process automation system for merging a set of loans.
In an embodiment, a lending platform is provided having an intelligent contract system that automatically adjusts a loan rate based on information collected via at least one of an internet of things system, a crowdsourcing system, a set of social network analysis services, and a set of data collection and monitoring services; and has a robotic process automation system for managing the warranty loan.
In an embodiment, a lending platform is provided having an intelligent contract system that automatically adjusts a loan rate based on information collected via at least one of an internet of things system, a crowdsourcing system, a set of social network analysis services, and a set of data collection and monitoring services; and has a robotic process automation system for brokering mortgages.
In an embodiment, a lending platform is provided having an intelligent contract system that automatically adjusts a loan rate based on information collected via at least one of an internet of things system, a crowdsourcing system, a set of social network analysis services, and a set of data collection and monitoring services; and has a crowd-sourcing and automatic classification system for verifying the condition of bond issuers.
In an embodiment, a lending platform is provided having an intelligent contract system that automatically adjusts a loan rate based on information collected via at least one of an internet of things system, a crowdsourcing system, a set of social network analysis services, and a set of data collection and monitoring services; and has a social network monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having an intelligent contract system that automatically adjusts a loan rate based on information collected via at least one of an internet of things system, a crowdsourcing system, a set of social network analysis services, and a set of data collection and monitoring services; and has an internet of things data collection and monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having an intelligent contract system that automatically adjusts a loan rate based on information collected via at least one of an internet of things system, a crowdsourcing system, a set of social network analysis services, and a set of data collection and monitoring services; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by the internet of things.
In an embodiment, a lending platform is provided having an intelligent contract system that automatically adjusts a loan rate based on information collected via at least one of an internet of things system, a crowdsourcing system, a set of social network analysis services, and a set of data collection and monitoring services; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored in the social network.
In an embodiment, a lending platform is provided having an intelligent contract system that automatically adjusts a loan rate based on information collected via at least one of an internet of things system, a crowdsourcing system, a set of social network analysis services, and a set of data collection and monitoring services; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by crowdsourcing.
In an embodiment, a lending platform is provided having an intelligent contract system that automatically adjusts a loan rate based on information collected via at least one of an internet of things system, a crowdsourcing system, a set of social network analysis services, and a set of data collection and monitoring services; and has an automated blockchain retention service for managing a set of retention assets.
In an embodiment, a lending platform is provided having an intelligent contract system that automatically adjusts a loan rate based on information collected via at least one of an internet of things system, a crowdsourcing system, a set of social network analysis services, and a set of data collection and monitoring services; and has a loan underwriting system with a set of data integration microservices including data collection and monitoring services, block chain services, artificial intelligence services, and intelligent contract services for underwriting lending entities and transactions.
In an embodiment, a lending platform is provided having an intelligent contract system that automatically adjusts a loan rate based on information collected via at least one of an internet of things system, a crowdsourcing system, a set of social network analysis services, and a set of data collection and monitoring services; and has a loan marketing system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for marketing loans to a set of potential parties.
In an embodiment, a lending platform is provided with an intelligent contract system that automatically adjusts a loan interest rate based on information gathered via at least one of an internet of things system, a crowdsourcing system, a set of social network analytics services, and a set of data collection and monitoring services; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a lending platform is provided having an intelligent contract system that automatically adjusts a loan rate based on information collected via at least one of an internet of things system, a crowdsourcing system, a set of social network analysis services, and a set of data collection and monitoring services; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a lending platform is provided having a crowdsourcing system for obtaining information about at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance; and has an intelligent contract that automatically adjusts the loan rate based on at least one of regulatory factors and market factors of a particular jurisdiction.
In an embodiment, a lending platform is provided having a crowdsourcing system for obtaining information about at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance; and has intelligent contracts that automatically reorganize debts based on monitored conditions.
In an embodiment, a lending platform is provided having a crowdsourcing system for obtaining information about at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance; and has a social network monitoring system for verifying the reliability of the loan guarantee.
In an embodiment, a lending platform is provided having a crowdsourcing system for obtaining information about at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance; and has an internet of things data collection and monitoring system for verifying the reliability of loan guarantees.
In an embodiment, a lending platform is provided having a crowdsourcing system for obtaining information about at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance; and has a robotic process automation system for negotiating a set of loan terms and conditions.
In an embodiment, a lending platform is provided having a crowdsourcing system for obtaining information about at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance; and has a robotic process automation system for loan gathering.
In an embodiment, a lending platform is provided having a crowdsourcing system for obtaining information about at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance; and has a robotic process automation system for merging a set of loans.
In an embodiment, a lending platform is provided having a crowdsourcing system for obtaining information about at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance; and has a robotic process automation system for managing the warranty loan.
In an embodiment, a lending platform is provided having a crowdsourcing system for obtaining information about at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance; and has a robotic process automation system for brokering mortgages.
In an embodiment, a lending platform is provided having a crowdsourcing system for obtaining information about at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance; and has a crowd-sourcing and automatic classification system for verifying the condition of bond issuers.
In an embodiment, a lending platform is provided having a crowdsourcing system for obtaining information about at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance; and has a social network monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having a crowdsourcing system for obtaining information about at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance; and has an internet of things data collection and monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having a crowdsourcing system for obtaining information about at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by the internet of things.
In an embodiment, a lending platform is provided having a crowdsourcing system for obtaining information about at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored in the social network.
In an embodiment, a lending platform is provided having a crowdsourcing system for obtaining information about at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by crowdsourcing.
In an embodiment, a lending platform is provided having a crowdsourcing system for obtaining information about at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance; and has an automated blockchain retention service for managing a set of retention assets.
In an embodiment, a lending platform is provided having a crowdsourcing system for obtaining information about at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance; and has a loan underwriting system with a set of data integration microservices including data collection and monitoring services for underwriting lending entities and transactions, blockchain services, artificial intelligence services, and intelligent contract services.
In an embodiment, a lending platform is provided having a crowdsourcing system for obtaining information about at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance; and has a loan marketing system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for marketing loans to a set of potential parties.
In an embodiment, a lending platform is provided having a crowdsourcing system for obtaining information about at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a lending platform is provided having a crowdsourcing system for obtaining information about at least one of a status of a set of loan mortgages and a status of an entity related to loan assurance; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a lending platform is provided having an intelligent contract that automatically adjusts a lending rate based on at least one of regulatory factors and market factors of a particular jurisdiction; and has intelligent contracts that automatically reorganize debts based on monitored conditions.
In an embodiment, a lending platform is provided having an intelligent contract that automatically adjusts a lending rate based on at least one of regulatory factors and market factors of a particular jurisdiction; and has a social network monitoring system for verifying the reliability of the loan guarantee.
In an embodiment, a lending platform is provided having an intelligent contract that automatically adjusts a lending rate based on at least one of regulatory factors and market factors of a particular jurisdiction; and has an internet of things data collection and monitoring system for verifying the reliability of loan guarantees.
In an embodiment, a lending platform is provided having an intelligent contract that automatically adjusts a lending rate based on at least one of regulatory factors and market factors of a particular jurisdiction; and has a robotic process automation system for negotiating a set of loan terms and conditions.
In an embodiment, a lending platform is provided having an intelligent contract that automatically adjusts a lending rate based on at least one of regulatory factors and market factors of a particular jurisdiction; and has a robotic process automation system for loan gathering.
In an embodiment, a lending platform is provided having an intelligent contract that automatically adjusts a lending rate based on at least one of regulatory factors and market factors of a particular jurisdiction; and has a robotic process automation system for merging a set of loans.
In an embodiment, a lending platform is provided having an intelligent contract that automatically adjusts a lending rate based on at least one of regulatory factors and market factors of a particular jurisdiction; and has a robotic process automation system for managing the warranty loan.
In an embodiment, a lending platform is provided having an intelligent contract that automatically adjusts a lending rate based on at least one of regulatory factors and market factors of a particular jurisdiction; and has a robotic process automation system for brokering mortgages.
In an embodiment, a lending platform is provided having an intelligent contract that automatically adjusts a lending rate based on at least one of regulatory factors and market factors of a particular jurisdiction; and has a crowd-sourcing and automatic classification system for verifying the condition of bond issuers.
In an embodiment, a lending platform is provided having an intelligent contract that automatically adjusts a lending rate based on at least one of regulatory factors and market factors of a particular jurisdiction; and has a social network monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having an intelligent contract that automatically adjusts a lending rate based on at least one of regulatory factors and market factors of a particular jurisdiction; and has an internet of things data collection and monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having an intelligent contract that automatically adjusts a lending rate based on at least one of regulatory factors and market factors of a particular jurisdiction; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by the internet of things.
In an embodiment, a lending platform is provided having an intelligent contract that automatically adjusts a lending rate based on at least one of regulatory factors and market factors of a particular jurisdiction; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored in the social network.
In an embodiment, a lending platform is provided having an intelligent contract that automatically adjusts a lending rate based on at least one of regulatory factors and market factors of a particular jurisdiction; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by crowdsourcing.
In an embodiment, a lending platform is provided having an intelligent contract that automatically adjusts a lending rate based on at least one of regulatory factors and market factors of a particular jurisdiction; and has an automated blockchain retention service for managing a set of retention assets.
In an embodiment, a lending platform is provided having an intelligent contract that automatically adjusts a lending rate based on at least one of regulatory factors and market factors of a particular jurisdiction; and has a loan underwriting system with a set of data integration microservices including data collection and monitoring services for underwriting lending entities and transactions, blockchain services, artificial intelligence services, and intelligent contract services.
In an embodiment, a lending platform is provided having an intelligent contract that automatically adjusts a lending rate based on at least one of regulatory factors and market factors of a particular jurisdiction; and has a loan marketing system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for marketing loans to a set of potential parties.
In an embodiment, a lending platform is provided having an intelligent contract that automatically adjusts a lending rate based on at least one of regulatory factors and market factors of a particular jurisdiction; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a lending platform is provided having an intelligent contract that automatically adjusts a lending rate based on at least one of regulatory factors and market factors of a particular jurisdiction; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a lending platform is provided having an intelligent contract for automatically reorganizing debts based on monitored conditions; and has a social network monitoring system for verifying the reliability of the loan guarantee.
In an embodiment, a lending platform is provided having an intelligent contract for automatically reorganizing debts based on monitored conditions; and has an internet of things data collection and monitoring system for verifying the reliability of loan guarantees.
In an embodiment, a lending platform is provided having an intelligent contract for automatically reorganizing debts based on monitored conditions; and has a robotic process automation system for negotiating a set of loan terms and conditions.
In an embodiment, a lending platform is provided having an intelligent contract for automatically reorganizing debts based on monitored conditions; and has a robotic process automation system for loan gathering.
In an embodiment, a lending platform is provided having an intelligent contract for automatically reorganizing debts based on monitored conditions; and has a robotic process automation system for merging a set of loans.
In an embodiment, a lending platform is provided having an intelligent contract for automatically reorganizing debts based on monitored conditions; and has a robotic process automation system for managing the warranty loan.
In an embodiment, a lending platform is provided having an intelligent contract for automatically reorganizing debts based on monitored conditions; and has a robotic process automation system for brokering mortgages.
In an embodiment, a lending platform is provided having an intelligent contract for automatically reorganizing debts based on monitored conditions; and has a crowd-sourcing and automatic classification system for verifying the condition of bond issuers.
In an embodiment, a lending platform is provided having an intelligent contract for automatically reorganizing debts based on monitored conditions; and has a social network monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having an intelligent contract for automatically reorganizing debts based on monitored conditions; and has an internet of things data collection and monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having an intelligent contract for automatically reorganizing debts based on monitored conditions; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by the internet of things.
In an embodiment, a lending platform is provided with an intelligent contract for automatically reorganizing debts based on monitored conditions; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored in the social network.
In an embodiment, a lending platform is provided having an intelligent contract for automatically reorganizing debts based on monitored conditions; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by crowdsourcing.
In an embodiment, a lending platform is provided with an intelligent contract for automatically reorganizing debts based on monitored conditions; and has an automated blockchain retention service for managing a set of retention assets.
In an embodiment, a lending platform is provided having an intelligent contract for automatically reorganizing debts based on monitored conditions; and has a loan underwriting system with a set of data integration microservices including data collection and monitoring services, block chain services, artificial intelligence services, and intelligent contract services for underwriting lending entities and transactions.
In an embodiment, a lending platform is provided having an intelligent contract for automatically reorganizing debts based on monitored conditions; and has a loan marketing system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for marketing loans to a set of potential parties.
In an embodiment, a lending platform is provided having an intelligent contract for automatically reorganizing debts based on monitored conditions; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a lending platform is provided having an intelligent contract for automatically reorganizing debts based on monitored conditions; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a lending platform is provided having a social network monitoring system for verifying the reliability of a loan guarantee; and has an internet of things data collection and monitoring system for verifying the reliability of loan guarantees.
In an embodiment, a lending platform is provided having a social network monitoring system for verifying the reliability of a loan guarantee; and has a robotic process automation system for negotiating a set of loan terms and conditions.
In an embodiment, a lending platform is provided having a social network monitoring system for verifying the reliability of a loan guarantee; and has a robotic process automation system for loan gathering.
In an embodiment, a lending platform is provided having a social network monitoring system for verifying the reliability of a loan guarantee; and has a robotic process automation system for merging a set of loans.
In an embodiment, a lending platform is provided having a social network monitoring system for verifying the reliability of a loan guarantee; and has a robotic process automation system for managing the warranty loan.
In an embodiment, a lending platform is provided having a social network monitoring system for verifying the reliability of a loan guarantee; and has a robotic process automation system for brokering mortgages.
In an embodiment, a lending platform is provided having a social network monitoring system for verifying the reliability of a loan guarantee; and has a crowd-sourcing and automatic classification system for verifying the condition of bond issuers.
In an embodiment, a lending platform is provided having a social network monitoring system for verifying the reliability of a loan guarantee; and has a social network monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having a social network monitoring system for verifying the reliability of a loan guarantee; and has an internet of things data collection and monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having a social network monitoring system for verifying the reliability of a loan guarantee; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by the internet of things.
In an embodiment, a lending platform is provided having a social network monitoring system for verifying the reliability of a loan guarantee; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored in the social network.
In an embodiment, a lending platform is provided having a social network monitoring system for verifying the reliability of a loan guarantee; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by crowdsourcing.
In an embodiment, a lending platform is provided having a social network monitoring system for verifying the reliability of a loan guarantee; and has an automated blockchain retention service for managing a set of retention assets.
In an embodiment, a lending platform is provided having a social network monitoring system for verifying the reliability of a loan guarantee; and has a loan underwriting system with a set of data integration microservices including data collection and monitoring services for underwriting lending entities and transactions, blockchain services, artificial intelligence services, and intelligent contract services.
In an embodiment, a lending platform is provided having a social network monitoring system for verifying the reliability of a loan guarantee; and has a loan marketing system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for marketing loans to a set of potential parties.
In an embodiment, a lending platform is provided having a social network monitoring system for verifying the reliability of a loan guarantee; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a lending platform is provided having a social network monitoring system for verifying the reliability of a loan guarantee; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a loan platform is provided having an internet of things data collection and monitoring system for verifying the reliability of a loan guarantee; and has a robotic process automation system for negotiating a set of loan terms and conditions.
In an embodiment, a loan platform is provided having an internet of things data collection and monitoring system for verifying the reliability of a loan guarantee; and has a robotic process automation system for loan gathering.
In an embodiment, a loan platform is provided having an internet of things data collection and monitoring system for verifying the reliability of a loan guarantee; and has a robotic process automation system for merging a set of loans.
In an embodiment, a loan platform is provided having an internet of things data collection and monitoring system for verifying the reliability of a loan guarantee; and has a robotic process automation system for managing the warranty loan.
In an embodiment, a loan platform is provided having an internet of things data collection and monitoring system for verifying the reliability of a loan guarantee; and has a robotic process automation system for brokering mortgages.
In an embodiment, a loan platform is provided having an internet of things data collection and monitoring system for verifying the reliability of a loan guarantee; and has a crowd-sourcing and automatic classification system for verifying the condition of bond issuers.
In an embodiment, a loan platform is provided having an internet of things data collection and monitoring system for verifying the reliability of a loan guarantee; and has a social network monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a loan platform is provided having an internet of things data collection and monitoring system for verifying the reliability of a loan guarantee; and has an internet of things data collection and monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a loan platform is provided having an internet of things data collection and monitoring system for verifying the reliability of a loan guarantee; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by the internet of things.
In an embodiment, a loan platform is provided having an internet of things data collection and monitoring system for verifying the reliability of a loan guarantee; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored in the social network.
In an embodiment, a loan platform is provided having an internet of things data collection and monitoring system for verifying the reliability of a loan guarantee; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by crowdsourcing.
In an embodiment, a loan platform is provided having an internet of things data collection and monitoring system for verifying the reliability of a loan guarantee; and has an automated blockchain retention service for managing a set of retention assets.
In an embodiment, a loan platform is provided having an internet of things data collection and monitoring system for verifying the reliability of a loan guarantee; and has a loan underwriting system with a set of data integration microservices including data collection and monitoring services for underwriting lending entities and transactions, blockchain services, artificial intelligence services, and intelligent contract services.
In an embodiment, a lending platform is provided with an internet of things data collection and monitoring system for verifying loan assurance reliability; and has a loan marketing system with a set of data integration microservices including a data collection and monitoring service, a block chain service, an artificial intelligence service, and an intelligent contract service for marketing loans to a set of potential parties.
In an embodiment, a loan platform is provided having an internet of things data collection and monitoring system for verifying the reliability of a loan guarantee; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a lending platform is provided with an internet of things data collection and monitoring system for verifying loan assurance reliability; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a lending platform is provided having a robotic process automation system for negotiating a set of loan terms and conditions; and has a robotic process automation system for loan gathering.
In an embodiment, a lending platform is provided having a robotic process automation system for negotiating a set of loan terms and conditions; and has a robotic process automation system for merging a set of loans.
In an embodiment, a lending platform is provided having a robotic process automation system for negotiating a set of loan terms and conditions; and has a robotic process automation system for managing the warranty loan.
In an embodiment, a lending platform is provided having a robotic process automation system for negotiating a set of loan terms and conditions; and has a robotic process automation system for brokering mortgages.
In an embodiment, a lending platform is provided having a robotic process automation system for negotiating a set of loan terms and conditions; and has a crowd-sourcing and automatic classification system for verifying the condition of bond issuers.
In an embodiment, a lending platform is provided having a robotic process automation system for negotiating a set of loan terms and conditions; and has a social network monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having a robotic process automation system for negotiating a set of loan terms and conditions; and has an internet of things data collection and monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having a robotic process automation system for negotiating a set of loan terms and conditions; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by the internet of things.
In an embodiment, a lending platform is provided having a robotic process automation system for negotiating a set of loan terms and conditions; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored in the social network.
In an embodiment, a lending platform is provided having a robotic process automation system for negotiating a set of loan terms and conditions; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by crowdsourcing.
In an embodiment, a lending platform is provided having a robotic process automation system for negotiating a set of loan terms and conditions; and has an automated blockchain retention service for managing a set of retention assets.
In an embodiment, a lending platform is provided having a robotic process automation system for negotiating a set of loan terms and conditions; and has a loan underwriting system with a set of data integration microservices including data collection and monitoring services for underwriting lending entities and transactions, blockchain services, artificial intelligence services, and intelligent contract services.
In an embodiment, a lending platform is provided having a robotic process automation system for negotiating a set of loan terms and conditions; and has a loan marketing system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for marketing loans to a set of potential parties.
In an embodiment, a lending platform is provided having a robotic process automation system for negotiating a set of loan terms and conditions; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a lending platform is provided having a robotic process automation system for negotiating a set of loan terms and conditions; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a lending platform is provided having a robotic process automation system for loan collection; and has a robotic process automation system for merging a set of loans.
In an embodiment, a lending platform is provided having a robotic process automation system for loan collection; and has a robotic process automation system for managing the warranty loan.
In an embodiment, a lending platform is provided having a robotic process automation system for loan collection; and has a robotic process automation system for brokering mortgages.
In an embodiment, a lending platform is provided having a robotic process automation system for loan collection; and has a crowd-sourcing and automatic classification system for verifying the condition of bond issuers.
In an embodiment, a lending platform is provided having a robotic process automation system for loan collection; and has a social network monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having a robotic process automation system for loan collection; and has an internet of things data collection and monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having a robotic process automation system for loan collection; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by the internet of things.
In an embodiment, a lending platform is provided having a robotic process automation system for loan collection; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored in the social network.
In an embodiment, a lending platform is provided having a robotic process automation system for loan collection; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by crowdsourcing.
In an embodiment, a lending platform is provided having a robotic process automation system for loan collection; and has an automated blockchain retention service for managing a set of retention assets.
In an embodiment, a lending platform is provided having a robotic process automation system for loan collection; and has a loan underwriting system with a set of data integration microservices including data collection and monitoring services for underwriting lending entities and transactions, blockchain services, artificial intelligence services, and intelligent contract services.
In an embodiment, a lending platform is provided having a robotic process automation system for loan collection; and has a loan marketing system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for marketing loans to a set of potential parties.
In an embodiment, a lending platform is provided having a robotic process automation system for loan collection; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a lending platform is provided having a robotic process automation system for loan collection; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a lending platform is provided having a robotic process automation system for merging a set of loans; and has a robotic process automation system for managing the warranty loan.
In an embodiment, a lending platform is provided having a robotic process automation system for merging a set of loans; and has a robotic process automation system for brokering mortgages.
In an embodiment, a lending platform is provided having a robotic process automation system for merging a set of loans; and has a crowdsourcing and automatic classification system for verifying the condition of bond issuers.
In an embodiment, a lending platform is provided having a robotic process automation system for merging a set of loans; and has a social network monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having a robotic process automation system for merging a set of loans; and has an internet of things data collection and monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having a robotic process automation system for merging a set of loans; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by the internet of things.
In an embodiment, a lending platform is provided having a robotic process automation system for merging a set of loans; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored in the social network.
In an embodiment, a lending platform is provided having a robotic process automation system for merging a set of loans; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by crowdsourcing.
In an embodiment, a lending platform is provided having a robotic process automation system for merging a set of loans; and has an automated blockchain retention service for managing a set of retention assets.
In an embodiment, a lending platform is provided having a robotic process automation system for merging a set of loans; and has a loan underwriting system with a set of data integration microservices including data collection and monitoring services for underwriting lending entities and transactions, blockchain services, artificial intelligence services, and intelligent contract services.
In an embodiment, a lending platform is provided having a robotic process automation system for merging a set of loans; and has a loan marketing system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for marketing loans to a set of potential parties.
In an embodiment, a lending platform is provided having a robotic process automation system for merging a set of loans; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a lending platform is provided having a robotic process automation system for merging a set of loans; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a lending platform is provided having a robotic process automation system for managing a warranty loan; and has a robotic process automation system for brokering mortgages.
In an embodiment, a lending platform is provided having a robotic process automation system for managing a warranty loan; and has a crowd-sourcing and automatic classification system for verifying the condition of bond issuers.
In an embodiment, a lending platform is provided having a robotic process automation system for managing a warranty loan; and has a social network monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having a robotic process automation system for managing a warranty loan; and has an internet of things data collection and monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having a robotic process automation system for managing a warranty loan; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by the internet of things.
In an embodiment, a lending platform is provided having a robotic process automation system for managing a warranty loan; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored in the social network.
In an embodiment, a lending platform is provided having a robotic process automation system for managing a warranty loan; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by crowdsourcing.
In an embodiment, a lending platform is provided having a robotic process automation system for managing a warranty loan; and has an automated blockchain retention service for managing a set of retention assets.
In an embodiment, a lending platform is provided having a robotic process automation system for managing a warranty loan; and has a loan underwriting system with a set of data integration microservices including data collection and monitoring services for underwriting lending entities and transactions, blockchain services, artificial intelligence services, and intelligent contract services.
In an embodiment, a lending platform is provided having a robotic process automation system for managing a warranty loan; and has a loan marketing system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for marketing loans to a set of potential parties.
In an embodiment, a lending platform is provided having a robotic process automation system for managing a warranty loan; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a lending platform is provided having a robotic process automation system for managing a warranty loan; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a lending platform is provided having a robotic process automation system for brokering mortgage loans; and has a crowd-sourcing and automatic classification system for verifying the condition of bond issuers.
In an embodiment, a lending platform is provided having a robotic process automation system for brokering mortgage loans; and has a social network monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having a robotic process automation system for brokering mortgage loans; and has an internet of things data collection and monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having a robotic process automation system for brokering mortgage loans; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by the internet of things.
In an embodiment, a lending platform is provided having a robotic process automation system for brokering mortgage loans; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored in the social network.
In an embodiment, a lending platform is provided having a robotic process automation system for brokering mortgage loans; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by crowdsourcing.
In an embodiment, a lending platform is provided having a robotic process automation system for brokering mortgage loans; and has an automated blockchain retention service for managing a set of retention assets.
In an embodiment, a lending platform is provided having a robotic process automation system for brokering mortgage loans; and has a loan underwriting system with a set of data integration microservices including data collection and monitoring services for underwriting lending entities and transactions, blockchain services, artificial intelligence services, and intelligent contract services.
In an embodiment, a lending platform is provided having a robotic process automation system for brokering mortgage loans; and has a loan marketing system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for marketing loans to a set of potential parties.
In an embodiment, a lending platform is provided having a robotic process automation system for brokering mortgage loans; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a lending platform is provided having a robotic process automation system for brokering mortgage loans; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a lending platform is provided having a crowd sourcing and automatic classification system for verifying the condition of a bond issuer; and has a social network monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having a crowd sourcing and automatic classification system for verifying the condition of a bond issuer; and has an internet of things data collection and monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having a crowd sourcing and automatic classification system for verifying the condition of a bond issuer; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by the internet of things.
In an embodiment, a lending platform is provided having a crowd sourcing and automatic classification system for verifying the condition of a bond issuer; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored in the social network.
In an embodiment, a lending platform is provided having a crowd sourcing and automatic classification system for verifying the condition of a bond issuer; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by crowdsourcing.
In an embodiment, a lending platform is provided having a crowd sourcing and automatic classification system for verifying the condition of a bond issuer; and has an automated blockchain retention service for managing a set of retention assets.
In an embodiment, a lending platform is provided having a crowd sourcing and automatic classification system for verifying the condition of a bond issuer; and has a loan underwriting system with a set of data integration microservices including data collection and monitoring services for underwriting lending entities and transactions, blockchain services, artificial intelligence services, and intelligent contract services.
In an embodiment, a lending platform is provided having a crowd sourcing and automatic classification system for verifying the condition of a bond issuer; and has a loan marketing system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for marketing loans to a set of potential parties.
In an embodiment, a lending platform is provided having a crowd sourcing and automatic classification system for verifying the condition of a bond issuer; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a lending platform is provided having a crowd sourcing and automatic classification system for verifying the condition of a bond issuer; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a lending platform is provided having a social network monitoring system employing artificial intelligence for classifying a condition of a bond; and has an internet of things data collection and monitoring system employing artificial intelligence for classifying the condition of the bond.
In an embodiment, a lending platform is provided having a social network monitoring system employing artificial intelligence for classifying a condition of a bond; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by the internet of things.
In an embodiment, a lending platform is provided having a social network monitoring system employing artificial intelligence for classifying a condition of a bond; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored in the social network.
In an embodiment, a lending platform is provided having a social network monitoring system employing artificial intelligence for classifying a condition of a bond; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by crowdsourcing.
In an embodiment, a lending platform is provided having a social network monitoring system employing artificial intelligence for classifying a condition of a bond; and has an automated blockchain retention service for managing a set of retention assets.
In an embodiment, a lending platform is provided having a social network monitoring system employing artificial intelligence for classifying a condition of a bond; and has a loan underwriting system with a set of data integration microservices including data collection and monitoring services for underwriting lending entities and transactions, blockchain services, artificial intelligence services, and intelligent contract services.
In an embodiment, a lending platform is provided having a social network monitoring system employing artificial intelligence for classifying a condition of a bond; and has a loan marketing system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for marketing loans to a set of potential parties.
In an embodiment, a lending platform is provided having a social network monitoring system employing artificial intelligence for classifying a condition of a bond; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a lending platform is provided having a social network monitoring system employing artificial intelligence for classifying a condition of a bond; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a lending platform is provided having an internet of things data collection and monitoring system employing artificial intelligence for classifying a condition of a bond; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by the internet of things.
In an embodiment, a lending platform is provided having an internet of things data collection and monitoring system employing artificial intelligence for classifying a condition of a bond; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored in the social network.
In an embodiment, a lending platform is provided having an internet of things data collection and monitoring system employing artificial intelligence for classifying a condition of a bond; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by crowdsourcing.
In an embodiment, a lending platform is provided having an internet of things data collection and monitoring system employing artificial intelligence for classifying a condition of a bond; and has an automated blockchain retention service for managing a set of retention assets.
In an embodiment, a lending platform is provided having an internet of things data collection and monitoring system employing artificial intelligence for classifying a condition of a bond; and has a loan underwriting system with a set of data integration microservices including data collection and monitoring services for underwriting lending entities and transactions, blockchain services, artificial intelligence services, and intelligent contract services.
In an embodiment, a lending platform is provided having an internet of things data collection and monitoring system employing artificial intelligence for classifying a condition of a bond; and has a loan marketing system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for marketing loans to a set of potential parties.
In an embodiment, a lending platform is provided having an internet of things data collection and monitoring system employing artificial intelligence for classifying a condition of a bond; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a lending platform is provided having an internet of things data collection and monitoring system employing artificial intelligence for classifying a condition of a bond; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a lending platform is provided having a system for altering terms and conditions of a subsidized loan based on parameters monitored by the internet of things; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored in the social network.
In an embodiment, a lending platform is provided having a system for altering terms and conditions of a subsidized loan based on parameters monitored by the internet of things; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by crowdsourcing.
In an embodiment, a lending platform is provided having a system for altering terms and conditions of a subsidized loan based on parameters monitored by the internet of things; and has an automated blockchain retention service for managing a set of retention assets.
In an embodiment, a lending platform is provided having a system for altering terms and conditions of a subsidized loan based on parameters monitored by the internet of things; and has a loan underwriting system with a set of data integration microservices including data collection and monitoring services for underwriting lending entities and transactions, blockchain services, artificial intelligence services, and intelligent contract services.
In an embodiment, a lending platform is provided having a system for altering terms and conditions of a subsidized loan based on parameters monitored by the internet of things; and has a loan marketing system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for marketing loans to a set of potential parties.
In an embodiment, a lending platform is provided having a system for altering terms and conditions of a subsidized loan based on parameters monitored by the internet of things; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a lending platform is provided having a system for altering terms and conditions of a subsidized loan based on parameters monitored by the internet of things; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a lending platform is provided having a system for altering terms and conditions of a subsidized loan based on parameters monitored in a social network; and has a system for changing the terms and conditions of the subsidized loan based on parameters monitored by crowdsourcing.
In an embodiment, a lending platform is provided having a system for altering terms and conditions of a subsidized loan based on parameters monitored in a social network; and has an automated blockchain retention service for managing a set of retention assets.
In an embodiment, a lending platform is provided having a system for altering terms and conditions of a subsidized loan based on parameters monitored in a social network; and has a loan underwriting system with a set of data integration microservices including data collection and monitoring services for underwriting lending entities and transactions, blockchain services, artificial intelligence services, and intelligent contract services.
In an embodiment, a lending platform is provided having a system for altering terms and conditions of a subsidized loan based on parameters monitored in a social network; and has a loan marketing system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for marketing loans to a set of potential parties.
In an embodiment, a lending platform is provided having a system for altering terms and conditions of a subsidized loan based on parameters monitored in a social network; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a lending platform is provided having a system for altering terms and conditions of a subsidized loan based on parameters monitored in a social network; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a lending platform is provided having a system for altering terms and conditions of a subsidized loan based on parameters monitored by crowd sourcing; and has an automated blockchain retention service for managing a set of retention assets.
In an embodiment, a lending platform is provided having a system for altering terms and conditions of a subsidized loan based on parameters monitored by crowd sourcing; and has a loan underwriting system with a set of data integration microservices including data collection and monitoring services for underwriting lending entities and transactions, blockchain services, artificial intelligence services, and intelligent contract services.
In an embodiment, a lending platform is provided having a system for altering terms and conditions of a subsidized loan based on parameters monitored by crowd sourcing; and has a loan marketing system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for marketing loans to a set of potential parties.
In an embodiment, a lending platform is provided having a system for altering terms and conditions of a subsidized loan based on parameters monitored by crowd sourcing; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a lending platform is provided having a system for altering terms and conditions of a subsidized loan based on parameters monitored by crowd sourcing; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a loan platform is provided having an automated blockchain retention service for managing a set of retention assets; and has a loan underwriting system with a set of data integration microservices including data collection and monitoring services for underwriting lending entities and transactions, blockchain services, artificial intelligence services, and intelligent contract services.
In an embodiment, a loan platform is provided having an automated blockchain retention service for managing a set of retention assets; and has a loan marketing system with a set of data integration microservices including a data collection and monitoring service, a block chain service, an artificial intelligence service, and an intelligent contract service for marketing loans to a set of potential parties.
In an embodiment, a loan platform is provided having an automated blockchain retention service for managing a set of retention assets; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a loan platform is provided having an automated blockchain retention service for managing a set of retention assets; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a lending platform is provided with a loan underwriting system having a set of data integration microservices including data collection and monitoring services, blockchain services, artificial intelligence services, and intelligent contract services for underwriting entities and transactions; and has a loan marketing system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for marketing loans to a set of potential parties.
In an embodiment, a lending platform is provided with a loan underwriting system having a set of data integration microservices including data collection and monitoring services, blockchain services, artificial intelligence services, and intelligent contract services for underwriting entities and transactions; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a lending platform is provided with a loan underwriting system having a set of data integration microservices including data collection and monitoring services, blockchain services, artificial intelligence services, and intelligent contract services for underwriting entities and transactions; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a loan platform is provided having a loan marketing system with a set of data integration microservices including a data collection and monitoring service for marketing loans to a set of potential parties, a blockchain service, an artificial intelligence service, and an intelligent contract service; and has a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a block chain service, an artificial intelligence service, and an intelligent contract service.
In an embodiment, a loan platform is provided having a loan marketing system with a set of data integration microservices including a data collection and monitoring service for marketing loans to a set of potential parties, a blockchain service, an artificial intelligence service, and an intelligent contract service; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a lending platform is provided having a rating system with a set of data integration microservices including a data collection and monitoring service for rating a set of loan-related entities, a blockchain service, an artificial intelligence service, and an intelligent contracts service; and having a compliance system with a set of data integration microservices including a data collection and monitoring service, a blockchain service, an artificial intelligence service, and an intelligent contract service for automatically facilitating compliance with at least one of laws, regulations, and policies related to the loan transaction.
In an embodiment, a database service may be provided that embodies, enables or is associated with a blockchain, ledger (e.g., a distributed ledger, etc.), such as in connection with any embodiment described herein or any embodiment incorporated by reference in a document. In the examples, theThe database service may include a transparent, immutable, cryptographically verifiable ledger database service, such as Amazon TM QLDB TM A database service. The database service may be included in or connected to one or more layers or microservices of the loan support platform 100, such as the adaptive intelligence system 158 layer or the data store layer 168. For example, the service may be used in conjunction with a centralized ledger that records all changes or transactions and maintains an immutable record of those changes, such as by various environmental or process tracking entities, tracking loan histories over a series of transactions, or verifying facts related to underwriting processes, claims, or legal or regulatory procedures. The ledger may be owned by a single trusted entity or a group of trusted entities and may be shared with any other entity (e.g., an entity that collaborates in the coordination of transactions, production processes, federated services, etc.). In contrast to relational databases, the database service may provide immutable, cryptographically verifiable ledger entries without the need for custom audit tables or trace records. Such database services may include the ability to perform queries, create tables, index data, and the like, as compared to blockchain frameworks. The database service may selectively ignore requirements for many blockchain frameworks that degrade performance, such as consistency requirements before submitting a transaction, or the database service may employ an optional consistency feature. In an embodiment, the database service may include a transparent, immutable, cryptographically verifiable ledger that a user can use to build an application that functions as a logging system in which multiple parties conduct transaction processing within a centralized trusted entity or group of entities. The database service may supplement or replace building audit functionality into relational databases or using conventional distributed ledger capabilities in a blockchain framework. The database service may use an immutable transaction log that can track all application data changes and maintain a comprehensive and verifiable change history. In embodiments, the transaction may be configured to comply with atomicity, consistency, isolation, and persistence (ACID) requirements to be recorded in a log configured to prevent deletion or repair And (5) changing. Changes may be linked in an encrypted manner such that the changes are auditable and verifiable, for example, in a history that a user may query or analyze, such as with a conventional query type such as an SQL query. In embodiments, the database service may be provided in a serverless form, and thus, need not provide specific server capacity or configure read/write limitations. To launch the database service, which will automatically expand to support application requirements, a user may create a ledger, a definition table, and the like. Compared to a blockchain based ledger, the database service can ignore the requirement for distributed consistency, and thus can perform more transactions simultaneously.
In embodiments of the present disclosure involving blockchains or distributed ledgers, a persistent blockchain service may be used, such as Amazon TM Custodial Blockchain TM Which may include facilities for conveniently creating and managing extended blockchain networks. The captive blockchain service may be provided as part of a hierarchical data services architecture described in this disclosure. Where users require immutable, verifiable capabilities provided by blockchains or ledgers, they may also seek the ability to allow multiple parties to conduct transaction processing, execute contracts (such as in the intelligent contract embodiments described herein), share data, etc. without a trusted central authority. Because of the significant amount of time and technical expertise required to build a traditional blockchain framework, each participant in a licensed network must provide hardware, install software, create and manage access control credentials, configure network settings. As a given blockchain application grows, some activities are also required to expand the network, monitor resources at blockchain nodes, add or delete hardware, and manage network availability. In an embodiment, a custody blockchain service may provide management of each of these requirements and enablement capabilities. This may include supporting an open source blockchain framework and enabling selection, setup, and deployment of selected frameworks in a control panel, console, or other user interface, where users may select their preferred frameworks, add network members, and configure member nodes that will process transaction requests. The above-mentioned The protection blockchain service may automatically create a blockchain network (e.g., a blockchain network that may have multiple accounts with multiple nodes across each member) and configure software, security, and network settings. The security module chaining service may protect and manage network credentials, for example, through a key management service, so that a customer may manage keys. In embodiments, the hosting block chain service may include one or more APIs, such as voting APIs, for example, voting APIs that allow members of the network to vote (e.g., vote to add or delete members). As the application usage of a given application (e.g., any of the applications described in conjunction with loan support platform 100) grows, users can add more capacity to the blockchain network, such as through simple API calls. In an embodiment, the persistent blockchain service may have a range of combinations of computing and memory capacity, for example, to enable a user to select the correct combination of resources for a given application based on the blockchain.
Referring to fig. 4-31, in embodiments of the present disclosure, including embodiments involving artificial intelligence 156, adaptive intelligence systems 158, robotic process automation 154, expert systems, self-organization, machine learning, model training, and the like, may benefit from using neural networks, e.g., training neural networks for pattern recognition, for prediction, for optimization based on a set of desired outcomes, for classification or recognition of one or more parameters, features, or phenomena, for supporting autonomous control, and other purposes. References throughout this disclosure to artificial intelligence, expert systems, models, adaptive intelligence, and/or neural networks should be understood to optionally include the use of various different types of neural networks, machine learning systems, artificial intelligence systems, etc. as particular embodiments allow, such as feed-forward neural networks, radial basis function neural networks, self-organizing neural networks (e.g., kohonen self-organizing neural networks), recurrent neural networks, modular neural networks, artificial neural networks, physical neural networks, multi-layer neural networks, convolutional neural networks, hybrids of neural networks with other expert systems (e.g., hybrid fuzzy logic-neural network systems), self-encoding neural networks, probabilistic neural networks, time-lag neural networks, convolutional neural networks, regulatory-feedback neural networks, radial basis function neural networks, recurrent neural networks, hopfield neural networks, boltzmann machine neural networks, self-organizing map (SOM) neural networks, learning Vector Quantization (LVQ) neural networks, total recurrent neural networks, simple recurrent neural networks, echo state neural networks, long-term short-term memory neural networks, bidirectional neural networks, hierarchical neural networks, stochastic neural networks, genetic scale RNN neural networks, machine neural networks, associative neural networks, physical neural networks, transient training neural networks, spike neural networks, new cognitive neural networks, dynamic neural networks, gcs, cascaded neural networks, fuzzy neural networks, time-gated neural networks, u-gated neural networks, recursive neural networks, and neural networks, A variational autoencoder neural network, a denoise autoencoder neural network, a sparse autoencoder neural network, a Markov chain neural network, a constrained Boltzmann machine neural network, a deep belief neural network, a deep convolutional neural network, a deconvolution neural network, a deep convolutional inverse graph neural network, a generative countermeasure neural network, a liquid machine neural network, an extreme learning machine neural network, an echo state neural network, a deep residual error neural network, a support vector machine neural network, a neuro-machine neural network, and/or a holographic associative memory neural network, or a mixture or combination of the aforementioned neural networks, or a combination with other expert systems, such as rule-based systems, model-based systems (including systems based on physical models, statistical models, flow-based models, biological models, biomimetic models, and the like).
The aforementioned neural networks may have various nodes or neurons that may perform various functions upon input, such as input received from sensors or other data sources (including other nodes). The functions may relate to weights, features, feature vectors, and the like. Neurons may include sensors, neurons that mimic biological functions (e.g., human touch, vision, taste, hearing, and smell), and the like. Successive neurons (e.g., with S-type activation) can be used in the context of various forms of neural networks, such as situations involving back propagation.
In many embodiments, the expert system or neural network may be trained, for example, by a human operator or supervisor, or based on a data set, model, or the like. Training may include presenting one or more training data sets representing values to a neural network, such as sensor data, event data, parameter data, and other types of data (including many of the types described in this disclosure), as well as one or more outcome indicators, such as results of a process, results of a calculation, results of an event, results of an activity, and so forth. Training may include optimization training, such as training a neural network to optimize one or more systems based on one or more optimization methods, such as bayesian methods, parametric bayesian classifier methods, k-nearest neighbor classifier methods, iterative methods, interpolation methods, pareto optimization methods, algorithmic methods, and the like. Feedback may be provided during the course of variation and selection, for example using a genetic algorithm that evolves one or more solutions based on feedback through a series of rounds.
In embodiments, a plurality of neural networks may be deployed in a cloud platform that receives data streams and other inputs collected in one or more transaction environments (e.g., collected by a mobile data collector) and sent to the cloud platform over one or more networks (including using network coding to provide efficient transmission). In a cloud platform, a number of different types of neural networks (including modular, architecture adaptive, hybrid, etc.) can be used to undertake prediction, classification, control functions, and provide other outputs related to the expert system disclosed in this disclosure, optionally using massively parallel computing power. The different neural networks may be configured to compete with each other (optionally including the use of evolutionary algorithms, genetic algorithms, etc.) such that, for example, an appropriate type of neural network with an appropriate set of inputs, weights, node types and functions, etc., may be selected by the expert system for use in a given context, workflow, environmental process, particular task involved in the system, etc.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a feed forward neural network that moves information in one direction through a series of neurons or nodes to an output, such as from a data input (e.g., a data source associated with at least one resource or a parameter associated with a trading environment) or any data source mentioned in this disclosure. Data may be moved from an input node to an output node, optionally through one or more hidden nodes, without looping. In embodiments, the feed-forward neural network may be constructed with various types of cells (e.g., binary McCulloch-buttons neurons, the simplest of which is a perceptron).
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a capsule neural network, for example, for predictive, categorical, or control functions relating to a transaction environment, for example, relating to one or more of the machines and automated systems described in the present disclosure.
In embodiments, the methods and systems described herein relating to expert systems or self-organizing capabilities may use Radial Basis Function (RBF) neural networks, which may be preferred in some cases involving interpolation in multidimensional spaces (e.g., where interpolation helps to optimize multidimensional functions, such as for optimizing data markets described herein, optimizing efficiency or output of power generation systems, plant systems, etc., or other cases involving multiple dimensions.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use Radial Basis Function (RBF) neural networks, such as neural networks that employ a distance criterion (e.g., a gaussian function) with respect to a center. In a multilayer perceptron radial basis functions may be applied as a replacement for hidden layers, e.g. S-shaped hidden layer transitions. The RBF network may have two layers, for example, where the input is mapped onto each RBF in the hidden layer. In an embodiment, the output layer may comprise a linear combination of hidden layer values, which represents, for example, an average prediction output. The output tier values may provide the same or similar output as the output of the regression model in the statistics. In the classification problem, the output layer may be a sigmoid function of a linear combination of hidden layer values, representing a posterior probability. The performance in both cases is typically improved by a shrinkage technique (e.g., ridge regression in classical statistics). This corresponds to a priori belief in the bayesian framework for small parameter values (and hence smooth output functions). The RBF network can avoid local minima because the only parameter adjusted in the learning process is the linear mapping from the hidden layer to the output layer. Linearity ensures that the error surface is quadratic and therefore has a single minimum. In the regression problem, this can be found in a matrix operation. In the classification problem, an iterative reweighted least squares function or the like may be used to handle the fixed non-linearity introduced by the sigmoid output function.
The RBF network may use kernel methods such as Support Vector Machines (SVMs) and gaussian processes (where RBFs are kernel functions). The input data may be projected using a non-linear kernel function into a space where the learning problem can be solved using a linear model.
In an embodiment, the RBF neural network may include an input layer, a hidden layer, and a summation layer. In the input layer, each predictor variable appears as a neuron in the input layer. In the case of categorical variables, N-1 neurons are used, where N is the number of categories. In an embodiment, the input neurons may normalize the range of values by subtracting the median and dividing by the interquartile range. The input neuron may then feed back a value to each neuron in the hidden layer. A variable number of neurons (determined by the training process) may be used in the hidden layer. Each neuron may consist of a radial basis function centered around a point having as many dimensions as there are predictor variables. The extent (e.g., radius) of the RBF function may be different for each dimension. The center and the spread may be determined by training. When presenting a vector of input values from the input layer, the hidden neuron may compute the euclidean distance of the test case from the neuron's center point and then apply the RBF kernel to that distance, e.g., using the extension values. The resulting value may then be passed to a summing layer. In the summation layer, values from neurons in the hidden layer may be multiplied by weights associated with the neurons, and may be added to weighted values of other neurons. This sum becomes the output. For the classification problem, one output is generated for each target class (with separate weight sets and summing units). The value output for a category is the probability that the situation being evaluated has that category. In the training of the RBF, various parameters may be determined, such as the number of neurons in the hidden layers, the coordinates of the center of each hidden layer function, the spread of each function in each dimension, and the weights applied to the output as they are passed to the summing layer. Training may be used by clustering algorithms (e.g., k-means clustering), by evolutionary methods, and the like.
In an embodiment, the recurrent neural network may have time-varying real-valued (not just 0 or 1) activations (outputs). Each connection may have a modifiable real-valued weight. Some nodes are referred to as marker nodes, some output nodes, and other hidden nodes. For supervised learning in discrete time settings, the training sequence of real valued input vectors may become the activation sequence of input nodes, one input vector at a time. At each time step, each non-input cell may compute its current activation as a non-linear function of the weighted sum of the activations of all the cells it receives the connection. The system may explicitly activate (independently of the input signal) certain output units at certain time steps.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use ad hoc neural networks, such as Kohonen ad hoc neural networks, for example, for visualization of data views, such as low dimensional views as high dimensional data. The ad hoc neural network may apply competitive learning to a set of input data, such as from one or more sensors or other data input from or associated with a transaction environment, including any machine or component associated with the transaction environment. In an embodiment, the ad-hoc neural network may be used to identify structures in data, such as unlabeled data, such as data sensed from a series of data sources or sensors in a transaction environment, where the data sources are unknown (e.g., an event may come from any of a series of unknown sources). The ad-hoc neural network may organize structures or patterns in the data such that they may be identified, analyzed, and labeled, such as identifying market behavior structures as corresponding to other events and signals.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a recurrent neural network, which may allow for bidirectional flow of data, for example where connected units (e.g., neurons or nodes) form a directed loop. Such networks may be used to model or present dynamic temporal behavior, e.g., relating to dynamic temporal behavior in dynamic systems, such as the various automated systems, machines, and devices described in this disclosure, e.g., automated agents interacting with a market for the purpose of collecting data, testing spot market transactions, executing transactions, etc., where dynamic system behavior relates to complex interactions that a user may wish to understand, predict, control, and/or optimize. For example, a recurrent neural network may be used to predict market states, e.g., market states that involve dynamic processes or actions, e.g., state changes of resources that train or implement a trading environment market in the trading environment market. In embodiments, the recurrent neural network may use internal memory to process various types of input sequences described herein, such as from other nodes and/or from sensors or other data inputs provided by or related to the transaction environment. In embodiments, the recurrent neural network may also be used for pattern recognition, e.g., to identify a machine, component, agent, or other item based on a behavioral signature, a profile, a set of feature vectors (e.g., in an audio file or image), and so forth. In a non-limiting example, the recurrent neural network may identify transitions in the operating mode of the market or machine by learning to classify transitions from a training data set that includes data streams from one or more data sources of sensors applied to or related to one or more resources.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a modular neural network, which may include a series of independent neural networks (e.g., neural networks of the various types described herein) that are adapted by an intermediary. Each individual neural network in the modular neural network may work with a separate input to accomplish a subtask that constitutes a task to be performed by the entire modular network. For example, the modular neural network may include a recurrent neural network for pattern recognition, such as an RBF neural network that identifies what type of machine or system one or more sensors provided as input channels to the modular network are sensing and for optimizing the behavior of the machine or system once understood. The intermediary may accept inputs for each individual neural network, process them, and create outputs for the modular neural network, such as appropriate control parameters, condition predictions, and the like.
Combinations between any two, three, or more of the various neural network types described herein are encompassed in this disclosure. This may include a combination where the expert system uses one neural network for identifying patterns (e.g., patterns indicative of problem or fault conditions) and a different neural network for self-organizing activities or workflows based on the identified patterns (e.g., providing output for managing system autonomous control in response to the identified conditions or patterns). This may also include a combination where the expert system uses one neural network for classifying the project (e.g., identifying a machine, component, or mode of operation) and a different neural network for predicting a condition of the project (e.g., a fault condition, an operating condition, an expected condition, a maintenance condition, etc.). The modular neural network may also include situations where the expert system uses one neural network for determining a condition or context (e.g., a condition of a machine, a process, a workflow, a market, a storage system, a network, a data collector, etc.) and one different neural network for self-organizing processes related to the condition or context (e.g., a data storage process, a network encoding process, a network selection process, a data market process, a power generation process, a manufacturing process, a refining process, a mining process, a boring process, or other processes described herein).
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a physical neural network in which one or more hardware elements are used to perform or simulate neural behavior. In an embodiment, one or more hardware neurons may be used to stream voltage values, current values, etc. representing sensor data, for example by computing information from analog sensor inputs representing energy consumption, energy production, etc. through one or more machines providing or consuming energy for one or more transactions. One or more hardware nodes may be used to stream output data generated by the activity of the neural network. Hardware nodes may include one or more chips, microprocessors, integrated circuits, programmable logic controllers, application specific integrated circuits, field programmable gate arrays, etc., which may be used to optimize a machine that is generating or consuming energy, or to optimize another parameter of some portion of any type of neural network described herein. The hardware nodes may include hardware for accelerating computations (e.g., a dedicated processor for performing basic or more complex computations on input data to provide output, a dedicated processor for filtering or compressing data, a dedicated processor for decompressing data, a dedicated processor for compressing a particular file or data type (e.g., for processing image data, video streams, acoustic signals, thermal images, etc.). The physical neural network may be embodied in a data collector, including a data collector that may be reconfigured by switching or routing inputs in varying configurations, e.g., different neural network configurations are provided within the data collector for handling different types of inputs (with switching and configurations optionally under control of an expert system, which may include a software-based neural network located on or remote from the data collector). The physical or at least partially physical neural network may comprise physical hardware nodes located in a storage system, for example, for storing data in a machine, data storage system, distributed ledger, mobile device, server, cloud resource, or transaction processing environment, for example, to accelerate input/output functions of one or more storage elements providing data to or retrieving data from the neural network. The physical or at least partially physical neural network may comprise physical hardware nodes located in the network, e.g. for transmitting data within, to or from the industrial environment, e.g. for accelerating input/output functions of one or more network nodes in the network, accelerating relay functions, etc. In an embodiment of a physical neural network, electrically tunable resistive material may be used to mimic the function of a neurosynaptic. In an embodiment, the physical hardware simulates neurons and the software simulates neural networks between the neurons. In an embodiment, the neural network supplements a conventional algorithm computer. They are versatile and can be trained to perform appropriate functions, such as classification functions, optimization functions, pattern recognition functions, control functions, selection functions, evaluation functions, etc., without requiring any instructions.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use multi-layer feed-forward neural networks, such as complex pattern classification for one or more items, phenomena, patterns, conditions, and the like. In embodiments, the multi-layer feed-forward neural network may be trained by optimization techniques such as genetic algorithms, for example, exploring large and complex option spaces to find an optimal or near optimal global solution. For example, one or more genetic algorithms may be used to train a multi-layer feed-forward neural network to classify complex phenomena, such as to identify complex operating modes of the machines, such as modes involving complex interactions between machines (including interference effects, resonance effects, etc.), modes involving non-linear phenomena, modes involving critical faults, such as in the case of multiple faults occurring simultaneously, making it difficult to analyze root causes, etc. In an embodiment, a multi-layer feed-forward neural network may be used to classify results from market monitoring, including, for example, monitoring systems operating within the market, such as automated agents, and monitoring resources that implement the market, such as computing, networking, energy, data storage, energy storage, and other resources.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use feed-forward, back-propagation multi-layer perceptive (MLP) neural networks, e.g., for processing one or more telemetry applications, e.g., for taking input from sensors distributed in various transaction environments. In embodiments, the MLP neural network may be used for trading environments and resource environment classifications, such as loan markets, spot markets, forward markets, energy markets, renewable energy resource units (REC) markets, networking markets, advertising markets, spectrum markets, ticketing markets, reward markets, computing markets, and other environments mentioned in this disclosure, as well as the physical resources and environments in which they are generated, such as energy resources (including renewable energy environments, mining environments, exploration environments, drilling environments, etc.), as well as for geological structure (including subsurface and above-ground features) classifications, material (including fluids, minerals, metals, etc.), classifications, and other issues. This may include fuzzy classification.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a structure-adapted neural network, wherein the structure of the neural network is adapted based on, for example, rules, sensed conditions, environmental parameters, and the like. For example, if the neural network does not converge to a solution, such as classifying an item or predicting an arrival, when operating on a set of inputs after a certain amount of training, the neural network, such as from a feedforward neural network to a recurrent neural network, may be modified, such as by switching data paths between some subset of nodes from unidirectional to bidirectional data paths. The adaptation of the structure may occur under the control of an expert system, for example to trigger adaptation in the event of a trigger, rule or event, for example to identify the occurrence of a threshold (e.g. no convergence to a solution within a given time) or to identify a phenomenon requiring a different or additional structure (e.g. identifying that the system is changing dynamically or in a non-linear manner). In one non-limiting example, the expert system may switch from a simple neural network structure (e.g., a feed-forward neural network) to a more complex neural network structure (e.g., a recurrent neural network, a convolutional neural network, etc.) upon receiving an indication that the continuously variable transmission in the system being analyzed is being used to drive a generator, turbine, etc.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use an auto-encoder, an auto-connector, or a Diabolo neural network, which may be similar to a multi-layer perceptron ("MLP") neural network, e.g., where there may be an input layer, an output layer, and one or more hidden layers connecting them. However, the output layer in an auto-encoder may have the same number of cells as the input layer, where the purpose of the MLP neural network is to reconstruct its own input (rather than just transmit the target values). Thus, the auto-encoder may operate as an unsupervised learning model. For example, the auto-encoder may be used for unsupervised learning efficient encoding, such as for dimension reduction, for learning generative models of data, and so forth. In an embodiment, an automatically encoded neural network may be used for self-learning efficient network encoding for transmitting analog sensor data from a machine or transmitting digital data from one or more data sources over one or more networks. In an embodiment, an automatically coded neural network may be used to self-learn an efficient storage method for storing a data stream.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a Probabilistic Neural Network (PNN), which in embodiments may include a multi-layer (e.g., four-layer) feed-forward neural network, where the layers may include an input layer, a hidden layer, a mode/summation layer, and an output layer. In an embodiment of the PNN algorithm, the parent Probability Distribution Function (PDF) of each class may be approximated, for example, by a Parzen window function and/or a non-parametric function. The class probability of the new input is then estimated using the PDF of each class and bayesian rules may be employed, for example, to assign it to the class with the highest a posteriori probability. The PNN may comprise a bayesian network and may use statistical algorithms or analytical techniques, such as the kernel Fisher discriminant analysis technique. PNNs may be used for classification and pattern recognition in any of the wide range of embodiments disclosed herein. In one non-limiting example, a probabilistic neural network may be used to predict a fault condition of an engine based on data input collection by sensors and instrumentation of the engine.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a time-delay neural network (TDNN), which may include a feed-forward structure for identifying sequence data of features independent of sequence location. In an embodiment, to account for time offsets in the data, a time delay is added to one or more inputs, or between one or more nodes, such that multiple data points are analyzed together (from different points in time). The time-lapse neural network may form part of a larger pattern recognition system using, for example, a perceptron network. In embodiments, the TDNN may be trained using supervised learning, e.g., using backpropagation or training the connection weights under feedback. In embodiments, the TDNN may be used to process sensor data from different streams, such as velocity data streams, acceleration data streams, temperature data streams, pressure data streams, and the like, where time delays are used to match the data streams in time, for example, to help understand patterns involving various streams (e.g., changes in price patterns in spot or forward markets).
In embodiments, the methods and systems described herein relating to expert systems or self-organizing capabilities may use convolutional neural networks (referred to in some cases as CNNs, convnets, translation-invariant neural networks, or space-invariant neural networks) in which the units are connected in a pattern similar to that of the visual cortex of a human brain. Neurons can respond to stimuli in a restricted spatial region (known as the receptive field). The sensory fields may partially overlap such that they collectively cover the entire (e.g., visual) field. The nodal responses may be mathematically calculated, for example, by convolution operations using, for example, a multi-layered perceptron with minimal preprocessing. Convolutional neural networks can be used for identification in image and video streams, for example, identifying machine types in large environments using a camera system disposed on a mobile data collector, e.g., on a drone or mobile robot. In an embodiment, a convolutional neural network may be used to provide recommendations based on data inputs, including sensor inputs and other contextual information, such as recommending routes for mobile data collectors. In an embodiment, a convolutional neural network may be used to process input, such as natural language processing for instructions provided by one or more parties involved in a workflow in an environment. In an embodiment, a large number of neurons (e.g., 100,000, 500,000, or more), multiple (e.g., 4, 5, 6, or more) layers, and many (e.g., millions) of parameters may be deployed for a convolutional neural network. The convolutional neural network may use one or more convolutional nets.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a management feedback network, for example, for identifying incidents (e.g., new types of behaviors not previously understood in a transactional environment).
In embodiments, the methods and systems described herein relating to expert systems or self-organizing capabilities may use self-organizing maps ("SOM"), involving unsupervised learning. A set of neurons may learn to map points in input space to coordinates in output space. The input space may have different dimensions and topologies from the output space, and the SOM may preserve these dimensions and topologies while mapping the phenomena into groups.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a learning vector quantization ("LVQ") neural network. Prototype representations of classes can be parameterized in a distance-based classification scheme, along with appropriate distance measures.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use an echo state network ("ESN"), which may include a recurrent neural network with sparsely connected random hidden layers. The weights of the output neurons may change (e.g., the weights may be trained based on feedback). In embodiments, the ESN may be used to process time series patterns, for example, in an example, identifying event patterns associated with a market, such as price change patterns in response to an incentive.
In embodiments, the methods and systems described herein relating to expert systems or self-organizing capabilities may use a Bidirectional Recurrent Neural Network (BRNN), for example, using a finite sequence of values (e.g., voltage values from sensors) to predict or mark each element of a sequence based on past and future contexts of the element. This can be done by adding the outputs of two RNNs, e.g., one processing the sequence from left to right and the other from right to left. The combined output is a prediction of the target signal, such as a signal provided by a teacher or supervisor. The bi-directional RNN may be combined with long-short term memory RNN.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a hierarchical RNN that variously joins elements to decompose hierarchical behavior, e.g., into useful subroutines. In embodiments, a hierarchical RNN may be used to manage one or more hierarchical templates of data collection in a transaction environment.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use stochastic neural networks that may introduce stochastic variants into the network. This random variation can be considered to be in the form of a statistical sample, such as a monte carlo sample.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a genetic scale recurrent neural network. In such an embodiment, RNNs (typically Long Short Term Memory (LSTM)) are used to decompose the sequence into several scales, where each scale forms a major length between two consecutive points. The first order consists of one normal RNN, the second order consists of all points separated by two indices, and so on. An N-order RNN connects the first node and the last node. The output from all the different scales can be considered a committee of membership, and the associated scores can be used for genetic use for the next iteration.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a machine committee (CoM), comprising a collection of different neural networks that collectively "vote" on a given example. Since neural networks may suffer from local minimization, starting from the same architecture and training, but using randomly different initial weights often gives different results. The CoM tends to stabilize the results.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use associative neural networks ("ASNN"), e.g., involving extensions to the machine committee that combines multiple feedforward neural networks and k-nearest neighbor technologies. In the analysis case of KNN, the correlation between the integrated responses can be used as a measure of distance. This corrects for deviations in neural network integration. The associative neural network may have memory that coincides with the training set. If new data becomes available, the network immediately improves its predictive power and provides data estimation (self-learning) without retraining. Another important feature of ASNN is that it is feasible to interpret neural network results by analyzing correlations between data instances in a model space.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use an Instantaneously Trained Neural Network (ITNN) in which weights of the hidden and output layers are mapped directly from training vector data.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use spiking neural networks, which may explicitly account for the time of input. The network inputs and outputs may be represented as a series of spikes (e.g., pulse functions or more complex shapes). The SNN may process information in the time domain (e.g., time-varying signals, such as signals relating to the dynamic behavior of a market or trading environment). They are typically implemented as recursive networks.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use dynamic neural networks that process non-linear multivariate behavior and include learning time-dependent behaviors such as transients and delay effects. Transients may include changing behavior of market variables such as price, available quantities, available partners, and the like.
In an embodiment, cascaded correlations may be used as an architectural and supervised learning algorithm to supplement the adjustment of weights in fixed topology networks. The cascade correlation may start with a minimum network and then automatically train and add new hidden units one by one, creating a multi-layer structure. Once a new hidden unit is added to the network, its input side weights may be frozen. This unit then becomes a permanent feature detector in the network, which can be used to generate output or to create other more complex feature detectors. The cascade-related architecture can learn quickly, determine its own size and topology, and retain its constructed structure even if the training set changes and does not need to be propagated backwards.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a neuro-fuzzy network, for example, a fuzzy inference system in the body relating to an artificial neural network. Several layers can model the process involved in fuzzy inference, such as fuzzification, inference, aggregation, and defuzzification, depending on the type. The fuzzy system is embedded into the general structure of the neural network as a benefit of using available training methods to find the parameters of the fuzzy system.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a variant of a complex pattern generation network ("CPPN"), such as an associative neural network ("ANN"), that is different from the set of activation functions and the manner in which they are applied. While a typical ANN typically contains only sigmoid functions (and sometimes gaussian functions), CPPN may include both types of functions as well as many other functions. In addition, CPPN can be applied to the entire space of possible inputs so that they can represent a complete image. Since they are a combination of functions, CPPN encodes images at virtually infinite resolution, and can sample a particular display regardless of whether the resolution is less than optimal.
This type of network can add new patterns without retraining. In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a one-time associative memory network that assigns each new mode to an orthogonal plane using a hierarchical array of adjacent connections, for example, by creating a particular memory structure.
In embodiments, the methods and systems described herein relating to expert systems or self-organizing capabilities may use Hierarchical Temporal Memory (HTM) neural networks, e.g., relating to structural and algorithmic properties of the neocortex. The HTM may use a biomimetic model based on memory prediction theory. The HTM can be used to discover and infer high-level causes of observed input patterns and sequences.
In embodiments, the methods and systems described herein relating to expert systems or self-organizing capabilities may use a Holographic Associative Memory (HAM) neural network, which may include analog, correlation-based, associative, stimulus-response systems. The information can be mapped to the phase orientation of the complex numbers. The memory is effective for associative memory tasks, generalization, and pattern recognition with variable attention.
In embodiments, various embodiments involving network coding may be used to encode transmission data between network nodes in a neural network, for example, where the nodes are located in one or more data collectors or machines in a trading environment.
With reference to fig. 22-49, embodiments of the present disclosure, including embodiments involving expert systems, self-organization, machine learning, artificial intelligence, etc., may benefit from using neural networks, e.g., training neural networks for pattern recognition, for classification of one or more parameters, features, or phenomena, for supporting autonomic control, and other purposes. <xnotran> , , , , , ( Kohonen ), , , , , , , ( - ), , , , , , , , hopfield , boltzmann , (SOM) , (LVQ) , , , , , , , , RNN , , , , , , , , , , , , , , (GCU) , , , , , </xnotran> Markov chain neural networks, constrained Boltzmann machine neural networks, deep belief neural networks, deep convolutional neural networks, deconvolution neural networks, deep convolutional inverse graph neural networks, generative countermeasure neural networks, liquid machine neural networks, extreme learning machine neural networks, echo state neural networks, deep residual error neural networks, support vector machine neural networks, neural turing machine neural networks, and/or holographic associative memory neural networks, or a mixture or combination of the foregoing neural networks, or a combination with other expert systems, such as rule-based systems, model-based systems (including systems based on physical models, statistical models, flow-based models, biological models, biomimetic models, and the like).
In an embodiment, fig. 23-49 depict an exemplary neural network, while fig. 22 depicts a diagram showing various components of the neural network depicted in fig. 23-49. FIG. 22 depicts various neural network components depicted in units assigned functions and requirements. In embodiments, various neural network examples may include (from top to bottom in the example of fig. 22): a feedback data/sensor input unit, a noise input unit, and a concealment unit. The neural network components also include probabilistic hiding units, spiking hiding units, output units, matching input/output units, recursion units, memory units, different memory units, kernels, and convolution or pool units.
In an embodiment, fig. 23 depicts an exemplary sensory neural network that may be connected to platform 100, integrated with platform 100, or interfaced with platform 100. The platform may also be associated with other neural network systems, such as feed-forward neural networks (fig. 24), radial basis neural networks (fig. 25), deep feed-forward neural networks (fig. 26), recurrent neural networks (fig. 27), long/short term neural networks (fig. 28), and gated recurrent neural networks (fig. 29). The platform may also be associated with other neural network systems, such as an autoencoder neural network (fig. 30), a variational neural network (fig. 31), a de-noising neural network (fig. 32), a sparse neural network (fig. 33), a markov chain neural network (fig. 34), and a Hopfield network neural network (fig. 35). The platform may also be associated with additional neural network systems such as Boltzmann machine neural networks (fig. 36), restricted BM neural networks (fig. 37), deep belief neural networks (fig. 38), deep convolutional neural networks (fig. 39), deconvolution neural networks (fig. 40), and deep convolutional inverse graph neural networks (fig. 41). The platform may also be associated with other neural network systems, such as generating an inverse neural network (fig. 42), a liquid machine neural network (fig. 43), an extreme learning machine neural network (fig. 44), an echo state neural network (fig. 45), a deep residual neural network (fig. 46), a Kohonen neural network (fig. 47), a support vector machine neural network (fig. 48), and a neural machine neural network (fig. 49).
The aforementioned neural networks may have various nodes or neurons that may perform various functions upon input, such as input received from sensors or other data sources (including other nodes). The functions may relate to weights, features, feature vectors, and the like. Neurons may include sensors, neurons that mimic biological functions (e.g., human touch, vision, taste, hearing, and smell), and the like. Successive neurons (e.g., with S-type activation) can be used in the context of various forms of neural networks, such as situations involving back propagation.
In many embodiments, the expert system or neural network may be trained, for example, by a human operator or supervisor, or based on a data set, model, or the like. Training may include presenting one or more training data sets representing values to a neural network, such as sensor data, event data, parameter data, and other types of data (including many of the types described in this disclosure), as well as one or more outcome indicators, such as results of a process, results of a calculation, results of an event, results of an activity, and so forth. Training may include optimization training, such as training a neural network to optimize one or more systems based on one or more optimization methods, such as bayesian methods, parametric bayesian classifier methods, k-nearest neighbor classifier methods, iterative methods, interpolation methods, pareto optimization methods, algorithmic methods, and the like. Feedback may be provided during the course of variation and selection, for example using a genetic algorithm that evolves one or more solutions based on feedback through a series of rounds.
In embodiments, a plurality of neural networks may be deployed in a cloud platform that receives data streams and other inputs collected in one or more transaction environments (e.g., collected by a mobile data collector) and sent to the cloud platform over one or more networks (including using network coding to provide efficient transmission). In a cloud platform, a number of different types of neural networks (including modular, architecture adaptive, hybrid, etc.) can be used to undertake prediction, classification, control functions, and provide other outputs related to the expert system disclosed in this disclosure, optionally using massively parallel computing power. The different neural networks may be configured to compete with each other (optionally including the use of evolutionary algorithms, genetic algorithms, etc.) such that, for example, an appropriate type of neural network with an appropriate set of inputs, weights, node types and functions, etc., may be selected by the expert system for use in a given context, workflow, environmental process, particular task involved in the system, etc.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a feed forward neural network that moves information in one direction through a series of neurons or nodes to an output, such as from a data input (e.g., a data source associated with at least one resource or a parameter associated with a trading environment) or any data source mentioned in this disclosure. Data may be moved from an input node to an output node, optionally through one or more hidden nodes, without looping. In embodiments, the feed-forward neural network may be constructed with various types of cells (e.g., binary McCulloch-buttons neurons, the simplest of which is a perceptron).
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a capsule neural network, for example, for predictive, categorical, or control functions relating to a transaction environment, for example, relating to one or more of the machines and automated systems described in the present disclosure.
In embodiments, the methods and systems described herein relating to expert systems or self-organizing capabilities may use Radial Basis Function (RBF) neural networks, which may be preferred in some cases involving interpolation in multidimensional spaces (e.g., where interpolation helps to optimize multidimensional functions, such as for optimizing data markets described herein, optimizing efficiency or output of power generation systems, plant systems, etc., or other cases involving multiple dimensions.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use Radial Basis Function (RBF) neural networks, such as neural networks that employ a distance criterion (e.g., a gaussian function) with respect to a center. In a multilayer perceptron radial basis functions may be applied as a replacement for hidden layers, e.g. S-shaped hidden layer transitions. The RBF network may have two layers, for example, where the input is mapped onto each RBF in the hidden layer. In an embodiment, the output layer may comprise a linear combination of hidden layer values, which represents, for example, an average prediction output. The output tier values may provide the same or similar output as the output of the regression model in the statistics. In the classification problem, the output layer may be a sigmoid function of a linear combination of hidden layer values, representing a posterior probability. The performance in both cases is typically improved by a shrinkage technique (e.g., ridge regression in classical statistics). This corresponds to a priori belief in the bayesian framework for small parameter values (and hence smooth output functions). The RBF network can avoid local minima because the only parameter adjusted in the learning process is the linear mapping from the hidden layer to the output layer. Linearity ensures that the error surface is quadratic and therefore has a single minimum. In the regression problem, this can be found in a matrix operation. In the classification problem, an iterative reweighted least squares function or the like may be used to handle the fixed non-linearity introduced by the sigmoid output function. The RBF network may use kernel methods such as Support Vector Machines (SVMs) and gaussian processes (where RBFs are kernel functions). The input data may be projected into a space using a non-linear kernel function, where a linear model may be used to solve the learning problem.
In an embodiment, the RBF neural network may include an input layer, a hidden layer, and a summation layer. In the input layer, each predictor variable appears as a neuron in the input layer. In the case of categorical variables, N-1 neurons are used, where N is the number of categories. In an embodiment, the input neurons may normalize the range of values by subtracting the median and dividing by the interquartile range. The input neuron may then feed back values to each neuron in the hidden layer. A variable number of neurons (determined by the training process) may be used in the hidden layer. Each neuron may consist of a radial basis function centered around a point having as many dimensions as there are predictor variables. The extent (e.g., radius) of the RBF function may be different for each dimension. The center and the spread may be determined by training. When represented using vectors of input values from the input layer, the hidden neuron may compute the euclidean distance of the test case from the neuron's center point and then apply the RBF kernel to that distance, e.g., using the spread values. The resulting value may then be passed to a summing layer. In the summation layer, values from neurons in the hidden layer may be multiplied by weights associated with the neurons, and may be added to weighted values of other neurons. This sum becomes the output. For the classification problem, one output is generated for each target class (with a separate set of weights and summing unit). The value output for a category is the probability that the case being evaluated has that category. In the training of the RBF, various parameters may be determined, such as the number of neurons in the hidden layer, the coordinates of the center of each hidden layer function, the spread of each function in each dimension, and the weights applied to the output as they are passed to the summation layer. Training may be used by clustering algorithms (e.g., k-means clustering), by evolutionary methods, and the like.
In embodiments, the recurrent neural network may have time-varying real-valued (not just 0 or 1) activations (outputs). Each connection may have a modifiable real-valued weight. Some nodes are referred to as marker nodes, some output nodes, and other hidden nodes. For supervised learning in discrete time settings, the training sequence of real valued input vectors may become the activation sequence of input nodes, one input vector at a time. At each time step, each non-input cell may compute its current activation as a non-linear function of the weighted sum of the activations of all the cells it receives the connection. The system may explicitly activate (independent of the input signal) some output units at a specific time step.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use ad hoc neural networks, such as Kohonen ad hoc neural networks, for example, for visualization of views of data, such as low-dimensional views as high-dimensional data. The ad hoc neural network may apply competitive learning to a set of input data, such as from one or more sensors or other data input from or associated with a transaction environment, including any machine or component associated with the transaction environment. In embodiments, the ad hoc neural network may be used to identify structures in data, such as unlabeled data, such as data sensed from a series of data sources or sensors in a transaction environment, where the data sources are unknown (e.g., an event may come from any of a series of unknown sources). The ad hoc neural network may organize structures or patterns in the data so that they may be identified, analyzed, and labeled, such as identifying market behavior structures as corresponding to other events and signals.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a recurrent neural network, which may allow for bidirectional flow of data, for example where connected units (e.g., neurons or nodes) form a directed loop. Such networks may be used to model or present dynamic temporal behavior, e.g., relating to dynamic temporal behavior in dynamic systems, such as the various automated systems, machines, and devices described in this disclosure, e.g., automated agents interacting with a market for the purpose of collecting data, testing spot market transactions, executing transactions, etc., where dynamic system behavior relates to complex interactions that a user may wish to understand, predict, control, and/or optimize. For example, a recurrent neural network may be used to predict market states, e.g., market states that involve dynamic processes or actions, e.g., state changes of resources that train or implement a trading environment market in the trading environment market. In embodiments, the recurrent neural network may use internal memory to process various types of input sequences described herein, such as from other nodes and/or from sensors or other data inputs provided by or related to the transaction environment. In embodiments, the recurrent neural network may also be used for pattern recognition, e.g., to identify a machine, component, agent, or other item based on a behavioral signature, a profile, a set of feature vectors (e.g., in an audio file or image), and so forth. In a non-limiting example, the recurrent neural network may identify transitions in the operating mode of the market or machine by learning to classify transitions from a training data set that includes data streams from one or more data sources of sensors applied to or related to one or more resources.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a modular neural network, which may include a series of independent neural networks (e.g., neural networks of the various types described herein) that are adapted by an intermediary. Each individual neural network in the modular neural network may work with a separate input to accomplish a subtask that constitutes a task to be performed by the entire modular network. For example, the modular neural network may include a recurrent neural network for pattern recognition, such as an RBF neural network that identifies what type of machine or system one or more sensors provided as input channels to the modular network are sensing and for optimizing the behavior of the machine or system once understood. The intermediary may accept inputs for each individual neural network, process them, and create outputs for the modular neural network, such as appropriate control parameters, condition predictions, and the like.
Combinations between any two, three, or more of the various neural network types described herein are encompassed in this disclosure. This may include a combination where the expert system uses one neural network for identifying patterns (e.g., patterns indicative of problem or fault conditions) and a different neural network for self-organizing activities or workflows based on the identified patterns (e.g., providing output for managing system autonomous control in response to the identified conditions or patterns). This may also include a combination where the expert system uses one neural network for classifying the project (e.g., identifying a machine, component, or mode of operation) and a different neural network for predicting a condition of the project (e.g., a fault condition, an operating condition, an expected condition, a maintenance condition, etc.). The modular neural network may also include situations where the expert system uses one neural network for determining a condition or context (e.g., a condition of a machine, a process, a workflow, a market, a storage system, a network, a data collector, etc.) and one different neural network for self-organizing processes related to the condition or context (e.g., a data storage process, a network encoding process, a network selection process, a data market process, a power generation process, a manufacturing process, a refining process, a mining process, a boring process, or other processes described herein).
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a physical neural network in which one or more hardware elements are used to perform or simulate neural behavior. In embodiments, one or more hardware neurons may be used to stream voltage values, current values, etc. representing sensor data, for example by computing information from analog sensor inputs representing energy consumption, energy production, etc. through one or more machines providing or consuming energy for one or more transactions. One or more hardware nodes may be used to stream output data generated by the activity of the neural network. Hardware nodes may include one or more chips, microprocessors, integrated circuits, programmable logic controllers, application specific integrated circuits, field programmable gate arrays, etc., which may be used to optimize a machine that is generating or consuming energy, or to optimize another parameter of some portion of any type of neural network described herein. A hardware node may include hardware for accelerating computations (e.g., a dedicated processor for performing basic or more complex computations on input data to provide output, a dedicated processor for filtering or compressing data, a dedicated processor for decompressing data, a dedicated processor for compressing a particular file or data type (e.g., for processing image data, video streams, acoustic signals, thermal images, etc.). The physical neural network may be embodied in a data collector, including a data collector that may be reconfigured by switching or routing inputs in varying configurations, e.g., different neural network configurations are provided within the data collector for handling different types of inputs (with switching and configurations optionally under control of an expert system, which may include a software-based neural network located on or remote from the data collector). The physical or at least partially physical neural network may comprise physical hardware nodes located in a storage system, for example, for storing data in a machine, data storage system, distributed ledger, mobile device, server, cloud resource, or transaction processing environment, for example, to accelerate input/output functions of one or more storage elements providing data to or retrieving data from the neural network. The physical or at least partially physical neural network may comprise physical hardware nodes located in the network, e.g. for transmitting data within, to or from the industrial environment, e.g. for accelerating input/output functions of one or more network nodes in the network, accelerating relay functions, etc. In an embodiment of a physical neural network, electrically tunable resistive material may be used to mimic the function of a neurosynaptic. In an embodiment, the physical hardware simulates neurons and the software simulates neural networks between the neurons. In an embodiment, the neural network supplements a conventional algorithm computer. These computers are general purpose and can be trained to perform the appropriate functions without requiring any instructions, such as classification functions, optimization functions, pattern recognition functions, control functions, selection functions, evolution functions, and the like.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use multi-layer feed-forward neural networks, such as complex pattern classification for one or more items, phenomena, patterns, conditions, and the like. In embodiments, the multi-layer feed-forward neural network may be trained by optimization techniques such as genetic algorithms, for example, exploring large and complex option spaces to find an optimal or near optimal global solution. For example, one or more genetic algorithms may be used to train a multi-layer feed-forward neural network to classify complex phenomena, such as to identify complex operating modes of the machines, such as modes involving complex interactions between machines (including interference effects, resonance effects, etc.), modes involving non-linear phenomena, modes involving critical faults, such as in the case of multiple faults occurring simultaneously, making it difficult to analyze root causes, etc. In an embodiment, a multi-layer feed-forward neural network may be used to classify results from market monitoring, including, for example, monitoring systems operating within the market, such as automated agents, and monitoring resources that implement the market, such as computing, networking, energy, data storage, energy storage, and other resources.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a feed-forward, back-propagation multi-layer perceptive (MLP) neural network, for example, for processing one or more telemetry applications, for example, for taking input from sensors distributed in various transaction environments. In embodiments, the MLP neural network may be used for trading environment and resource environment classifications, such as spot markets, forward markets, energy markets, renewable Energy Credits (REC) markets, networking markets, advertising markets, spectrum markets, ticketing markets, reward markets, computing markets, and other environments mentioned in this disclosure, as well as the physical resources and environments in which they are generated, such as energy resources (including renewable energy environments, mining environments, exploration environments, drilling environments, etc.), as well as for geological structure (including subsurface and above-ground features) classifications, material (including fluids, minerals, metals, etc.) classifications, and other issues. This may include fuzzy classification.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may adapt a neural network using a structure, wherein the structure of the neural network is adapted based on, for example, rules, sensed conditions, environmental parameters, and the like. For example, if the neural network does not converge to a solution, such as classifying an item or predicting an arrival, the neural network, e.g., from a feedforward neural network to a recurrent neural network, may be modified when operating on a set of inputs after a certain amount of training, e.g., by switching data paths between some subset of nodes from unidirectional data paths to bidirectional data paths. The adaptation of the structure may occur under the control of an expert system, for example to trigger adaptation in the event of a trigger, rule or event, for example to identify the occurrence of a threshold (e.g. no convergence to a solution within a given time) or to identify a phenomenon requiring a different or additional structure (e.g. identifying that the system is changing dynamically or in a non-linear manner). In one non-limiting example, the expert system may switch from a simple neural network structure (e.g., a feed-forward neural network) to a more complex neural network structure (e.g., a recurrent neural network, a convolutional neural network, etc.) upon receiving an indication that the continuously variable transmission in the system being analyzed is being used to drive a generator, turbine, etc.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use an auto-encoder, an auto-connector, or a Diabolo neural network, which may be similar to a multi-layer perceptron ("MLP") neural network, e.g., where there may be an input layer, an output layer, and one or more hidden layers connecting them. However, the output layer in an auto-encoder may have the same number of cells as the input layer, where the purpose of the MLP neural network is to reconstruct its own input (rather than just transmit the target values). Thus, the auto-encoder may operate as an unsupervised learning model. For example, the auto-encoder may be used for unsupervised learning efficient encoding, such as for dimension reduction, for learning generative models of data, and so forth. In an embodiment, an automatically encoded neural network may be used for self-learning efficient network encoding for transmitting analog sensor data from a machine or transmitting digital data from one or more data sources over one or more networks. In an embodiment, an automatically coded neural network may be used to self-learn an efficient storage method for storing a data stream.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a Probabilistic Neural Network (PNN), which in embodiments may include a multi-layer (e.g., four-layer) feed-forward neural network, where each layer may include an input layer, a hidden layer, a mode/summation layer, and an output layer. In an embodiment of the PNN algorithm, the parent Probability Distribution Function (PDF) of each class may be approximated, for example, by a Parzen window function and/or a non-parametric function. The class probability of the new input is then estimated using the PDF of each class and bayesian rules may be employed, for example, to assign it to the class with the highest a posteriori probability. The PNN may comprise a bayesian network and may use statistical algorithms or analytical techniques, such as the kernel Fisher discriminant analysis technique. PNNs may be used for classification and pattern recognition in any of the wide range of embodiments disclosed herein. In one non-limiting example, a probabilistic neural network may be used to predict a fault condition of an engine based on data input collection by sensors and instrumentation of the engine.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a time-delay neural network (TDNN), which may include a feed-forward structure for identifying sequence data of features independent of sequence location. In an embodiment, to account for time offsets in the data, a time delay is added to one or more inputs, or between one or more nodes, such that multiple data points are analyzed together (from different points in time). The time-lapse neural network may form part of a larger pattern recognition system using, for example, a perceptron network. In embodiments, the TDNN may be trained using supervised learning, e.g., using backpropagation or training the connection weights under feedback. In embodiments, the TDNN may be used to process sensor data from different streams, such as velocity data streams, acceleration data streams, temperature data streams, pressure data streams, and the like, where time delays are used to match the data streams in time, for example, to help understand patterns involving various streams (e.g., changes in price patterns in spot or forward markets).
In embodiments, the methods and systems described herein relating to expert systems or self-organizing capabilities may use convolutional neural networks (referred to in some cases as CNNs, convnets, translation-invariant neural networks, or space-invariant neural networks) in which the units are connected in a pattern similar to that of the visual cortex of a human brain. Neurons can respond to stimuli in a restricted spatial region (known as the receptive field). The sensory fields may partially overlap such that they collectively cover the entire (e.g., visual) field. The nodal responses may be mathematically calculated, for example, by convolution operations, using a multi-layered perceptron with minimal preprocessing, for example. Convolutional neural networks can be used for identification in image and video streams, for example, identifying machine types in large environments using a camera system disposed on a mobile data collector, e.g., on a drone or mobile robot. In an embodiment, a convolutional neural network may be used to provide recommendations based on data inputs, including sensor inputs and other contextual information, such as recommending routes for mobile data collectors. In an embodiment, a convolutional neural network may be used to process input, such as natural language processing for instructions provided by one or more parties involved in a workflow in an environment. In an embodiment, a large number of neurons (e.g., 100,000, 500,000, or more), multiple (e.g., 4, 5, 6, or more) layers, and many (e.g., millions) of parameters may be deployed for a convolutional neural network. The convolutional neural network may use one or more convolutional nets.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a management feedback network, for example, for identifying incidents (e.g., new types of behaviors not previously understood in a transactional environment).
In embodiments, the methods and systems described herein relating to expert systems or self-organizing capabilities may use self-organizing maps ("SOM"), involving unsupervised learning. A set of neurons may learn to map points in input space to coordinates in output space. The input space may have different dimensions and topologies than the output space, and the SOM may preserve these dimensions and topologies while mapping the phenomena into groups.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a learning vector quantization ("LVQ") neural network. Prototype representations of classes can be parameterized in a distance-based classification scheme, along with appropriate distance measures.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use an echo state network ("ESN"), which may include a recurrent neural network with sparsely connected random hidden layers. The weights of the output neurons may change (e.g., the weights may be trained based on feedback). In embodiments, the ESN may be used to process time series patterns, for example, in an example, identifying a pattern of events associated with a market, such as a price change pattern in response to an incentive.
In embodiments, the methods and systems described herein relating to expert systems or self-organizing capabilities may use a Bidirectional Recurrent Neural Network (BRNN), for example, using a finite sequence of values (e.g., voltage values from sensors) to predict or mark each element of a sequence based on past and future contexts of the element. This can be done by adding the outputs of two RNNs, e.g., one processing the sequence from left to right and the other from right to left. The combined output is a prediction of the target signal, such as a signal provided by a teacher or supervisor. The bi-directional RNN may be combined with long-short term memory RNN.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a hierarchical RNN that variously joins elements to decompose hierarchical behavior, e.g., into useful subroutines. In embodiments, a hierarchical RNN may be used to manage one or more hierarchical templates of data collection in a transaction environment.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use stochastic neural networks that may introduce stochastic variants into the network. Such random variations may be considered to be in the form of statistical samples, such as monte carlo samples.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a genetic scale recurrent neural network. In such embodiments, RNNs (typically LSTM) are used, where the sequence is decomposed into scales, where each scale informs the major length between two consecutive points. The first order consists of one normal RNN, the second order consists of all points separated by two indices, and so on. An N-order RNN connects the first node and the last node. The output from all the different scales can be considered a committee of membership, and the associated scores can be used for genetic use for the next iteration.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a machine committee (CoM), comprising a collection of different neural networks that collectively "vote" on a given example. Since neural networks may suffer from local minimization, starting from the same architecture and training, but using randomly different initial weights often gives different results. The CoM tends to stabilize the results.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use an associative neural network (ASNN), such as an extension of the machine committee that involves combining multi-feed forward neural networks and k nearest neighbor technologies. In the analysis case of KNN, the correlation between the integrated responses can be used as a measure of distance. This corrects for deviations in neural network integration. The associative neural network may have memory that coincides with the training set. If new data becomes available, the network immediately improves its predictive power and provides data estimation (self-learning) without retraining. Another important feature of ASNN is that it is feasible to interpret neural network results by analyzing correlations between data instances in a model space.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use an Instantaneously Trained Neural Network (ITNN) in which weights of the hidden and output layers are mapped directly from training vector data.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use spiking neural networks, which may explicitly account for the time of input. The network inputs and outputs may be represented as a series of spikes (e.g., pulse functions or more complex shapes). The SNN may process information in the time domain (e.g., time-varying signals, such as signals relating to the dynamic behavior of a market or trading environment). They are usually implemented as recursive networks.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use dynamic neural networks that process non-linear multivariate behavior and include learning time-dependent behaviors such as transients and delay effects. Transients may include changing behavior of market variables such as price, available quantities, available partners, and the like.
In an embodiment, cascaded correlations may be used as an architectural and supervised learning algorithm to supplement the adjustment of weights in fixed topology networks. The cascade correlation may start with a minimum network and then automatically train and add new hidden units one by one, creating a multi-layer structure. Once a new hidden unit is added to the network, its input side weights may be frozen. This unit then becomes a permanent feature detector in the network, which can be used to generate output or to create other more complex feature detectors. The cascade-related architecture can learn quickly, determine its own size and topology, and retain its constructed structure even if the training set changes and does not need to be propagated backwards.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a neuro-fuzzy network, for example, a fuzzy inference system in the body relating to an artificial neural network. Several layers can model the process involved in fuzzy inference, such as fuzzification, inference, aggregation, and defuzzification, depending on the type. The fuzzy system is embedded into the general structure of the neural network as a benefit of using available training methods to find the parameters of the fuzzy system.
In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a variant of a complex pattern generation network ("CPPN"), such as an associative neural network ("ANN"), that is different from the set of activation functions and the manner in which they are applied. While a typical ANN typically contains only sigmoid functions (and sometimes gaussian functions), CPPN may include both types of functions and many others. In addition, CPPN can also be applied over the entire space of possible inputs so that these inputs can represent a complete image. Since these inputs are a combination of functions, CPPN encodes images at virtually infinite resolution, and can sample a particular display at any optimal resolution.
This type of network can add new patterns without retraining. In embodiments, the methods and systems described herein relating to expert systems or ad hoc capabilities may use a one-time associative memory network that uses a hierarchical array of adjacent connections to assign each new mode to an orthogonal plane, for example by creating a particular memory structure.
In embodiments, the methods and systems described herein relating to expert systems or self-organizing capabilities may use Hierarchical Temporal Memory (HTM) neural networks, e.g., relating to structural and algorithmic properties of the neocortex. The HTM may use a biomimetic model based on memory prediction theory. The HTM can be used to discover and infer high-level causes of observed input patterns and sequences.
In embodiments, the methods and systems described herein relating to expert systems or self-organizing capabilities may use a Holographic Associative Memory (HAM) neural network, which may include analog, correlation-based, associative, stimulus-response systems. The information can be mapped to the phase orientation of the complex numbers. The memory is effective for associative memory tasks, generalization, and pattern recognition with variable attention.
In embodiments, various embodiments involving network coding may be used to encode transmission data between network nodes in a neural network, for example, where the nodes are located in one or more data collectors or machines in a trading environment.
Referring to fig. 50, a system 5000 for automatic loan management is depicted. The various entities/parties 5038 may have connections to a loan 5024, the loan 5024 including borrowers 5040, borrowers 5042, third parties neutral (e.g., evaluators, collateral/equipment 5060), or interested third parties (e.g., regulatory agencies, company employees, etc.), 5044. The loan 5024 may be governed by intelligent loan contracts 5090 that include information such as loan terms and conditions 5029, loan actions 5030, loan events 5032, borrower priorities 5028, and so on. The intelligent lending contract 5090 may be recorded in a loan entry 5041 in a distributed ledger 5063. The intelligent loan contracts 5090 may be stored as blockchain data 5034.
In an illustrative example, controller 5022 can receive collateral data 5074, such as collateral-related events 5008, collateral attributes 5010, environmental data 5012 regarding the environment in which collateral 5002 is located, sensor data 5014, where sensor 5004 can be attached to the collateral and in cases where the collateral is contained or proximate to the collateral. In an embodiment, collateral data may be obtained by: internet of things circuit 5020, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system and an interactive crowdsourcing system.
In an embodiment, the artificial intelligence system 5062 may be part of the controller 5022 or located on a remote system. The AI system 5062 may include a valuation circuit 5064 and a value model improvement circuit 5066, the valuation circuit 5064 configured to determine a value of a collateral based on collateral data 5074 and a valuation model; the value model refinement circuit 5066 refines the valuation model based on the first set of received collateral data 5074 and the outcome of the loan warranted by the collateral associated with the first set of received collateral data. The AI system 5062 may include an automated agent circuit 5070 that takes action based on mortgage events, loan events, and the like. The actions may include loan-related actions such as, for example, approving a loan, accepting the loan, underwriting the loan, setting a loan interest rate, deferring payment requirements, modifying a loan interest rate, verifying the property of the collateral, recording changes in the property, evaluating the value of the collateral, initiating collateral checks, expecting the loan, completing the loan, setting terms and conditions for the loan, providing notification to the borrower of the claim, stopping the redemption of property subject to the loan constraint, and modifying terms and conditions for the loan, etc. The actions may include collateral-related actions, such as verifying the title of one of the assigned set of collateral, recording changes to the title of one of the assigned set of collateral, evaluating the value of one of the assigned set of collateral, initiating an inspection of one of the assigned set of collateral, initiating maintenance of one of the assigned set of collateral, initiating a vouching of one of the assigned set of collateral, and modifying terms and conditions of one of the assigned set of collateral 5018. The AI system 5062 may include a clustering circuit 5072 to create groups of mortgages based on common attributes. The clustering circuit 5072 may also determine a set of cancellation mortgages, wherein a cancellation mortgage shares a common attribute with one or more mortgages. Data regarding the cancellation collateral may be collected and used to represent the collateral. Intelligent contract circuitry 5068 may create an intelligent loan contract 5090 as elsewhere herein.
Referring to fig. 51, the controller may include a blockchain service circuit 5144 configured to interpret a plurality of access control features 5148, e.g., corresponding to a principal associated with a loan 5130 and a principal associated with blockchain data 5140. The system 5100 may include a data collection circuit 5112 configured to interpret entity information 5102, collateral data 5104, and the like, e.g., corresponding to entities associated with loan transactions corresponding to loans, collateral conditions, and the like. The system may include an intelligent contract circuit 5122 configured to specify loan terms and conditions 5124, contracts 5128, etc., relating to loans. The system may include a loan management circuit 5132 configured to interpret a loan-related action 5134 and/or an event 5138 in response to the entity information, the plurality of access control features, and the loan terms and conditions, wherein the loan-related event is associated with the loan; in response to the entity information, the plurality of access control features, and the loan terms and conditions, performing a loan-related activity, wherein the loan-related activity is associated with the loan; and wherein each of the blockchain service circuit, the data collection circuit, the intelligent contract circuit, and the loan management circuit further comprises a respective Application Programming Interface (API) component configured to facilitate communication between the circuits of the system. For example, the borrower 5108 may be connected with the controller through a secure access control interface 5152 (e.g., through access control instructions 5154) that is configured to connect with the controller through a secure access control circuit 5150. The data gathering circuit 5112 may be configured to receive collateral data 5104 and entity information 5102, such as information about the lending party, e.g., the borrower, or third party, the collateral, the machine or property associated with the lending party, the lender's product, etc. Collateral data 5104 may include: type of the collateral, category of the collateral, value of the collateral, price of the type of the collateral, value of the type of the collateral, description of the collateral, product feature set of the collateral, model of the collateral, brand of the collateral, manufacturer of the collateral, age of the collateral, liquidity of the collateral, expiration date of the collateral, condition of the collateral, valuation of the collateral, state of the collateral, background of the collateral, state of the collateral, storage location of the collateral, history of the collateral, ownership of the collateral, caretaker of the collateral, guarantee of the collateral, condition of owner of the collateral, lien of the collateral, storage conditions of the collateral, maintenance of the collateral, use of the collateral, history of the history, accident of the owner, place of the history of the collateral, place of the evaluation, and the like. The data collection circuit 5112 can determine a collateral condition based on the received data. The received data 5102, 5104 and collateral conditions 5110 may be provided to an AI circuit 5142, which may include an automated agent circuit 5114 (e.g., processing events 5118, 5120), an intelligent contract service circuit 5122, and a loan management circuit 5132.
Referring to fig. 52, an illustrative and non-limiting example method for processing a loan 5200 is described. An example method may include interpreting a plurality of access control features (step 5202); interpreting the entity information (step 5204); specifying loan terms and conditions (step 5208); executing the contract-related event in response to the entity information (step 5210); interpreting loan-related events (step 5212); performing a loan action in response to the event (step 5214); providing a user interface (step 5218); creating an intelligent loan contract (step 5220); and recording the intelligent loan contract as blockchain data (step 5222).
Referring to fig. 53, a system 5300 for adaptive intelligence and robotic process automation capabilities for trading, financial and marketing support is depicted. System 5300 can include a controller 5323 that can include a data collection circuit 5302 that receives the collateral data 5301 and determines a collateral condition 5304. The controller 5323 may also include a plurality of AI circuits 5654. The plurality of AI circuits 5654 can include a valuation circuit 5308, which can include a valuation model improvement circuit 5310 and a clustering circuit 5312. The plurality of AI circuits 5654 may include an intelligent contract service circuit 5314 that includes an intelligent lending contract 5316 for a loan 5325. The plurality of AI circuits 5654 may include an automatic agent circuit 5318 that takes loan-related actions 5320. Controller 5323 may also include reporting circuit 5322 and market value monitoring circuit 5324, which also determine a collateral condition 5304. The controller 5323 may also include a secure access user interface 5328 that receives access control instructions 5330 from the borrower 5342. Access control instructions 5330 provide secure access control circuitry 5332 which provide instructions to blockchain service circuitry 5334, which block chain service circuitry 5334 interprets the access control characteristics 5338 and provides access rights to the borrower 5342 or other party. The block chain service circuit 5334 stores the collateral data and the unique collateral ID as block chain data 5335.
Referring to fig. 54, a method 5400 for automatic intelligent contract creation and collateral distribution is described. The method 5400 may include receiving first and second collateral data for a collateral (5402); creating an intelligent lending contract (5404); associating (5408) the collateral data with a unique identifier of the collateral; and storing the unique identifier and the collateral in a block chain structure (5410). The method may also include interpreting a condition of the collateral based on the collateral data (5412); identifying a collateral event (5414); reporting a collateral event (5418); and perform actions in response to collateral 5420. The method 5400 may also include identifying a set of cancellation collateral (5422); accessing market information related to counteracting a collateral or mortgage (5424); and modifying the terms or conditions of the loan based on the market information (5428). The method 5400 can also include receiving an access control instruction (5430); interpreting a plurality of access control features (5432); and providing access to the mortgage date (5434).
Referring to fig. 55, an illustrative and non-limiting example system 5500 for processing a loan 5530 is depicted. The example system may include a controller 5501. The controller 5501 may include a data collection circuit 5512, an valuation circuit 5544, a user interface 5554 (e.g., for an interface with the user 5506), a block chain servicing circuit 5558, and a number of artificial intelligence circuits 5542, including an intelligent contract servicing circuit 5522, a loan management circuit 5922, a clustering circuit 5532, an automatic brokerage circuit 5514 (e.g., for processing loan-related events 5539, and loan actions 5538).
The blockchain service circuit 5558 may be configured to interface with the distributed ledger 5540. Data collection circuitry 5512 may be configured to receive data relating to plurality of mortgages 5504 or data relating to the environment of plurality of mortgages 5502. The valuation circuit 5544 can be configured to determine a value for each of a plurality of mortgages based on the valuation model 5552 and the received data. The intelligent contract service circuit 5522 may be configured to interpret an intelligent lending contract 5531 for the loan and modify the intelligent lending contract 5531 by assigning at least a portion of the plurality of mortgages as a guarantee for the loan based on the determined value of each of the plurality of mortgages such that the determined value of each of the plurality of mortgages 5528 is sufficient to provide a guarantee for the loan. The blockchain service circuit 5558 may also be configured to record at least a portion of the allocated collateral 5528 into an entry in the distributed ledger 5540, wherein the entry is for recording an event related to the loan. Each of the blockchain service circuit, the data collection circuit, the valuation circuit, and the intelligent contract circuit can further include a corresponding Application Programming Interface (API) component configured to facilitate communication between the system circuits.
Modifying the intelligent lending contract 5531 may also include specifying terms and conditions 5524 governing one of: loan terms, loan conditions, loan-related events, and loan-related activities. Clauses and conditions 5524 may each include at least one member of the following group: principal amount of the loan, balance of the loan, fixed interest rate, variable interest rate description, payment amount, payment plan, endmost grand payback plan, collateral description, collateral substitutability description, description of at least one party, insured person description, guarantor description, personal guaranty, lien, redemption condition, default outcome, a contract relating to any of the foregoing, and a term of any of the foregoing.
The loan 5530 may include at least one of the following loan types: the system comprises an automobile loan, an inventory loan, a capital equipment loan, a performance bond, a capital improvement loan, a construction loan, an account receivable guarantee loan, an invoice financing arrangement, a warranty arrangement, a payday loan, a refund expected loan, an academic loan, a banking loan, a property loan, a housing loan, a risk debt loan, an intellectual property loan, a contractual right loan, a floating fund loan, a small business loan, an agricultural loan, a municipal bond, and a subsidy loan.
The collateral may include at least one of the following items: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, tools, machinery, and personal property.
The data collection circuit 5512 may also be configured to receive result data 5510 relating to the loan 5530 and the corresponding mortgage, and wherein the valuation circuit 5544 includes an artificial intelligence circuit configured to iteratively refine 5550 the valuation model 5552 based on the result data 5510.
The valuation circuitry 5544 can also include market value data collection circuitry 5548 configured to monitor and report market information relating to the value of at least one of the plurality of collateral. The market value data collection circuit 5548 is further configured to monitor pricing or financial data for items similar to collateral in at least one public market.
The clustering circuit 5532 may be configured to identify a set of countermeasures 5534 for evaluating a collateral based on similarity to attributes of the collateral.
The attributes of the collateral may be selected from the following: the type of collateral object, the age of the collateral object, the condition of the collateral object, the history of the collateral object, the storage conditions of the collateral object, and the geographic location of the collateral object.
The data collection circuit 5512 may also be configured to interpret the condition 5511 of the collateral.
The data collection circuit may further include at least one of the following systems: the system comprises an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system and an interactive crowdsourcing system.
The loan may comprise at least one of the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
The loan management circuit 5922 may be configured to interpret events related to the loan 5539 and to perform a loan-related action 5538 in response to the loan-related events.
The loan-related events may include events related to at least one of: the value of the loan, the condition of the mortgage of the loan, or the ownership of the mortgage of the loan.
The loan-related action may include at least one of: modifying the terms and conditions of the loan; providing a notification to one of the parties; providing necessary notification to the loan borrower; and the redemption of loan-bound property.
The respective API component of the circuit may also include a user interface configured to interact with a plurality of users of the system.
The plurality of users may each include: one of the plurality of parties, one of the plurality of entities, or a representation of any of the foregoing. At least one of the plurality of users may include: the prospective principal, the prospective entity, or a representative of any of the foregoing.
Referring to fig. 56, an illustrative and non-limiting example method for processing a loan 5600 is described. An example method may include receiving data related to a plurality of mortgages (step 5602); setting a value of each of a plurality of collateral (step 5604); assigning at least a portion of the plurality of mortgages as a guarantee for the loan (step 5608); and recording at least a portion of the allocated plurality of mortgages in an entry in the distributed ledger, wherein the entry is for recording an event related to the loan (step 5610). The intelligent loan contract for the loan may be modified (step 5612).
The terms and conditions of the loan may be specified (step 5614). The terms and conditions are each selected from the following: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line plan, party, insured person, collateral, personal guaranty, lien, deadline, contract, redemption hold, default condition, and result of default.
Result data associated with the loan may be received (step 5618). The valuation model can be iteratively refined based on the result data and the corresponding collateral (step 5620). Market information relating to the value of at least one of the plurality of collateral may be monitored (step 5622).
A set of items similar to one of the plurality of mortgages may be identified based on similarity to the attributes of the one of the plurality of mortgages (step 5624).
The status of one of the mortgages may be interpreted (step 5628).
Events related to the value of one of the mortgages, the status of one of the mortgages or ownership of one of the mortgages may be reported (step 5630).
Events related to the value of one of the mortgages, the condition of one of the mortgages or ownership of one of the mortgages may be interpreted (step 5632); and actions related to the secured loan may be performed in response to an event related to securing one of the mortgages of the loan (step 5634).
The loan-related action may be selected from the following actions: the method includes the steps of offering a loan, accepting the loan, underwriting the loan, setting a loan interest rate, deferring payment requirements, modifying the loan interest rate, verifying the property of the collateral, recording changes in the property, evaluating the value of the collateral, initiating collateral review, expediting the loan, closing the loan, setting terms and conditions of the loan, providing notification to the borrower of the requirements, stopping the redemption of property subject to the loan, and modifying the terms and conditions of the loan.
Referring to FIG. 57, an illustrative and non-limiting example system 5700 for a system for adaptive intelligence and robotic process automation capabilities is described. The example system may include a controller 5701. The controller may include a data collection circuit 5728 that may collect data from a variety of sources and systems, such as collateral data 5732, collateral-related environment data 5734, and the like, including: the system comprises an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system and an interactive crowdsourcing system. Based on the received data 5732, 5734, the data collection circuit 5728 may identify a collateral event 5730.
The controller 5701 may also include various AI circuits 5744, including an evaluation circuit 5702, which may determine a value of a collateral based in part on the received data 5732, 5734. The valuation circuit 5702 can include a market value monitor circuit 5706 that is configured to determine market data about a collateral or a cancellation collateral, where the market data can contribute to valuation of the collateral. The AI circuits may also include intelligent contract service circuits 5710 to facilitate services related to loans 5729, such as creating intelligent contracts 5722, identifying terms and conditions 5724 of intelligent contracts 5722, identifying borrower priorities, and tracking value allocations 5726 between borrowers. The intelligent contract service circuit 5710 may provide data to the blockchain service circuit 5736 that the blockchain service circuit 5736 is capable of creating and modifying loan entries 5727 on the distributed ledger 5725, where the loan entries 5717 may include terms and conditions, data about collateral used to secure the loan, borrower priorities and value assignments, and the like. The AI circuit 5744 may also include a collateral classification circuit 5740 that creates a counteraction collateral 5704, the counteraction collateral 5704 sharing at least one attribute with one of the collateral, where the common attribute may be a category of the item, a life of the item, a condition of the item, a history of the item, ownership of the item, a caretaker of the item, a warranty of the item, an owner condition of the item, liens of the item, storage conditions of the item, a geographic location of the item, and a jurisdiction of the item. Offsetting the use of the collateral 5742 may facilitate the market value monitoring circuit 5706 in obtaining relevant market data and an overall determination of the value of the collateral.
The data collection circuit 5728 may identify a collateral event 5730 using the received data and a determination of the value of the collateral. Based on the collateral event 5730, the automatic agent circuit 5746 may take action 5748. Action 5748 may be a loan-related action, such as: offer loan; receiving a loan; underwriting loan; setting interest rate of the loan; a deferred payment requirement; modifying interest rate of the loan; the loan is collected; settlement loan; setting the terms and conditions of the loan; providing a notification to be provided to the borrower; the redemption of loan assets; modify the terms and conditions of the loan, etc. The action 5748 may be a collateral-related action, such as verifying the title of one of a set of collateral, recording changes to the title of one of a set of collateral, evaluating the value of one of a set of collateral, initiating an inspection of one of a set of collateral, initiating maintenance of one of a set of collateral, initiating a vouching of one of a set of collateral, and modifying terms and conditions of one of a set of collateral.
Referring to fig. 58, an illustrative and non-limiting example method 5800 for loan creation and management is depicted. An example method 5800 may include receiving data relating to a set of mortgages for providing a guarantee for the loan (step 5802), and receiving data relating to an environment of one of the set of mortgages (step 5804). An intelligent loan contract for the loan may be created (step 5806), and the set of mortgages may be recorded in the intelligent loan contract (step 5808). A loan entry may be recorded in the distributed ledger (step 5810), where the loan entry includes an intelligent lending contract or a reference to an intelligent contract.
The value of each of a set of mortgages may be determined (step 5812), and the value of the mortgages may be apportioned among the borrowers based on the priorities of the different borrowers (step 5816). The valuation model may be modified based on a learning set (step 5814) that includes a set of valuation determinations for a set of mortgages, the results of loans having the mortgages as a guarantee, and valuations of the mortgages.
Collateral events may be determined based on the received data or the valuation of one of the collateral (step 5818). Loan-related actions may be performed in response to the determined mortgage event (step 5820), where the loan-related actions include: offer loans, accept loans, underwritten loans, set loan interest rates, defer payment requirements, modify loan interest rates, urge loans, settle loans, set terms and conditions of loans, provide notification to borrowers of claim offerings, stop the redemption of property subject to loan restrictions, modify terms and conditions of loans, and the like.
Loan-related actions may be performed in response to the determined mortgage event (step 5822), where the loan-related actions include: verifying the title of one of the set of collateral, recording changes to the title of one of the set of collateral, evaluating the value of one of the set of collateral, initiating an inspection of one of the set of collateral, initiating maintenance of one of the set of collateral, initiating a vouching of one of the set of collateral, modifying terms and conditions of one of the set of collateral, and the like.
One or more sets of offset mortgages can be identified (step 5824), wherein each item in a set of offset mortgages shares a common attribute with at least one of the mortgages. Market information may then be monitored to obtain data related to offsetting the collateral (step 5826). The value of the collateral may be updated using the monitored market information about one or more counteracting collateral (step 5828). The loan entries in the distributed ledger may be updated with the updated values of the mortgages (5830).
Referring to FIG. 59, an example system 5900 for adaptive intelligence and robotic process automation capabilities for trading, financial, and marketing support is depicted. The system 5900 can include a controller 5901, and the controller 5901 can include a plurality of AI circuits 5920. The plurality of AI circuits 5920 may include an intelligent contract service circuit 5910 to create and modify intelligent loan contracts 5912 for loans 5918. The intelligent lending contract 5912 may include terms and conditions 5914 of the loan 5918, contracts specifying the value of the collateral desired, information about the loan 5918 and the collateral, information about the borrowers including borrower priorities including the allocation 5916 of collateral value among the borrowers.
The plurality of AI circuits 5920 can include an valuation circuit 5902 configured to determine one or more values 5908 of a collateral based on the valuation model 5909 and the collateral data 5940. The valuation circuitry 5902 may include collateral classification circuitry 5903 to identify a cancellation collateral 5907 based on common attributes with the collateral used to secure the loan 5918. The market value monitoring circuit 5906 may receive market information 5942 about the collateral and cancellation collateral 5907. The market information 5942 may be used by the valuation model 5909 to determine the value 5908 of the collateral. The valuation circuitry 5902 can also include a valuation model improvement circuitry 5904 to improve a valuation model 5909 used to determine the value 5908. The valuation model refinement circuit 5904 may utilize a training set that includes previously determined values 5908 for mortgages and data about the mortgages as the result of a guaranteed loan.
The plurality of AI circuits 5920 may include a loan management circuit 5922 that may include a value comparison circuit 5928 to compare the value 5908 of the collateral to a desired value of the collateral specified in the loan obligation to determine a collateral compensation value 5930. The intelligent contract service circuit 5910 may determine the terms of the loan 5918 or the conditions 5914 in response to the mortgage compensation value 5930, where the terms of the conditions 5914 are related to loan components, such as the lending parties, the loan mortgages, the loan-related events and the loan-related activities of the intelligent loan contract 5912, and the like. The terms of the conditions may be: the principal amount of the loan, the balance of the loan, the fixed interest rate, the variable interest rate description, the payment amount, the payment plan, the last significant payback plan, the collateral description, the collateral replacement description, the party description, the insured description, the insurer description, the warranty description, the personal warranty, the lien, the redemption condition, the default condition, the result of the default, the contract associated with any of the foregoing, and the term of any of the foregoing. The terms of the conditions may be: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last term big return plan, party, insured person, guarantor, guaranty, personal guaranty, lien, deadline, contract, redemption-up condition, default outcome, and the like. The intelligent contract service circuit 5910 may modify the intelligent lending contract 5912 to include new terms or conditions 5914, such as the terms and conditions 5914 determined in response to the collateral compensation value 5930.
The loan management circuitry 5922 may also include automated brokering circuitry 5924 to take action 5926 based on the collateral compensation value 5930. Act 5926 may be: verifying the title of the collateral, recording changes to the title of the collateral, evaluating the value of the collateral, initiating inspection of the collateral, initiating maintenance of the collateral, initiating collateral coverage, and modifying the terms and conditions of the collateral.
The controller 5901 may also include a data collection circuit 5932 to receive the collateral data 5940 and determine a collateral event 5934. The reporting circuit 5936 may then report the collateral event 5934 and the collateral data 5940. The blockchain service circuit 5938 may create and update blockchain data 5925 that stores a copy of the intelligent loan contracts 5912.
Referring to FIG. 60, an illustrative and non-limiting method 6000 for robotic process automation for trading, financial, and marketing activities is depicted. An example method may include receiving data relating to one or a set of mortgages (step 6002), where the mortgages serve as a collateral for the loan. Based on the received data and the valuation model, the value of the collateral is determined (step 6004). An intelligent lending contract is created (step 6006) that specifies information about the loan, including a contract that specifies a desired value for securing a desired collateral for the loan.
The value of the collateral may be compared to the value of the collateral specified in the contract (step 6008) and a collateral compensation value may be determined (step 6010), wherein the collateral compensation value may be positive if the value of the collateral exceeds the desired value of the collateral and negative if the value of the collateral is lower than the desired value of the collateral. Loan-related actions may be performed in response to the collateral compensation value (step 6012). Terms or conditions may be determined in response to the collateral compensation value (step 6014), and the intelligent loan contract may be modified (step 6016).
The valuation model can be modified based on a first set of valuation determinations for the first set of mortgages and a set of corresponding loan results having the first set of mortgages as a guarantee using the following system (step 6018): machine learning systems, model-based systems, rule-based systems, deep learning systems, neural networks, convolutional neural networks, feedforward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, simulation systems, and hybrid systems of at least two of any of the foregoing, and the like.
A set of counteracting mortgages may be identified based on common attributes of the mortgage (step 6020), such as the category of the mortgage, the age of the mortgage, the condition of the mortgage, the history of the mortgage, ownership of the mortgage, the caretaker of the mortgage, the collateral warranty, the condition of the owner of the mortgage, the lien of the mortgage, the storage condition of the mortgage, the geographic location of the mortgage, and the jurisdiction of the mortgage. Market information may be monitored to obtain data related to offsetting collateral (step 6022), such as pricing or financial data; and may modify the intelligent loan contract in response to the market information (step 6024). An action may be automatically initiated based on the market information (step 6026). The action may include modifying the terms of the loan, issuing a notice of the default, initiating a redemption action that modifies the condition of the loan, providing a notice to the party of the loan, providing the borrower of the loan with the necessary notice and redeeming property that is subject to the loan constraint, verifying the property rights of the collateral, recording changes to the property rights of the collateral, evaluating the value of the collateral, initiating inspection of the collateral, initiating maintenance of the collateral, initiating the collateral warranty, and modifying the terms and conditions of the collateral.
Referring to FIG. 61, an illustrative and non-limiting example system 6100 for a system for adaptive intelligence and robotic process automation capabilities is described. An example system may include a controller 6101, the controller 6101 including data collection circuitry 6128 configured to receive collateral data 6132 for a plurality of collateral used to guarantee a set of loans 6118. The data collection circuit 6128 may also include: the system comprises an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system and an interactive crowdsourcing system. The collateral can include vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, tools, machinery, personal property, and the like. The set of loans may include: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, subsidy loans, and the like. The set of loans 6118 may be distributed among multiple borrowers as a means of dispersing loan risk.
The controller 6101 can also include a plurality of AI circuits 6144, including a collateral classification circuit 6120, to identify from the collateral a set of collateral 6122 that are related by sharing common attributes, such as the type of collateral, the category of collateral, the value of collateral, the price of the type of collateral, the value of the type of collateral, the description of collateral, the product feature set of collateral, the model of collateral, the brand of collateral, the manufacturer of collateral, the age of collateral, the condition of collateral, the valuation of collateral, the state of collateral, the background of collateral, the state of collateral, the storage location of collateral, the history of collateral, the ownership, the management of collateral, the security of collateral, the history of retention, the history of collateral, the storage location, the history of retention, the history of collateral, the history of all of the use history, the use history of collateral, the use history, and the administration history of all the collateral. The collateral classification circuitry 6120 may also identify a cancellation collateral 6123, where the cancellation collateral 6123 and the collateral share a common attribute.
The reporting circuit 6134 may also report a mortgage event 6130 based on the mortgage data 6132. Automated agent circuit 6108 may automatically perform action 6109 based on collateral event 6130. The action 6109 may be a collateral-related action, such as verifying the property rights of one of the plurality of collateral, recording changes to the property rights of one of the plurality of collateral, evaluating the value of one of the plurality of collateral, initiating an inspection of one of the plurality of collateral, initiating maintenance of one of the plurality of collateral, initiating a vouch-for of one of the plurality of collateral, and modifying terms and conditions of one of the plurality of collateral, and the like. Action 6109 may be a loan-related action, such as: offer loan; receiving a loan; an underwriting loan; setting interest rate of loan; a deferred payment requirement; modifying the interest rate of the loan; the loan is collected; settlement loan; setting the terms and conditions of the loan; providing a notification to be provided to the borrower; the redemption of loan assets; modify the terms and conditions of the loan, etc.
The controller 6101 may also include intelligent contract service circuitry 6110 to create an intelligent lending contract 6112 for a single loan or a group of loans 6118, where the intelligent lending contract 6112 identifies a subset of mortgages 6116 selected from the group of related mortgages 6122 that share common attributes to serve as a guarantee for the group of loans 6118. The intelligent contract service circuitry 6110 may also redefine the collateral subset 6116 based on the updated value of the collateral, thereby rebalancing the collateral for a set of loans based on the collateral value. The identification of the subset of collateral 6116 may be identified in real-time as the common attributes change in real-time (e.g., the status of the collateral or whether the collateral is in transit within a defined period of time). Further, the intelligent contract service circuit 6110 may determine the terms or conditions 6114 of the loan based on the value of one of the mortgages, where the terms or conditions 6114 are related to the loan component (e.g., the principal of the loan, the mortgage of the loan, the loan-related event, and the loan-related activity). Clause or condition 6114 may be: principal amount of the loan, balance of the loan, fixed interest rate, variable interest rate description, payment amount, payment plan, last minute best effort plan, collateral description, collateral replacement description, party description, insured description, insurer description, warranty description, personal warranty, lien, redemption condition, default outcome, contract relating to any of the foregoing, term of any of the foregoing, and the like. The controller 6101 can also include intelligent contract service circuitry 6110 that uses blockchain data 6124, including intelligent lending contracts 6126 and blockchain service circuitry 6136, to also communicate with the intelligent contract service circuitry 6110 using blockchain data 6124.
The controller may also include a valuation circuit 6102 to determine a value 6140 for each of the subset of mortgages based on the received data and the valuation model 6142. The valuation model refinement circuit 6104 may modify the valuation model 6142 based on a first set of valuation determinations for a first set of mortgages and a corresponding set of loan results having the first set of mortgages as a guarantee. The valuation model improvement circuit 6104 may include: machine learning systems, model-based systems, rule-based systems, deep learning systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, simulation systems, hybrid systems including at least two of any of the foregoing, and the like. The valuation circuitry 6102 can also include market value data collection circuitry 6106 to monitor and report market information 6138, such as pricing or financial data related to a mortgage 6123 or a set of mortgages 6122.
Referring to FIG. 62, a method 6200 for automated trading, financial and marketing activities is depicted. A method may include: receiving data relating to a collateral (6202); identifying a group of mortgages, wherein items in the group share a common attribute or characteristic (6204); identifying a subset of the group as a group of collateral for the loan (6208); and creating an intelligent lending contract for the group of loans, wherein the intelligent lending contract identifies a subset of the group that serves as a guarantee (6210). The common attribute shared by the set of collateral may be in the received data.
The value of each collateral can be determined using the received data and the valuation model (6212). The subset of mortgages used as a collateral can then be redefined based on the value of the different mortgages (6214). Terms or conditions of at least one of the intelligent lending contracts may be determined based on the value of at least one of the mortgages in the subset of the set (6218), and the intelligent lending contract is modified to include the determined terms or conditions (6220). Further, in some embodiments, the valuation model (6222) can be modified based on a first set of valuation determinations for a first set of mortgages and a corresponding set of loan results having the first set of mortgages as a guarantee.
A set of cancellation mortgages can be identified (step 6224), wherein each member of the set of cancellation mortgages and a set of the plurality of items share a common attribute. The information market may be monitored and a set of market information for the offset collateral may be reported (step 6226).
Fig. 63 depicts a system 6300 that includes a data collection circuit 6324, the data collection circuit 6324 being configured to receive data 6302 about a group of parties to a loan 6312. The data collection circuit may also be configured to receive collateral-related data 6308 related to a set of collateral 6314 that serves as a collateral for the loan, and determine a condition of the set of collateral, wherein the change in interest rate is further based on the condition of the set of collateral. The collateral may be: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, personal property, and the like. The received data may include attributes of the group of parties to the loan, where the change in interest rate may be based in part on the attributes. The data collection circuit may include an internet of things circuit, an image capture device, a networked monitoring circuit, an internet monitoring circuit, a mobile device, a wearable device, a user interface circuit, an interactive crowdsourcing circuit, and the like. For example, the data collection circuitry may include internet of things circuitry 6354, the internet of things circuitry 6354 configured to monitor attributes of the set of parties to the loan. The data collection circuit may include a wearable device 6306 associated with at least one of the set of parties, wherein the wearable device is structured to obtain human-related data 6304, and wherein the received data includes at least a portion of the human-related data. The data collection circuit may include a user interface circuit 6326, the user interface circuit 6326 being configured to receive data from the parties to the loan, and to provide data from at least one of the parties to the loan as part of the received data. The data collection circuit may include an interactive crowdsourcing circuit 6338, the interactive crowdsourcing circuit 6338 configured to request data related to at least one of the group of parties to the loan, receive the requested data, and provide at least a subset of the requested data as part of the received data. The data collection circuit may include an internet monitoring circuit 6340, the internet monitoring circuit 6340 being configured to retrieve data related to the principal of the loan from at least one public information website 6322. The system may include intelligent contract circuitry 6332 configured to create intelligent loan contracts 6334 for loans 6316. The loan may be of a type selected from the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, subsidy loans, and the like. The intelligent contract circuit may be configured to determine the terms or conditions 6318 of the intelligent loan contract based on the attributes and to modify the intelligent loan contract to include the terms or conditions. Terms or conditions may be related to the loan component, such as the lender, the loan mortgage, the loan-related event, the loan-related activity, and so on. The term or condition may be the principal amount of the loan, the balance of the loan, the fixed interest rate, the variable interest rate description, the payment amount, the payment plan, the last-minute payment plan, the collateral description, the collateral replacement description, the description of the party, the description of the insured person, the description of the insurer, the description of the insured person, the personal guaranty, the lien, the redemption condition, the default condition, the consequence of the default, the contract relating to any of the foregoing, the term of any of the foregoing, or the like. The system may include an automated agent circuit 6336, the automated agent circuit 6336 configured to automatically perform a loan-related action 6320 in response to the received data, wherein the loan-related action is a change in the interest rate of the loan, and wherein the intelligent contract circuit is further configured to update the intelligent loan contract using the changed interest rate. The system may include a valuation circuit 6328, e.g., valuation circuit 6328 configured to determine a value of at least one of the set of collateral based on the received data and a valuation model 6330. The intelligent contract circuit may be configured to determine terms or conditions of the intelligent lending contract based on the value of at least one of the set of collateral and modify the intelligent lending contract to include the terms or conditions. Terms or conditions may be related to the loan component, such as the lender, the loan mortgage, the loan-related event, the loan-related activity, and so on. The term or condition may be the principal amount of the loan, the balance of the loan, the fixed interest rate, the variable interest rate description, the payment amount, the payment plan, the last-minute payment plan, the collateral description, the collateral replacement description, the description of the party, the description of the insured person, the description of the insurer, the description of the insured person, the personal guaranty, the lien, the redemption condition, the default condition, the consequence of the default, the contract relating to any of the foregoing, the term of any of the foregoing, or the like. The valuation circuitry can include valuation model refinement circuitry 6342, where the valuation model refinement circuitry modifies the valuation model based on, for example, a first set of valuation determinations 6344 for a first set of mortgages and a corresponding set of loan results having the first set of mortgages as guarantees. The valuation model improvement circuit can include a system, such as a machine learning system, a model-based system, a rule-based system, a deep learning system, a neural network, a convolutional neural network, a feed-forward neural network, a feedback neural network, a self-organizing map, a fuzzy logic system, a random walk system, a random forest system, a probabilistic system, a bayesian system, a simulation system, a hybrid system comprising at least two of the foregoing, and the like. The change in interest rate may also be based on the value of at least one of a set of collateral. The valuation circuitry can include market value data collection circuitry 6346, the market value data collection circuitry 6346 configured to monitor and report market information 6343 for a countermortgage associated with the value of the mortgage. The market value data collection circuit may be configured to monitor one of pricing or financial data of the offset collateral in the at least one public market and report the monitored one of pricing or financial data. The system may include a collateral classification circuit 63150, the collateral classification circuit 63150 configured to identify a set of cancellation collateral 6352, where each member of the set of cancellation collateral and at least one of the set of collateral share a common attribute. The common attribute may be a category of the item, a service life of the item, a condition of the item, a history of the item, ownership of the item, a caretaker of the item, a guarantee of the item, a condition of an owner of the item, a lien of the item, a storage condition of the item, a geographic location of the item, a place of jurisdiction of the item, and the like.
FIG. 64 depicts a method 6400 that includes receiving data related to at least one of a group of lending parties (6402); creating an intelligent loan contract for the loan (6404); performing a loan-related action in response to the received data (6408), wherein the loan-related action is a change in the interest rate of the loan; and updating the intelligent loan contract using the changed interest rate (6410). The method may also include receiving data related to a set of mortgages that serve as a guarantee of the loan (6414); determining a condition of the set of collateral (6418); and performing a loan-related action in response to the condition of the set of mortgages, wherein the loan-related action may be a change in interest rate of the loan (6420). The method may also include receiving data related to a set of mortgages that act as a loan guarantee (6422); determining a condition of at least one of the set of collateral (6424); determining terms or conditions of the intelligent lending contract based on the condition of at least one of the set of collateral (6428); and modifying the intelligent lending contract to include the terms or conditions (6430). The method may include identifying a set of cancellation mortgages, wherein each member of the set of cancellation mortgages and at least one of the set of mortgages share a common attribute, and monitoring the set of cancellation mortgages in a common market, and may also report the monitored data. The method may include changing the interest rate of a loan warranted by at least one of the set of collateral, for example, based on the monitored set of counteracting collateral.
Fig. 65 depicts a system 6500 that includes a data collection circuit 6518, the data collection circuit 6518 configured to obtain data 6502 from a public information source 6504 (e.g., a website, news article, social network, crowd-sourced information, etc.) related to at least one party in a group of parties 6506 to a loan 6508 (e.g., a primary borrower, a secondary borrower, a lending bank, a corporate borrower, a government borrower, a bank borrower, a secured borrower, a bond issuer, a bond purchaser, an unsecured lender, a secured borrower, a secured supplier, a borrower, a debtor, an underwriter, an inspector, an evaluator, an auditor, an appraisal professional, a government, an accountant, etc.). The data collection circuit may also be configured to receive collateral-related data 6308 related to a set of collateral 6512 that serves as a collateral for the loan, and determine a condition of at least one of the set of collateral, wherein the change in interest rate is further based on the condition of the at least one of the set of collateral. The obtained data may include financial status of at least one of the parties in the group of lending parties. The financial condition may be determined based on at least one attribute of at least one of the parties in the set of lending parties, the attribute selected from the group consisting of: a public valuation of a party, a set of properties owned by a party as indicated by a public record, a valuation of a set of properties owned by a party, a bankruptcy state of a party, a redemption state of a party, a contract violation state of a party, a criminal state of a party, an export regulation state of a party, a contraband state of a party, a duty state of a party, a tax state of a party, a credit report of a party, a credit rating of a party, a website rating of a party, a set of customer reviews of a party product, a social network rating of a party, a set of credentials of a party, a set of referrals of a party, a set of credentials of a party, a set of behaviors of a party, a location of a party, a geographic location of a party, a place of jurisdiction of a party, and the like. The system may include intelligent contract circuitry 6524 configured to create intelligent loan contracts 6526 for loans 6508. The intelligent contract circuit may be configured to specify terms and conditions in the intelligent lending contract, wherein one of the terms or conditions in the intelligent lending contract governs one of a loan-related event or a loan-related activity. The system may include an automated brokering circuit 6528, the automated brokering circuit 6528 configured to automatically perform a loan-related action 6516 in response to the acquired data, wherein the loan-related action is a change in the interest rate of the loan, and wherein the intelligent contract circuit is further configured to update the intelligent loan contract using the changed interest rate. The automated brokering circuit may be configured to identify an event related to the loan (e.g., a value of the loan, a condition of the mortgage, or ownership of the mortgage) based, at least in part, on the received data. The automated brokering circuit may be configured to perform one of the following actions in response to a loan-related event: offer the loan, accept the loan, underwrite the loan, set the interest rate of the loan, defer payment requirements, modify the interest rate of the loan, verify the property of at least one of the set of collateral, evaluate the value of at least one of the set of collateral, initiate a check of at least one of the set of collateral, set or modify terms and conditions 6514 of the loan (principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, top-of-the-line plan, party, insured person, guarantor, guaranty, personal guaranty, lien, deadline, contract, redemption condition, default condition, and default outcome), provide notification to one of the parties, provide necessary notification to the borrower of the loan, and prevent property that is bound by the loan. The loan may include a loan type, such as an automobile loan, an inventory loan, a capital equipment loan, a performance bond, a capital improvement loan, a construction loan, an accounts receivable warranty loan, an invoice financing arrangement, a warranty arrangement, a payday loan, a refund prospective loan, an assisted loan, a banking loan, a property loan, a housing loan, a risk debt loan, an intellectual property loan, a contractual obligation loan, a floating fund loan, a small business loan, an agricultural loan, a municipal bond, a subsidy loan, and the like. The acquired data may be associated with the set of collateral objects, such as vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a set of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, tools, machinery, personal property, and the like. The system may include a valuation circuit 6520, the valuation circuit 6520 configured to determine a value of at least one of a set of collateral based on the acquired data and a valuation model 6522. The valuation circuitry can include valuation model refinement circuitry 6530, where the valuation model refinement circuitry modifies the valuation model based on a first set of valuation determinations 6532 for a first set of mortgages and a corresponding set of loan results having the first set of mortgages as a guarantee. The valuation model refinement circuitry may include: machine learning systems, model-based systems, rule-based systems, deep learning systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, simulation systems, hybrid systems including at least two of any of the foregoing, and the like. The intelligent contract circuit may be further configured to determine terms or conditions of the intelligent loan contract based on the value of at least one of the set of collateral, modify the terms or conditions of the loan based on market information for counteracting the collateral relating to the value of the collateral, and so on. The system may include a collateral sorting circuit 65138, the collateral sorting circuit 65138 being configured to identify a set of cancellation collateral, wherein each member of the set of cancellation collateral 6540 and at least one of the set of collateral share a common attribute (e.g., a category of the item, a life of the item, a condition of the item, a history of the item, ownership of the item, a caretaker of the item, a guarantee of the item, an owner condition of the item, lien rights of the item, storage conditions of the item, a geographic location of the item, jurisdiction of the item, etc.). The valuation circuitry can also include market value data collection circuitry 6534, the market value data collection circuitry 6534 configured to monitor and report market information 6536 for countermeasures related to the value of the collateral, monitor pricing or financial data for the countermeasures in the public market, and the like, and report the monitored pricing or financial data.
FIG. 66 depicts a method 6600, comprising obtaining data related to at least one of a group of lending parties from a common source (6602), wherein the common information source may be selected from the following: websites, news articles, social networks, and crowd sourced information. The method may include creating an intelligent lending contract (6604). The method may include performing a loan-related action in response to the obtained data (6606), where the loan-related action is a change in interest rate of the loan. The method may include updating the intelligent loan contract with the changing interest rate (6608). The method may include receiving collateral-related data related to a set of collateral acting as a collateral for the loan (6610), and determining a condition of at least one of the set of collateral, wherein the change in interest rate is further based on the condition of the at least one of the set of collateral (6612). The method may include identifying a loan-related event based at least in part on the data related to the loan (6614), and performing an action in response to the loan-related event (6618): the method includes the steps of offering a loan, accepting the loan, underwriting the loan, setting an interest rate of the loan, deferring payment requirements, modifying an interest rate of the loan, verifying a property of at least one of the set of collateral, evaluating a value of at least one of the set of collateral, initiating an inspection of at least one of the set of collateral, setting or modifying terms and conditions of the loan, providing a notification to one of the parties, providing a necessary notification to a borrower of the loan, stopping the redemption of property that is subject to the loan, and the like. The method may include determining a value of at least one of the set of collateral based on at least one of collateral-related data or the acquired data and a valuation model. The method may include determining at least one of a term or a condition of the intelligent lending contract based on a value of at least one of the set of collateral. The method may include modifying the intelligent lending contract to include at least one of the terms or conditions. The method may include modifying the valuation model based on a first set of valuation determinations for a first set of mortgages and a corresponding set of loan results having the first set of mortgages as a guarantee. The method may include identifying a set of cancellation mortgages, wherein each member of the set of cancellation mortgages and at least one of the set of cancellation mortgages share a common attribute (6620); monitoring one of pricing data or financial data of at least one of the set of offset collateral in at least one public market (6622); reporting monitoring data for at least one of the set of cancellation collateral (6624); and modifying the terms or conditions of the loan based on the reported monitored data (6628).
Fig. 67 depicts a system 6700 that includes a data collection circuit 6720, the data collection circuit 6720 being configured to receive data 6702 relating to the status 6704 of a loan 6712 and data relating to a set of collateral objects 6706 that serve as a collateral for the loan. The data collection circuit may monitor one or more of the lending entities using the following system: internet of things systems, camera systems, networked monitoring systems, internet monitoring systems, mobile device systems, wearable device systems, user interface systems, and interactive crowdsourcing systems 67132. For example, the interactive crowd-sourcing system may include a user interface 6734, the user interface 6734 for requesting information from the crowd-sourcing site 6718 related to one or more loan entities, and wherein the user interface is configured to allow one or more of the loan entities to enter information about one or more of the loan entities. In another example, the networked monitoring system may include a network search circuit 6721, the network search circuit 6721 configured to search publicly available information sites for information related to one or more of the loan entities. The system may include a blockchain service circuit 6744, the blockchain service circuit 6744 configured to maintain a safety history ledger 6746 for the loan-related event and to interpret a plurality of access control features 6708 corresponding to a plurality of parties 6710 associated with the loan. The system may include a loan evaluation circuit 67148, the loan evaluation circuit 67148 configured to determine a loan status based on the received data. The data collection circuitry may receive data relating to one or more of the loan entities 6714, where the loan assessment circuitry may determine whether the contract is met based on the data relating to one or more of the loan entities. The loan assessment circuit may be configured to determine an execution status of a condition of the loan based on the received data and a status of one or more of the loan entities, and wherein the determination of the loan status is determined based in part on the status of the at least one or more of the loan entities and the execution status of the condition of the loan. For example, the terms of the loan may relate to at least one of payment fulfillment and contract satisfaction. The data collection circuit may include a market data collection circuit 6736, the market data collection circuit 6736 configured to receive financial data 6738 regarding at least one of the plurality of parties associated with the loan. The loan evaluation circuit may be configured to determine a financial condition of at least one of a plurality of parties associated with the loan based on the received financial data, where the at least one of the plurality of parties may be a primary borrower, a secondary borrower, a lending bank, a corporate borrower, a government borrower, a bank borrower, a secured borrower, a bond issuer, a bond purchaser, an unsecured lender, a secured contributor, a borrower, a debtor, an underwriter, an inspector, an evaluator, a valuation professional, a government official, an accountant, and the like. The received financial data may be related to an attribute of the entity of one of the plurality of parties, such as: a public valuation of a party, a set of properties owned by a party as indicated by a public record, a valuation of a set of properties owned by a party, a bankruptcy status of a party, a redemption status of an entity, a contract breach status of an entity, a violation status of an entity, a criminal status of an entity, an export regulation status of an entity, a contraband status of an entity, a duty status of an entity, a tax status of an entity, a credit report of an entity, a credit rating of an entity, a website rating of an entity, a set of customer reviews of a product of an entity, a social network rating of an entity, a set of credentials of an entity, a set of referrals of an entity, a set of proofs of an entity, a set of behaviors of an entity, a location of an entity, a geographic location of an entity, and the like. The system may include an intelligent contract circuit 6726, the intelligent contract circuit 6726 being configured to create an intelligent lending contract 6728 for the loan. The intelligent contract circuit may be configured to determine a term or condition of the intelligent loan contract based on the value of at least one of the set of collateral, and modify the intelligent loan contract to include the term or condition, wherein the term or condition may be a principal amount of the debt, a balance of the debt, a fixed interest rate, a variable interest rate, a payment amount, a payment plan, a last significant payback plan, a party, a policyholder, a guarantor, a guaranty, a personal guaranty, a right to reserve, a term, a contractual, a redemption condition, a default placement outcome, or the like. The system may include an automated brokering circuit 6730, the automated brokering circuit 6730 configured to perform a loan action 6716 based on the loan status, wherein the block chain service circuit may be configured to update the historical ledger of the event using the loan action. The system can include a valuation circuit 6722, the valuation circuit 6722 configured to determine a value of at least one of a set of collateral based on the received data and a valuation model 6724. The valuation circuitry can include valuation model refinement circuitry 6740, where the valuation model refinement circuitry modifies the valuation model based on a first set of valuation determinations for a first set of mortgages and a corresponding set of loan results having the first set of mortgages as a guarantee. The valuation model refinement circuitry may include: a machine learning system, a model-based system, a rule-based system, a deep learning system, a hybrid system, a neural network, a convolutional neural network, a feed-forward neural network, a feedback neural network, a self-organizing map, a fuzzy logic system, a random walk system, a random forest system, a probabilistic system, a Bayesian system, or a simulation system. The valuation circuit can include a market value data collection circuit 6742 configured to monitor and report market information for a cancellation collateral in relation to the value of the collateral. The market value data collection circuit may also be configured to monitor pricing or financial data for offsetting collateral in the public market, such as reporting the monitored pricing or financial data. The intelligent contract circuit may be further configured to modify terms or conditions of the loan based on collateral-counteracting market information relating to the value of the collateral. The system can include a collateral classification circuit 67150, the collateral classification circuit 67150 configured to identify a set of cancellation collateral 6752, wherein each member of the set of cancellation collateral and at least one of the set of collateral can share a common attribute. The common attribute may be a category of the collateral, a lifetime of the collateral, a condition of the collateral, a history of the collateral, ownership of the collateral, a caretaker of the collateral, a guarantee of the collateral, a condition of an owner of the collateral, a lien of the collateral, a storage condition of the collateral, a geographic location of the collateral, a jurisdiction of the collateral, and the like.
FIG. 68 depicts a method 6800, including maintaining a safety history ledger for loan-related events (6802); receiving data relating to a status of the loan (6804); receiving data relating to a set of mortgages, the set of mortgages serving as a collateral for the loan (6808); determining the status of the loan (6810); performing a loan action based on the loan status (6812); and updating the historical ledger for the loan-related event (6814). The method may also include receiving data relating to one or more loan entities (6818), and determining whether a contract for the loan is met based on the received data (6820). The method may also include determining an execution status of the loan condition, wherein the determination of the loan status is based in part on the execution status of the loan condition. The method may also include receiving financial data associated with at least one party to the loan. The method may also include determining a financial status of at least one party to the loan based on the financial data. The method may also include determining a value of at least one set of collateral based on the received data and the valuation model. The method may also include determining at least one of the terms or conditions of the loan based on the value of at least one of the mortgages (6822), and modifying the intelligent lending contract to include the at least one of the terms or conditions (6824). The method may include identifying a set of cancellation mortgages, wherein each member of the set of cancellation mortgages and at least one of the set of mortgages share a common attribute (6828); receiving data related to a set of canceling collateral, wherein determining a value of at least one set of collateral is based in part on the received data related to the set of canceling collateral (6830).
Referring to fig. 69, an illustrative and non-limiting example smart contract system for managing mortgages of a loan 6900 is depicted. The example system may include a controller 69101. The controller 69101 may include a data collection circuit 6912 configured to monitor the status of the loan 6930 and the loan collateral 6928, and a number of artificial intelligence circuits 6942 including an intelligent contract circuit 6922, the intelligent contract circuit 6922 being configured to process information from the data collection circuit 6912 and, in response to at least one of the status of the loan or the status of the loan collateral, automatically initiate at least one of replacement, removal, or addition of one or more items of the collateral of the loan based on the information and the intelligent loan contract 6931; and a blockchain service circuit 6958, the blockchain service circuit 6958 configured to interpret the plurality of access control features 698 corresponding to the at least one principal associated with the loan and record the at least one replacement, removal, or addition in the distributed ledger 6940 for the loan. The data collection circuit may also include at least one other system 6962 of the following systems: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and an interactive crowdsourcing system.
The status of the loan 6930 may be determined based on at least one of a status of at least one of the entities associated with the loan, e.g., the user 6951, and an execution status of the conditions of the loan. The status of fulfillment of the condition may relate to at least one of payment fulfillment of the loan or contract satisfaction. The status of the loan may be determined based on the status of at least one entity associated with the loan and the fulfillment status of the loan conditions; fulfillment of the condition may involve at least one of payment fulfillment or loan contract satisfaction. The data collection circuit 6912 may also be configured to determine compliance with the compact by monitoring at least one entity. The data collection circuit 6912 may monitor the financial status of at least one entity acting as the party to the loan when the at least one entity is the party to the loan. The condition of the loan may include a financial status of the loan, and wherein the execution state of the financial status may be determined based on an attribute of the following attributes: a public valuation of at least one entity, a property owned by at least one entity as indicated by a public record, a valuation of a property owned by at least one entity, a bankruptcy status of at least one entity, a redemption status of at least one entity, a contract breach status of at least one entity, a violation status of at least one entity, a criminal status of at least one entity, an export regulation status of at least one entity, a contraband status of at least one entity, a tariff status of at least one entity, a tax status of at least one entity, a credit report of at least one entity, a credit rating of at least one entity, a website rating of at least one entity, a plurality of customer reviews of products of at least one entity, a social network rating of at least one entity, a plurality of credentials of at least one entity, a plurality of referrals of at least one entity, a behavior of at least one entity, a location of at least one entity, a geographic location of at least one entity, and a relevant jurisdiction of at least one entity.
The lending party may be selected from the following: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, and accountants.
The data collection circuit 6912 may be further configured to monitor the status of the mortgage based on at least one of the following attributes: the type of collateral object, the age of the collateral object, the condition 6911 of the collateral object, the history of the collateral object, the storage conditions of the collateral object, and the geographic location of the collateral object.
The controller 69101 may include a valuation circuit 6944, the valuation circuit 6944 configured to determine a value of the collateral based on a state of the collateral for the loan using a valuation model 6952. The intelligent contract circuit 6922 may initiate at least one substitution, removal, or addition of one or more items in the collateral to maintain the value of the collateral within a predetermined range.
The valuation circuit 6944 can also include a trade result processing circuit 6964 configured to interpret result data 6910 relating to the collateral trade and iteratively refine 6950 the valuation model in response to the result data.
The valuation circuitry 6944 can also include a market value data collection circuit 6948 configured to monitor and report market information related to the value of a collateral. The market value data collection circuitry 6948 may monitor pricing or financial data for the cancellation collateral 6934 in at least one public market.
The market value data collection circuit 6948 is further configured to construct a set of offset collateral 6934, the offset collateral 6934 for determining a value of the collateral using the clustering circuit 6932 of the controller 69101 based on attributes of the collateral. The attributes may be selected from the following: the type of collateral object, the age of the collateral object, the condition of the collateral object, the history of the collateral object, the storage conditions of the collateral object, and the geographic location of the collateral object.
The terms and conditions 6924 of the loan may include at least one member of the following group: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line payment plan, collateral description, collateral substitutability description, party, insured person, guarantor, personal guaranty, lien, term, contract, redemption condition, default condition, and default outcome.
The intelligent contract circuitry may further include loan management circuitry 6960 or be in communication with the loan management circuitry 6960 configured to specify terms and conditions of the intelligent loan contract 6931 that govern at least one of the terms and conditions of the loan, the loan-related events 6939, or the loan-related activities or actions 6938.
Referring to fig. 70, an example smart contract method 7000 for managing a mortgage is described. The example method may include monitoring the status of the loan and the mortgage of the loan (step 7002); processing information from the monitoring (step 7004); automatically initiating at least one of a replacement, removal, or addition of one or more items of a mortgage of the loan based on the information (step 7008); and interpreting a plurality of access control features corresponding to at least one party associated with the loan (step 7010) and recording at least one of a replacement, removal, or addition operation in a distributed ledger of the loan (step 7012). The status of the loan may be determined based on at least one of a status of at least one of the entities related to the loan and an execution status of the conditions of the loan.
The method may also include interpreting the information from the monitoring (step 7014) and determining a value using a valuation model of a set of mortgages based on at least one of the status of the loan or the mortgages of the loan (step 7018). At least one of the substitution, removal, or addition operations may maintain the value of the collateral within a predetermined range. The method may also include interpreting result data related to the transaction of one of the collateral or the cancellation collateral (step 7020), and iteratively refining the valuation model in response to the result data (step 7022). The method may also include monitoring and reporting market information related to the value of the collateral (step 7024).
The method may also include monitoring pricing data or financial data for the counteracting collateral in the at least one public market (step 7028).
The method may also include specifying at least one of terms and conditions of the intelligent contract, terms and conditions of the intelligent contract management loan, a loan-related event, or a loan-related activity (step 7030).
Referring to fig. 71, an illustrative and non-limiting exemplary crowdsourcing system for verifying the condition of a collateral or guarantor for a loan 7100 is depicted. The example system may include a controller 71101. The controller 71101 may include a data collection circuit 7112, a user interface 7154, and a number of artificial intelligence circuits 7142 (including intelligent contract circuits 7122), a robotic process automation circuit 7174, a crowdsourcing request circuit 7160, a crowdsourcing communication circuit 7162, a crowdsourcing distribution circuit 7164, and a blockchain service circuit 7158.
The crowdsourcing request circuit 7160 may be configured to configure at least one parameter of a crowdsourcing request 7168, the crowdsourcing request 7168 relating to obtaining information 7104 about a status 7111 of a mortgage 7102 of a loan 7130 or a status of a guarantor of the loan 7130. It may also enable a workflow through which the human user 7106 enters at least one parameter to establish a crowdsourcing request. The at least one parameter may include a type of information requested, an award, and a condition for receiving the award. The reward may be selected from the following rewards: financial rewards, tokens, tickets, contract rights, cryptocurrency, a plurality of reward points, discounts on currency, products or services, and access rights.
The crowdsourcing distribution circuit 7164 may be used to distribute crowdsourcing requests 7168 to a group of information providers.
The crowd-sourced communication circuit 7162 may be configured to collect and process at least one response 7172 from a group of information providers 7170 and provide a reward 7180 to at least one of the group of information providers in response to a successful information provision event.
The crowd-sourced communication circuit 7162 also includes a smart contract circuit 7122, the smart contract circuit 7122 configured to manage a reward 7180 by determining a successful information provision event in response to at least one parameter configured for the crowd-sourced request 7168, and automatically assign the reward 7180 to at least one of a set of information providers 7170 in response to the successful information provision event. It may also be configured to process the at least one response 7172 and, in response, automatically take loan-related action. The action may be at least one of a redemption hold action, a lien management action, an interest rate setting action, a default origination action, a collateral replacement, or a loan claim.
The loan 7130 may comprise at least one of the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
The crowdsourcing request circuit 7160 may also be configured to configure at least one additional parameter of the crowdsourcing request 7168 to obtain information about the status 7111 of the mortgage of the loan.
The collateral 7102 may include at least one of: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
The mortgage status 7111 may be determined based on attributes from the following: the quality of the collateral, the condition of the collateral, the state of the property right of the collateral, the state of possession of the collateral and the state of the lien of the collateral. When the collateral is an item, the condition may be determined based on an attribute of the following attributes: a new or used state of the item, a type of the item, a category of the item, a description of the item, a product feature set of the item, a model of the item, a brand of the item, a manufacturer of the item, a state of the item, a background of the item, a condition of the item, a value of the item, a storage location of the item, a geographic location of the item, a life of the item, a maintenance history of the item, a usage history of the item, an accident history of the item, a failure history of the item, ownership of the item, an ownership history of the item, a price of the type of the item, a value of the type of the item, an assessment of the item, and an assessment of the item.
The blockchain service circuit 7158 may be configured to record in the distributed ledger 7140 identification information and at least one parameter of a crowdsourcing request, at least one response to the crowdsourcing request, and a reward description.
The robotic process automation circuit 7174 may be configured to configure a crowdsourcing request based on at least one attribute of the loan based on training with at least one of a crowdsourcing request circuit or a crowdsourcing communication circuit on a training data set 7178 that includes human user interaction. At least one attribute of the loan may be obtained from the intelligent contract circuit 7122 that manages the loan. The training data set 7178 may also include results 7110 from a plurality of crowdsourcing requests.
The robotic process automation circuit 7174 may also be configured to determine a reward 7180.
The robotic process automation circuit 7174 may also be configured to determine at least one domain to which the crowdsourcing publication circuit 7164 publishes the crowdsourcing request 7168.
Referring to fig. 72, a crowdsourcing method 7200 for verifying the status of a collateral or guarantor for a loan is provided herein. At least one parameter of the crowdsourcing request may be used to obtain information about the condition of the loan mortgage or the condition of the loan guarantor (step 7202). The crowdsourcing request may be issued to a group of information providers (step 7204). At least one response to the crowdsourcing request may be collected and processed (step 7208). An incentive may be provided to at least one of the set of information providers in response to a successful information provision event (step 7210). A reward description may be issued to at least a portion of the set of information provider groups in response to a successful information provision event (step 7212). A reward may be automatically assigned to at least one of the group of information providers in response to a successful information provision event (step 7230). The method may also include recording identification information and at least one parameter of the crowdsourcing request, at least one response to the crowdsourcing request, and a reward description in a distributed ledger of the crowdsourcing request (step 7214). The graphical user interface may be used to enable a workflow through which a human user enters at least one parameter to establish a crowd-sourced request (step 7218). Loan-related actions may be automatically taken in response to a successful information provision event (step 7220). The robotic process automation circuit may train the robotic process automation circuit based on a training data set including a plurality of results corresponding to a plurality of crowdsourcing requests and operate the robotic process automation circuit to iteratively improve the crowdsourcing requests (step 7222). At least one attribute of the loan may be provided to the robotic process automation circuit to configure the crowdsourcing request (step 7224). Configuring the crowdsourcing request may include determining a reward. At least one attribute of the loan may be provided to the robotic process automation circuit to determine at least one domain to which to issue a crowdsourcing request (step 7228).
Referring to fig. 73, an illustrative and non-limiting example smart contract system 7300 for modifying a loan 7330 is depicted. The example system may include a controller 7301. The controller 7301 may include a data collection circuit 7312, a valuation circuit 7344, and several artificial intelligence circuits 7342, which include an intelligent contract circuit 7322, a clustering circuit 7332, and a loan management circuit 7360. The data collection circuit 7312 may be configured to determine location information corresponding to each of a plurality of entities involved in the loan. Smart contract circuitry 7322 may be configured to determine a jurisdiction of at least one of the plurality of entities in response to the location information. Smart contract circuitry 7322 may be configured to automatically perform loan-related actions 7338 for loans based at least in part on a jurisdiction of at least one of the plurality of entities.
The smart contract circuit 7322 may be further configured to automatically perform loan-related actions in response to a first one of the plurality of entities being in a first jurisdiction and a second one of the plurality of entities being in a second jurisdiction.
The loan-related actions 7338 may include at least one of the following loan-related actions: the method includes the steps of offering a loan, accepting the loan, underwriting the loan, setting a loan interest rate, deferring payment requirements, modifying the loan interest rate, verifying the property of a collateral, recording changes in the property, evaluating the value of the collateral, initiating collateral review, expediting the loan, closing the loan, setting terms and conditions of the loan, providing notification to the borrower of the requirements, stopping the redemption of property subject to the loan, and modifying the terms and conditions of the loan.
The smart contract circuit 7322 may also be configured to process a plurality of jurisdiction-specific regulatory requirements 7368 (e.g., requirements related to notifications) and provide appropriate notifications to borrowers based on the jurisdiction corresponding to at least one of the following entities: a borrower, funds provided via a loan, a repayment for a loan, or a collateral for a loan.
The smart contract circuit 7322 may also be configured to process a plurality of jurisdiction-specific regulatory requirements 7368, such as requirements related to redemption suspension, and provide appropriate redemption suspension notification to the borrower based on the jurisdiction of at least one of the borrower, funds provided over the loan, the repayment of the loan, and the collateral for the loan.
The intelligent contract circuit 7322 may be further structured to process a plurality of jurisdiction-specific rules 7370 for setting terms and conditions of loans 7324, and configure the intelligent contract 7331 based on the jurisdiction corresponding to at least one of the following entities: the borrower, the funds provided via the loan, the repayment of the loan, and the collateral for the loan.
The smart contract circuit 7322 may be further configured to determine the interest rate of the loan such that the loan complies with a maximum interest rate limit applicable to the jurisdiction corresponding to the selected one of the plurality of entities.
The data collection circuit 7312 may be further configured to monitor the result data 7310 and the status 7311 of the mortgage of the loan, for example, using the mortgage data 7304, and where the smart contract circuit is further configured to determine the interest rate of the loan responsive to the status of the mortgage of the loan.
The data collection circuit 7312 may be further configured to monitor attributes of at least one of the plurality of entities that is a party to the loan, and where the intelligent contract circuit is further configured to determine an interest rate of the loan in response to the attributes.
The smart contract circuit 7322 may also include a loan management circuit 7360, the loan management circuit 7360 being operable to specify terms and conditions of the smart contract, the terms and conditions governing at least one of loan terms and conditions 7324, loan-related events 7339, or loan-related activities 7372.
The loan may comprise at least one of the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty administration, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
The terms and conditions of the loan may each comprise at least one member of the group: principal amount of the debt, balance of the debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line payment plan, collateral description, collateral substitutability description, party, insured person, guarantor, guaranty, personal guaranty, lien, term, contract, redemption condition, default condition, and result of default.
The data collection circuitry 7312 may also include at least one additional system 7362 of: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and an interactive crowdsourcing system.
The valuation circuit 7344 may be configured to determine a value of a collateral for the loan based on a jurisdiction corresponding to at least one of the plurality of entities using the valuation model 7352. The valuation model 7352 can be a jurisdiction-specific valuation model, and wherein a jurisdiction corresponding to at least one of the plurality of entities includes a jurisdiction corresponding to at least one of the following entities: the borrower, the funds provided in accordance with the loan, the delivery location of the funds provided in accordance with the loan, the payment of the loan, and the collateral for the loan.
At least one of the terms and conditions of the loan may be based on the value of the mortgage of the loan.
The collateral may include at least one of the following items: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
The valuation circuit 7344 may also include a trade result processing circuit 7364 configured to interpret result data relating to the mortgage trade and iteratively refine 7350 the valuation model in response to the result data.
The valuation circuitry 7344 may also include market value data collection circuitry 7348 configured to monitor and report market information related to the value of the collateral. The market value data collection circuit may monitor pricing data or financial data of the offset collateral in the at least one public market. A set of canceling collateral 7334 for evaluating the collateral can be constructed using a clustering circuit 7332 based on the collateral attributes. The attributes may be selected from: the type of collateral object, the age of the collateral object, the condition of the collateral object, the history of the collateral object, the storage conditions of the collateral object, and the geographic location of the collateral object.
Referring to fig. 74, a smart contract method 7400 for modifying a loan is provided herein. An example method may include monitoring location information corresponding to each of a plurality of entities involved in the loan (step 7402); location information regarding the entity is processed and loan-related actions are automatically taken on the loan based at least in part on the location information (step 7404). An example method includes processing a plurality of jurisdiction-specific regulatory notification requirements and providing appropriate notifications to the borrower based on the borrower, the funds provided over the loan, the repayment of the loan, and/or the location of the loan collateral (step 7408). The example method includes processing a plurality of jurisdiction-specific rules for setting terms and conditions of the loan and configuring an intelligent contract based on the borrower, the funds provided over the loan, the repayment of the loan, and/or the location of the mortgage of the loan (step 7410). The example method also includes determining the interest rate of the loan such that the loan meets the maximum interest rate limit applicable to the jurisdiction (step 7412). The example method may monitor at least one of a condition of a plurality of mortgages of the loan or an attribute of one of the entities that is the party to the loan, where the condition or attribute is used to determine the interest rate (step 7414). The example method may specify at least one of the terms and conditions of the intelligent contract, the intelligent contract management terms and conditions, the loan-related event, or the loan-related activity (step 7418). The example method includes interpreting the location information and using a valuation model to determine the value of a plurality of mortgages of the loan based on the location information (step 7420). The exemplary method includes interpreting result data relating to the mortgage transaction and iteratively refining the valuation model in response to the result data (step 7422). The example method includes monitoring and reporting market information related to collateral value (step 7424).
A plurality of jurisdiction-specific requirements based on a jurisdiction of a related entity of the plurality of entities may be processed, and at least one operation may be selected from the operations comprising: providing an appropriate notification to the borrower in response to a plurality of jurisdiction-specific requirements including regulatory notification requirements; setting specific rules for setting loan terms and conditions in response to a plurality of jurisdiction-specific requirements; in response to a plurality of jurisdiction-specific requirements including a maximum interest rate limit, determining an interest rate of the loan to conform the loan to the maximum interest rate limit; and wherein the related entities of the plurality of entities comprise at least one of the following entities: the borrower, the funds provided in accordance with the loan, the repayment from the loan, and the collateral for the loan (step 7408).
At least one of the status of the various mortgages of the loan or at least one of the attributes of at least one of the various entities that is a party to the loan may be monitored, with the conditions or attributes used to determine the interest rate (step 7414).
The valuation model may be operated to determine the value of the collateral for the loan based on the jurisdiction of at least one of the plurality of entities (step 7420).
The outcome data associated with the collateral transaction may be interpreted and the valuation model iteratively refined in response to the outcome data (step 7422).
Referring now to FIG. 75, an illustrative and non-limiting example intelligent contract system 7500 for modifying a loan is described. The example system can include a controller 75101. The controller 75101 may include a data collection circuit 7512, an assessment circuit 7544, and a number of artificial intelligence circuits 7542 including an intelligent contract circuit 7522, a clustering circuit 7532, and a loan management circuit 7560.
The data collection circuit 7512 may be configured to monitor and collect information about at least one entity 7530 involved in the loan. The smart contract circuit 7522 may be configured to automatically reorganize the debts associated with the loan based on the monitored and collected information about at least one entity involved in the loan. The monitored and collected information may include a status 7511 of mortgages for the loan, or according to at least one rule that is based on an agreement for the loan and wherein the reorganization occurs at an event determined with respect to at least one entity associated with the agreement, or the reorganization may be based on an attribute of the at least one entity monitored by the data collection circuitry. The event may be the failure of the mortgage to exceed the required partial value of the remaining balance of the loan, or the default of the agreement by the buyer.
The smart contract circuit 7522 may also be configured to determine the occurrence of an event based on the obligation of the loan and the monitored and collected information about at least one entity involved in the loan, and to automatically reorganize the debt in response to the occurrence of the event.
The intelligent contract circuit 7522 may also include a loan management circuit 7560, and the loan management circuit 7560 may be configured to specify terms and conditions of the intelligent contract, the terms and conditions managing at least one of loan terms and conditions 7524, loan-related events 7539, or loan-related activities 7572.
The loan may include at least one of the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
The terms and conditions of the loan may include at least one member of the group: principal amount of the debt, balance of the debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line payment plan, collateral description, collateral substitutability description, party, insured person, guarantor, guaranty, personal guaranty, lien, term, contract, redemption condition, default condition, and result of default.
The data collection circuitry 7512 may also include at least one additional system 7562 of: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and an interactive crowdsourcing system.
The valuation circuit 7544 can be configured to determine the value of a collateral based on monitored and collected information about at least one entity involved in the loan using the valuation model 7552. The intelligent contract circuit may also be configured to automatically reorganize the debt based on the value of the collateral.
The collateral may include at least one of: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
The valuation circuit 7544 can also include a transaction result processing circuit 7564 configured to interpret result data 7510 related to the collateral transaction and iteratively refine 7550 the valuation model in response to the result data.
The valuation circuitry 7544 can also include a market value data collection circuit 7548 configured to monitor and report market information related to the value of a collateral. Market value data collection circuitry 7548 monitors pricing data or financial data of cancellation collateral 7534 in at least one public market. A set of cancellation collateral 7534 for evaluating the collateral can be constructed using a collateral attribute based clustering circuit 7532. The attributes may be selected from: the type of collateral object, the age of the collateral object, the condition of the collateral object, the history of the collateral object, the storage conditions of the collateral object, and the geographic location of the collateral object.
Referring now to FIG. 76, an illustrative and non-limiting example intelligent contract method 7600 for modifying a loan is described. The method includes monitoring and collecting information about at least one entity related to the loan (step 7602); processing information from monitoring at least one entity (step 7604); and automatically reorganizing the debt associated with the loan based on the monitored and collected information about the at least one entity (step 7608). Determining the occurrence of the event may be based on the obligation of the loan and the monitored and collected information about at least one entity involved in the loan, and the method may include automatically reorganizing the debt in response to the occurrence of the event.
Terms and conditions of a smart contract governing at least one of loan terms and conditions, loan-related events, and loan-related activities may be specified (step 7610).
The operational valuation model determines the value of the collateral based on the monitored and collected information about at least one entity involved in the loan (step 7612).
The result data associated with the collateral transaction may be interpreted and the valuation model iteratively refined in response to the result data (step 7614).
The method may also include monitoring and reporting market information related to the value of the collateral (step 7618).
Pricing or financial data for offsetting collateral may be monitored in at least one public market (step 7620).
A set of canceling collateral for the valuation collateral can be constructed using similarity clustering algorithms based on the collateral attributes (step 7622).
Referring now to FIG. 77, an illustrative and non-limiting example smart contract system 7700 for modifying a loan is described. The example system may include a controller 77101. The controller 77101 may include a data collection circuit 7712, social network input circuitry 7744, social network data collection circuitry 7732, and a number of artificial intelligence circuits 7742 (including intelligence contract circuitry 7722), warranty verification circuitry 7798, and robotic process automation circuitry 7748.
The social network data collection circuit 7732 may be configured to collect the result data 7710, etc. data using a plurality of algorithms for monitoring social network information about the entity 7764 involved in the loan 7730 in response to the loan guarantee parameters and identifying the data collection results. Social network input circuitry 7744 may be configured to interpret loan guarantee parameters. The warranty verification circuit 7798 may be configured to confirm the warranty of the loan in response to the monitored social networking information.
The loan guarantee parameter may include the financial status of the entity, where the entity is the insurer for the loan.
The vouch-for verification circuit 7798 may be further configured to determine a financial condition based on at least one attribute selected from the following: a public valuation of an entity, an entity-owned property as indicated by a public record, a valuation of an entity-owned property, a bankruptcy status of an entity, a redemption-out status of an entity, a contract breach status of an entity, a violation status of an entity, a criminal status of an entity, an export regulation status of an entity, a contraband status of an entity, a duty status of an entity, a tax status of an entity, a credit report of an entity, a credit rating of an entity, a website rating of an entity, a plurality of customer reviews of a product of an entity, a social network rating of an entity, a plurality of credentials of an entity, a plurality of referrals of an entity, a plurality of attestations of an entity, a plurality of behaviors of an entity, a location of an entity, a jurisdiction of an entity, and a geographic location of an entity.
The loan may include at least one of the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
The data collection circuit 7712 may be configured to obtain information about the status 7711 of a collateral of the loan, where the collateral includes at least one of: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property; wherein the collateral verification circuitry is further configured to verify the collateral of the loan in response to a condition of a collateral of the loan.
The condition 7711 of the mortgage may include condition attributes from the following group: the quality of the collateral, the status of the title of the collateral, the state of possession of the collateral, the lien status of the collateral, new or used status, type, category, description, product feature set, model, brand, manufacturer, status, background, condition, value, storage location, geographic location, age, maintenance history, usage history, accident history, failure history, ownership history, price, assessment, and valuation. The condition may be stored as collateral data 7704.
Social network input circuitry 7744 may also be configured to enable workflows by which a human user enters loan assurance parameters to establish social network data collection and monitoring requests.
The smart contract circuit 7722 may be configured to automatically take action related to the loan in response to verification of the loan. The action may be related to the loan in response to the loan guarantee not being verified, and wherein the action comprises at least one of: a redemption action, a lien management action, an interest rate adjustment action, a default origination action, a mortgage replacement, a loan hasty, and providing an alert to a secondary entity related to the loan.
The robotic process automation circuit 7748 may be configured to configure loan guarantee parameters based on at least one attribute of the loan based on iterative training with the social network data collection circuit on a training data set 7746 that includes human user interaction. At least one attribute of the loan 7730 may be obtained from the intelligent contract circuit that manages the loan.
The robotic process automation circuit 7748 may also be configured to determine at least one domain to which the social network data collection circuit will apply.
Training may include training the robotic process automation circuit 7748 to configure a plurality of algorithms.
Referring now to FIG. 78, an illustrative and non-limiting example intelligent contract method 7800 for modifying a loan is described. The loan guarantee parameters may be interpreted (step 7801). Data collection data may be collected using a plurality of algorithms for monitoring social networking information about entities involved in the loan in response to the loan guarantee parameters (step 7802). The loan guarantee may be verified in response to the monitored social networking information (step 7804). A workflow may be enabled through which a human user enters the loan guarantee parameters to establish a social network data collection and monitoring request (step 7808). In response to verification of the loan, loan-related actions may be automatically performed (step 7810). The robotic process automation circuit may configure the data collection and monitoring actions based on the at least one attribute of the loan by iterative training, wherein the robotic process automation circuit is trained using a plurality of algorithms based on a training data set including at least one of the results from the human user interaction (step 7812). At least one domain to which the plurality of algorithms are to be applied may be determined (step 7814).
Referring to FIG. 79, an illustrative and non-limiting example monitoring system 7900 for verifying loan guarantee conditions is depicted. The example system may include a controller 79101. The controller 79101 may include an internet of things data collection input circuit 7944, an internet of things data collection circuit 7932, and several artificial intelligence circuits 7942 (including an intelligent contract circuit 7922), a warranty verification circuit 7998, and a robotic process automation circuit 7948.
The internet of things data collection input circuit 7944 may be configured to interpret the loan guarantee parameters 7992. The internet of things data collection circuit 7932 may be configured to collect data using at least one algorithm for monitoring internet of things information collected from the entity 7964 involved in the loan 7930 and about the entity 7964 involved in the loan 7930 in response to the loan guarantee parameters. The warranty verification circuitry 7998 may be configured to confirm the warranty of the loan in response to the monitored internet of things information.
The loan guarantee parameter 7992 may include the financial status of the entity, where the entity is the holder of the loan. The monitored internet of things information may include at least one of: a public valuation of an entity, an entity-owned property as indicated by a public record, a valuation of an entity-owned property, a bankruptcy status of an entity, a redemption-out status of an entity, a contract breach status of an entity, a violation status of an entity, a criminal status of an entity, an export regulation status of an entity, a contraband status of an entity, a duty status of an entity, a tax status of an entity, a credit report of an entity, a credit rating of an entity, a website rating of an entity, a plurality of customer reviews of a product of an entity, a social network rating of an entity, a plurality of credentials of an entity, a plurality of referrals of an entity, a plurality of attestations of an entity, a plurality of behaviors of an entity, a location of an entity, a jurisdiction of an entity, and a geographic location of an entity.
The loan may include at least one of the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
The internet of things data collection circuit 7932 may be further configured to obtain the result data 7910, the collateral data 7904 to determine information about collateral conditions 7911 for the loan, wherein the collateral includes at least one of: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, merchandise, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property; wherein the collateral verification circuitry 7998 is further configured to verify the collateral of the loan in response to a condition of a collateral of the loan.
The collateral status 7911 may include status attributes in: the quality of the collateral, the status of the title of the collateral, the state of possession of the collateral, the lien status of the collateral, new or used status, type, category, description, product feature set, model, brand, manufacturer, status, background, condition, value, storage location, geographic location, age, maintenance history, usage history, accident history, failure history, ownership history, price, assessment, and valuation.
The internet of things data collection circuit 7944 may also be configured to enable a workflow by which a human user enters loan assurance parameters 7992 to establish an internet of things data collection request.
The intelligent contract circuit 7922 may be configured to automatically take actions related to the loan in response to verification of the loan. The loan-related action may be in response to the loan guarantee not being verified, and wherein the action comprises at least one of: a redemption action, a lien management action, an interest rate adjustment action, a default origination action, a mortgage replacement, a loan hasty, and providing an alert to a secondary entity related to the loan.
The robotic process automation circuit 7948 may be configured to configure a loan assurance parameter based on at least one attribute of the loan based on iterative training with the internet of things data collection circuit on a training data set that includes human user interaction. At least one attribute of the loan is obtained from an intelligent contract circuit that manages the loan. The training data set 7946 may also include results of a plurality of internet of things data collection and monitoring requests performed by the internet of things data collection circuitry.
The robotic process automation circuit 7948 may also be configured to determine at least one domain to which the internet of things data collection circuit is to be applied.
The training may include training the robotic process automation circuit 7948 to configure at least one algorithm.
Referring to fig. 80, an illustrative and non-limiting exemplary monitoring method for verifying the warranty terms of the loan 8000 is depicted. An example method may include interpreting loan guarantee parameters (step 8002); collecting data using a plurality of algorithms for monitoring collected internet of things (IoT) information from and about entities involved in the loan in response to the loan guarantee parameters (step 8004); and verifying the loan guarantee in response to the monitored internet of things information (step 8005).
The loan guarantee parameters may be configured to obtain information about the financial status of the entity that is the guarantor of the loan (step 8008). At least one algorithm may be configured to obtain information regarding the status of a collateral for the loan (step 8010), wherein the collateral includes at least one of: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property; the collateral of the loan is further verified in response to the condition of the collateral of the loan.
A workflow may be initiated through which a human user enters loan assurance parameters to establish an internet of things data collection request (step 8012).
Loan-related actions may be automatically taken in response to the verification (step 8014).
The loan-related action may be in response to the loan guarantee not being verified, and wherein the action comprises an out-of-redemption action.
The loan-related action may be in response to the loan guarantee not being verified, and wherein the action comprises a lien management action.
The loan-related action may be in response to the loan guarantee not being verified, and wherein the action comprises an interest rate setting action.
The loan-related action may be in response to the loan guarantee not being verified, and wherein the action comprises a default origination action.
The loan-related action may be in response to the loan guarantee not being verified, and wherein the action includes the replacement of a collateral.
The loan-related action may be in response to the loan guarantee not being verified, and wherein the action includes loan payment.
The loan-related action may be in response to the loan guarantee not being verified, and wherein the action includes providing an alert to a second entity involved in the loan.
The robotic process automation circuit may be iteratively trained to configure the internet of things data collection and monitoring action based on the at least one attribute of the loan, wherein the robotic process automation circuit is trained using a plurality of algorithms based on a training data set including at least one of the results from the human user interaction (step 8018).
At least one domain to which at least one algorithm is to be applied may be determined (step 8020). Training may include training the robotic process automation circuit to configure a plurality of algorithms.
The training data set may also include results from a set of internet of things data collection and monitoring requests.
Referring now to fig. 81, an illustrative and non-limiting exemplary robotic process automation system for negotiating a loan 8100 is depicted. The example system may include a controller 81101. The controller 81101 may include data collection circuitry 8112, valuation circuitry 8144, and a number of artificial intelligence circuitry 8142 (including automatic loan classification circuitry 8132), robotic process automation circuitry 8160, intelligent contract circuitry 8184, and clustering circuitry 8182.
The data collection circuitry 8112 may be configured to collect collateral data 8104 and create an interactive training set 8110 from at least one entity 8178 related to at least one loan transaction. The automatic loan classification circuit 8132 may be trained based on the interactive training set 8110 to classify at least one loan negotiation action. The robotic process automation circuit 8160 may be trained based on a plurality of loan negotiation actions 8174 and a plurality of training sets of loan transaction results 8139 classified by the automatic loan classification circuit 8132 to negotiate terms and conditions 8124 of a new loan on behalf of the party to the new loan 8130.
The data collection circuitry may also include at least one other system 8162 of the following: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and an interactive crowdsourcing system. The at least one entity may be a party to the at least one loan transaction, and may be selected from the following entities: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, and accountants.
The automatic loan classification circuit 8132 may include one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
The robotic process automation circuit 8160 may also be trained based on a plurality of party interactions with a plurality of user interfaces 8172 involved in a plurality of lending processes.
The smart contract circuit 8184 may be configured to automatically configure the smart contract 8188 for the new loan 8130 based on the results of the negotiation.
A distributed ledger 8180 may be associated with the new loan 8130, wherein the distributed ledger 8180 is structured to record at least one of a result of the negotiation and a negotiation event.
The new loan may include at least one of the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
The valuation circuit 8144 may be configured to determine the value of a collateral for a new loan using the valuation model 8152. The collateral may include at least one of the following items: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
The valuation circuitry can also include market value data collection circuitry 8148, the market value data collection circuitry 8148 configured to monitor and report market information related to the value of the collateral. The market value data collection circuitry 8148 may monitor pricing or financial data for the offset collateral 8134 in at least one public market. A set of cancellation collateral 8134 for evaluating the collateral can be constructed using a clustering circuit 8182 based on the collateral attributes. The attributes may be selected from the following: the type of collateral, the age of the collateral, the condition 8111 of the collateral, the history of the collateral, the storage conditions of the collateral, and the geographic location of the collateral. The terms and conditions 8124 of the new loan may include at least one member of the following group: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line payment plan, collateral description, collateral substitutability description, party, insured person, guarantor, personal guaranty, lien, term, contract, redemption condition, default condition, and default outcome.
Referring now to fig. 82, an illustrative and non-limiting example robotic process automation method 8200 for negotiating a loan 8100 is depicted. An example method may include collecting a training set of interactions from at least one entity related to at least one loan transaction (step 8202); training an automatic loan classification circuit based on the interactive training set to classify the at least one loan negotiation action (step 8204); and training the robotic process automation circuit to negotiate terms and conditions of a new loan on behalf of the party to the new loan based on the training set of the plurality of loan negotiation actions and the plurality of loan transaction results classified by the automatic loan classification circuit (step 8208).
The robotic process automation circuit can be trained based on multiple party interactions with multiple user interfaces involved in multiple lending processes (step 8210).
The smart contract for the new loan may be configured based on the results of the negotiation (step 8212).
At least one of the result of the negotiation and the negotiation event may be recorded in a distributed ledger associated with the new loan (step 8214).
The value of the mortgage for the new loan may be determined using the valuation model (step 8218).
The example method may also include monitoring and reporting market information related to the collateral value (step 8220).
A set of canceling collateral for the valuation collateral may be constructed using a clustering algorithm based on the similarity of the collateral attributes (step 8222).
Referring to fig. 83, an illustrative and non-limiting example system 8300 for a system for adaptive intelligence and robotic process automation capabilities is described. An example system may include a data collection circuit 8306 that may collect data such as a loan payment result 8303, a training set of loan interactions 8304, etc., where the training set of loan interactions 8304 may include payments 8305. Data may be collected from loan transactions 8319, loan data 8301, data about entities 8302 associated with the loan, and so on. Data can be collected from various sources and systems, such as: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and an interactive crowdsourcing system. The loan checkout result 8303 may include at least one of the following results: responses to a cash-receiving contact event, loan repayment, borrower's loan default, borrower's bankruptcy of the loan, cash lawsuit results, financial benefits of a set of cash-receiving actions, return on investment of the cash-receiving, reputation measures of parties involved in the cash-receiving, and the like.
The system may also include an artificial intelligence circuit 8310, the artificial intelligence circuit 8310 may be configured to classify a set of loan payment actions 8309 based at least in part on a training set 8304 of loan interactions. The artificial intelligence circuit 8310 can include at least one of the following systems, for example: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, simulation systems, and the like.
The system may also include a robotic process automation circuit 8313, the robotic process automation circuit 8313 configured to perform at least one loan payment action 8311 on behalf of the party to the loan 8312 based at least in part on the training set of loan interactions 8304 and the set of loan payment results 8303. The loan payment action 8311 taken by the robotic process automation circuit 8313 may be at least one of: refer the loan to the collection agency; configuring a checkout communication; arranging for a checkout communication; configuring the content of the checkout communication; configuring an offer to settle the loan; terminating the collection action; a deferred collection action; configuring an offer for an alternative payment plan; initiating litigation; initiating redemption stopping; initiating a production-breaking process; a re-occupation process; set collateral liens, etc. The loan party 8312 may include at least one of the following parties: primary borrowers, secondary borrowers, lending consortiums, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, accountants, and the like. The loan may include at least one of: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account receivable warranty loans, invoice financing arrangements, warranty arrangements, payday loans, refund expected loans, school loans, banker loans, property loans, housing loans, risk debt loans, intellectual property loans, contractual right loans, floating fund loans, small business loans, agricultural loans, municipal bond bonds, subsidy loans, and the like.
The system may also include an interface circuit 8308, the interface circuit 8308 being structured to receive interactions 8307 from one or more loan entities 8302. In some embodiments, the robotic process automation circuit 8313 may be trained based on the interactions 8307. The system may also include an intelligent contract circuit 8318, the intelligent contract circuit 8318 being structured to determine that the negotiation of the loan payment action 8311 is complete and to modify the contract 8316 based on the result of the cancellation 8317.
The system may also include a distributed ledger circuit 8315, the distributed ledger circuit 8315 being structured to determine at least one of a collection result 8320 or an event 8321 associated with the loan payment action 8311. The distributed ledger circuit 8315 may be configured to record events 8321 and/or collection results 8320 in the distributed ledger 8314 associated with the loan.
Referring to FIG. 84, an illustrative and non-limiting example method 8400 is described. The example method 8400 may include a step 8401 for collecting a training set of loan interactions and a set of loan receipt results among a set of entities for the loan transaction, where the training set of loan interactions includes a set of payments for a set of loans. A set of loan payment actions may be classified based at least in part on a training set of loan interactions (step 8402). The method may also include step 8403 specifying a loan-receiving action on behalf of the party to the loan based at least in part on the training set of loan interactions and the set of loan-receiving results.
The method 8400 may also include a step 8404 of determining that the negotiation of the loan receipt action is complete. In step 8405, the smart contract may be modified based on the results of the negotiation. The method may also include a step 8406 of determining at least one of a collection result or an event associated with the loan receipt action. At least one of the collection results or events may be recorded in a distributed ledger associated with the loan at step 8407.
Referring to FIG. 85, an illustrative and non-limiting example system 8500 for a system for adaptive intelligence and robotic process automation capabilities is described. An example system may include a data collection circuit 8506, the data collection circuit 8506 configured to collect a training set 8502 of loan interactions between entities, where the training set of loan interactions includes a set of loan refinancing activities 8503 and a set of loan refinancing results 8504. The system may include an artificial intelligence circuit 8310, the artificial intelligence circuit 8310 configured to classify the set of loan refinancing activities, wherein the artificial intelligence circuit is trained based on a training set of loan interactions. The system may include robotic process automation circuitry 8513, the robotic process automation circuitry 8513 configured to perform a second loan refinancing activity 8511 on behalf of a principal of a second loan 8312, wherein the robotic process automation circuitry is trained based on the set of loan refinancing activities and the set of loan refinancing results. An example system may include a data collection circuit 8506 that may collect data, such as a training set 8502 of loan interactions between entities. The data related to the training set 8502 of loan interactions between entities may include data related to loan refinancing activities 8503 and loan refinancing results 8504. Data may be collected from loan data 8501, entity information 8502, and the like. Data can be collected from various sources and systems, such as: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and an interactive crowdsourcing system. The loan refinancing activity 8503 may include at least one of: initiating a re-financing offer; initiating a re-financing request; configuring a re-financing rate; configuring a re-financing payment plan; configuring a refinancing balance; allocating a refinancing collateral; managing use of refinancing revenue; removing or setting liens associated with the refinancing; verifying the property right of the re-financing; managing an inspection flow; filling in an application; negotiating terms and conditions for rewarding; complete re-financing, etc.
The system may also include an artificial intelligence circuit 8310, the artificial intelligence circuit 8310 may be configured to classify the set of loan refinancing activities 8503 based at least in part on a training set of loan interactions 8505. The artificial intelligence circuit 8310 can include at least one of the following systems, for example: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, simulation systems, and the like.
The system may also include a robotic process automation circuit 8513, the robotic process automation circuit 8513 configured to perform a second loan refinancing activity 8511 on behalf of the party to the second loan 8312 based at least in part on the set of loan refinancing activities 8503 and the set of loan refinancing results 8504. The party of the second loan 8312 may include at least one of the following parties: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, accountants, and the like.
The second loan 8519 may comprise at least one loan from the group of: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, subsidy loans, and the like.
The system may also include an interface circuit 8508 that is configured to receive interactions 8507 from one or more entities 8502. In some embodiments, the robotic process automation circuit 8513 may be trained based on the interactions 8507. The system may also include an intelligent contract circuit 8518, the intelligent contract circuit 8518 being configured to determine that the second loan refinance activity 8511 is complete, and modify the intelligent refinance contract 8517 based on the results of the second loan refinance activity 8511.
The system may also include a distributed ledger circuit 8315, the distributed ledger circuit 8315 being structured to determine an event 8321 associated with the second loan refinance activity 8511. The distributed ledger circuit 8315 may be configured to record events 8321 associated with the second loan refinance activity 8511 in the distributed ledger 8314 associated with the second loan 8519.
Referring to fig. 86, an illustrative and non-limiting example method 8600 is depicted. An example method 8600 may include a step 8601 for collecting a training set of loan interactions between entities, where the training set of loan interactions includes a set of loan refinancing activities and a set of loan refinancing results. A set of loan refinancing activities may be classified based at least in part on a training set of loan interactions (step 8602). The method may also include a step 8603 for specifying a second loan refinancing activity on behalf of the party to the second loan based at least in part on the set of loan refinancing activities and the set of loan refinancing results.
The method 8600 may also include a step 8604 that includes determining that the second loan refinance activity is complete. Based on the results of the second loan refinancing campaign, the intelligent refinancing contract may be modified in step 8605. The method may also include a step 8606 of determining an event associated with the second loan refinancing activity. In step 8607, an event associated with the second loan refinancing activity may be recorded in a distributed ledger associated with the second loan.
Referring to FIG. 87, an illustrative and non-limiting example system 8700 for a system for adaptive intelligence and robotic process automation capabilities is described. An example system may include a data collection circuit 8705, the data collection circuit 8705 may collect data for a training set 8704 of loan interactions between entities, etc., the training set 8704 of loan interactions between entities may include a set of loan merge transactions 8703, etc. Such data may be collected from a loan 8701, information about the entity 8702, and the like. Data can be collected from various sources and systems, such as: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and a crowdsourcing system.
The system may also include an artificial intelligence circuit 8310, the artificial intelligence circuit 8310 may be configured to classify a group of loans as pending merger candidate loans based at least in part on the training set of loan interactions 8704. The artificial intelligence circuit 8310 can include at least one of the following systems, for example: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, simulation systems, and the like.
The system may also include a robotic process automation circuit 8713, the robotic process automation circuit 8713 configured to manage the merging of at least a subset of a set of loans 8711 on behalf of a loan merge party 8712 based at least in part on a training set 8703 of the loan merge transaction. Managing the merge may include: identifying loans in a set of candidate loans; compiling a combined offer; compiling a merging plan; compiling content conveying the consolidated offer; arranging for a combined offer; communicating a consolidated offer; negotiating a merge offer modification; compiling a merging protocol; executing a merge protocol; modifying a collateral for a group of loans; processing a merged application workflow; managing and checking; management evaluation; setting interest rate; a deferred payment requirement; set up a payment plan or reach a merge agreement.
The artificial intelligence circuit may also include a model that may be used to classify the candidate loans to be merged. The model may handle attributes of the entity, which may include: the identity of the party, interest rate, payment balance, payment terms, payment plan, loan type, collateral type, financial status of the party, payment status, collateral value, and the like.
The parties to the loan merger 8712 may include at least one of the following: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, accountants, and the like.
The loan 8701 may include at least one of: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, subsidy loans, and the like.
The system can also include an interface circuit 8707 configured to receive interactions 8706 from one or more entities 8702. In some embodiments, the robotic process automation circuit 8713 may be trained based on the interactions 8706. The system may also include an intelligent contract circuit 8720, the intelligent contract circuit 8720 configured to determine completion of the consolidated negotiation and modify the contract 8718 based on the results of the negotiation 8719.
The system can also include a distributed ledger circuit 8717, the distributed ledger circuit 8717 configured to determine at least one of a collection result 8715 or a negotiation event 8716 associated with the merge. The distributed ledger circuit 8717 may be configured to record negotiation events 8716 and/or collection results 8715 in the distributed ledger 8714 associated with the loan.
Referring to FIG. 88, an illustrative and non-limiting example method 8800 is described. The example method 8800 may include a step 8801 to collect a training set of loan interactions between entities, where the training set of loan interactions includes a set of loan merger transactions. A set of loan portfolios may be classified as merging candidates based at least in part on the training set of loan interactions (step 8802). The method may also include a step 8803 for managing the merger of at least a subset of the set of loans on behalf of the merging parties based at least in part on the set of loan merger transactions.
The method 8800 may also include a step 8804 to determine a consolidated negotiation completion for at least one loan from the subset of the set of loans. In step 8805, the smart contract may be modified based on the results of the negotiation. The method may further include the step 8806 determining at least one of results and negotiation events associated with the merger of at least a subset of the set of loans. At step 8807, at least one of the results and the negotiation events may be recorded in a distributed ledger associated with the merger.
Referring to FIG. 89, an illustrative and non-limiting example system 8900 for a system for adaptive intelligence and robotic process automation capabilities is described. An example system may include a data collection circuit 8905, where the data collection circuit 8905 may collect data information about an entity 8902 involved in a set of warranty loans 8901 and a training set 8904 of interactions between entities of a set of warranty loan transactions 8903. Data can be collected from various sources and systems, such as: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and a crowdsourcing system.
The system may also include an artificial intelligence circuit 8911, the artificial intelligence circuit 8911 may be configured to classify an entity 8908 involved in a set of warranty loans based at least in part on the interactive training set 8904. The artificial intelligence circuit 8911 can include at least one of the following systems, for example: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, simulation systems, and the like.
The system may also include a robotic process automation circuit 8913, the robotic process automation circuit 8913 configured to manage a warranty loan 8912 based at least in part on a warranty loan transaction 8903. Managing a warranty loan may include managing at least one of a set of warranty assets; identifying a warranty loan in a set of candidate loans; compiling a warranty offer; compiling a warranty plan; compiling content conveying warranty offers; arranging a warranty offer; communicating a warranty offer; negotiating a modification to the warranty offer; compiling a warranty protocol; executing a warranty protocol; modifying a set of mortgages of a warranty loan; processing a set of receivables transfers; processing a warranty application workflow; managing and checking; managing an evaluation of a set of assets to be warranted; setting interest rate; a deferred payment requirement; set up a payment plan or reach a merge agreement.
The artificial intelligence circuit 8911 may also include a model 8909, the model 8909 being usable to process attributes of entities involved in the set of warranty loans, which attributes may include assets for warranty, identity of the party, interest rate, payment balance, payment terms, payment plan, loan type, collateral type, financial status of the party, payment status, collateral status, or collateral value. The assets for the warranty may include a set of accounts receivable 8910. At least one of the entities 8902 may be a principal of at least one warranty loan transaction 8903. The principal may include at least one of the following, for example: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, accountants, and the like.
The system may also include an interface circuit 8907 configured to receive interactions 8906 from one or more entities 8902. In some embodiments, the robotic process automation circuit 8913 may be trained based on the interactions 8906.
The system may also include intelligent contract circuitry 8920, intelligent contract circuitry 8920 configured to determine that negotiation of the warranty loan is complete; and modify the intelligent insurance policy 8918 based on the results of the negotiation 8919.
The system may also include a distributed ledger circuit 8917, the distributed ledger circuit 8917 being structured to determine at least one of a result 8915 or a negotiation event 8916 associated with a negotiation of a warranty loan. The distributed ledger circuit 8917 may be configured to record negotiation events 8916 and/or results 8915 in a distributed ledger 8914 associated with a warranty loan.
Referring to FIG. 90, an illustrative and non-limiting example method 9000 is depicted. An example method 9000 may include a step 9001 of collecting information about an entity for a set of warranty loans and a training set of interactions between entities for a set of warranty loan transactions. Entities related to a set of warranty loans may be classified based at least in part on a training set of loan interactions (step 9002). The method can also include step 9003, which interactively manages the warranty loan based at least in part on the set of warranty loans.
The method 9000 may also include a step 9004 of determining that the negotiation of the warranty loan is complete. In step 9005, the intelligent contract may be modified based on the results of the negotiation. The method may also include a step 9006 of determining at least one of a result and a negotiation event associated with the negotiation of the warranty loan. At step 9007, at least one of the results and the negotiation events may be recorded in a distributed ledger associated with the warranty loan.
Referring to FIG. 91, an illustrative and non-limiting example system 9100 for a system for adaptive intelligence and robotic process automation capabilities is described. An example system may include a data collection circuit 9106, which may collect data information about entities 9102 and 9101 involved in a set of mortgage and mortgage activities 9105 and a training set 9104 of interactions between entities of the mortgage transactions 9103. Data can be collected from various sources and systems, such as: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and a crowdsourcing system.
The system can further include an artificial intelligence circuit 9110, the artificial intelligence circuit 9110 can be configured to classify an entity 9109 involved in a set of mortgage loan activities based at least in part on the interactive training set 9104. The artificial intelligence circuit 9110 can include at least one of the following systems, for example: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, simulation systems, and the like.
The system may further include a robotic process automation circuit 9112, the robotic process automation circuit 9112 configured to proxy the mortgage loan 9111 based at least in part on at least one of the mortgage loan activity set 9105 and the interactive training set 9104. The set of mortgage activities 9105 and/or the set of mortgage transactions 9103 may include activities selected from the group consisting of: a marketing campaign; identifying a group of potential borrowers; identifying property; identifying a collateral; ensuring that the borrower obtains qualification; searching for property rights; verifying the property right; evaluating the property; checking property; evaluating the property; verifying revenue; performing a demographic analysis on the borrower; identifying the patron; determining an available interest rate; determining available payment terms and conditions; analyzing an existing mortgage loan; performing a comparative analysis of existing loan conditions and new mortgage terms; completing the application workflow; filling an application field; compiling a mortgage protocol; completing the collateral protocol attached table; negotiating mortgage terms and conditions with the patron; negotiating mortgage terms and conditions with the borrower; transferring property rights; setting a lien right; or to achieve a mortgage agreement.
The artificial intelligence circuit 9110 may also include a model that may be used to process attributes of entities involved in the set of mortgage activities, which may be attributes subject to the mortgage loan, assets serving as mortgages, identities of parties, interest rates, payment spreads, payment terms, payment plans, types of mortgages, types of property, financial status of parties, payment status, state of property, or value of property. In an embodiment, a proxy mortgage includes at least one of the following activities: managing at least one of the mortgage assets; identifying candidate mortgages according to the condition of the borrower; compiling a mortgage offer; compiling content conveying a mortgage offer; arranging a mortgage offer; communicating a mortgage offer; negotiating a mortgage offer modification; compiling a mortgage protocol; executing a mortgage protocol; modifying a collateral for a set of collateral offers; processing the lien transfer; processing an application workflow; managing and checking; managing an evaluation of a set of assets to be collated; setting interest rate; a deferred payment requirement; setting a payment plan; to achieve a mortgage agreement, etc.
In an embodiment, at least one of the entities 9102 may be a party to at least one mortgage loan transaction of a set of mortgage loan transactions 9103. The principal may include at least one of the following, for example: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, accountants, and the like.
The system can also include interface circuitry 9108 that is configured to receive interactions 9107 from one or more entities 9102. In some embodiments, the robotic process automation circuit 9112 may be trained based on the interactions 9107.
The system may further include an intelligent contract circuit 9119, the intelligent contract circuit 9119 configured to determine that the negotiation of the mortgage loan is complete; and modify the intelligent insurance policy 9117 based on the results of the negotiation 9118.
The system can further include a distributed ledger circuit 9116, the distributed ledger circuit 9116 being configured to determine at least one of a result 9114 or a negotiation event 9115 associated with negotiation of a mortgage loan. The distributed ledger circuit 9116 may be configured to record negotiation events 9115 and/or results 9114 in a distributed ledger 9113 associated with a mortgage.
Referring to fig. 92, an illustrative and non-limiting example method 9200 is described. The example method 9200 may include a step 9201 of collecting information about entities involved in a set of mortgage loan activities and a training set of interactions between entities for a set of warranty loan transactions. Entities related to a set of warranty loans may be classified based at least in part on a training set of loan interactions (step 9202). The method may also include step 9203, which is based at least in part on at least one of a set of interactions of a set of mortgage activities and training, to broker the mortgage.
The method 9200 may also include a step 9204 that includes determining that the negotiation for the mortgage is complete. In step 9205, the smart contract may be modified based on the results of the negotiation. The method may also include step 9206, which includes determining at least one of a result and a negotiation event associated with the negotiation of the mortgage. At step 9207, at least one of the results and negotiation events may be recorded in a distributed ledger associated with the mortgage.
Referring to FIG. 93, an illustrative and non-limiting example system 9300 for a system for adaptive intelligence and robotic process automation capabilities is described. An example system may include a data collection circuit 9308, the data collection circuit 9308 may collect information about an entity 9305 involved in a set of debt transactions 9301, a training data set 9306 of results related to the entity, and a training set 9307 of debt management activities. Data can be collected from a variety of sources and systems, for example: the network domain query algorithm comprises the following components of the internet of things device, a set of environmental condition sensors, a set of crowdsourcing services, a set of social network analysis services or a set of network domain query algorithms and the like.
The system may further comprise a condition classification circuit 9314, the condition classification circuit 9314 may be configured to classify a condition 9311 of at least one of the entities 9305. The condition classification circuit 9314 can include a model 9312 and a set of artificial intelligence circuits 9313. The model 9312 can be trained using a training data set of results 9306 related to entities. The artificial intelligence circuit 9313 can include at least one of the following systems: a machine learning system, a model-based system, a rule-based system, a deep learning system, a hybrid system, a neural network, a convolutional neural network, a feed-forward neural network, a feedback neural network, a self-organizing map, a fuzzy logic system, a random walk system, a random forest system, a probabilistic system, a bayesian system, or a simulation system.
The system may further comprise an automatic debt management circuit 9316, the automatic debt management circuit 9316 being configured to manage debt related actions 9315. The automatic liability management circuit 9316 may be trained based on a training set 9307 of liability management activities.
In an embodiment, at least one debt transaction of the set of debt transactions 9301 may comprise: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, subsidy loans, and the like.
In an embodiment, the entity 9305 participating in the set of debt transactions may comprise at least one of a set of parties 9302 and a set of assets 9304. Assets 9304 can include municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, groups of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, or personal property. The system may further comprise a set of sensors 9303, said set of sensors 9303 being located on at least one of: at least one asset 9304 of the set of assets, a container for at least one asset of the set of assets, or a package for at least one asset of the set of assets, and wherein the set of sensors is to associate sensor information sensed by the set of sensors with a unique identifier of at least one asset of the set of assets. The sensors 9303 can include image, temperature, pressure, humidity, velocity, acceleration, rotation, torque, weight, chemical, magnetic, electric or position sensors.
In an embodiment, the system may further comprise a set of blockchain circuits 9324, the blockchain circuits 9324 being configured to receive information from the data collection circuits 9308 and the sensors 9303 and to store the information in the blockchain 9326. Access to blockchain 9326 may be provided via secure access control interface circuitry 9323.
The automated agent circuit 9325 can be configured to process events related to at least one of value, status or ownership of at least one asset in a set of assets, and further configured to take a set of actions related to a debt transaction involving the asset.
The system may further comprise an interface circuit 9310, the interface circuit 9310 being configured to receive the interaction 9309 from at least one of the entities 9305. In an embodiment, the automated debt management circuitry 9316 may be trained based on the interactions 9309. In some embodiments, the system may further include a market value data collection circuit 9318, the market value data collection circuit 9318 configured to monitor and report market information 9317 related to the value of at least one asset from the set of assets 9304. The market value data collection circuit 9318 may also be configured to monitor at least one pricing and financial data for items similar to at least one asset of the set of assets in at least one public market. A set of similar items for valuing at least one asset in the set of assets may be constructed using a similarity clustering algorithm based on attributes of the assets. In embodiments, at least one of the attributes of an asset may include an asset class, an asset age, an asset condition, an asset history, an asset storage, an asset geographic location, and the like.
In an embodiment, the system may further comprise an intelligent contract circuit 9322, the intelligent contract circuit 9322 being configured as an intelligent contract 9319 for managing the debt transactions 9321. The smart contract circuit 9322 may also be configured to establish a set of terms and conditions 9320 for the debt transaction 9321. At least one of the terms and conditions may include principal amount of the debt, balance of the debt, fixed interest rate, variable interest rate, payment amount, payment plan, last life return plan, collateral description, collateral substitutability description, party, insured person, guarantor, personal guaranty, lien, term, contract, redemption condition, default outcome, etc.
In an embodiment, the at least one debt-related action 9315 may include providing a debt transaction, underwriting a debt transaction, setting an interest rate, deferring a payment requirement, modifying an interest rate, verifying a property right, managing an inspection, recording a change in a property right, evaluating a value of a property, earning a loan, completing a transaction, setting terms and conditions of a transaction, providing a notification of the required provision, stopping the redemption of a set of properties, modifying terms and conditions, setting a rating of an entity, uniting a debt, or consolidating a debt. At least one debt management activity from the training set 9307 of debt management activities may include providing a debt transaction, underwriting a debt transaction, setting an interest rate, deferring a payment requirement, modifying an interest rate, verifying a property right, managing an inspection, recording a change in a property right, evaluating a value of a property, earning a loan, completing a transaction, setting terms and conditions of a transaction, providing a notification that requires provision, stopping the redemption of a set of properties, modifying terms and conditions, setting a rating of an entity, federating or consolidating a debt.
Referring to FIG. 94, an illustrative and non-limiting example method 9400 is described. The example method 9400 may include a step 9401 of collecting information about entities involved in a set of debt transactions, a training data set of results related to the entities, and a training set of debt management activities. The example method may also include classifying a condition of at least one of the entities based at least in part on a training data set of results associated with the entity (step 9402). The example method may also include managing the debt-related action based at least in part on the trained set of debt management activities (step 9403). The example method may also include receiving information from a set of sensors located on at least one asset (step 9404). The example method may also include storing the information in a blockchain, wherein the party to the debt transaction involving at least one asset in the set of assets is provided access to the blockchain through a secure access control interface (step 9405). In step 9406, the method can include processing an event related to at least one of a value, a status, or an ownership of at least one asset of the set of assets. At step 9407, the method can include processing a set of actions related to a debt transaction involving the asset. In an embodiment, the method may further include receiving an interaction from at least one of the entities (step 9408), monitoring and reporting market information related to the value of at least one asset from the set of assets (step 9409), constructing a set of similar items for rating at least one asset from the set of assets using a similarity clustering algorithm based on asset attributes (step 9410), managing an intelligent contract for liability transactions (step 9411), and establishing a set of terms and conditions for the intelligent contract for liability transactions (step 9412).
Referring to FIG. 95, an illustrative and non-limiting example system 9500 is described for a system for adaptive intelligence and robotic process automation capabilities.
An example system may include a crowdsourcing data collection circuit 9505, the crowdsourcing data collection circuit 9505 configured to collect information about entities 9503 involved in a set of bond transactions 9502 and a training data set of results related to the entities 9503. The system can also include a status classification circuit 9511, the classification circuit 9511 configured to classify the status of a group of publishers 9508 using information from the crowdsourced data collection circuit 9505 and the model 9509. Condition classification circuitry 9511 may include artificial intelligence circuitry 9510. The model 9509 can be trained using a training data set of results 9504 associated with the set of publishers. The example system may further include an automated agent circuit 9519, the automated agent circuit 9519 configured to perform debt transaction-related actions in response to a classification status of at least one issuer of the set of issuers. In an embodiment, at least one entity 9503 may include a set of publishers, a set of bonds, a set of parties, and/or a set of assets. The at least one publisher may comprise a municipality, corporation, contractor, government entity, non-government entity or non-profit entity. The at least one bond may comprise a bond type, wherein the bond type may comprise a municipal bond, a government bond, a treasury bond, an asset security bond, or a corporate bond.
In an embodiment, the conditions 9508 classified by the condition classification circuit 9511 may include default conditions, redemption-stop conditions, conditions indicative of a breach contract, financial risk conditions, behavioral risk conditions, policy risk conditions, financial health conditions, physical defect conditions, physical health conditions, entity risk conditions, entity health conditions, and the like. The crowdsourcing data collection circuit 9505 can be configured to enable a user interface 9507 through which a user can configure a crowdsourcing request 9506 for information related to the status of the group of publishers.
The system may further include a configurable data collection and monitoring circuit 9513, the configurable data collection and monitoring circuit 9513 configured to monitor at least one distributor of the set of distributors 9512. The configurable data collection and monitoring circuit 9513 may include systems such as: the system comprises the Internet of things equipment, a set of environmental condition sensors, a set of social network analysis services or a set of network domain query algorithms. The configurable data collection and monitoring services circuit 9513 may be configured to monitor at least one of the following environments: a municipal environment, an educational environment, a corporate environment, a securities trading environment, a property environment, a commercial facility, a warehousing facility, a transportation environment, a manufacturing environment, a storage environment, a house or a vehicle.
In an embodiment, a set of bonds associated with the set of bond transactions 9502 may be supported by a set of assets 9501. The at least one asset 9501 may include a municipal asset, a vehicle, a ship, an aircraft, a building, a house, real estate, undeveloped land, a farm, a crop, a municipal facility, a warehouse, a group of inventory, a commodity, a security, currency, a value token, a ticket, cryptocurrency, a consumable, an edible item, a beverage, a precious metal, a jewelry item, a gemstone, an intellectual property item, an intellectual property, a contractual right, an antique, a fixture, furniture, equipment, a tool, a machine, personal property, or the like.
In an embodiment, the system may further comprise an automated agent circuit 9519, the automated agent circuit 9519 configured to process events related to at least one of value, status, or ownership of at least one asset of at least one issuer of the set of issuers and perform debt transaction related actions in response to at least one of the processed events.
In an embodiment, the system may further comprise an automatic bond management circuit 9527, the automatic bond management circuit 9527 operable to manage bond-related actions 9524, the bond-related actions 9524 being related to at least one issuer of the set of issuers. The automated bond management circuit 9527 may be trained based on a training set 9526 of bond management activities. The automated bond management circuit 9527 may also be trained based on a set of party interactions 9525 with a set of user interfaces involved in a set of bond transaction activities. The at least one bond transaction may include providing a debt transaction, underwriting a debt transaction, setting an interest rate, deferring a payment requirement, modifying an interest rate, verifying a property right, managing an inspection, recording a change in a property right, assessing a value of an asset, earning a loan, completing a transaction, setting terms and conditions of a transaction, providing a notification of the required provision, stopping the redemption of a set of assets, modifying terms and conditions, setting a rating of an entity, consolidating a debt, merging a debt, and the like.
In an embodiment, the system can further include a market value data collection circuit 9517, the market value data collection circuit 9517 configured to monitor and report market information 9514 related to a value of at least one of a distributor or a property group. The report may include reports on: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, or personal property. Market value data collection circuit 9517 may be configured to monitor pricing 9516 or financial data 9515 of items similar to assets in at least one public market. The market value data collection circuit 9517 may also be configured to construct a set of similar items for valuation of a property using a similarity clustering algorithm based on the property of the property. At least one of the attributes may be selected from: asset class, asset age, asset condition, asset history, asset storage, or asset geographic location.
In an embodiment, the system may further include an intelligent contract circuit 9523, the intelligent contract circuit 9523 being configured to manage an intelligent contract 9520 for a bond transaction 9522 in response to a classification status of at least one issuer of the set of issuers. The smart contract circuit 9523 may be configured to determine terms and conditions 9521 for the bonds. The at least one term and condition 9521 may include a balance of the debt, a principal amount of the debt, a balance of the debt, a fixed interest rate, a variable interest rate, a payment amount, a payment plan, a final return plan, a warranty asset description of the debt, an asset substitutability description, a party, a publisher, a purchaser, a insured person, a guarantor, a guaranty, an individual guaranty, a lien, a term, a contract, a redemption condition, a default outcome, and the like.
Referring to FIG. 96, an illustrative and non-limiting example method 9600 is described. An example method 9600 can include a step 9601 of collecting a training data set of information about entities involved in a set of bond transactions for a set of bonds and results related to the entities. The method can also include step 9602 of classifying a condition of a group of publishers using the collected information and a model, wherein the model is trained using a resulting training data set associated with the group of publishers. The method may also include processing an event related to at least one of a value, a status, or ownership of at least one asset in the set of assets (step 9603). The method may also include step 9604, which takes action related to the debt transaction to which the asset relates; a step 9605 of managing an action related to the bond based at least in part on the training set of bond management activities; a step 9606 of monitoring and reporting market information related to the value of at least one of the issuer and the set of assets; step 9607, which manages smart contracts for bond transactions; and a step 9608 of determining terms and conditions of the smart contract for the at least one bond.
Referring now to fig. 97, an illustrative and non-limiting example system 9700 for monitoring the condition of a bond issuer is described. The example system may include a controller 9701. The controller 9701 may include a data collection circuit 9712, a market value data collection circuit 9756, a social network input circuit 9744, a social network data collection circuit 9732, and a number of artificial intelligence circuits 9742 including an intelligent contract circuit 9722, an automatic bond management circuit 9750, a condition classification circuit 9748, a clustering circuit 9762, and an event processing circuit 9752.
The social network data collection circuit 9732 may be configured to collect social network information 9710 about at least one entity 9764 involved in at least one transaction 9730 including at least one bond; and the condition classification circuit 9748 may be configured to classify a condition of the at least one entity according to a model 9774 trained using a training data set (9754, 9746) of a plurality of results related to the at least one entity and based on information from the social network data collection circuit. The at least one entity may be selected from the following entities: bond issuers, bonds, parties and assets. The bond issuer may be selected from the following bond issuers: municipalities, companies, contractors, government entities, non-government entities, and non-profit entities. The bond may be selected from the following entities: municipal bonds, government bonds, treasury bonds, asset security bonds, and corporate bonds.
The conditions classified by the condition classification circuit 9748 may include at least one of: a breach condition, a redemption-out condition, a condition indicative of a breach of a contract, a financial risk condition, a behavioral risk condition, a policy risk condition, a financial health condition, a physical defect condition, a physical health condition, an entity risk condition, or an entity health condition.
The social network data collection circuit 9732 may also include a social network input circuit 9744, which may be configured to receive input from a user for configuring a query for information about at least one entity.
The data collection circuit 9712 may be configured to monitor at least one of internet of things devices, environmental condition sensors, crowd-sourced request circuits, crowd-sourced communication circuits, crowd-sourced distribution circuits, and algorithms for querying network domains associated with the monitoring item 9711.
The data collection circuit 9712 may also be configured to monitor an environment selected from the group consisting of: a municipal environment, a corporate environment, a stock exchange environment, a property environment, a commercial facility, a warehousing facility, a transportation environment, a manufacturing environment, a storage environment, a house, and a vehicle associated with the monitoring project 9711.
At least one bond is secured by at least one asset. The at least one asset may be selected from the following assets: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
The event processing circuitry 9752 may be configured to process events related to at least one of value, status, and ownership of the at least one asset and take actions related to the at least one transaction. The action may be selected from the following actions: an offer bond transaction; underwriting bond transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the assets; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notification that the providing is required; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; a joint bond; and merging the bonds.
The condition classification circuit 9748 may also include systems in the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
The automatic bond management circuit 9750 may be configured to manage actions related to at least one bond, wherein the automatic bond management circuit is trained based on training data sets of a plurality of bond management activities.
The automatic bond management circuit 9750 may be trained based on a training set 9754 that includes a plurality of interactions of a principal with a plurality of user interfaces involved in a plurality of bond transactions. The plurality of bond transaction campaigns may be selected from the following bond transaction campaigns: an offer bond transaction; underwriting bond transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notification requiring provisioning; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; a joint bond; and merging the bonds.
The market value data collection circuit 9756 may be configured to monitor and report market information related to the value of at least one of the bond issuer, the at least one bond, and the asset. The assets may be selected from the following: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
The market value data collection circuit 9756 may also be configured to monitor pricing or financial data of offsetting assets in at least one public market.
A set of counteracting assets 9758 for valuation of assets can be constructed using clustering circuits 9762 based on attributes of the assets. The attributes may be selected from the following: category, age of asset, status of asset, history of asset, storage of asset, and geographic location.
The smart contract circuit 9722 may be configured to manage smart contracts 9770 for at least one transaction. The intelligent contract circuit may also be configured to determine terms and conditions of at least one bond 9772.
Clauses and conditions 9772 are selected from the group consisting of: principal amount of the debt, balance of the debt, fixed interest rate, variable interest rate, payment amount, payment plan, end-most grand hold plan, guaranteed asset description of at least one debt, asset exchangeability description, party, issuer, purchaser, insured person, guarantor, collateral, personal guaranty, lien, term, contract, redemption status, breach status, and breach outcome.
Referring now to fig. 98, an illustrative and non-limiting example method 9800 for monitoring the condition of a bond issuer is described. An example method may include: collecting social network information (9802) about at least one entity involved in at least one transaction comprising at least one bond; classifying (9804) a condition of the at least one entity according to a model and based on the social network information, wherein the model is trained using a training dataset of a plurality of results related to the at least one entity; managing actions related to at least one bond in response to the classification status of at least one entity (9806).
An event related to at least one of a value, a status, and an ownership of at least one asset may be processed (9808). An action related to at least one transaction may be taken in response to the event, wherein managing the action includes operating an automatic bond management circuit (9810). The automatic bond management circuitry may be trained based on a training set of a plurality of bond management activities to manage an action related to at least one bond (9812). An example method may also include: market information relating to a value of at least one of a bond issuer, at least one bond, and an asset is monitored and reported (9814).
Referring now to fig. 99, an illustrative and non-limiting example system 9900 for monitoring the condition of a bond issuer is described. The example system may include a controller 9901. The controller 9901 may include a data collection circuit 9912, a market value data collection circuit 9956, an internet of things input circuit 9944, an internet of things data collection circuit 9932, and a number of artificial intelligence circuits 9942 including an intelligent contract circuit 9922, an automatic bond management circuit 9950, a situation classification circuit 9948, a clustering circuit 9962, and an event processing circuit 9952. The condition classification circuit 9948 may include a model 9974 that is trained based on a training data set 9946.
The internet of things data collection circuitry 9932 may be configured to collect information about at least one entity 9964 involved in at least one transaction 9930 including at least one bond; and the condition classification circuit 9948 may be configured to classify a condition of the at least one entity according to a model 9974 trained using a plurality of resulting training data sets 9954 associated with the at least one entity and based on information from the internet of things data collection circuit. The at least one entity may be selected from the following entities: bond issuers, bonds, parties and assets. The bond issuer may be selected from the following bond issuers: municipalities, companies, contractors, government entities, non-government entities, and non-profit entities. The bond may be selected from the following entities: municipal bonds, government bonds, treasury bonds, asset security bonds, and corporate bonds.
The conditions classified by the condition classification circuit 9948 may include at least one of: a breach condition, a redemption-out condition, a condition indicative of a breach of a contract, a financial risk condition, a behavioral risk condition, a policy risk condition, a financial health condition, a physical defect condition, a physical health condition, an entity risk condition, or an entity health condition.
The internet of things data collection circuitry 9932 may also include internet of things input circuitry 9944, which may be configured to receive input from a user for configuring a query for information 9910 about at least one entity.
The data collection circuitry 9912 may be configured to monitor at least one of internet of things devices, environmental condition sensors, crowd sourcing request circuitry, crowd sourcing communication circuitry, crowd sourcing distribution circuitry, and algorithms for querying network domains to obtain information related to monitoring the item 9911. The condition classification circuit 9948 may also be configured to classify conditions in response to information from the data collection circuit 9912.
The data collection circuit 9912 may also be configured to monitor an environment selected from the group consisting of: a municipal environment, a corporate environment, a securities trading environment, a property environment, a commercial facility, a warehousing facility, a transportation environment, a manufacturing environment, a storage environment, a house, and a vehicle. The condition classification circuit 9948 may also be configured to classify a condition in response to the monitored environment.
At least one bond is secured by at least one asset. The at least one asset may be selected from the following assets: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, unexplored land, farms, crops, municipal facilities, warehouses, a group of inventory, goods, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
The event processing circuit 9952 can be configured to process an event related to at least one of a value, a status, and ownership of the at least one asset and take an action related to the at least one transaction. The action may be selected from the following actions: an offer bond transaction; underwriting bond transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notification that the providing is required; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; a joint bond; and merging the bonds.
The condition classification circuit 9948 may also include one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
The automatic bond management circuit 9950 can be configured to manage actions related to at least one bond, wherein the automatic bond management circuit is trained based on a training data set 9954 of a plurality of bond management campaigns.
The automated bond management circuit 9950 may be trained based on a plurality of interactions of a principal with a plurality of user interfaces involved in a plurality of bond transaction activities. The plurality of bond transaction campaigns may be selected from the following bond transaction campaigns: an offer bond transaction; underwriting bond transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notification that the providing is required; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; a joint bond; and merging the bonds.
The market value data collection circuit 9956 may be configured to monitor and report market information related to the value of at least one of the bond issuer, the at least one bond, and the asset. The assets may be selected from the following: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
The market value data collection circuit 9956 may also be configured to monitor pricing or financial data for offsetting assets in at least one public market.
A set of counteracting assets 9958 for valuation of the assets can be constructed using the clustering circuitry 9962 based on the attributes of the assets. The attributes may be selected from the following: category, age of asset, status of asset, history of asset, storage of asset, and geographic location.
Smart contract circuitry 9922 may be configured to manage smart contracts 9970 for at least one transaction. The intelligent contract circuit may also be configured to determine terms and conditions of at least one bond 9772.
The terms and conditions may be selected from the group consisting of: principal amount of the debt, balance of the debt, fixed interest rate, variable interest rate, payment amount, payment plan, end-most grand hold plan, guaranteed asset description of at least one debt, asset exchangeability description, party, issuer, purchaser, insured person, guarantor, collateral, personal guaranty, lien, term, contract, redemption status, breach status, and breach outcome.
Referring now to fig. 100, an illustrative and non-limiting example method 10000 for monitoring the condition of a bond issuer is described. An example method may include: collecting internet of things information (10002) about at least one entity involved in at least one transaction including at least one bond; classifying a condition of the at least one entity according to a model and based on the internet of things information, wherein the model is trained using a training data set of a plurality of results related to the at least one entity (10004); taking an action related to at least one transaction in response to the classification status of at least one entity (10006).
An event related to at least one of a value, a status, and an ownership of at least one asset may be processed (10008). An action related to at least one transaction may be taken in response to the event (10010). The automated bond management circuitry may be trained based on a training set of a plurality of bond management activities to manage actions related to at least one bond (10012). An example method may also include: market information relating to a value of at least one of a bond issuer, at least one bond, or a property is monitored and reported (10014).
Fig. 101 depicts a system 10100 that includes an internet of things data collection circuit 10114 configured to collect information about an entity 10102 involved in a subsidy loan transaction 10104 (e.g., where the entity may be a subsidy loan, a principal, a subsidy, a guarantor, a subsidizing principal, a collateral, etc., where the principal may be at least one of a municipality, a company, a contractor, a governmental entity, a non-governmental entity, and a non-profit entity). In an embodiment, the internet of things data collection circuit may include a user interface 10116 structured to enable a user to configure a query for information about at least one entity. The system may include a condition classification circuit 10118, which may include a model 10120 configured to classify a parameter 10106 of a subsidy loan 10108 (e.g., a municipal subsidy loan, a government subsidy loan, a school loan, an asset guarantee subsidy loan, or a corporate subsidy loan) involved in the subsidy loan transaction, for example, based on information from the internet of things data collection circuit. In an embodiment, the condition classification circuit may include: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, simulation systems, and the like. The subsidy loan may be secured by the following assets: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, personal property, and the like. The conditions classified by the condition classification circuit may include default conditions, redemption-stop conditions, conditions indicative of a breach of contract, financial risk conditions, behavioral risk conditions, contract performance conditions, policy risk conditions, financial health conditions, physical defect conditions, physical health conditions, entity risk conditions, entity health conditions, and the like. The model may be trained using a training data set 10110 for a plurality of results relating to subsidy loans. For example, the subsidy loan may be a study aid loan, and the condition classification circuit may classify at least one of: the students get the progress of academic degree, participate in non-profit activities, participate in public welfare activities and the like. The system may include a smart contract circuit 10122 configured to automatically modify the terms of the subsidized loan and the conditions 10112, for example, based on the classification parameters from the condition classification circuit. The system may include configurable data collection and circuitry 10124 structured to monitor entities, such as further including social network analysis circuitry 10130, environmental condition circuitry 10132, crowdsourcing circuitry 10134, and an algorithm 10136 for querying a network domain, where the configurable data collection and circuitry may monitor an environment in which to select, for example: municipal environments, educational environments, corporate environments, securities trading environments, real estate environments, commercial facilities, warehousing facilities, transportation environments, manufacturing environments, storage environments, houses, vehicles, and the like. The system may include an automated agent 10126 configured to process events related to the value, status, and ownership of the property, and perform actions related to the subsidized loan transaction to which the property relates, wherein the actions may be: a loan transaction to be tendered; underwriting subsidy loan transaction; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the assets; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notification that needs to be provided; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; jointly subsidizing a loan; merging subsidy loans and the like. The system may include an automatic subsidy loan management circuit 10138 configured to manage actions related to at least one subsidy loan, wherein the automatic subsidy loan management circuit is trained based on a set of subsidy loan management activity training sets. For example, the automated subsidized loan management circuit may be trained based on a plurality of interactions of the party with a plurality of user interfaces involved in a plurality of subsidized loan transaction activities selected from the group consisting of: a loan transaction to be tendered; underwriting subsidy loan transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notification that needs to be provided; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; joint subsidy loans and merged subsidy loans. The system may include a blockchain service circuit 10140 configured to record a modified set of terms and conditions for the subsidy in, for example, a distributed ledger 10142. The system may include a market value data collection circuit 10128 configured to monitor and report market information related to the value of the issuer, subsidized loans, properties, etc., wherein properties selected from the following properties may be reported: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, unexplored land, farms, crops, municipal facilities, warehouses, a group of inventory, goods, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property. The market value data collection circuit may also be configured to monitor pricing or financial data of offsetting assets in the public market. A set of counteracting assets for valuation of assets can be constructed using clustering circuits based on asset attributes, where the attributes can be categories, asset age, asset condition, asset history, asset storage, geographic location, and the like. The intelligent contract circuitry may be configured to manage intelligent contracts for subsidized loan transactions, wherein the intelligent contract circuitry may set terms and conditions for the subsidized loan, wherein the terms and conditions for the subsidized loan specified and managed by the intelligent contract circuitry may include: principal amount of the debt, balance of the debt, fixed interest rate, variable interest rate, payment amount, payment plan, end-most grand payback plan, guaranteed asset description of at least one subsidy, asset exchangeability description, party, issuer, purchaser, insured person, collateral, personal guarantee, lien, term, contract, redemption-out condition, default outcome, etc.
Fig. 102 depicts a method 10200 that includes collecting information about entities involved in a subsidy loan transaction (10202). The method may include classifying (10204) parameters of the subsidy loans involved in the subsidy loan transaction based on the information using a model trained based on a training dataset for a plurality of results associated with at least one subsidy loan. The method may include automatically modifying the terms and conditions of the subsidized loan based on the classification parameters (10208). The method may include processing events related to the value, status, and ownership of the property to which the at least one subsidy relates and taking actions related to the transaction of the subsidy to which the property relates (10210). The method may include recording the modified set of terms and conditions of the subsidy in a distributed ledger (10212). The method may include monitoring and reporting market information related to the value of the issuer, the subsidy, the property to which the at least one subsidy relates, etc. (10214).
Fig. 103 depicts a system 10300 that includes a social network analysis data collection circuit 10314 configured to collect social network information about an entity 10302 involved in a subsidy loan transaction 10304 (e.g., where the entity may be a subsidy loan, a principal, a subsidy, a guarantor, a subsidy principal, a collateral, etc., where the principal may be at least one of a municipality, a company, a contractor, a government entity, a non-government entity, and a non-profit entity). In an embodiment, the social network analysis data collection circuit may include a user interface 10316 configured to enable a user to configure a query for information about at least one entity, wherein the social network analysis data collection circuit may initiate at least one algorithm to respond to the query, the at least one algorithm searching and retrieving data from at least one social network based on the query. The system can include a condition classification circuit 10318 that can include a model 10320 that is configured to classify a parameter 10306 of a subsidy loan 10308 (e.g., a municipal subsidy loan, a government subsidy loan, a school loan, an asset guarantee subsidy loan, or a corporate subsidy loan) involved in the subsidy transaction, for example, based on social network information from the social network analysis data collection circuit. In an embodiment, the condition classification circuit may include: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, simulation systems, and the like. The subsidy loan may be secured by the following assets: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, personal property, and the like. The parameters classified by the condition classification circuit may include default conditions, redemption-up conditions, conditions indicative of a breach of contract, financial risk conditions, behavioral risk conditions, contract performance conditions, policy risk conditions, financial health conditions, physical defect conditions, physical health conditions, entity risk conditions, entity health conditions, and the like. The model may be trained using a training data set 10310 of a plurality of results relating to subsidized loans. For example, the subsidized loan may be a school loan, and the condition classification circuit may classify at least one of: the students get the progress of academic degree, participate in non-profit activities, participate in public welfare activities and the like. The system may include an intelligent contract circuit 10322 configured to automatically modify terms and conditions 10312 of the subsidized loan, for example, based on the classification parameters. The system may include configurable data collection and circuitry 10324 configured to monitor entities, such as further including social network analysis circuitry 10330, environmental condition circuitry 10332, crowdsourcing circuitry 10334, and algorithms 10336 for querying network domains, wherein the configurable data collection and circuitry may monitor the environment in selecting: municipal environments, educational environments, corporate environments, securities trading environments, real estate environments, commercial facilities, warehousing facilities, transportation environments, manufacturing environments, storage environments, houses, vehicles, and the like. The system may include an automated agent 10326 configured to process events related to the value, status, and ownership of the property and perform actions related to the subsidy loan transaction to which the property relates, where the actions may be: a loan transaction to be tendered; underwriting subsidy loan transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notification that needs to be provided; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; jointly subsidizing a loan; and merging subsidy loans and the like. The system may include an automatic subsidy loan management circuit 10338 configured to manage actions related to at least one subsidy loan, wherein the automatic subsidy loan management circuit is trained based on a training set of subsidy loan management activities. For example, the automated subsidy loan management circuitry may be trained based on a plurality of interactions of the party with a plurality of user interfaces involved in a plurality of subsidy loan transactions activities selected from the group consisting of: a loan transaction to be tendered; underwriting subsidy loan transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notification that needs to be provided; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; joint subsidy loans and merged subsidy loans. The system may include a blockchain service circuit 10340 configured to record a modified set of terms and conditions for the subsidy in, for example, a distributed ledger 10342. The system may include a market value data collection circuit 10328 configured to monitor and report market information related to the value of an issuer, subsidy, property, etc., where a property selected from the following properties may be reported: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property. The market value data collection circuit may also be configured to monitor pricing or financial data of offsetting assets in the public market. A set of counteracting assets for valuation of an asset may be constructed using clustering circuitry based on asset attributes, where the attributes may be categories, asset age, asset condition, asset history, asset storage, geographic location, and the like. The intelligent contract circuitry may be configured to manage intelligent contracts for subsidizing a loan transaction, wherein the intelligent contract circuitry may set terms and conditions for subsidizing the loan, wherein the terms and conditions for the subsidizing the loan specified and managed by the intelligent contract circuitry may include: principal amount of the debt, balance of the debt, fixed interest rate, variable interest rate, payment amount, payment plan, end-most grand payback plan, guaranteed asset description of at least one subsidy, asset exchangeability description, party, issuer, purchaser, insured person, collateral, personal guarantee, lien, term, contract, redemption-out condition, default outcome, etc.
FIG. 104 depicts a method 10400 that includes collecting social network information regarding an entity involved in a subsidy loan transaction (10402). The method may include classifying parameters of the subsidy loans involved in the subsidy loan transaction based on social network information using a model trained based on a training dataset for a plurality of results associated with at least one subsidy loan (10404). The method may include automatically modifying the terms and conditions of the subsidized loan based on the classification parameters (10408). The method may include processing events related to the value, status, and ownership of the property and taking actions related to the subsidy loan transaction to which the property relates (10410). The method may include recording the modified set of terms and conditions for the subsidized loan in a distributed ledger (10412). The method may include monitoring and reporting market information related to the value of the issuer, subsidy, property, etc. (10414).
Fig. 105 depicts a system 10500 for automatically processing a subsidy loan, the system comprising a crowdsourcing service circuit 10525 configured to collect information related to a set of entities 10502 involved in a set of subsidy loan transactions 10504. The set of entities may include entities such as, for example, a subsidy in a set of subsidized loans corresponding to a set of subsidized loan transactions, a principal associated with at least one of the set of subsidized loan transactions, a subsidy corresponding to a set of subsidized loans corresponding to a set of subsidized loan transactions, a subsidized principal associated with at least one of the set of subsidized loan transactions, a subsidy corresponding to a set of subsidized loans corresponding to a set of subsidized loan transactions, a collateral associated with at least one of the set of subsidized loan transactions, and a subsidy corresponding to a set of subsidized loans corresponding to a set of subsidized loan transactions. A set of subsidy parties may include: municipalities, companies, contractors, government entities, non-profit entities, and the like. The loan may be a study-aid loan and the condition classification circuit classifies at least one of: the progress of the student getting the academic degree, the participation of the student in the non-profit activity, the participation of the student in the public welfare activity and the like. The crowdsourcing service circuitry may also be configured with a user interface 10520 through which a user can configure queries for information about a set of entities, and the crowdsourcing service circuitry automatically configures crowdsourcing requests based on the queries. A set of subsidy loans may be secured by a set of properties 10512: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, personal property, and the like. An example system may include: a condition classification circuit 10522 comprising a model 10524; and an artificial intelligence service circuit 10536 configured to classify a set of parameters 10506 of a set of subsidized loans 10510 involved in the transaction based on information from the crowdsourcing service circuit, wherein the model is trained using a training data set of results 10514 relating to the subsidized loans. The set of subsidized loans may include at least one of a municipal subsidy loan, a government subsidy loan, an assisted loan, an asset guarantee subsidy loan, and a company subsidy loan. The conditions classified by the condition classification circuit may include default conditions, redemption-up conditions, conditions indicative of a breach of contract, financial risk conditions, behavioral risk conditions, contract performance conditions, policy risk conditions, financial health conditions, physical defect conditions, physical health conditions, entity risk conditions, entity health conditions, and the like. The artificial intelligence service circuit may include: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, simulation systems, and the like. An example system may include: intelligent contract circuitry 10526 for automatically modifying the terms and conditions of the subsidized loan 10518 based on a set of classification parameters from the condition classification circuitry. The intelligent contract service circuit may be used to manage intelligent contracts for subsidized loan transactions, set terms and conditions for subsidized loans, and the like. In an embodiment, the set of terms and conditions of the debt transaction specified and managed by the intelligent contract service circuit may be selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, top-end big payback plan, guaranteed property description of subsidized loan, property substitutability description, party, issuer, purchaser, insured person, collateral, personal guarantee, lien, term, contract, redemption status, default status, and default outcome. An example system may include: configurable data collection and monitoring service circuitry 10528 for monitoring entities such as a set of internet of things services, a set of environmental condition sensors, a set of social network analysis services, a set of algorithms for querying network domains, and the like. The configurable data collection and monitoring service circuit may also be configured to monitor the following environments, for example: municipal environments, educational environments, corporate environments, securities trading environments, real estate environments, commercial facilities, warehousing facilities, transportation environments, manufacturing environments, storage environments, houses, vehicles, and the like. An example system may include: an automated brokering circuit 10530 configured to process events related to at least one of value, status, and ownership of the property and take actions 10508 related to the subsidy loan transaction to which the property relates, wherein the actions 10508 may be: offer subsidy loan transaction, underwriting subsidy loan transaction, setting interest rate, deferring payment requirements, modifying interest rate, verifying property rights, managing inspection, recording changes to property rights, assessing value of property, hastening loan, ending transaction, setting terms and conditions of transaction, providing notice that needs to be provided, stopping the redemption of a set of properties, modifying terms and conditions, setting entity ratings, joint subsidy loan, merging subsidy loans, and the like. An example system may include: an automatic subsidy loan management circuit 10538 configured to manage actions related to subsidizing loans, wherein the automatic subsidy loan management circuit may be trained based on a training set of subsidy loan management activities. The automated subsidy loan management circuitry may be trained based on a set of interactions of the party with a set of user interfaces involved in a set of subsidy loan transactions, such as: offer subsidized loan transaction, underwriting subsidized loan transaction, setting interest rate, deferring payment requirements, modifying interest rate, verifying property, managing inspections, recording changes to property, assessing value of property, expediting loan, ending transaction, setting terms and conditions for transaction, providing notice that needs to be provided, stopping the redemption of a set of property, modifying terms and conditions, setting entity's rating, joint subsidized loan, merging subsidized loans, and the like. An example system may include: a blockchain service circuit 10540 configured to record a modified set of terms and conditions for the set of subsidies in the distributed ledger. An example system may include: a market value data collection service circuit 10532 configured to monitor and report market information 10534 related to the value of at least one of a party, a set of subsidized loans, and a set of properties, wherein a set of properties consisting of, for example: one of a municipal asset, a vehicle, a ship, an aircraft, a building, a house, real estate, undeveloped land, a farm, a crop, a municipal facility, a warehouse, a set of inventory, a commodity, a security, currency, a value token, a ticket, a cryptocurrency, a consumable, an edible item, a beverage, a precious metal, a jewelry item, a gemstone, an intellectual property item, an intellectual property, a contractual right, an antique, a fixture, furniture, an equipment, a tool, a mechanical item, and personal property. The market value data collection service circuitry may be further configured to monitor pricing or financial data for items similar to the property in the at least one public market. In an embodiment, a set of similar items for valuation of assets can be constructed using the similarity clustering algorithm 10542 based on the following attributes of the assets, such as asset class, asset age, asset condition, asset history, asset storage, geographic location of the assets, and the like.
FIG. 106 depicts a method 10600 for automatically processing a subsidized loan, the method comprising: collecting information related to a set of entities involved in a set of subsidy loan transactions (10602); classifying a set of parameters of a set of subsidies involved in the transaction based on an artificial intelligence service, a model, and information from a crowdsourcing service, wherein the model is trained based on a training dataset of results related to the subsidy loans (10604); and modifying the terms and conditions of the subsidized loan based on a set of classification parameters (10608). The set of entities may include the following entities: a set of subsidies, a set of parties, a set of subsidies, a set of guarantors, a set of subsidizing parties, and a set of collateral (10610). The set of entities includes a set of subsidizing parties 10516, wherein each party in the set of subsidizing parties may include a municipality, a company, a contractor, a government entity, a non-government entity, and a non-profit entity (10612). The set of subsidy loans may include municipal subsidy loans, government subsidy loans, school-aid loans, property guarantee subsidy loans, and corporate subsidy loans (10614). The subsidy loan may be a study-aid loan, wherein the condition classification system classifies at least one of: the student makes a degree of progress, the student participates in non-profit activities, or the student participates in public welfare activities (10618).
Fig. 107 depicts a system 10700 that includes an asset identification service circuit 10712 structured to interpret an asset 10724 corresponding to a financial entity 10722 for custody of an asset (e.g., identifying an asset that a bank may custody), wherein the identity management service circuit 10714 may be structured to authenticate an identifier 10728 (e.g., including credentials 10730) corresponding to an executable action entity 10726 (e.g., owner, beneficiary, agent, consignee, custodian, etc.) that is authorized to perform an action with respect to the asset. For example, a group of financial entities may have rights to perform an action with respect to an asset. The blockchain services circuit 10716 may be configured to store a plurality of asset control features 10732 in a blockchain structure 10718, which may include a distributed ledger configuration 10720. For example, transaction events may be stored in a distributed ledger in a blockchain architecture through which financial entities and actionable entities have distributed access to share and distribute asset events. The financial management circuitry 10710 may be configured to communicate the interpreted asset and authenticated identifier to the blockchain service circuitry for storage in the blockchain structure as asset control features recorded in the distributed ledger configuration as asset events 10734 (e.g., transfer of property, owner death, owner disability, owner bankruptcy, redemption, setting liens, using an asset as a collateral, designating beneficiary, lending with an asset as a collateral, providing notification about an asset, reviewing an asset, evaluating an asset, reporting an asset for tax purposes, assigning asset ownership, handling an asset, selling an asset, purchasing an asset, designating an ownership status, etc.). The data collection circuit 10702 may be configured to monitor interpretations of a plurality of assets, authentications of a plurality of identifiers, and records of asset events, wherein the data collection circuit may be communicatively coupled with an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and an interactive crowdsourcing system. The intelligent contract circuit 10704 may be configured to manage custody of assets, wherein asset events related to a plurality of assets may be managed by the intelligent contract circuit based on terms and conditions 10708 implemented in the intelligent contract configuration 10706 and based on data collected by the data collection service circuit. In an embodiment, the asset identification service circuit, the identity management service circuit, the blockchain service circuit, and the financial management circuit may include corresponding Application Programming Interface (API) components configured to facilitate communication between the system circuits, e.g., where the corresponding API components of the circuits also include a user interface configured to interact with a system user.
FIG. 108 depicts a method 10800 that includes interpreting assets corresponding to a financial entity for custody of a plurality of assets, for example wherein the interpretation of assets may include identifying a plurality of assets that the financial entity is responsible for custody (10802). The method may include authenticating an identifier (e.g., including credentials) corresponding to an executable action entity (e.g., owner, beneficiary, agent, trustee, and custodian) having authority to perform actions with respect to the plurality of assets, for example, wherein authenticating the identifier includes verifying an identifier corresponding to the executable action entity having authority to perform actions with respect to the assets (10804). The method may include storing a plurality of asset control features in a block-chaining structure (e.g., including a distributed ledger configuration) (10808). The blockchain structure may be provided in conjunction with a blockchain marketplace, utilize an automated trading application based on blockchains, may be a distributed blockchain structure across multiple asset nodes, and the like. The method can include communicating the interpreted asset and the authenticated identifier for storage in the blockchain structure as an asset control feature, where the asset control feature can be recorded in a distributed ledger configuration as an asset event (10810). The method may include monitoring an interpretation of the asset, an authentication of the identifier, and a record of asset events (10812), for example, where the asset events may include: transferring property, owner death, owner disability, owner bankruptcy, stopping redemption, setting liens, using property as a collateral, designating beneficiary, lending with property as a collateral, providing notice about property, reviewing property, evaluating property, reporting property for tax purposes, assigning property ownership, disposing of property, selling property, purchasing property, and designating ownership status. In embodiments, monitoring may be performed by an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, an interactive crowdsourcing system, and the like. The method may include managing custody of assets, wherein asset events related to a plurality of assets may be based on terms and conditions implemented in the intelligent contract configuration and based on data collected by the data collection service circuitry (10814). The method may include sharing and distributing asset events with a plurality of executable action entities (10818). The method may include storing asset transaction data in a blockchain structure based on interactions between executable action entities (10820). The asset may comprise a virtual asset tag, wherein interpreting the asset comprises identifying the virtual asset tag (e.g., the storing of the asset control feature may comprise storing virtual asset tag data, e.g., wherein the virtual asset tag data is location data, tracking data, etc.). For example, an identifier corresponding to a financial entity or an executable action entity may be stored as virtual asset tag data.
Fig. 109 illustrates a system 10900 that includes a loan protocol storage circuit 10902 configured to store loan protocol data 10904 that includes a loan protocol 10914, which may include loan condition data 10916. In an embodiment, the loan condition data may include at least one loan agreement's terms and condition data 10918, the loan agreement's terms and condition data relating to the redemption-out condition 10922 of the asset 10920, which provides collateral conditions 10924 relating to the collateral asset 10926, such as for securing the loan agreement's repayment obligation 10928. The system can include a data collection service circuit 10906 that is configured to monitor the loan condition data and detect a default condition 10908 based on a change in the loan condition data. Further, the data collection service circuit may include an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and an interactive crowd sourcing system. The system may include an intelligent contract service circuit 10910 configured to interpret the breach condition 10912 and communicate an indication of the breach condition 10930 when the data collection service circuit detects the breach condition, so as to initiate a redemption process 10932 based on the collateral condition. For example, the redemption process can configure and initiate a listing of mortgage assets on a public auction website; configuring and transmitting a set of shipping instructions for the mortgage asset; configuring an instruction set for the drone to transport the mortgage asset; configuring a set of instructions for the robotic device to transport the mortgage asset; initiating a process for automatically replacing a set of substitute collateral; initiating a collateral tracking process; initiating a collateral valuation process; a message is initiated to the borrower initiating a negotiation regarding redemption, etc. The breach condition indication can be communicated to the smart lock and the smart container to lock the mortgage asset. The negotiation may be managed by a robotic process automation system trained based on a redemption-only negotiation training set, and may involve modification of interest rates, payment terms, loan agreement collateral, and the like. In an embodiment, each of the loan protocol storage circuit, the data collection service circuit, and the intelligent contract service circuit may further include a corresponding Application Programming Interface (API) component configured to facilitate communication between the system circuits, wherein the corresponding API component of the circuits may include a user interface configured to interact with a plurality of users of the system.
Fig. 110 depicts a method 11000 for facilitating redemption of a collateral, the method including storing loan protocol data including a loan protocol, wherein the loan protocol may include loan condition data (11002), for example wherein the loan condition data includes terms and condition data of the loan protocol, the terms and condition data of the loan protocol relating to a redemption-stop condition of an asset, the redemption-stop condition of the asset providing a collateral condition associated with the collateral asset for securing a repayment obligation of at least one loan protocol. The method may include monitoring the loan condition data and detecting a default condition based on a change in the loan condition data (11004). The method may include interpreting the breach condition (11008), and communicating a breach condition indication (11010), the breach condition indication initiating a redemption process based on the collateral condition. For example, the redemption-stopping process may configure and initiate a listing of mortgage assets on a public auction website (11014); configuring and transmitting a set of shipping instructions for the mortgage asset; configuring an instruction set for the drone to transport the mortgage asset; configuring a set of instructions for the robotic device to transport the mortgage asset; initiating a process for automatically replacing a set of substitute collateral; initiating a collateral tracking process; initiating a collateral valuation process; a message is initiated to the borrower initiating a negotiation regarding redemption, etc. A breach condition indication may be communicated to the smart lock and smart container to lock the mortgage asset (11012). The negotiation may be managed by a robotic process automation system trained based on a redemption-stop negotiation training set (11018), and may involve modification of interest rates, payment terms, loan agreement collateral, and the like. In an embodiment, the communication may be provided (11020) by a corresponding Application Programming Interface (API), where the corresponding API may include a user interface structured to interact with a plurality of users.
In an embodiment, a system for adaptive intelligence and robotic process automation capabilities for trading, financial and market support is provided herein. An example system may include: a blockchain service circuit configured to interpret a plurality of access control features corresponding to a plurality of parties associated with the loan; a data collection circuit configured to interpret entity information corresponding to a plurality of entities related to a loan transaction corresponding to a loan; intelligent contract circuitry configured to specify loan terms and conditions relating to a loan; a loan management circuit configured to: interpreting a loan-related event in response to the entity information, the plurality of access control features, and the loan terms and conditions, wherein the loan-related event is associated with the loan; performing a loan-related activity in response to the entity information, the plurality of access control features, and the loan terms and conditions, wherein the loan-related activity is associated with the loan; and wherein each of the block chain service circuit, the data collection circuit, the intelligent contract circuit, and the loan management circuit further comprises a corresponding Application Programming Interface (API) component configured to facilitate communication between the system circuits.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein each of the plurality of entities comprises at least one entity selected from the following entities: a borrower, a insurer, loan-related equipment, loan-related goods, loan-related systems, loan-related fixtures, buildings, storage facilities, and mortgages.
An example system may include at least one of a plurality of entities that includes a collateral, and wherein the data collection circuitry is further configured to interpret a condition of the collateral, wherein the collateral includes at least one of: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, collateral objects, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, tools, machinery, and personal property.
An example system may include: wherein the data collection circuit further comprises at least one of: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and an interactive crowdsourcing system.
An example system may include: wherein each of the loan-related events comprises at least one event selected from the following: requesting a loan; offer loan; receiving a loan; providing loan underwriting information; providing a credit report; a deferred payment; requesting a deferred payment; identifying a collateral; verifying the property rights of the mortgage; verifying the property right of the guarantee object; checking assets; altering a condition of at least one of the plurality of entities; altering the value of the entity; altering the value of the collateral; changing the value of the collateral; altering a professional reputation of at least one of the parties; changing the financial rating of the borrower; providing insurance for the loan; providing insurance evidence for property; providing loan qualifications; identifying a loan guarantee; executing loan underwriting; paying a loan; a loan default; the loan is collected; settlement loan; modifying the specified loan terms and conditions; specifying initial loan terms and conditions; and the redemption of loan assets.
An example system may include: wherein each of the loan terms and conditions comprises at least one member selected from the group consisting of: the principal amount of the loan, the balance of the loan, the fixed interest rate, the variable interest rate description, the payment amount, the payment plan, the end-most grand payback plan, the collateral description, the collateral substitutability description, the description of the at least one party, the collateral description, the personal collateral, the lien, the redemption condition, the default outcome, the contract associated with any of the foregoing, and the term of any of the foregoing.
An example system may include: wherein at least one of the parties comprises at least one party selected from the following: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, government agencies, and accountants.
An example system may include: wherein each of the loan-related activities comprises at least one activity selected from the following: finding at least one of the parties interested in participating in the loan transaction; applying for loan; underwriting loan; making a legal contract for the loan; monitoring the performance of the loan; paying a loan; adjusting or modifying the loan; settlement loan; monitoring the loan mortgage; establishing a loan bank; stopping the redemption of the loan; and closing the loan transaction, wherein the loan comprises at least one type selected from the following loan types: the system comprises an automobile loan, an inventory loan, a capital equipment loan, a performance bond, a capital improvement loan, a construction loan, an account receivable guarantee loan, an invoice financing arrangement, a warranty arrangement, a payday loan, a refund expected loan, an academic loan, a banking loan, a property loan, a housing loan, a risk debt loan, an intellectual property loan, a contractual right loan, a floating fund loan, a small business loan, an agricultural loan, a municipal bond, and a subsidy loan.
An example system may include: wherein the intelligent contract circuitry is further configured to perform a contract-related loan action in response to the entity information.
An example system may include: wherein the contract-related loan action comprises at least one action selected from the following: offer loan; receiving a loan; underwriting loan; setting interest rate of the loan; a payment requirement for a deferred loan; modifying interest rate of the loan; verifying the property rights of the loan mortgage; recording the change of property rights; evaluating the value of the collateral; initiating a check for collateral; the loan is collected; settlement loan; modifying the terms and conditions of the loan; providing a notification to one of the parties; providing necessary notification to the loan borrower; and the redemption of loan assets.
An example system may also include: automated brokering circuitry configured to interpret a loan-related event and perform a loan-related action in response to the loan-related event, wherein the loan-related event comprises an event related to at least one of: the value of the loan, the condition of the loan mortgage, or the ownership of the loan mortgage, and wherein the action related to the loan comprises at least one of: modifying the terms and conditions of the loan; providing a notification to one of the parties; providing necessary notification to the loan borrower; and redeeming the loan asset.
An example system may include: wherein the corresponding API component of the circuit further comprises a user interface configured to interact with a plurality of users of the system.
An example system may include: wherein each of the plurality of users comprises one of the one or more entities of the plurality of principals, and wherein at least one of the plurality of users comprises one of the prospective principal or the prospective entity.
An example system may include: wherein one of the user interfaces is responsive to a plurality of access control features.
In an embodiment, a method for providing access control to loan terms and conditions on a distributed ledger is provided herein. An example method may include: interpreting a plurality of access control features corresponding to a plurality of parties associated with a loan in a distributed ledger; interpreting entity information corresponding to a plurality of entities associated with a loan transaction corresponding to a loan; specifying loan terms and conditions associated with the loan; the loan-related event is interpreted in response to the entity information, the plurality of access control features, and the loan terms and conditions, wherein the loan-related event is associated with the loan.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example method may include: wherein at least one of the plurality of entities comprises a collateral, the method further comprising interpreting a condition of the collateral.
An example method may also include: a contract-related loan action is performed in response to the entity information.
An example method may include: wherein a contract-related loan action is performed, the contract-related loan action comprising at least one action selected from the following: offer loan; receiving a loan; underwriting loan; setting interest rate of the loan; a payment requirement for a deferred loan; modifying interest rate of the loan; verifying the property rights of the loan mortgage; recording the change of property rights; evaluating the value of the collateral; initiating a check for collateral; urging to loan payment; settlement loan; modifying the terms and conditions of the loan; providing a notification to one of the parties; providing necessary notification to the loan borrower; and the redemption of loan assets.
An example method may also include: interpreting a loan-related event and performing a loan-related action in response to the loan-related event, wherein the loan-related event comprises an event related to at least one of: the value of the loan, the condition of the loan mortgage, or the ownership of the loan mortgage, and wherein performing the action related to the loan comprises at least one of: modifying the terms and conditions of the loan; providing a notification to one of the parties; providing necessary notification to the loan borrower; and the redemption of loan assets.
An example method may also include: providing a user interface to a user, wherein the user includes at least one of: one of the plurality of parties, one of the plurality of entities, the intended party, or the intended entity, wherein providing the user interface is further responsive to the plurality of access control features.
An example method may also include: an intelligent loan contract for the loan is created and recorded as blockchain data.
In an embodiment, a system for adaptive intelligence and robotic process automation capabilities for trading, financial and market support is provided herein. An example platform or system may include: a blockchain service circuit configured to interpret a plurality of access control features corresponding to a plurality of parties associated with a secured loan; a data collection circuit configured to: receiving first collateral data from at least one sensor associated with a collateral used to vouch for the loan; receiving second collateral data about a collateral environment from the internet of things circuit; associating the collateral data with a unique identifier associated with the collateral, wherein the blockchain service circuit is further configured to store the unique identifier and the associated collateral data as blockchain data. The example platform or system may further include: intelligent contract circuitry configured to create an intelligent loan contract; a secure access control circuit configured to receive an access control instruction from a borrower that vouches for the loan through the access control interface, wherein the secure access control circuit is further configured to provide instructions to the blockchain services circuit regarding access to blockchain data associated with the mortgage, wherein each of the blockchain services circuit, the data collection circuit, the secure access control circuit, and the internet of things circuit further comprises a corresponding Application Programming Interface (API) component configured to facilitate communication between the system circuits.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein the sensor associated with the collateral is placed in a location selected from the list consisting of: a collateral, a collateral container, and a collateral package.
An example system may include: wherein the data collection circuit is further configured to interpret the condition of the collateral in response to the received subset of collateral data.
An example system may include: wherein the collateral is selected from a list of items consisting of: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, collateral objects, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, tools, machinery, and personal property.
An example system may include: wherein the secured loan is at least one of: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
An example system may include: wherein the collateral environment is selected from a list of environments consisting of: real estate environments, commercial facilities, storage facilities, transportation environments, manufacturing environments, storage environments, houses, and vehicles.
An example system may include: wherein the at least one sensor is selected from the group consisting of: an image capture device, a thermometer, a manometer, a humidity sensor, a velocity sensor, an acceleration sensor, a rotation sensor, a torque sensor, a scale sensor, a chemical sensor, a magnetic field sensor, an electric field sensor, and a position sensor.
An example system, may further include: reporting circuitry configured to report collateral events related to collateral aspects selected from a list of aspects consisting of: the value of the collateral, the condition of the collateral, and ownership of the collateral.
An example system, may further include: an automated agent circuit configured to interpret the mortgage event and perform a loan-related action in response to the mortgage event.
An example system, may further include: wherein the loan-related action is selected from the actions consisting of: offer loan; receiving a loan; underwriting loan; setting interest rate of the loan; a deferred payment requirement; modifying interest rate of the loan; verifying the property rights of the mortgage; recording the change of property rights; evaluating the value of the collateral; initiating a check for collateral; urging to loan payment; settlement and loan; setting the terms and conditions of the loan; providing a notification to be provided to the borrower; the redemption of loan assets; and modifying the terms and conditions of the loan.
An example system, may further include: a collateral classification circuit configured to identify a set of cancellation collateral, wherein each member of the set of cancellation collateral shares a common attribute with the collateral.
An example system may include: wherein the common attribute is selected from a list of attributes consisting of: the type of the collateral, the age of the collateral, the condition of the collateral, the history of the collateral, the ownership of the collateral, the manager of the collateral, the security of the collateral, the condition of the owner of the collateral, the lien of the collateral, the storage conditions of the collateral, the geographic location of the collateral, and the jurisdiction of the collateral.
An example system, may further include: a market value data collection circuit configured to monitor and report market information related to the value of the collateral or at least one of the set of offset collateral.
An example system may include: wherein the market value data collection circuit is further configured to monitor pricing or financial data of at least one of the collateral or the set of offset collateral in at least one public market.
An example system may include: wherein the market value data collection circuit is further configured to report the monitored one of the pricing or financial data.
An example system may include: wherein the intelligent contract circuit is further configured to modify the terms or conditions of the loan based on collateral-counteracting market information relating to the value of the collateral.
An example system, may further include: and a smart contract service circuit configured to manage a smart contract securing the loan.
An example system may include: wherein the intelligent contract service circuit is further configured to set terms and conditions associated with providing a collateral for the loan guarantee.
An example system may include: wherein the terms and conditions are selected from the list consisting of: description of a collateral, description of substitutability of a collateral, description of a condition of a collateral, description relating to lien of a collateral, description relating to collateral guarantee, and description relating to collateral environment.
In an embodiment, a method for automated intelligent contract creation and collateral distribution is provided herein. An example method may include: receiving first collateral data from a sensor associated with a collateral used to secure the loan; receiving second collateral data regarding an environment of the collateral; associating the collateral data with a unique identifier associated with the collateral; creating an intelligent borrowing and lending contract; storing the unique identifier and the collateral data in a block-chain structure; receiving an access control instruction from a borrower who guarantees a loan; interpreting a plurality of access control features; and providing access to data regarding the collateral.
Certain additional aspects of the example methods are described below, any one or more of which may be present in certain embodiments. An example method may also include: the condition of the collateral is interpreted in response to the received subset of collateral data.
An example method may also include: identifying a collateral event from a condition of the collateral and reporting the collateral event, wherein the collateral event is related to a collateral characteristic selected from the list consisting of: the value of the collateral, the condition of the collateral, and ownership of the collateral.
An example method may also include: the value of the collateral is determined.
An example method may also include: interpreting a collateral event; and performing loan-related actions in response to the mortgage event.
An example method may also include: a set of cancellation mortgages is identified, wherein each member of the set of cancellation mortgages shares a common attribute with the mortgage.
An example method may also include: monitoring market information relating to the value of the collateral or at least one of the set of counteracting collateral; and modifying the terms and conditions of the loan based on the market information.
An example method may also include: an intelligent loan contract for the loan is created.
An example method may also include: receiving an access control instruction; interpreting a plurality of access control features; and providing access to the collateral data.
In an embodiment, a system for processing a loan is provided herein. An example platform, system, or apparatus may include: a blockchain service circuit configured to interface with a distributed ledger; a data collection circuit configured to receive data relating to a plurality of collateral objects or data relating to an environment of the plurality of collateral objects; a valuation circuit configured to determine a value of each of the plurality of collateral based on the valuation model and the received data; an intelligent contract circuit configured to interpret an intelligent lending contract for the loan and modify the intelligent lending contract by allocating at least a portion of the plurality of mortgages as a loan guarantee based on the determined value of each of the plurality of mortgages, such that the determined values of the plurality of mortgages are sufficient to provide a guarantee for the loan. The blockchain service circuit may be further configured to record at least a portion of the assigned collateral into an entry in the distributed ledger, wherein the entry is for recording an event related to the loan. Each of the blockchain service circuit, the data collection circuit, the valuation circuit, and the intelligent contract circuit can further include a corresponding Application Programming Interface (API) component configured to facilitate communication between the system circuits.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein modifying the intelligent lending contract further comprises specifying terms and conditions governing one item selected from the list consisting of: loan terms, loan conditions, loan-related events, and loan-related activities.
An example system may include: wherein each of the terms and conditions comprises at least one member selected from the group consisting of: the principal amount of the loan, the balance of the loan, the fixed interest rate, the variable interest rate description, the payment amount, the payment plan, the end-most grand payback plan, the collateral description, the collateral substitutability description, the description of the at least one party, the description of the insured person, the description of the insured matter, the personal guaranty, the lien, the redemption condition, the default condition, the consequence of the default, the contract associated with any of the foregoing, and the term of any of the foregoing.
An example system may include: wherein the loan includes at least one of the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
An example system may include: wherein the collateral comprises at least one item selected from: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, tools, machinery, and personal property.
An example system may include: wherein the data collection circuit is further configured to receive result data relating to the loan and the corresponding collateral, and wherein the valuation circuit includes an artificial intelligence circuit configured to iteratively refine the valuation model based on the result data.
An example system may include: wherein the valuation circuitry further comprises market value data collection circuitry configured to monitor and report market information relating to the value of at least one of the plurality of collateral.
An example system may include: wherein the market value monitoring circuitry is further configured to monitor pricing or financial data for items similar to the collateral in at least one public market.
An example system, may further include: a clustering circuit configured to identify a set of similar items for valuing a collateral based on similarity to attributes of the collateral.
An example system may include: wherein the attribute of the collateral is selected from a list of attributes consisting of: the type of collateral object, the age of the collateral object, the condition of the collateral object, the history of the collateral object, the storage conditions of the collateral object, and the geographic location of the collateral object.
An example system may include: wherein the data collection circuit is further configured to interpret a condition of the collateral.
An example system may include: wherein the data collection circuit further comprises at least one of: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and an interactive crowdsourcing system.
An example system may include: wherein the loan includes at least one of the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
An example system, may further include: loan management circuitry configured to interpret a loan-related event and to perform a loan-related action in response to the loan-related event.
An example system may include: wherein the loan-related events include events related to at least one of: the value of the loan, the condition of the mortgage of the loan, or the ownership of the mortgage of the loan.
An example system may include: wherein the loan-related action comprises at least one of: modifying the terms and conditions of the loan; providing a notification to one of the parties; providing necessary notification to the loan borrower; and the redemption of loan-bound property.
An example system may include: wherein the corresponding API component of the circuit further comprises a user interface configured to interact with a plurality of users of the system.
An example system may include: wherein each of the plurality of users comprises: one of the plurality of parties, one of the plurality of entities, or a representation of any of the foregoing.
An example system may include: wherein at least one of the plurality of users may include: the prospective principal, the prospective entity or a representative of any of the foregoing.
In an embodiment, a method for processing a loan is provided herein. An example method may include: receiving data relating to a plurality of mortgages; setting a value for each of a plurality of collateral; allocating at least a portion of the plurality of mortgages as a guarantee for the loan; and recording at least a portion of the assigned mortgages into an entry in the distributed ledger, wherein the entry is used to record an event related to the loan.
Certain additional aspects of the example methods are described below, any one or more of which may be present in certain embodiments. An example method may also include: the intelligent loan contract for the loan is modified.
An example method may also include: modifying the intelligent lending contract includes adjusting or specifying the terms and conditions of the loan.
An example method may include: wherein each of the terms and conditions is selected from the list consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line plan, party, insured person, collateral, personal guaranty, lien, deadline, contract, redemption hold, default condition, and result of default.
An example method may also include: receiving result data associated with the loan; and iteratively refining the valuation model based on the result data and the corresponding collateral.
An example method may also include:
market information relating to the value of at least one of the plurality of collateral is monitored.
An example method may also include: a set of items similar to one of the plurality of mortgages is identified based on similarity to an attribute of the one of the plurality of mortgages.
An example method may also include: the condition of one of the mortgages is explained.
An example method may also include: reporting an event related to a value of one of the plurality of mortgages, a condition of one of the plurality of mortgages, or ownership of one of the mortgages.
An example method may also include: interpreting events related to: a value of one of the plurality of collateral, a condition of one of the plurality of collateral, or ownership of one of the plurality of collateral; and performing an action associated with a secured loan in response to an event associated with one of a plurality of mortgages of the secured loan.
An example method may also include: wherein the loan-related action is selected from the actions consisting of: offer a loan; accepting the loan; underwriting loan; setting interest rate of loan; a deferred payment requirement; modifying the interest rate of the loan; verifying the property rights of the mortgage; recording the change of property rights; evaluating the value of the collateral; initiating a check for collateral; the loan is collected; settlement loan; setting the terms and conditions of the loan; providing a notification to be provided to the borrower; the redemption of loan assets; and modifying the terms and conditions of the loan.
In an embodiment, a system for adaptive intelligence and robotic process automation capabilities for trading, financial and market support is provided herein. An example platform or system may include: a blockchain service circuit configured to interface with a distributed ledger; a data collection circuit configured to receive data relating to a set of collateral objects that provide a guarantee for the loan; an intelligent contract circuit configured to create an intelligent loan contract for the loan and to assign at least a portion of the set of collateral for the loan, thereby creating an assigned set of collateral; wherein the blockchain service circuit is further configured to record the assigned set of collateral into a loan entry in the distributed ledger, and wherein each of the blockchain service circuit, the data collection circuit, and the intelligent contract circuit further comprises a corresponding Application Programming Interface (API) component configured to facilitate communication between the system circuits.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein the data collection circuit is further configured to receive data related to the environment of the assigned set of collateral.
An example system may include: wherein the intelligent contract circuitry is further configured to specify terms or conditions for managing a loan of one item selected from the list consisting of: the method may include the steps of, in one embodiment, the method may include the steps of, loan terms, loan conditions, loan-related events, and loan-related activities, wherein each of the terms and conditions of the loan includes at least one member selected from the group consisting of: the principal amount of the loan, the balance of the loan, the fixed interest rate, the variable interest rate description, the payment amount, the payment plan, the last line payoff plan, the collateral description, the collateral replacement description, the description of the at least one party to the loan, the description of the insured person, the description of the insurer, the description of the insured person, the personal guaranty, the lien, the redemption condition, the default condition, the consequences of the default, the obligation associated with any of the foregoing, and the term of any of the foregoing.
An example system may include: wherein the loan includes at least one of the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
An example system may include: wherein the assigned set of collateral includes at least one of: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, tools, machinery, and personal property.
An example system, may further include: a valuation circuit configured to determine a value of each of the set of mortgages or the assigned set of mortgages based on a valuation model and the received data, wherein the valuation circuit includes a valuation model improvement circuit, wherein the valuation model improvement circuit modifies the valuation model based on a first set of valuation determinations for a first set of mortgages and a corresponding set of loan results with the first set of mortgages as a guarantee.
An example system, may further include: wherein the valuation model refinement circuit includes at least one system in a list of systems consisting of: machine learning systems, model-based systems, rule-based systems, deep learning systems, neural networks, convolutional neural networks, feedforward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, simulation systems, hybrid systems, and hybrid systems including at least two of the foregoing.
An example system, may further include: a collateral classification circuit configured to identify a set of cancellation collateral, wherein each member of the set of cancellation collateral shares a common attribute with at least one of the assigned set of collateral, wherein the common attribute is selected from a list of attributes consisting of: the type of the item, the age of the item, the condition of the item, the history of the item, ownership of the item, an administrator of the item, warranty of the item, the condition of the owner of the item, lien rights for the item, storage conditions of the item, geographic location of the item, and jurisdiction of the item.
An example system, may further include: wherein the valuation circuit further comprises a market value data collection circuit configured to monitor and report market information for a cancellation collateral associated with the value of at least one of the assigned set of collateral. An example system, may further include: wherein the intelligent contract circuitry is further configured to apportion the value of one of the assigned set of collateral among a set of borrowers.
An example system may include: wherein the loan entry in the distributed ledger further comprises priority information related to the borrower, and wherein the value apportionment is based on the borrower's priority information, wherein the borrower is selected from the list consisting of: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, and unsecured lenders.
An example system, may further include: wherein the data collection circuit comprises at least one of: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and an interactive crowdsourcing system.
An example system, may further include: wherein the data collection circuit is further configured to identify a collateral event based on the received data, wherein the collateral event is related to a value of one of the assigned set of collateral, a condition of one of the assigned set of collateral, or ownership of one of the assigned set of collateral; also included is an automatic agent circuit configured to perform a collateral-related action in response to a collateral event, wherein the collateral-related action is selected from the group consisting of: verifying the title of one of the assigned set of collateral, recording a title change of one of the assigned set of collateral, evaluating the value of one of the assigned set of collateral, initiating an inspection of one of the assigned set of collateral, initiating maintenance of one of the assigned set of collateral, initiating a vouching of one of the assigned set of collateral, and modifying terms and conditions of one of the assigned set of collateral.
An example system may include: wherein the automated brokering circuit is further configured to perform a loan-related action in response to the mortgage event, wherein the loan-related action is selected from a list of actions consisting of: offer loan; receiving a loan; underwriting loan; setting interest rate of the loan; a deferred payment requirement; modifying interest rate of the loan; the loan is collected; settlement loan; setting the terms and conditions of the loan; providing a notification to be provided to the borrower; the redemption of loan assets; and modifying the terms and conditions of the loan.
In an embodiment, a method for adaptive intelligence and robotic process automation capabilities for trading, financial and market support is provided herein. An example method may include: receiving data relating to a set of mortgages that warrant a loan; creating an intelligent loan contract for the loan; recording a group of mortgage materials in the intelligent lending contract; and recording a loan entry in the distributed ledger, wherein the loan entry comprises one of an intelligent lending contract or a reference to an intelligent lending contract.
Certain additional aspects of the example systems will be described below, any one or more of which may be present in certain embodiments. An example method may also include: data relating to the environment of one of a set of collateral is received.
An example method may also include: determining a value for each of a set of collateral based on the valuation model and the received data; the valuation model is modified based on a first set of valuation determinations for a first set of mortgages and a corresponding set of loan results secured with the first set of mortgages.
An example method may also include: the value of one of a set of mortgages is apportioned among a set of borrowers.
An example method may also include: determining a collateral event based on at least one of a value of one of a set of collateral and the received data; and performing a loan-related action in response to the mortgage event, wherein the loan-related action is selected from a list of actions consisting of: offer loan; receiving a loan; an underwriting loan; setting interest rate of the loan; a deferred payment requirement; modifying interest rate of the loan; the loan is collected; settlement loan; setting the terms and conditions of the loan; providing a notification to be provided to the borrower; the redemption of loan assets; and modifying the terms and conditions of the loan.
An example method may also include: performing a collateral-related action in response to the collateral event, wherein the collateral-related action is selected from a list of actions consisting of: verifying the title of one of a set of collateral; recording a title change for one of a set of collateral; evaluating a value of one of a set of collateral; initiating a review of one of a set of collateral; initiating maintenance of one of a set of collateral; initiating a wager on one of a set of collateral; and modifying the terms and conditions of one of the set of collateral.
An example method may also include: identifying a set of cancellation collateral, wherein the set of cancellation collateral shares a common attribute with at least one of the set of collateral; monitoring market information for data related to the set of offset collateral items; updating a value of at least one of a set of collateral based on the monitored data; and updating the loan entry in the distributed ledger with the updated value.
In an embodiment, a system for adaptive intelligence and robotic process automation capabilities for trading, financial and market support is provided herein. An example platform or system may include: a data collection circuit configured to receive data relating to a collateral that guarantees a loan; a valuation circuit configured to determine a value of the collateral based on a valuation model and the received data; intelligent contract circuitry configured to create an intelligent lending contract, wherein the intelligent lending contract specifies a contract defining a desired value of a collateral; and a loan management circuit comprising: a value comparison circuit configured to compare the value of the item with the designated contract and determine a collateral compensation value; an automated brokering circuit configured to automatically perform loan-related activities in response to the collateral compensation value, wherein the loan-related activities include: issuing a breach notification or redemption-stopping action.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein the smart contract circuit is further configured to: determining at least one of a term or condition of the intelligent lending contract in response to the collateral compensation value; and modifying the intelligent lending contract to include at least one of a term or a condition, wherein the at least one of a term or a condition is related to a loan component of the following loan components: the loan principal, the loan mortgage, the loan-related event, and the loan-related activity.
An example system may include: wherein at least one of the terms or conditions is selected from the list consisting of: the principal amount of the loan, the balance of the loan, the fixed interest rate, the variable interest rate description, the payment amount, the payment plan, the end-most grand payback plan, the collateral description, the collateral replacement description, the party description, the insured description, the warranty description, the personal warranty, the lien, the redemption stop condition, the default condition, the result of the default, the principal amount of the debt, the balance of the debt, the fixed interest rate, the variable interest rate, the payment amount, the payment plan, the end-most grand payback plan, the party, the insured, the guarantor, the collateral, the personal warranty, the lien, the deadline, the contract, the redemption stop condition, the default condition and the result of the default, the contract related to any of the foregoing, and the deadline of any of the foregoing.
An example system may include: wherein the valuation circuitry includes valuation model improvement circuitry, wherein the valuation model improvement circuitry modifies the valuation model based on a first set of valuation determinations for a first set of mortgages and a corresponding set of loan results secured with the first set of mortgages, and wherein the valuation model improvement circuitry includes at least one system in a list of systems consisting of: a machine learning system, a model-based system, a rule-based system, a deep learning system, a neural network, a convolutional neural network, a feedforward neural network, a feedback neural network, a self-organizing map, a fuzzy logic system, a random walk system, a random forest system, a probabilistic system, a bayesian system, a simulation system, and a hybrid system of at least two of the foregoing.
An example system may include: wherein the data collection circuit comprises at least one of: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and an interactive crowdsourcing system.
An example system may include: wherein the evaluation circuit further comprises a collateral classification circuit configured to identify a set of cancellation collateral, wherein each member of the set of cancellation collateral shares a common attribute with the collateral, wherein the common attribute is selected from a list of attributes consisting of: the type of the collateral, the age of the collateral, the condition of the collateral, the history of the collateral, the ownership of the collateral, the manager of the collateral, the security of the collateral, the condition of the owner of the collateral, the lien of the collateral, the storage conditions of the collateral, the geographic location of the collateral, and the jurisdiction of the collateral.
An example system may include: wherein the valuation circuit further comprises a market value data collection circuit configured to monitor and report market information for a counterattack collateral related to the value of the collateral, wherein the market value data collection circuit is further configured to: monitoring one of pricing or financial data of the offsetting collateral in the at least one public market; and reporting the monitored one of the pricing or financial data.
An example system may include: wherein the loan includes at least one of the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
An example system may include: wherein the collateral is selected from a list of items consisting of: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, collateral objects, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, tools, machinery, and personal property.
An example system, may further include: a blockchain service circuit configured to store at least one of an intelligent lending contract or a reference to an intelligent lending contract as blockchain data; and reporting circuitry configured to report a collateral event based on the received data, wherein the collateral event is related to a value of the collateral, a condition of the collateral, or ownership of the collateral.
An example system, may further include: an automatic agent circuit configured to perform a mortgage-related action in response to a mortgage event, wherein the mortgage-related event is selected from the group consisting of: verifying the property rights of the mortgage; recording property right change of the mortgage; evaluating the value of the collateral; initiating a check for collateral; initiating maintenance of the collateral; initiating a collateral for the collateral; and modifying the terms and conditions of the collateral.
An example system may include: wherein the automated brokering circuit is further configured to perform a loan-related action in response to the mortgage event, wherein the loan-related action is selected from a list of actions consisting of: offer loan; receiving a loan; underwriting loan; setting interest rate of loan; a deferred payment requirement; modifying the interest rate of the loan; urging to loan payment; settlement and loan; setting the terms and conditions of the loan; providing a notification to be provided to the borrower; redeeming the loan asset; and modifying the terms and conditions of the loan. In an embodiment, a method for robotic process automation for trading, financial and marketing activities is provided herein. An example method may include: receiving data relating to a collateral that provides a guarantee for the loan; determining a value of a collateral based on a valuation model and the received data; creating an intelligent lending contract, wherein the intelligent lending contract specifies a contract with a desired collateral value; comparing the value of the collateral with the value of the collateral specified in the contract; determining a collateral compensation value; and performing loan-related activities in response to the collateral compensation value.
An example method may also include: determining at least one of a term or condition of the intelligent lending contract in response to the collateral compensation value; and modifying the intelligent lending contract to include at least one of the terms or conditions.
An example method may also include: the valuation model is modified based on a first set of valuation determinations for a first set of mortgages and a corresponding set of loan results secured with the first set of mortgages.
An example method may also include: identifying a set of cancellation mortgages, wherein each member of the set of cancellation mortgages shares a common attribute with the mortgages, wherein the common attribute is selected from a list of attributes consisting of: the type of the collateral, the age of the collateral, the condition of the collateral, the history of the collateral, the ownership of the collateral, the manager of the collateral, the security of the collateral, the condition of the owner of the collateral, the lien of the collateral, the storage conditions of the collateral, the geographic location of the collateral, and the jurisdiction of the collateral.
An example method may also include: monitoring and reporting market information for data related to a group of members who cancel a collateral; and modifying the intelligent lending contract in response to the market information, wherein monitoring the market information comprises monitoring at least one public market for pricing data or financial data related to members of the set of offset collateral.
An example method may also include: automatically initiating a loan-related action in response to one of the pricing data or the financial data, wherein the loan-related action comprises an action selected from a list of actions consisting of: modifying the terms of the loan; issuing a breach notification; initiating a redemption-stopping action; modifying the status of the loan; providing notification to the lending party; providing necessary notification to the loan borrower; and the redemption of loan assets.
In an embodiment, a system for adaptive intelligence and robotic process automation capabilities for trading, financial and market support is provided herein. An example platform or system may include: a data collection circuit configured to receive data relating to a plurality of mortgages; a collateral classification circuit configured to identify at least one group of related collateral of the plurality of collateral, wherein each member of the at least one group shares a common attribute; intelligent contract circuitry configured to create an intelligent loan contract, wherein the intelligent loan contract defines a subset of collateral as a set of collateral for the loan, wherein the subset of collateral is selected from at least one set of related collateral.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein the collateral classification circuitry is further configured to select a common attribute from the received data, wherein the common attribute is: the type of the collateral, the category of the collateral, the value of the collateral, the price of the type of the collateral, the value of the type of the collateral, the description of the collateral, the product feature set of the collateral, the liquidity of the collateral, the expiration date of the collateral, the lifetime of the collateral, the model of the collateral, the brand of the collateral, the manufacturer of the collateral, the age of the collateral, the status of the collateral, the valuation of the collateral, the status of the collateral, the background of the collateral, the status of the collateral, the storage location of the collateral, the history of the collateral, the ownership of the collateral, the manager of the collateral, the guarantee of the collateral, the status of the owner of the collateral, the lien of the collateral, the storage condition of the collateral, the maintenance of the collateral, the use of the collateral, the historical location of the historical evaluation of the collateral, the historical failure of the historical site of the collateral, and the like.
An example system may include: wherein the intelligent loan contract is further configured to identify a subset of the collateral in real-time, and wherein the common attribute is a similarity of the states of the collateral.
An example system may include: wherein the similarity of states is based on each of a subset of the collateral that are in transit for a prescribed period of time.
An example system may include: wherein the data collection circuit comprises at least one of: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and an interactive crowdsourcing system.
An example system may include: wherein a set of loans includes a plurality of loans distributed among a plurality of borrowers.
An example system may include: wherein the valuation circuitry is configured to determine a value of each of the subset of collateral based on the valuation model and the received data; and wherein the intelligent contract circuitry is further configured to redefine the subsets based on the value of each collateral.
An example system may include: wherein the intelligent contract circuitry is further configured to determine at least one of a term or a condition of the intelligent lending contract based on the value of at least one of the subset of collateral; and modifying the intelligent lending contract to include the determined terms or conditions, wherein the terms or conditions are associated with a loan component selected from the following loan components: the loan party, the loan mortgage, the loan-related event, and the loan-related activity, and wherein the determined terms or conditions are: principal amount of the loan, balance of the loan, fixed interest rate, variable interest rate description, payment amount, payment plan, last-minute best-line payoff plan, collateral statement, collateral substitute statement, party statement, insured statement, guarantor statement, personal guarantor, lien, redemption condition, default outcome, contracts related to any of the foregoing, terms of any of the foregoing, and the like.
An example system may include: wherein the valuation circuitry includes valuation model improvement circuitry, wherein the valuation model improvement circuitry is configured to modify the valuation model based on a first set of valuation determinations for a first set of mortgages and a corresponding set of loan results secured with the first set of mortgages, and wherein the valuation model improvement circuitry includes at least one system in a list of systems consisting of: machine learning systems, model-based systems, rule-based systems, deep learning systems, neural networks, convolutional neural networks, feedforward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, simulation systems, and hybrid systems comprising at least two of the foregoing.
An example system may include: wherein the collateral classification circuitry is further configured to identify a set of cancellation collateral, wherein each member of the set of cancellation collateral shares a common attribute with the subset of collateral.
An example system may include: wherein the valuation circuitry further comprises market value data collection circuitry configured to: monitoring and reporting at least one market information (e.g., pricing data and financial data in at least one public market) in a set of offset collateral items; and reporting the monitored one of the pricing or financial data.
An example system may include: wherein at least one of the set of loans comprises one of the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
An example system may include: wherein at least one of the plurality of collateral is selected from a list of items consisting of: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, collateral objects, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, tools, machinery, and personal property.
An example system: the method can also comprise the following steps: a blockchain service circuit to store the intelligent loan contract or a reference to the intelligent loan contract as blockchain data.
An example system, may further include: a reporting circuit configured to report a collateral event based on the received data, wherein the collateral event is related to a value of one of the plurality of collateral, a condition of the one of the plurality of collateral, or ownership of the one of the plurality of collateral.
An example system, may further include: an automatic agent circuit configured to perform a collateral-related action in response to a collateral event, wherein the collateral-related action is selected from the group consisting of: verifying the title of one of the plurality of mortgages; recording a title change for one of the mortgages; evaluating a value of one of the plurality of collateral; initiating a check of one of a plurality of collateral; initiating maintenance of one of the plurality of collateral; initiating a wager on one of the plurality of collateral; and modifying the terms and conditions of one of the plurality of collateral.
In an embodiment, a method for trading, financial and market support is provided herein. An example method may include: receiving data relating to at least one of a plurality of mortgages; identifying a group of the plurality of collateral, wherein each member of the group shares a common attribute; identifying a subset of the group as a guarantee of a group of loans; and creating a set of intelligent loan contracts for a set of loans.
Certain additional aspects of the example methods are described below, any one or more of which may be present in certain embodiments. An example method may also include: a value for each of a subset of a set of mortgages is determined using a valuation model and the received data.
An example method may also include: a subset of a set of mortgages is redefined based on the value of each mortgage in the subset of mortgages, the subset of mortgages serving as a guarantee for a set of loans.
An example method may also include: at least one of the terms or conditions of at least one of the intelligent lending contracts is determined based on the value of at least one of the subset of the set of collateral.
An example method may also include: the intelligent lending contract is modified to include at least one of the terms and conditions.
An example method may also include: the valuation model is modified based on a first set of valuation determinations for a first set of mortgages and a corresponding set of loan results secured with the first set of mortgages.
An example method may also include: a set of cancellation mortgages is identified, wherein each member of the set of cancellation mortgages shares a common attribute with a set of multiple mortgages.
An example method may also include: a set of cancellation collateral market information is monitored and reported.
In an embodiment, an example platform or system may include: a data collection circuit configured to receive data relating to at least one of a group of lenders; an intelligent contract circuit configured to create an intelligent loan contract for a loan; and automatic agent circuitry configured to automatically perform a loan-related action in response to the received data, wherein the loan-related action is an interest rate change of the loan, and wherein the intelligent contract circuitry is further configured to update the intelligent loan contract using the changed interest rate.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein the data collection circuit is further configured to receive collateral-related data related to a set of collateral objects serving as a collateral for the loan, and to determine a condition of at least one of the set of collateral objects, wherein the change in interest rate is further based on the condition of the at least one of the set of collateral objects.
An example system may include: wherein the received data includes an attribute of at least one of the group of parties to the loan, and wherein the change in interest rate is based in part on the attribute.
An example system may include: wherein the intelligent contract circuitry is further configured to determine at least one of a term or a condition of the intelligent lending contract based on the attribute; and modifying the intelligent lending contract to include at least one of the terms or conditions.
An example system may include: wherein at least one of the terms or conditions is related to a loan component of the following loan components: the loan principal, the loan mortgage, the loan-related event, and the loan-related activity.
An example system may include: wherein at least one of the terms or conditions is selected from the list consisting of: the principal amount of the loan, the balance of the loan, the fixed interest rate, the variable interest rate description, the payment amount, the payment plan, the last line payoff plan, the collateral description, the collateral substitutability description, the party description, the insured description, the collateral description, the personal guaranty, the lien, the redemption condition, the default condition, the consequence of the default, the contract associated with any of the foregoing, and the term of any of the foregoing.
An example system may include: wherein the data collection circuit comprises at least one of: the mobile device comprises an internet of things circuit, an image capture device, a networking monitoring circuit, an internet monitoring circuit, a mobile device, a wearable device, a user interface circuit, and an interactive crowdsourcing circuit.
An example system may include: wherein the data collection circuitry includes internet of things circuitry configured to monitor attributes of at least one of the group of lenders.
An example system may include: wherein the data collection circuit comprises a wearable device associated with at least one of a group of parties, wherein the wearable device is configured to obtain human-related data, and wherein the received data comprises at least a portion of the human-related data.
An example system may include: wherein the data collection circuit includes a user interface circuit configured to receive data from at least one of the parties to the loan and to provide the data from the at least one of the parties to the loan as part of the received data.
An example system may include: wherein the data collection circuit comprises an interactive crowdsourcing circuit configured to: requesting data about at least one of a group of lending parties; receiving the requested data; and providing at least a subset of the requested data as part of the received data.
An example system may include: wherein the data collection circuit further comprises an internet monitoring circuit configured to retrieve data associated with at least one of the lenders from at least one public information website.
An example system, may further include: a valuation circuit configured to determine a value of at least one of a set of collateral based on a valuation model and the received data.
An example system may include: wherein the intelligent contract circuitry is further configured to determine at least one of a term or a condition of the intelligent lending contract based on the value of at least one of the set of collateral; and modifying the intelligent lending contract to include at least one of the terms or conditions.
An example system may include: wherein at least one of the terms or conditions is related to a loan component of the following loan components: the loan principal, the loan mortgage, the loan-related event, and the loan-related activity.
An example system may include: wherein at least one of the terms or conditions is selected from the list consisting of: the principal amount of the loan, the balance of the loan, the fixed interest rate, the variable interest rate description, the payment amount, the payment plan, the last line payoff plan, the collateral description, the collateral substitutability description, the party description, the insured description, the collateral description, the personal guaranty, the lien, the redemption condition, the default condition, the consequence of the default, the contract associated with any of the foregoing, and the term of any of the foregoing.
An example system may include: wherein the valuation circuitry includes valuation model refinement circuitry, wherein the valuation model refinement circuitry modifies the valuation model based on a first set of valuation determinations for a first set of mortgages and a corresponding set of loan results secured with the first set of mortgages.
An example system may include: wherein the valuation model refinement circuit includes at least one system in a list of systems consisting of: machine learning systems, model-based systems, rule-based systems, deep learning systems, neural networks, convolutional neural networks, feedforward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, simulation systems, and hybrid systems comprising at least two of the foregoing.
An example system may include: wherein the change in interest rate is further based on a value of at least one of the set of collateral.
An example system may also include: a collateral classification circuit configured to identify a set of cancellation collateral, wherein each member of the set of cancellation collateral shares a common attribute with at least one of the set of collateral.
An example system may include: wherein the common attribute is selected from a list of attributes consisting of: the type of the item, the age of the item, the condition of the item, the history of the item, ownership of the item, an administrator of the item, warranty of the item, the condition of the owner of the item, lien rights for the item, storage conditions of the item, geographic location of the item, and jurisdiction of the item.
An example system may include: wherein the valuation circuit further comprises a market value data collection circuit configured to monitor and report market information for a countermortgage associated with the value of the mortgage.
An example system may include: wherein the market value data collection circuit is further configured to monitor one of pricing or financial data of the offset collateral in the at least one public market; and reporting the monitored one of the pricing or financial data.
An example system may include: wherein the collateral is selected from a list of items consisting of: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, tools, machinery, and personal property.
An example system may include: wherein the loan comprises one of the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
In an embodiment, an example method may include: receiving data relating to at least one of a group of lending parties; creating an intelligent loan contract for the loan; performing a loan-related action in response to the received data, wherein the loan-related action is an interest rate change of the loan; and updating the intelligent loan contract using the changed interest rate.
Certain additional aspects of the example methods are described below, any one or more of which may be present in certain embodiments. A set of example methods may further comprise: receiving data relating to a set of mortgages that act as a guarantee for the loan; determining a condition of at least one of the set of collateral; and performing a loan-related action in response to a condition of at least one of the set of mortgages, wherein the loan-related action is an interest rate change of the loan.
An example set of methods may include: receiving data relating to a set of mortgages that act as a guarantee for the loan; determining a condition of at least one of the set of collateral; determining at least one of a term or a condition of the intelligent lending contract based on a condition of at least one of the set of collateral; and modifying the intelligent lending contract to include at least one of the terms or conditions.
An example set of methods may include: identifying a set of cancellation collateral, wherein each member of the set of cancellation collateral shares a common attribute with at least one of the set of collateral; monitoring the set of offset collateral in at least one public market; and reporting the monitored data.
An example method may also include: the interest rate of a loan secured with at least one of the mortgages is altered based at least in part on the monitored set of counteracting mortgages.
In an embodiment, an example platform or system may include: a data collection circuit configured to obtain data relating to at least one party of a group of lending parties from a common information source; an intelligent contract circuit configured to create an intelligent loan contract for a loan; and an automated brokerage circuit configured to automatically perform a loan-related action in response to the acquired data, wherein the loan-related action is an interest rate change of the loan, and wherein the intelligent contract circuit is further configured to update the intelligent loan contract using the changed interest rate.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein the common information source comprises at least one of the following information sources: website information, news article information, social networking information, and crowd sourcing information.
An example system may include: wherein the obtained data includes financial status of at least one of the parties in the group of lending parties.
An example system may include: wherein the financial condition is determined based on at least one attribute of at least one of the parties in the group of lending parties, the attribute selected from a list of attributes consisting of: a public valuation of a party, a set of properties owned by a party as indicated by a public record, a valuation of a set of properties owned by a party, a bankruptcy condition of a party, a redemption status of a party, a contract violation status of a party, a criminal status of a party, an export regulation status of a party, a contraband status of a party, a duty status of a party, a tax status of a party, a credit report of a party, a credit rating of a party, a website rating of a party, a set of customer reviews of a product of a party, a social network rating of a party, a set of credentials of a party, a set of referrals of a party, a set of credentials of a party, a set of behaviors of a party, a location of a party, a geographic location of a party, and a place of jurisdiction of a party.
An example system may include: wherein at least one of the parties is selected from a list of parties consisting of: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, and accountants.
An example system may include: wherein the data collection circuit is further configured to receive collateral-related data related to a set of collateral objects serving as a collateral for the loan, and to determine a condition of at least one of the set of collateral objects, wherein the change in interest rate is further based on the condition of the at least one of the set of collateral objects.
An example system, may further include: an automated brokering circuit configured to identify an event related to the loan based at least in part on the received data.
An example system may include: wherein the loan-related events include events related to at least one of: the value of the loan, the condition of the mortgage of the loan, or the ownership of the mortgage of the loan.
An example system may include: wherein the automated brokering circuit is further configured to perform an action selected from a list of actions consisting of: offer loan; receiving a loan; underwriting loan; setting interest rate of the loan; a deferred payment requirement; modifying interest rate of the loan; verifying the title of at least one of the set of collateral; evaluating a value of at least one of a set of collateral; initiating a review of at least one of a set of collateral; setting or modifying the terms and conditions of the loan; providing a notification to one of the parties; providing necessary notification to the loan borrower; and redeeming the loan asset.
An example system may include: wherein the intelligent contract circuitry may be further configured to specify terms and conditions in the intelligent lending contract, wherein one of the terms or conditions in the intelligent lending contract governs one of the loan-related events or loan-related activities.
An example system may include: wherein each of the terms and conditions is selected from the list consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line plan, party, insured person, collateral, personal guaranty, lien, deadline, contract, redemption hold, default condition, and result of default.
An example system may include: wherein the loan comprises one of the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
An example system may include: wherein the acquired data relates to one of a group of mortgages selected from the list consisting of: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, collateral objects, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, tools, machinery, and personal property.
An example system, may further include: a valuation circuit configured to determine a value of at least one of a set of collateral based on a valuation model and the acquired data.
An example system may include: wherein the intelligent contract circuitry is further configured to determine at least one of a term or a condition of the intelligent lending contract based on the value of at least one of the set of collateral; and modifying the intelligent lending contract to include at least one of the terms or conditions.
An example system may include: wherein the valuation circuitry includes valuation model improvement circuitry, wherein the valuation model improvement circuitry modifies the valuation model based on a first set of valuation determinations for a first set of mortgages and a corresponding set of loan results secured with the first set of mortgages.
An example system may include: wherein the valuation model refinement circuit includes at least one system in a list of systems consisting of: machine learning systems, model-based systems, rule-based systems, deep learning systems, neural networks, convolutional neural networks, feedforward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, simulation systems, and hybrid systems comprising at least two of the foregoing.
An example system, may further include: a collateral classification circuit configured to identify a set of cancellation collateral, wherein each member of the set of cancellation collateral shares a common attribute with at least one of the set of collateral.
An example system may include: wherein the common attribute is selected from a list of attributes consisting of: the type of the item, the age of the item, the condition of the item, the history of the item, ownership of the item, an administrator of the item, warranty of the item, the condition of the owner of the item, lien rights for the item, storage conditions of the item, geographic location of the item, and jurisdiction of the item.
An example system may include: wherein the valuation circuit further comprises a market value data collection circuit configured to monitor and report market information for a countermortgage associated with the value of the mortgage.
An example system may include: wherein the market value data collection circuit is further configured to monitor one of pricing or financial data of the offset collateral in the at least one public market; and reporting the monitored one of the pricing or financial data.
An example system may include: wherein the intelligent contract circuit is further configured to modify the terms or conditions of the loan based on collateral-counteracting market information relating to the value of the collateral.
In an embodiment, an example method may include; obtaining data relating to at least one of a group of lending parties from a common source, wherein the common source is selected from a list of sources consisting of: website information, news article information, social network information, and crowdsourcing information; creating an intelligent borrowing and lending contract; performing a loan-related action in response to the acquired data, wherein the loan-related action is a change in interest rate of the loan; and updating the intelligent loan contract using the changed interest rate.
Certain additional aspects of the example methods are described below, any one or more of which may be present in certain embodiments. An example method may include: receiving collateral-related data relating to a set of collateral that serves as a guarantee for the loan; and determining a condition of at least one of the set of collateral, wherein the change in interest rate is further based on the condition of the at least one of the set of collateral.
An example method may include: identifying a loan-related event based at least in part on the mortgage-related data; performing an action selected from a list of actions consisting of: offer loan; receiving a loan; underwriting loan; setting interest rate of the loan; a deferred payment requirement; modifying interest rate of the loan; verifying the title of at least one of the set of collateral; evaluating a value of at least one of a set of collateral; initiating a review of at least one of a set of collateral; setting or modifying the terms and conditions of the loan; providing a notification to one of the parties; providing necessary notification to the loan borrower; and redeeming the loan asset.
An example method may also include: determining a value of at least one of the set of mortgages based on at least one of the mortgage-related data or the acquired data and the valuation model.
An example method may also include: at least one of the terms or conditions of the intelligent lending contract is determined based on the value of at least one of the set of collateral.
An example method may also include: the intelligent loan contract is modified to include at least one of the terms or conditions.
An example method may also include: the valuation model is modified based on a first set of valuation determinations for a first set of mortgages and a corresponding set of loan results secured with the first set of mortgages.
An example method may include: identifying a set of cancellation collateral, wherein each member of the set of cancellation collateral and at least one of the set of collateral share a common attribute; monitoring one of pricing data or financial data of at least one of the set of offset collateral in at least one public market; reporting the monitored data for at least one of the set of offset collateral objects; and modifying the terms or conditions of the loan based on the reported monitored data.
In an embodiment, an example platform or system may include: a data collection circuit configured to receive data relating to a status of the loan and data relating to a set of mortgages that serve as a guarantee of the loan; a blockchain service circuit configured to maintain a safety history ledger for the loan-related event, the blockchain circuit further configured to interpret a plurality of access control features corresponding to a plurality of parties associated with the loan; a loan assessment circuit configured to determine a loan status based on the received data; an intelligent contract circuit configured to create an intelligent loan contract for a loan; and an automatic brokerage circuit configured to perform a loan action based on the loan status; wherein the blockchain servicing circuit is further configured to update the historical ledger of the event using the loan action.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein the data collection circuit is further configured to receive data related to one or more of the loan entities, and wherein the loan assessment circuit is further configured to determine compliance with the contract based on the data related to one or more of the loan entities.
An example system may include: wherein the data collection circuit further comprises at least one system for monitoring one or more of the lending entities, the system selected from the group consisting of: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and an interactive crowdsourcing system.
An example system may include: wherein the interactive crowdsourcing system comprises a user interface for requesting information from a crowdsourcing station related to one or more of the loan entities.
An example system may include: wherein the user interface is configured to allow one or more of the loan entities to enter information for one or more of the loan entities.
An example system may include: wherein the networked monitoring system includes network search circuitry configured to search the public information website for information related to one or more of the loan entities.
An example system may include: wherein the loan assessment circuit is further configured to determine a fulfillment status of a condition of the loan based on the received data and the status of one or more of the loan entities, and wherein the determination of the loan status is determined based in part on the status of at least one or more of the loan entities and the fulfillment status of the condition of the loan.
An example system may include: wherein the condition of the loan is related to at least one of payment fulfillment and satisfaction of the contract.
An example system may include: wherein the data collection circuit further comprises a market data collection circuit configured to receive financial data about at least one of the plurality of parties associated with the loan.
An example system may include wherein the loan assessment circuit is further configured to determine a financial status of at least one of the plurality of parties associated with the loan based on the received financial data.
An example system may include: wherein at least one of the plurality of parties is selected from a list of parties consisting of: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, and accountants.
An example system may include: wherein the received financial data relates to an attribute of an entity selected from at least one of the plurality of parties to an attribute list consisting of: a public valuation of a party, a set of properties owned by a party as indicated by a public record, a valuation of a set of properties owned by a party, a bankruptcy condition of a party, a redemption status of an entity, a contract breach status of an entity, a violation status of an entity, a criminal status of an entity, an export regulation status of an entity, a contraband status of an entity, a duty status of an entity, a tax status of an entity, a credit report of an entity, a credit rating of an entity, a website rating of an entity, a set of customer reviews of a product of an entity, a social network rating of an entity, a set of credentials of an entity, a set of referrals of an entity, a set of proofs of an entity, a set of behaviors of an entity, a location of an entity, and a geographic location of an entity.
An example system, may further include: a valuation circuit configured to determine a value of at least one of a set of collateral based on a valuation model and the received data.
An example system may include: wherein the intelligent contract circuitry is further configured to determine at least one of a term or a condition of the intelligent lending contract based on the value of at least one of the set of collateral; and modifying the intelligent lending contract to include at least one of the terms or conditions.
An example system may include: wherein each of the terms and conditions is selected from the list consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line plan, party, insured person, collateral, personal guaranty, lien, deadline, contract, redemption hold, default condition, and result of default.
An example system may include: wherein the valuation circuitry includes valuation model improvement circuitry, wherein the valuation model improvement circuitry modifies the valuation model based on a first set of valuation determinations for a first set of mortgages and a corresponding set of loan results secured with the first set of mortgages.
An example system may include: wherein the valuation model refinement circuit includes at least one system in a list of systems consisting of: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
An example system, may further include: a collateral classification circuit configured to identify a set of cancellation collateral, wherein each member of the set of cancellation collateral shares a common attribute with at least one of the set of collateral.
An example system may include: wherein the common attribute is selected from a list of attributes consisting of: the type of the collateral, the age of the collateral, the condition of the collateral, the history of the collateral, the ownership of the collateral, the manager of the collateral, the security of the collateral, the condition of the owner of the collateral, the lien of the collateral, the storage conditions of the collateral, the geographic location of the collateral, and the jurisdiction of the collateral.
An example system may include: wherein the valuation circuit further comprises a market value data collection circuit configured to monitor and report market information for a countermortgage associated with the value of the mortgage.
An example system may include: wherein the market value data collection circuit is further configured to monitor one of pricing or financial data of the offset collateral in the at least one public market; and reporting the monitored one of the pricing or financial data.
An example system may include: wherein the intelligent contract circuit is further configured to modify the terms or conditions of the loan based on collateral-counteracting market information relating to the value of the collateral.
In an embodiment, an example method may include: maintaining a safety history ledger for loan-related events; receiving data relating to the status of the loan; receiving data relating to a set of mortgages that act as a guarantee for the loan; determining the status of the loan; performing a loan action based on the loan status; and updating a historical ledger for the loan-related event.
Certain additional aspects of the example methods will be described below, any one or more of which may be present in certain embodiments. An example method may include: receiving data relating to one or more lending entities; and determining compliance with the contract for the loan based on the received data.
An example method may include: a fulfillment status of a condition of the loan is determined, wherein the loan status is determined based in part on the fulfillment status of the condition of the loan.
An example method may include: financial data associated with at least one of the lending parties is received.
An example method may include: the financial status of at least one of the parties to the loan is determined based on the financial data.
An example method may include: a value of at least one set of collateral is determined based on the valuation model and the received data.
An example method may include: determining at least one of the terms or conditions of the loan based on the value of at least one of the mortgages; and modifying the intelligent lending contract to include at least one of the terms or conditions.
An example method may include: identifying a set of cancellation collateral, wherein each member of the set of cancellation collateral and at least one of the set of collateral share a common attribute; receiving data relating to the set of offset mortgages, wherein a value of at least one set of mortgages is determined based in part on the received data relating to the set of offset mortgages.
In an embodiment, an intelligent contract system for managing mortgages of a loan is provided herein. An example platform, system, or apparatus may include: a data collection circuit configured to monitor a status of a loan and a status of a collateral of the loan; intelligent contract circuitry configured to process information from the data collection circuitry and automatically initiate at least one of replacement, removal or addition of one or more of the mortgages of the loan based on the information and the intelligent lending contract in response to at least one of the status of the loan or the status of the mortgages of the loan; and a blockchain service circuit configured to interpret a plurality of access control features corresponding to at least one party associated with the loan and record at least one of the replacement, removal, or addition in a distributed ledger of the loan.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein the data collection circuit further comprises at least one of: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and an interactive crowdsourcing system.
An example system may include: wherein the loan includes at least one of the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
An example system may include: wherein the status of the loan is determined based on the status of at least one entity associated with the loan and the fulfillment status of the conditions of the loan.
An example system may include: wherein the fulfillment status of the condition is related to at least one of payment fulfillment or satisfaction of an agreement on the loan.
An example system may include: wherein the status of the loan is determined based on the status of at least one entity associated with the loan and the fulfillment status of the conditions of the loan; wherein fulfillment of the condition is associated with at least one of payment fulfillment or satisfaction of an agreement on the loan; and wherein the data collection circuitry is further configured to determine compliance with the contract by monitoring at least one entity.
An example system may include: wherein at least one of the entities is a principal of the loan, and wherein the data collection circuit is further configured to monitor a financial status of the at least one entity.
An example system may include: wherein the conditions of the loan include a financial condition of the loan, and wherein the fulfillment state of the financial condition is determined based on attributes selected from the following: a public valuation of at least one entity, a property owned by at least one entity as indicated by a public record, a valuation of a property owned by at least one entity, a bankruptcy condition of at least one entity, a redemption status of at least one entity, a contract default status of at least one entity, a violation status of at least one entity, a criminal status of at least one entity, an export regulation status of at least one entity, a contraband status of at least one entity, a tariff status of at least one entity, a tax status of at least one entity, a credit report of at least one entity, a credit rating of at least one entity, a website rating of at least one entity, a plurality of customer reviews of products of at least one entity, a social network rating of at least one entity, a plurality of credentials of at least one entity, a plurality of referrals of at least one entity, a behavior of at least one entity, a location of at least one entity, a geographic location of at least one entity, and a relevant jurisdiction of at least one entity.
An example system may include: wherein the principal of loan comprises at least one principal selected from the following: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, and accountants.
An example system may include: wherein the data monitoring circuit is further configured to monitor a status of a collateral of the loan based on at least one collateral attribute selected from the following attributes: the type of collateral object, the age of the collateral object, the condition of the collateral object, the history of the collateral object, the storage conditions of the collateral object, and the geographic location of the collateral object.
An example system may include: wherein the collateral includes at least one of: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, merchandise, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
An example system, may further include: a valuation circuit configured to determine a value of a collateral for the loan based on a state of the collateral using a valuation model.
An example system may include: wherein the smart contract circuit is further configured to initiate at least one of a replacement, removal, or addition of one or more of the mortgages of the loan to maintain the value of the mortgages within a predetermined range.
An example system may include: wherein the valuation circuitry further comprises transaction result processing circuitry configured to interpret result data relating to the collateral transactions and iteratively refine the valuation model in response to the result data.
An example system may include: wherein the valuation circuit further comprises a market value data collection circuit configured to monitor and report market information relating to the value of the collateral.
An example system may include: wherein the market value data collection circuit is further configured to monitor at least one of pricing data or financial data of the counteracting collateral in the at least one public market.
An example system may include: wherein the market value data collection circuit is further configured to construct a set of cancellation mortgages for evaluating the mortgage using the clustering circuit based on the mortgage attributes.
An example system may include: wherein the attributes include at least one of: the type of collateral object, the age of the collateral object, the condition of the collateral object, the history of the collateral object, the storage conditions of the collateral object, and the geographic location of the collateral object.
An example system may include: wherein the intelligent lending contract comprises terms and conditions of the loan, wherein each of the terms and conditions comprises at least one member selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line return plan, collateral description, collateral substitutability description, party, insured person, collateral, personal guaranty, lien, term, contract, redemption condition, default condition, and default outcome.
An example system may include: wherein the intelligent contract circuitry further comprises loan management circuitry configured to specify terms and conditions of an intelligent lending contract that manages at least one of: terms and conditions of the loan, loan-related events, or loan-related activities.
In an embodiment, a smart contract method for managing mortgages of a loan is provided herein. An example method may include: monitoring the status of the loan and the status of the mortgage of the loan; automatically initiating at least one of a replacement, removal, or addition of one or more of the mortgages of the loan based on at least one of the status of the loan or the status of the mortgages of the loan; and interpreting a plurality of access control features corresponding to at least one party associated with the loan and recording at least one of the replacement, removal, or addition in a distributed ledger of the loan.
Certain additional aspects of the example methods are described below, any one or more of which may be present in certain embodiments.
An example method may include: wherein the status of the loan is determined based on the status of at least one entity associated with the loan and the fulfillment status of the conditions of the loan.
An example method may include: a value is determined using a set of valuation models for the collateral based on at least one of a status of the loan or the collateral of the loan.
An example method may include: wherein at least one of replacement, removal, or addition is initiated to maintain the value of the collateral within a predetermined range.
An example method may include: interpreting result data relating to a transaction of one of the collateral or the cancellation collateral; and iteratively refining the valuation model in response to the result data.
An example method may include: market information relating to the value of the collateral is monitored and reported.
An example method may include: at least one of pricing data or financial data of the offsetting collateral in the at least one public market is monitored.
An example method may include: terms and conditions of an intelligent contract that specifies at least one of terms and conditions for managing a loan, a loan-related event, or a loan-related activity.
An example apparatus may include: a data collection circuit configured to monitor at least one of a status of the loan or a status of a mortgage of the loan; a smart contract circuit configured to interpret a smart contract for the loan and to adjust at least one term or condition of the smart contract for the loan in response to at least one of a state of the loan or a state of a collateral for the loan; and a blockchain service circuit configured to interpret a plurality of access control features corresponding to a plurality of parties associated with the loan and record at least one term or condition of an intelligent contract for the adjusted loan in a distributed ledger of the loan. The data collection circuit may monitor a status of a collateral of the loan, the apparatus further comprising a valuation circuit configured to determine a value of the collateral based on the status of the collateral of the loan using a valuation model, and wherein the intelligent contract circuit is further configured to adjust at least one term or condition of an intelligent contract for the loan in response to the value of the collateral.
In an embodiment, a crowdsourcing system for verifying a condition of a mortgage of a loan is provided herein. An example platform, system, or apparatus may include: a crowdsourcing request circuit configured to configure at least one parameter of a crowdsourcing request, the parameter being related to obtaining information about a condition of a collateral for the loan; a crowdsourcing issuing circuit configured to issue crowdsourcing requests to a set of information providers; a crowdsourcing communication circuit configured to collect and process at least one response from the set of information providers and provide a reward to at least one of the set of information providers in response to a successful information provision event. A successful information provision event may be the receipt of information identified as being relevant to the collateral that is the subject of the crowdsourcing request, and where the information is relevant to the condition of the collateral. Information about identifying the characteristics of the collateral (e.g., serial number or model number) may not be a successful information provision event.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein the crowdsourcing distribution circuit is further configured to distribute the reward description to at least a portion of a set of information providers in response to a successful information provision event. The reward description may include the type or type of reward, the value of the reward, the amount of the reward, information about the effective use date of the reward or information for using the reward, etc.
An example system may include: wherein the crowdsourcing communication circuit further comprises or is in communication with an intelligent contract circuit configured to: managing rewards by determining successful information provision events in response to at least one parameter configured for crowdsourcing requests; and automatically assigning a reward to at least one of the set of information providers in response to a successful information provision event.
An example system may include: wherein the loan includes at least one of the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
An example system may include: wherein the collateral includes at least one of: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
An example system may include: wherein the condition of the collateral is determined based on an attribute of the following attributes: the quality of the collateral, the condition of the collateral, the state of the property right of the collateral, the possession state of the collateral and the lien state of the collateral.
An example system may include: wherein when the collateral is an item, the condition of the collateral is determined based on an attribute of the following attributes: a new or used status of the item, a type of the item, a category of the item, a description of the item, a product feature set of the item, a model of the item, a brand of the item, a manufacturer of the item, a status of the item, a background of the item, a condition of the item, a value of the item, a storage location of the item, a geographic location of the item, a age of the item, a maintenance history of the item, a usage history of the item, an accident history of the item, a failure history of the item, ownership of the item, an ownership history of the item, a price of the type of the item, a value of the type of the item, an assessment of the item, and an assessment of the item.
An example system, may further include: block chain service circuitry configured to record identification information and at least one parameter of the crowdsourcing request, at least one response to the crowdsourcing request, and the reward description in a distributed ledger of the crowdsourcing request.
An example system may include: wherein the crowdsourcing request circuit is further configured to enable a workflow through which a human user inputs at least one parameter to establish the crowdsourcing request.
An example system may include: wherein the at least one parameter includes a type of information requested, an award, and a condition for receiving the award.
An example system may include: wherein the reward is selected from the following rewards: financial rewards, tokens, tickets, contract rights, cryptocurrency amounts, multiple reward points, monetary amounts, discounts on products or services, and access rights.
An example system, may further include: intelligent contract circuitry configured to process the at least one response and, in response, automatically take an action related to the loan.
An example system may include: wherein the action is at least one of a redemption hold action, a lien management action, an interest rate setting action, a default origination action, a collateral replacement, or a loan claim.
An example system, may further include: a robotic process automation circuit configured to configure a crowdsourcing request based on at least one attribute of the loan based on training on a training data set comprising human user interactions with at least one of the crowdsourcing request circuit or the crowdsourcing communication circuit.
An example system may include: wherein at least one attribute of the loan is available from intelligent contract circuitry that manages the loan.
An example system may include: wherein the training data set further comprises results from a plurality of crowdsourcing requests.
An example system may include: wherein the robotic process automation circuit is further configured to determine a reward.
An example system may include: wherein the robotic process automation circuit is further configured to determine at least one domain to which the crowdsourcing issuing circuit issues the crowdsourcing request.
In an embodiment, a crowdsourcing method for verifying a condition of a mortgage of a loan is provided herein. An example method may include: configuring at least one parameter of the crowdsourcing request, the parameter being related to obtaining information about a condition of a collateral of the loan; issuing a crowdsourcing request to a group of information providers; collecting and processing at least one response to the crowdsourcing request; and providing a reward in response to a successful information provision event.
Certain additional aspects of the example methods are described below, any one or more of which may be present in certain embodiments.
An example method may also include: a reward description is issued to at least a portion of a group of information providers in response to a successful information provision event.
An example method may also include: wherein the reward is automatically assigned to at least one of a group of information providers in response to a successful information provision event.
An example method may also include: identifying information and at least one parameter of the crowdsourcing request, at least one response to the crowdsourcing request, and the reward description are recorded in a distributed ledger of the crowdsourcing request.
An example method may also include: the graphical user interface is configured to enable a workflow through which a human user enters at least one parameter to establish a crowdsourcing request.
An example method may also include: actions related to the loan are automatically taken in response to a successful information provision event.
An example method may also include: training a robotic process automation circuit based on a training data set, the training data set including a plurality of results corresponding to a plurality of crowdsourcing requests; and operating the robotic process automation circuit to iteratively improve the crowdsourcing request.
An example method may also include: providing at least one attribute of the loan to the robotic process automation circuit to configure the crowdsourcing request.
An example method may also include: configuring the crowdsourcing request includes determining a reward.
An example method may also include: at least one attribute of the loan is input to the robotic process automation circuit to determine at least one domain to which to issue the crowdsourcing request.
An example apparatus may include: a crowdsourcing request circuit configured to provide an interface to enable configuration of at least one parameter of a crowdsourcing request, the parameter being associated with obtaining information regarding a condition of a collateral of a loan; crowdsourcing issuing circuitry for issuing crowdsourcing requests to a group of information providers in response to the crowdsourcing requests; and a crowdsourcing communication circuit configured to provide an interface to collect at least one response from a member of the set of information providers to a crowdsourcing request, and to provide a reward to at least one of the set of information providers in response to a successful information provision event.
The apparatus may also include an intelligent contract circuit configured to: managing rewards by determining successful information provision events in response to at least one parameter configured for crowdsourcing requests; and automatically assigning a reward to at least one of the group of information providers in response to a successful information provision event.
In an embodiment, a crowdsourcing system for verifying a condition of a guarantor of a loan is provided herein. An example platform, system, or apparatus may include: a crowdsourcing request circuit configured to configure at least one parameter of a crowdsourcing request, the parameter being related to obtaining information about a condition of a collateral for the loan; a crowdsourcing issuing circuit configured to issue crowdsourcing requests to a set of information providers; a crowdsourcing communication circuit configured to collect and process at least one response from the set of information providers and provide a reward to at least one of the set of information providers in response to a successful information provision event.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein the status is a financial status of the entity, wherein the entity is a guarantor of the loan. An example system may include: wherein the financial condition is determined based at least in part on information about the entity selected from the group consisting of: a public valuation of an entity, an entity-owned property as indicated by a public record, a valuation of an entity-owned property, a bankruptcy condition of an entity, a redemption-out status of an entity, a contract breach status of an entity, a violation status of an entity, a criminal status of an entity, an export regulation status of an entity, a contraband status of an entity, a duty status of an entity, a tax status of an entity, a credit report of an entity, a credit rating of an entity, a website rating of an entity, a plurality of customer reviews of a product of an entity, a social network rating of an entity, a plurality of credentials of an entity, a plurality of referrals of an entity, a plurality of certifications of an entity, a plurality of behaviors of an entity, a location of an entity, a geographic location of an entity, and a jurisdiction of an entity.
The crowdsourcing communications circuit may further comprise an intelligent contract circuit configured to: managing rewards by determining successful information provision events in response to at least one parameter configured for crowdsourcing requests; and automatically assigning a reward to at least one of the set of information providers in response to a successful information provision event.
An example system may include: wherein the loan includes at least one of the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
An example system may include: wherein the crowdsourcing request circuit is further configured to configure at least one additional parameter of the crowdsourcing request to obtain information about a condition of a collateral for the loan.
An example system may include: wherein the collateral includes at least one of: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
An example system may include: wherein when the collateral is an item, the condition of the collateral is determined based on an attribute of the following attributes: a new or used status of the item, a type of the item, a category of the item, a description of the item, a product feature set of the item, a model of the item, a brand of the item, a manufacturer of the item, a status of the item, a background of the item, a condition of the item, a value of the item, a storage location of the item, a geographic location of the item, a age of the item, a maintenance history of the item, a usage history of the item, an accident history of the item, a failure history of the item, ownership of the item, an ownership history of the item, a price of the type of the item, a value of the type of the item, an assessment of the item, and an assessment of the item.
An example system, may further include: block chain service circuitry configured to record identification information and at least one parameter of the crowdsourcing request, at least one response to the crowdsourcing request, and the reward description in a distributed ledger of the crowdsourcing request.
An example system may include: wherein the crowdsourcing request circuit is further configured to enable a workflow through which a human user inputs at least one parameter to establish the crowdsourcing request.
An example system may include: wherein the at least one parameter includes a type of information requested, an award, and a condition for receiving the award.
An example system may include: wherein the reward is selected from the following rewards: financial rewards, tokens, tickets, contract rights, cryptocurrency amounts, multiple reward points, monetary amounts, discounts on products or services, and access rights.
An example system, may further include: intelligent contract circuitry configured to process the at least one response and, in response, automatically take an action related to the loan.
An example system may include: intelligent contract circuitry configured to process the at least one response and in response automatically take an action related to the loan, wherein the action is at least one of a redemption-out action, a lien management action, an interest rate setting action, a default origination action, a collateral replacement, and an underwriting action.
An example system, may further include: a robotic process automation circuit configured to configure a crowdsourcing request based on at least one attribute of the loan based on training on a training data set comprising human user interactions with at least one of the crowdsourcing request circuit or the crowdsourcing communication circuit.
An example system may include: wherein at least one attribute of the loan is available from intelligent contract circuitry that manages the loan.
An example system may include: wherein the training data set further comprises results from a plurality of crowdsourcing requests.
An example system may include: wherein the robotic process automation circuit is further configured to determine a reward.
An example system may include: wherein the robotic process automation circuit is further configured to determine at least one domain to which the crowdsourcing issuing circuit issues the crowdsourcing request.
In an embodiment, a crowdsourcing method for verifying a condition of a mortgage of a loan is provided herein. An example method may include: configuring at least one parameter of the crowdsourcing request, the parameter being associated with obtaining information about a condition of a guarantor of the loan; issuing a crowdsourcing request to a group of information providers; collecting and processing at least one response to the crowdsourcing request; and providing a reward to at least one of the set of information providers in response to a successful information provision event.
Certain additional aspects of the example methods will be described below, any one or more of which may be present in certain embodiments. An example method may also include: a reward description is issued to at least a portion of a group of information providers in response to a successful information provision event.
An example method may also include: wherein the reward is automatically assigned to at least one of a group of information providers in response to a successful information provision event.
An example method may also include: identifying information and at least one parameter of the crowdsourcing request, at least one response to the crowdsourcing request, and the reward description are recorded in a distributed ledger of the crowdsourcing request.
An example method may also include: the graphical user interface is configured to enable a workflow through which a human user enters at least one parameter to establish a crowdsourcing request.
An example method may also include: actions related to the loan are automatically taken in response to a successful information provision event.
An example method may also include: training a robotic process automation circuit based on a training data set, the training data set including a plurality of results corresponding to a plurality of crowdsourcing requests; and operating the robotic process automation circuit to iteratively improve the crowdsourcing request.
An example method may also include: providing at least one attribute of the loan to the robotic process automation circuit to configure the crowdsourcing request.
An example method may also include: configuring the crowdsourcing request includes determining a reward.
An example method may also include: at least one attribute of the loan is input to the robotic process automation circuit to determine at least one domain to which to issue the crowdsourcing request.
In an embodiment, an intelligent contract system for modifying a loan with a set of computing services is provided herein. An example platform, system, or apparatus may include: a data collection circuit configured to determine location information corresponding to each of a plurality of entities involved in the loan; a jurisdiction definition circuit configured to determine a jurisdiction of at least one of the plurality of entities in response to the location information; and intelligent contract circuitry configured to automatically take loan-related actions for the loan based at least in part on a jurisdiction of at least one of the plurality of entities.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein the intelligent contract circuit is further configured to automatically take a loan-related action in response to a first one of the plurality of entities being in a first jurisdiction and a second one of the plurality of entities being in a second jurisdiction.
An example system may include: wherein the intelligent contract circuit is further configured to automatically take a loan-related action in response to the movement of one of the plurality of entities from the first jurisdiction to the second jurisdiction.
An example system may include: wherein the loan-related action comprises at least one of the following loan-related actions: offer loan; receiving a loan; underwriting loan; setting interest rate of the loan; a deferred payment requirement; modifying the interest rate of the loan; verifying the property rights of the mortgage; recording the change of property rights; evaluating the value of the collateral; initiating a check for collateral; urging to loan payment; settlement and loan; setting the terms and conditions of the loan; providing a notification to be provided to the borrower; the redemption of loan assets; and modifying the terms and conditions of the loan.
An example system may include: the intelligent contract circuit is further configured to process a plurality of jurisdiction-specific regulatory notification requirements and provide appropriate notifications to the borrower based on the jurisdiction corresponding to at least one of the following entities: a borrower, funds provided through a loan, a loan repayment, or a collateral for the loan.
An example system may include: wherein the intelligent contract circuitry is further configured to process a plurality of jurisdiction-specific regulatory redemption-stop requirements and provide an appropriate redemption-stop notification to the borrower based on the jurisdiction corresponding to at least one of the following entities: a borrower, funds provided through a loan, a loan repayment, or a collateral for the loan.
An example system may include: wherein the intelligent contract circuitry is further configured to process a plurality of jurisdiction-specific rules for setting terms and conditions of the loan, and configure the intelligent contract based on a jurisdiction corresponding to at least one of the following entities: the borrower, the funds provided over the loan, the loan repayment, and the collateral for the loan.
An example system may include: wherein the intelligent contract circuit is further configured to determine the interest rate of the loan such that the loan complies with a maximum interest rate limit applicable to the jurisdiction corresponding to the selected one of the plurality of entities.
An example system may include: wherein the data collection circuit is further configured to monitor a condition of a collateral of the loan, and wherein the smart contract circuit is further configured to determine an interest rate of the loan in response to the condition of the collateral of the loan.
An example system may include: wherein the data collection circuit is further configured to monitor an attribute of at least one of the plurality of entities that is a principal of the loan, and wherein the intelligent contract circuit is further configured to determine an interest rate of the loan in response to the attribute.
An example system may include: wherein the intelligent contract circuitry further comprises loan management circuitry for specifying terms and conditions of an intelligent loan contract, the intelligent loan contract managing at least one of: terms and conditions of the loan, loan-related events, or loan-related activities.
An example system may include: wherein the loan includes at least one of the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty administration, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
An example system may include: wherein each of the terms and conditions of the loan includes at least one member selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line return plan, collateral description, collateral substitutability description, party, insured person, collateral, personal guaranty, lien, term, contract, redemption condition, default condition, and default outcome.
An example system may include: wherein the data collection circuit further comprises at least one of: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and an interactive crowdsourcing system.
An example system may include: a valuation circuit configured to determine a value of a collateral for the loan based on a jurisdiction corresponding to at least one of the plurality of entities using the valuation model.
An example system may include: wherein the valuation model is a jurisdiction-specific valuation model, and wherein a jurisdiction corresponding to at least one of the plurality of entities comprises a jurisdiction corresponding to at least one of the following entities: the borrower, the funds provided in accordance with the loan, the delivery location of the funds provided in accordance with the loan, the payment of the loan, and the collateral for the loan.
An example system may include: wherein at least one of the terms and conditions of the loan is based on the value of the mortgage of the loan.
An example system may include: wherein the collateral includes at least one of: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
An example system may include: wherein the valuation circuitry further comprises transaction result processing circuitry configured to interpret result data relating to the collateral transactions and iteratively refine the valuation model in response to the result data.
An example system may include: wherein the valuation circuit further comprises a market value data collection circuit configured to monitor and report market information relating to the value of the collateral.
An example system may include: wherein the market value data collection circuit monitors pricing data or financial data of the counteracting collateral in the at least one public market.
An example system may include: wherein the clustering circuit constructs a set of offset collateral for evaluating the collateral based on attributes of the collateral.
An example system may include: wherein the attributes are selected from: the type of collateral object, the age of the collateral object, the condition of the collateral object, the history of the collateral object, the storage conditions of the collateral object, and the geographic location of the collateral object.
In an embodiment, a method is provided for modifying a loan with a set of computing services. An example method may include: monitoring location information corresponding to each of a plurality of entities involved in the loan; determining a jurisdiction of at least one of the plurality of entities in response to the location information; and automatically taking a loan-related action for the loan based at least in part on the jurisdiction of the at least one of the plurality of entities.
Certain additional aspects of the example methods are described below, any one or more of which may be present in certain embodiments. An example method may include: loan-related actions are automatically taken in response to a first of the plurality of entities being in a first jurisdiction and a second of the plurality of entities being in a second jurisdiction.
An example method may include: loan-related actions are automatically taken in response to a movement of one of the plurality of entities from the first jurisdiction to the second jurisdiction.
An example method may include: processing a plurality of jurisdiction-specific requirements based on a jurisdiction of a related one of the plurality of entities, and performing at least one of: providing appropriate notification to the borrower in response to a plurality of jurisdiction-specific requirements including regulatory notification requirements; setting up specific rules for setting up terms and conditions of the loan in response to a plurality of jurisdiction-specific requirements including jurisdiction-specific rules for the terms and conditions of the loan; determining the interest rate of the loan such that the loan complies with the maximum interest rate limit in response to a plurality of jurisdiction-specific requirements including the maximum interest rate limit; and wherein the associated one of the plurality of entities comprises at least one of: the borrower, the funds provided in accordance with the loan, the repayment from the loan, and the collateral for the loan.
An example method may include: at least one of a condition of a plurality of mortgages of the loan or an attribute of at least one of a plurality of entities that is a party to the loan is monitored, wherein the condition or the attribute is used to determine an interest rate.
An example method may include: the valuation model is operated to determine a value of a collateral for the loan based on a jurisdiction of at least one of the plurality of entities.
An example method may include: interpreting outcome data related to the collateral transaction; and iteratively refining the valuation model in response to the result data.
In an embodiment, an intelligent contract system for modifying a loan is provided herein. An example platform, system, or apparatus may include: a data collection circuit configured to monitor and collect information about at least one entity involved in the loan; and intelligent contract circuitry configured to automatically reorganize debts associated with the loan based on the monitored and collected information about at least one entity involved in the loan.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: where the monitored and collected information includes the status of the mortgage of the loan.
An example system may include: wherein the intelligent contract circuitry may be further configured to determine an occurrence of an event based on the contract for the loan and the monitored and collected information about at least one entity involved in the loan; and automatically reorganizing the debt in response to the occurrence of the event.
An example system may include: where the event is a situation in which the mortgage of the loan does not exceed the desired point value for the remaining balance of the loan.
An example system may include: wherein the event is a default of the compact by the purchaser.
An example system may include: wherein the monitored and collected information includes attributes of at least one entity involved in the loan.
An example system may include: wherein the intelligent contract circuitry further comprises loan management circuitry configured to specify terms and conditions of an intelligent contract that manages at least one of: terms and conditions of the loan, loan-related events, or loan-related activities.
An example system may include: wherein the loan includes at least one of the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
An example system may include: wherein each of the terms and conditions of the loan includes at least one member selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line return plan, collateral description, collateral substitutability description, party, insured person, collateral, personal guaranty, lien, term, contract, redemption condition, default condition, and default outcome.
An example system may include: wherein the data collection circuit further comprises at least one of: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and an interactive crowdsourcing system.
An example system, may further include: a valuation circuit configured to use a valuation model to determine a value of a collateral based on monitored and collected information about at least one entity involved in the loan.
An example system may include: wherein the repacking of the debt is based on the valuation of the collateral for the loan as monitored by the data collection circuit.
An example system may include: wherein the collateral includes at least one of: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
An example system may include: wherein the valuation circuitry further comprises transaction result processing circuitry configured to interpret result data relating to the collateral transactions and iteratively refine the valuation model in response to the result data.
An example system may include: wherein the valuation circuit further comprises a market value data collection circuit configured to monitor and report market information relating to the value of the collateral.
An example system may include: wherein the market value data collection circuit monitors pricing or financial data of the counteracting collateral in the at least one public market.
An example system may include: wherein a set of canceling collateral used to value the collateral is constructed using a clustering circuit based on attributes of the collateral.
An example system may include: wherein the attributes are selected from: the type of collateral object, the age of the collateral object, the condition of the collateral object, the history of the collateral object, the storage conditions of the collateral object, and the geographic location of the collateral object.
In an embodiment, a method for modifying a smart contract for a loan is provided herein. An example method may include: monitoring and collecting information about at least one entity involved in the loan; and automatically reorganizing the debt associated with the loan based on the monitored and collected information about the at least one entity.
Certain additional aspects of the example methods are described below, any one or more of which may be present in certain embodiments.
An example method may include: determining an occurrence of an event based on a contract for the loan and the monitored and collected information about at least one entity involved in the loan; and automatically reorganizing the debt in response to the occurrence of the event.
An example method may include: terms and conditions of an intelligent contract that specifies at least one of terms and conditions for managing a loan, a loan-related event, or a loan-related activity.
An example method may include: the valuation model is operated to determine the value of the collateral based on the monitored and collected information about at least one entity involved in the loan.
An example method may also include: interpreting outcome data related to the collateral transaction; and iteratively refining the valuation model in response to the result data.
An example method may also include: market information relating to the value of the collateral is monitored and reported.
An example method may also include: pricing or financial data of the counteracting collateral in the at least one public market is monitored.
An example method may also include: a set of canceling collateral for valuing the collateral is constructed using a similarity clustering algorithm based on attributes of the collateral.
An apparatus, may comprise: a data collection circuit configured to monitor and collect information about at least one of a borrower or a mortgage of the loan; and intelligent contract circuitry configured to automatically reorganize debt related to the loan based on the monitored and collected information regarding at least one of the borrower or the mortgage of the loan.
The data collection circuit may be configured to monitor and collect information about mortgages of the loan, and wherein the monitored and collected information includes a condition of the mortgages of the loan.
The apparatus may also include a valuation circuit configured to determine a value of a collateral of the loan based at least in part on a condition of the collateral of the loan and using a valuation model.
The valuation circuitry can also include transaction result processing circuitry configured to interpret result data relating to the collateral transactions and iteratively refine the valuation model in response to the result data.
In an embodiment, a social network monitoring system for verifying the condition of a loan guarantee is provided herein. An example platform, system, or apparatus may include: social network input circuitry configured to interpret a loan guarantee parameter; a social network data collection circuit configured to collect data using a plurality of algorithms for monitoring social network information about entities involved in the loan in response to the loan guarantee parameters; and a collateral validation circuit configured to validate the loan collateral in response to the monitored social network information.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein the loan assurance parameter comprises a financial status of an entity, wherein the entity is an insurer for the loan.
An example system may include: the vouch-for verification circuit is further configured to determine the financial condition based on at least one of the following attributes: a public valuation of an entity, an entity-owned property as indicated by a public record, a valuation of an entity-owned property, a bankruptcy condition of an entity, a redemption-out status of an entity, a contract breach status of an entity, a violation status of an entity, a criminal status of an entity, an export regulation status of an entity, a contraband status of an entity, a duty status of an entity, a tax status of an entity, a credit report of an entity, a credit rating of an entity, a website rating of an entity, a plurality of customer reviews of a product of an entity, a social network rating of an entity, a plurality of credentials of an entity, a plurality of referrals of an entity, a plurality of attestations of an entity, a plurality of behaviors of an entity, a location of an entity, a jurisdiction of an entity, and a geographic location of an entity.
An example system may include: wherein the loan includes at least one of the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
An example system may include: a data collection circuit configured to obtain information about a condition of a collateral of the loan, wherein the collateral includes at least one of: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, collateral items, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property; and wherein the collateral verification circuitry is further configured to verify the collateral of the loan in response to a condition of a collateral of the loan.
An example system may include: wherein the condition of the collateral includes a condition attribute selected from the group consisting of: the quality of the collateral, the status of the title of the collateral, the possession status of the collateral, the lien status of the collateral, new or used status, type, category, description, product feature set, model, brand, manufacturer, status, background, condition, value, storage location, geographic location, age, maintenance history, usage history, accident history, failure history, ownership history, price, assessment, and valuation.
An example system may include: wherein the social network input circuitry is further configured to enable a workflow by which a human user inputs loan assurance parameters to establish a social network data collection and monitoring request.
An example system may include: intelligent contract circuitry configured to automatically take action related to the loan in response to verification of the loan.
An example system may include: wherein the loan-related action is responsive to the loan guarantee not being verified, and wherein the action comprises at least one of: a redemption action, a lien management action, an interest rate adjustment action, a default origination action, a mortgage replacement, a loan hasty, and providing an alert to a secondary entity related to the loan.
An example system may include: a robotic process automation circuit configured to configure a loan assurance parameter based on at least one attribute of the loan based on iterative training on a training data set comprising human user interactions with the social network data collection circuit.
An example system may include: wherein at least one attribute of the loan is available from intelligent contract circuitry that manages the loan.
An example system may include: wherein the training data set further comprises results from a plurality of social network data collection and monitoring requests performed by the social network data collection circuitry.
An example system may include: wherein the robotic process automation circuitry is further configured to determine at least one domain to which the social network data collection circuitry is to be applied.
An example system may include: wherein training comprises training the robotic process automation circuit to configure the plurality of algorithms.
In an embodiment, a social network monitoring method for verifying a condition of a loan guarantee is provided herein. An example method may include: interpreting loan guarantee parameters; collecting data using a plurality of algorithms for monitoring social networking information about entities involved in the loan in response to the loan assurance parameters; and verifying the guarantee of the loan in response to the monitored social networking information.
Certain additional aspects of the example methods are described below, any one or more of which may be present in certain embodiments. An example method may also include: a workflow is enabled through which a human user enters loan assurance parameters to establish a social network data collection and monitoring request.
An example method may also include: actions associated with the loan are automatically taken in response to verification of the loan.
An example method may also include: wherein the action related to the loan is responsive to the loan guarantee not being verified, and wherein the action comprises an act of redemption.
An example method may also include: wherein the loan-related action is responsive to the loan guarantee not being verified, and wherein the action comprises a lien management action.
An example method may also include: wherein the action related to the loan is responsive to the loan guarantee not being verified, and wherein the action comprises an interest rate adjustment action.
An example method may also include: wherein the action related to the loan is responsive to the loan guarantee not being verified, and wherein the action comprises a default origination action.
An example method may also include: wherein the action related to the loan is responsive to the loan guarantee not being verified, and wherein the action comprises a mortgage replacement.
An example method may also include: wherein the action related to the loan is responsive to the loan guarantee not being verified, and wherein the action comprises an incentive to loan.
An example method may also include: wherein the action related to the loan is in response to the loan guarantee not being verified, and wherein the action comprises providing an alert to a secondary entity related to the loan.
An example method may also include: iteratively training a robotic process automation circuit to configure data collection and monitoring actions based on at least one attribute of the loan, wherein the robotic process automation circuit is trained using a plurality of algorithms based on a training data set including at least one of the results from the human user interaction.
An example method may also include: at least one domain to which a plurality of algorithms are to be applied is determined. For example, the algorithm may query multiple domains when determining.
An example apparatus may include: social network input circuitry configured to interpret a loan guarantee parameter; a social network data collection circuit configured to collect data using a plurality of algorithms for monitoring social network information about a guarantor of the loan in response to the loan guaranty parameters; and a collateral validation circuit configured to validate the loan collateral in response to the monitored social network information.
The loan assurance parameter may comprise a financial condition of an insurer for the loan, and wherein the assurance verification circuit is further configured to determine the financial condition of the insurer for the loan based on at least one of the following attributes: a public valuation of an entity, a set of properties owned by the entity as indicated by a public record, a valuation of a set of properties owned by the entity, a bankruptcy condition of the entity, a redemption-out status of the entity, a contract breach status of the entity, a violation status of the entity, a criminal status of the entity, an export regulation status of the entity, a contraband status of the entity, a duty status of the entity, a tax status of the entity, a credit report of the entity, a credit rating of the entity, a website rating of the entity, a set of customer reviews of products of the entity, a social network rating of the entity, a set of credentials of the entity, a set of referrals of the entity, a set of proofs of the entity, a set of behaviors of the entity, a location of the entity, and a geographic location of the entity.
In an embodiment, a monitoring system for verifying the condition of a loan guarantee is provided herein. An example platform, system, or apparatus may include: an internet of things (IoT) data input circuit configured to interpret a loan assurance parameter; an IoT data collection circuit configured to collect data using at least one algorithm for monitoring IoT information collected about an entity involved in a loan in response to a loan assurance parameter; and a warranty verification circuit configured to verify the loan warranty in response to the monitored IoT information.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein the loan assurance parameter comprises a financial status of an entity, wherein the entity is an insurer for the loan.
An example system may include: wherein the monitored IoT information comprises at least one of: a public valuation of an entity, an entity-owned property as indicated by a public record, a valuation of an entity-owned property, a bankruptcy condition of an entity, a redemption-out status of an entity, a contract breach status of an entity, a violation status of an entity, a criminal status of an entity, an export regulation status of an entity, a contraband status of an entity, a duty status of an entity, a tax status of an entity, a credit report of an entity, a credit rating of an entity, a website rating of an entity, a plurality of customer reviews of a product of an entity, a social network rating of an entity, a plurality of credentials of an entity, a plurality of referrals of an entity, a plurality of attestations of an entity, a plurality of behaviors of an entity, a location of an entity, a jurisdiction of an entity, and a geographic location of an entity.
An example system may include: wherein the loan includes at least one of the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
An example system may include: wherein the IoT data collection circuit is further configured to obtain information regarding a condition of a collateral of the loan, wherein the collateral includes at least one of: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, collateral items, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property; and wherein the collateral verification circuitry is further configured to verify the collateral of the loan in response to a condition of a collateral of the loan.
An example system may include: wherein the condition of the collateral includes a condition attribute selected from the group consisting of: the quality of the collateral, the status of the title of the collateral, the state of possession of the collateral, the lien status of the collateral, new or used status, type, category, description, product feature set, model, brand, manufacturer, status, background, condition, value, storage location, geographic location, age, maintenance history, usage history, accident history, failure history, ownership history, price, assessment, and valuation.
An example system may include: wherein the IoT data collection circuit is further configured to enable a workflow by which a human user enters loan assurance parameters to establish the internet of things data collection request.
An example system may include: intelligent contract circuitry configured to automatically take action related to the loan in response to verification of the loan.
An example system may include: wherein the loan-related action is responsive to the loan guarantee not being verified, and wherein the action comprises at least one of: a redemption action, a lien management action, an interest rate adjustment action, a default origination action, a mortgage replacement, a loan hasty, and providing an alert to a secondary entity related to the loan.
An example system may include: a robotic process automation circuit configured to configure a loan assurance parameter based on at least one attribute of a loan based on iterative training on a training data set comprising human user interactions with an IoT data collection circuit.
An example system may include: wherein at least one attribute of the loan is available from intelligent contract circuitry that manages the loan.
An example system may include: wherein the training data set further includes results from a plurality of IoT data collection and monitoring requests performed by the IoT data collection circuit.
An example system may include: wherein the robotic process automation circuit is further configured to determine at least one domain to which the IoT data collection circuit is to be applied.
An example system may include: wherein training comprises training the robotic process automation circuit to configure at least one algorithm.
In an embodiment, a monitoring method for verifying the condition of a loan guarantee is provided herein. An example method may include: interpreting loan guarantee parameters; collecting data using a plurality of algorithms for monitoring internet of things (IoT) information about an entity involved in the loan collected from the entity in response to the loan assurance parameters; and verifying the guarantee of the loan in response to the monitored IoT information.
Certain additional aspects of the example methods are described below, any one or more of which may be present in certain embodiments. An example method may also include: the loan guarantee parameters are configured to obtain financial conditions about the entity, wherein the entity is a guarantor of the loan.
An example method may also include: configuring at least one algorithm to obtain information regarding a condition of a collateral of the loan, wherein the collateral includes at least one of: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, collateral items, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property; and verifying the collateral of the loan to further respond to the condition of the collateral of the loan.
An example method may also include: a workflow is enabled through which a human user enters loan assurance parameters to establish an IoT data collection request.
An example method may also include: actions associated with the loan are automatically taken in response to verification of the loan.
An example method may also include: wherein the action related to the loan is responsive to the loan guarantee not being verified, and wherein the action comprises an act of redemption.
An example method may also include: wherein the loan-related action is responsive to the loan guarantee not being verified, and wherein the action comprises a lien management action.
An example method may also include: wherein the action related to the loan is responsive to the loan guarantee not being verified, and wherein the action comprises an interest rate adjustment action.
An example method may also include: wherein the action related to the loan is responsive to the loan guarantee not being verified, and wherein the action comprises a default origination action.
An example method may also include: wherein the action related to the loan is responsive to the loan guarantee not being verified, and wherein the action comprises a mortgage replacement.
An example method may also include: wherein the action related to the loan is responsive to the loan guarantee not being verified, and wherein the action comprises an incentive to loan.
An example method may also include: wherein the action related to the loan is in response to the loan guarantee not being verified, and wherein the action comprises providing an alert to a secondary entity related to the loan.
An example method may also include: iteratively training a robotic process automation circuit to configure an IoT data collection and monitoring action based on at least one attribute of the loan, wherein the robotic process automation circuit is trained using a plurality of algorithms based on a training dataset that includes at least one of the results from the human user interaction.
An example method may also include: at least one domain to which a plurality of algorithms are to be applied is determined.
An example method may also include: wherein training comprises training the robotic process automation circuit to configure the plurality of algorithms.
An example method may also include: wherein the training data set further includes results from the set of IoT data collection and monitoring requests.
In an embodiment, a robotic process automation system for negotiating loans is provided herein. An example platform, system, or apparatus may include: a data collection circuit configured to collect a training set of interactions from at least one entity related to at least one loan transaction; an automatic loan classification circuit that trains based on an interactive training set to classify at least one loan negotiation action; and a robotic process automation circuit that trains based on the plurality of loan negotiation actions and the training set of the plurality of loan transaction results classified by the automatic loan classification circuit to negotiate terms and conditions of a new loan on behalf of a party to the new loan.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein the data collection circuit further comprises at least one of: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and an interactive crowdsourcing system.
An example system may include: wherein at least one entity is a party to at least one loan transaction.
An example system may include: wherein at least one entity is selected from the following entities: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, and accountants.
An example system may include: wherein the automatic loan classification circuitry comprises one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
An example system may include: wherein the robotic process automation circuit is further trained based on a plurality of interactions of the principal with a plurality of user interfaces involved in a plurality of lending processes.
An example system, may further include: and intelligent contract circuitry configured to automatically configure an intelligent contract for the new loan based on the results of the negotiation.
An example system, may further include: a distributed ledger associated with the new loan, wherein the distributed ledger is configured to record at least one of a result of the negotiation and a negotiation event.
An example system may include: wherein the new loan comprises at least one of the following loan types: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
An example system, may further include: a valuation circuit configured to determine a value of a collateral for the new loan using a valuation model.
An example system may include: wherein the collateral includes at least one of: vehicles, boats, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipalities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
An example system may include: wherein the valuation circuit further comprises a market value data collection circuit configured to monitor and report market information relating to the value of the collateral.
An example system may include: wherein the market value data collection circuit monitors pricing or financial data of the counteracting collateral in the at least one public market.
An example system may include: wherein a set of canceling collateral used to value the collateral is constructed using a clustering circuit based on attributes of the collateral.
An example system may include: wherein the attributes are selected from: the type of collateral object, the age of the collateral object, the condition of the collateral object, the history of the collateral object, the storage conditions of the collateral object, and the geographic location of the collateral object.
An example system may include: wherein the terms and conditions of the new loan include at least one member selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best-line return plan, collateral description, collateral substitutability description, party, insured person, collateral, personal guaranty, lien, term, contract, redemption condition, default condition, and default outcome.
In an embodiment, a robotic process automation method for negotiating loans is provided herein. An example method may include: collecting a training set of interactions from at least one entity associated with at least one loan transaction; training an automatic loan classification circuit based on an interactive training set to classify at least one loan negotiation action; and training the robotic process automation circuit to negotiate terms and conditions of a new loan on behalf of a party to the new loan based on a training set of a plurality of loan negotiation actions and a plurality of loan transaction results classified by the automatic loan classification circuit.
Certain additional aspects of the example methods are described below, any one or more of which may be present in certain embodiments. An example method may also include:
An example method may also include: wherein the robotic process automation circuit is trained based on a plurality of interactions of the principal with a plurality of user interfaces involved in a plurality of lending processes.
An example method may also include: and configuring the intelligent contract of the new loan based on the negotiation result.
An example method may also include: at least one of a result of the negotiation and the negotiation event is recorded in a distributed ledger associated with the new loan.
An example method may also include: a valuation model is used to determine the value of the collateral for the new loan.
An example method may also include: market information relating to the value of the collateral is monitored and reported.
An example method may also include: a set of canceling collateral for valuing the collateral is constructed using a similarity clustering algorithm based on attributes of the collateral.
In an embodiment, a system for adaptive intelligence and robotic process automation capabilities for trading, financial and market support is provided herein.
An example apparatus or system may include: data collection circuitry configured to interpret interactions between entities corresponding to a plurality of entities related to at least one transaction of a first set of loans, wherein the at least one transaction involves a first collect action corresponding to a set of payments of the first set of loans; an artificial intelligence circuit configured to classify a first payment action, wherein the artificial intelligence circuit is trained based on interactions corresponding to a first set of loans; and a robotic process automation circuit that trains based on the interaction and a set of loan receipt results corresponding to the first set of loans to perform a second loan receipt action on behalf of the party for the second loan.
Certain additional aspects of the example systems or apparatus are described below, any one or more of which may be present in certain embodiments.
An example apparatus or system may include: wherein the second loan gathering action is selected from the following actions: initiating a collection process; referral of the loan to an agent for collection; configuring a payment communication; scheduling a payment communication; configuring the content of the checkout communication; configuring a settlement loan offer; terminating the collection action; postponing the collection action; configuring an offer for an alternative payment plan; initiating litigation; initiating redemption stopping; initiating a production-breaking process; initiating a re-owning process; and setting collateral liens.
An example apparatus or system may include: wherein the set of loan payment results is selected from: a response to a collect contact event; loan repayment; a default by the loan borrower; the loan borrower breaks the labor; collecting litigation results; financial benefits of a set of cash register actions; return on investment with respect to collection; and a reputation measure of the party involved in the collection.
An example apparatus or system may include: wherein the data collection circuit comprises at least one of: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and an interactive crowdsourcing system.
An example apparatus or system may include: where the entity is a group of parties to a loan transaction.
An example apparatus or system may include: wherein the group of parties is selected from the following: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, and accountants.
An example apparatus or system may include: wherein the artificial intelligence circuit comprises at least one of: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
An example apparatus or system may include: wherein the robotic process automation circuit is trained based on a set of interactions of the parties, the system further comprising at least one user interface for interacting with at least one of the parties involved in a set of lending processes.
An example apparatus or system may include: wherein after the negotiation of the collection process is completed, the intelligent contract for the loan is automatically configured by a set of intelligent contract circuits based on the result of the negotiation.
An example apparatus or system may include: wherein the robotic process automation circuit is configured to record the set of loan receipt results and the first receipt action in a distributed ledger associated with the first set of loans.
An example apparatus or system may include: wherein the second loan comprises at least one loan selected from the group of loans consisting of: automobile loans, inventory loans, capital equipment loans, performance bonds, capital improvement loans, construction loans, account payable collateral loans, invoice financing arrangements, warranty arrangements, payday loans, refund prospective loans, school-assistance loans, banking loans, property loans, house loans, risk debt loans, intellectual property loans, contractual obligation loans, liquidity loans, small business loans, agricultural loans, municipal bonds, and subsidy loans.
An example apparatus or system may include: wherein the artificial intelligence circuit comprises at least one of: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
An example apparatus or system may include: wherein each of the entities comprises at least one of the following entities: a borrower, a insurer, equipment associated with a first set of loans, goods associated with a first set of loans, systems associated with a first set of loans, fixtures associated with a first set of loans, buildings, storage facilities, and mortgages.
An example apparatus or system may include: wherein the robotic process automation circuit is configured to record the second loan receipt action in a distributed ledger associated with the second loan.
An example apparatus or system may include: wherein the first loan checkout action is selected from the following actions: initiating a collection process; referral of the loan to an agent for collection; configuring a checkout communication; scheduling a payment communication; configuring the content of the checkout communication; configuring a settlement loan offer; terminating the collection action; a deferred collection action; configuring an offer for an alternative payment plan; initiating litigation; initiating redemption cessation; initiating a bankruptcy process; initiating a re-owning process; and setting collateral liens.
In an embodiment, a method for adaptive intelligence and robotic process automation capabilities for trading, financial and market support is provided herein. An example method may include: interpreting a plurality of interactions between entities corresponding to a plurality of entities related to at least one transaction of a first set of loans, wherein the at least one transaction involves a first collect action corresponding to a set of payments of the first set of loans; classifying the first collect action based at least in part on the plurality of interactions; and specifying a second loan receipt action on behalf of the party for the second loan based at least in part on the plurality of interactions and a set of loan receipt results corresponding to the first set of loans.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example method may also include: wherein the second loan checkout action comprises at least one of: initiating a collection process; configuring a checkout communication; or schedule a collection action.
An example method may also include: wherein the second loan checkout action comprises at least one of: referral of the loan to an agent for collection; configuring an offer to settle the second loan; or configure the content of the checkout communication.
An example method may also include: wherein the second loan checkout action comprises at least one of: terminating the collection action; a deferred collection action; or to configure offers for alternative payment plans.
An example method may also include: wherein the second loan checkout action includes at least one of: initiating litigation; initiating redemption cessation; or initiate a bankruptcy process.
An example method may also include: wherein the second loan checkout action comprises at least one of: initiating a re-owning process; or set a mortgage lien for the second loan.
An example method may also include: wherein the set of loan payment results is selected from: a response to a collect contact event; loan repayment; a default by the loan borrower; the loan borrower is bankruptcy; collecting litigation results; financial benefits of a set of cash register actions; return on investment with respect to collection; and a reputation measure of the party involved in the collection.
An example method may also include: wherein after the negotiation of the collection process is completed, the intelligent contract for the loan is automatically configured by a set of intelligent contract services based on the result of the negotiation.
An example method may also include: at least one of the set of loan receipt results is recorded in a distributed ledger associated with the first set of loans.
An example method may also include: providing a user interface to the party on the second loan; and notifying the party to the second loan of the specified second payment action.
An example method may also include: the specified second collect action is initiated in response to the party to the second loan entering into the user interface.
An example method may also include: the second loan checkout action is recorded in a distributed ledger associated with the second loan.
An example method may also include: wherein the first loan gathering action comprises at least one of: initiating a collection process; configuring a checkout communication; or scheduling a collection action; referral of the loan to an agent for collection; configuring an offer to settle the second loan; or configuring the content of the checkout communication.
An example method may also include: wherein the first loan gathering action comprises at least one of: terminating the collection action; a deferred collection action; or to configure offers for alternative payment plans.
An example method may also include: wherein the first loan checkout action comprises at least one of: initiating litigation; initiating redemption stopping; or initiating a bankruptcy process; initiating a re-owning process; or set a mortgage lien for the second loan.
In an embodiment, a system for adaptive intelligence and robotic process automation capabilities for trading, financial and market support is provided herein.
In an embodiment, a system for adaptive intelligence and robotic process automation capabilities for trading, financial and market support is provided herein.
An example apparatus or system may include: data collection circuitry configured to collect a training set of loan interactions between entities, wherein the training set of loan interactions includes a set of loan refinancing activities and a set of loan refinancing results; an artificial intelligence circuit configured to classify the set of loan refinancing activities, wherein the artificial intelligence circuit is trained based on a set of loan interactions; and a robotic process automation circuit configured to perform a second loan refinancing activity on behalf of a principal of a second loan, wherein the robotic process automation circuit is trained based on the set of loan refinancing activities and the set of loan refinancing results.
Certain additional aspects of the example systems or apparatus are described below, any one or more of which may be present in certain embodiments.
An example apparatus or system may include: wherein at least one loan refinancing campaign of a group of loan refinancing campaigns is selected from the group consisting of: initiating a re-financing offer; initiating a re-financing request; configuring a re-financing rate; configuring a re-financing payment plan; configuring a re-financing balance; allocating a refinancing collateral; managing the use of re-financing revenue; removing or setting liens associated with the re-financing; verifying the re-financing property right; managing the inspection process; filling an application program; negotiating re-financing terms and conditions; or end the re-financing.
An example apparatus or system may include: wherein the data collection circuit comprises at least one of: an internet of things system for monitoring an entity; a set of cameras for monitoring the entity; a set of software services for obtaining information related to an entity from an open information website; a set of mobile devices for reporting information related to an entity; a set of wearable devices for wearing by a human entity; a set of user interfaces through which entities provide information about the entities; and a set of crowdsourcing services for requesting and reporting information related to the entity.
An example apparatus or system may include: at least one of the entities is a party to at least one loan refinancing activity of the set of loan refinancing activities.
An example apparatus or system may include: wherein the principal is at least one principal selected from the group consisting of: primary borrower, secondary borrower, lending bank, corporate borrower, government borrower, bank borrower, secured borrower, bond issuer, bond purchaser, unsecured lender, secured supplier, borrower, debtor, insured carrier, inspector, evaluator, auditor, valuation professional, government officer, or accountant.
An example apparatus or system may include: wherein the artificial intelligence circuit comprises at least one of: a machine learning system, a model-based system, a rule-based system, a deep learning system, a hybrid system, a neural network, a convolutional neural network, a feed-forward neural network, a feedback neural network, a self-organizing map, a fuzzy logic system, a random walk system, a random forest system, a probabilistic system, a bayesian system, or a simulation system.
An example apparatus or system may further include: an interface circuit configured to receive an interaction from at least one of the entities, and wherein the robotic process automation circuit is further trained based on the interaction.
An example apparatus or system may include: intelligent contract circuitry configured to determine that the second loan refinancing campaign is complete and modify the intelligent refinancing contract based on results of the second loan refinancing campaign.
An example apparatus or system may include: a distributed ledger circuit configured to determine an event associated with the second loan refinancing activity and record the event associated with the second loan refinancing activity in a distributed ledger associated with the second loan.
An example apparatus or system may include: wherein the second loan comprises at least one loan selected from the group consisting of: an automobile loan, an inventory loan, a capital equipment loan, a performance bond, a capital improvement loan, a construction loan, an account receivable warranty loan, an invoice financing arrangement, a warranty arrangement, a payday loan, a refund prospective loan, a school-aid loan, a banking loan, a property loan, a house loan, a risk debt loan, an intellectual property loan, a contractual obligation loan, a floating fund loan, a small business loan, an agricultural loan, a municipal bond, or a subsidy loan.
An example apparatus or system may include: wherein the artificial intelligence circuit comprises at least one of: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
In an embodiment, a method for adaptive intelligence and robotic process automation capabilities for trading, financial and market support is provided herein. An example method may include: collecting a training set of loan interactions between entities, wherein the training set of loan interactions comprises a set of loan refinancing activities and a set of loan refinancing results; classifying the set of loan refinancing activities based at least in part on the training set of loan interactions; specifying a second loan refinancing activity on behalf of the party for the second loan based at least in part on the set of loan refinancing activities and the set of loan refinancing results.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example method may also include:
An example method may also include: wherein at least one loan refinancing campaign of the set of loan refinancing campaigns comprises: initiating a re-financing offer; initiating a re-financing request; configuring a re-financing rate; configuring a re-financing payment plan; configuring a re-financing balance; allocating a refinancing collateral; managing the use of re-financing revenue; removing or setting liens associated with the re-financing; verifying the re-financing property right; managing the inspection process; filling the application program; negotiate re-financing terms and conditions, etc.
An example method may also include: at least one of the entities is a party to at least one loan refinancing campaign of the set of loan refinancing campaigns. An interaction from at least one of the entities is received, and wherein the classification is further trained based on the interaction.
An example method may also include: wherein the party is at least one party selected from the group consisting of: primary borrower, secondary borrower, lending bank, corporate borrower, government borrower, bank borrower, secured borrower, bond issuer, bond purchaser, unsecured lender, secured supplier, borrower, debtor, insurer, inspector, auditor, valuation professional, government officer, or accountant.
An example method may also include: determining that the second loan refinancing campaign is complete; and modifying the intelligent refinancing contract based on the results of the second loan refinancing campaign.
An example method may also include: one of the modified intelligent re-financing contract or a reference to the modified intelligent re-financing contract is recorded in a distributed ledger associated with the second loan.
An example method may also include: determining an event associated with the second loan refinancing activity; and recording the event associated with the second loan refinancing campaign in a distributed ledger associated with the second loan.
In an embodiment, a system for adaptive intelligence and robotic process automation capabilities for trading, financial and market support is provided herein.
In an embodiment, a system for adaptive intelligence and robotic process automation capabilities for trading, financial and market support is provided herein.
An example apparatus or system may include: data collection circuitry configured to collect a training set of loan interactions between entities. The training set of loan interactions includes a set of loan merger transactions. The apparatus or system may further comprise: an artificial intelligence circuit configured to classify a set of loans as merging candidate loans, wherein the artificial intelligence circuit is trained based on an interactive training set; a robotic process automation circuit configured to manage a consolidation of at least a subset of the set of loans on behalf of a consolidated party, wherein the robotic process automation circuit is trained based on the set of loan consolidated transactions.
Certain additional aspects of the example systems or apparatus are described below, any one or more of which may be present in certain embodiments.
An example apparatus or system may include: wherein the data collection circuit comprises at least one of: the system of Internet of things is used for monitoring the entity; a set of cameras for monitoring the entity; a set of software services for obtaining information related to an entity from an open information website; a set of mobile devices for reporting information related to an entity; a set of wearable devices for wearing by a human entity; a set of user interfaces through which entities provide information about the entities; and a set of crowdsourcing services for requesting and reporting information related to the entity.
An example apparatus or system may include: wherein a set of loans classified as candidate loans to be merged is determined based on a model of attributes of the processing entity; and wherein the at least one attribute is selected from the group consisting of: the identity of the party, the interest rate, the payment balance, the payment terms, the payment plan, the loan type, the collateral type, the financial status of the party, the payment status, the status of the collateral, or the value of the collateral.
An example apparatus or system may include: wherein at least one management consolidation comprises managing items selected from the group consisting of: identifying loans in a set of candidate loans; compiling a combined offer; compiling a merging plan; compiling content conveying the consolidated offer; arranging for a combined offer; communicating a consolidated offer; negotiating a merging offer modification; compiling a merging protocol; executing a merge protocol; modifying the collateral for a set of loans; processing a merged application workflow; managing and checking; managing and evaluating; setting interest rate; a deferred payment requirement; setting a payment plan; or to achieve a merge agreement.
An example apparatus or system may include: wherein at least one of the entities is a party to at least one of the set of loan merge transactions.
An example apparatus or system may include: wherein the principal is at least one principal selected from the group consisting of: primary borrower, secondary borrower, lending bank, corporate borrower, government borrower, bank borrower, secured borrower, bond issuer, bond purchaser, unsecured lender, secured supplier, borrower, debtor, insured carrier, inspector, evaluator, auditor, valuation professional, government officer, or accountant.
An example apparatus or system may include: wherein the artificial intelligence circuit comprises at least one of: a machine learning system, a model-based system, a rule-based system, a deep learning system, a hybrid system, a neural network, a convolutional neural network, a feed-forward neural network, a feedback neural network, a self-organizing map, a fuzzy logic system, a random walk system, a random forest system, a probabilistic system, a Bayesian system, or a simulation system.
An example apparatus or system may further include: an interface circuit configured to receive an interaction from at least one of the entities, and wherein the robotic process automation circuit is further trained based on the interaction.
An example apparatus or system may further include: intelligent contract circuitry configured to determine that a consolidated negotiation of at least one loan of the subset of the set of loans is complete, and modify an intelligent consolidated contract based on a result of the negotiation.
An example apparatus or system may further include: a distributed ledger circuit configured to determine at least one of results and negotiation events associated with a merger of at least a subset of the set of loans; and recording at least one of the results and negotiation events associated with the merge in a distributed ledger associated with a subset of the set of loans.
An example apparatus or system may include: wherein at least one loan of the subset of the set of loans is selected from the group consisting of: an automobile loan, an inventory loan, a capital equipment loan, a performance bond, a capital improvement loan, a construction loan, an account receivable warranty loan, an invoice financing arrangement, a warranty arrangement, a payday loan, a refund prospective loan, a school-aid loan, a banking loan, a property loan, a house loan, a risk debt loan, an intellectual property loan, a contractual obligation loan, a floating fund loan, a small business loan, an agricultural loan, a municipal bond, or a subsidy loan.
In an embodiment, a method for adaptive intelligence and robotic process automation capabilities for trading, financial and market support is provided herein. An example method may include: collecting a training set of loan interactions between entities, wherein the training set of loan interactions comprises a set of loan merger transactions; classifying a set of loans as merging candidate loans based at least in part on a training set of the loan interactions; and managing the merger of at least a subset of the set of loans on behalf of the merged party based at least in part on the set of loan merge transactions.
Certain additional aspects of the example systems will be described below, any one or more of which may be present in certain embodiments. An example method may also include: classifying the set of loans as a model of candidate loans to be merged based on attributes of the processing entity; and wherein the at least one attribute is selected from the group consisting of: the identity of the party, the interest rate, the payment balance, the payment terms, the payment plan, the loan type, the collateral type, the financial status of the party, the payment status, the status of the collateral, or the value of the collateral.
An example method may also include: at least one of the entities is a party to at least one of the set of loan merge transactions.
An example method may also include: wherein at least one management consolidation comprises managing items selected from the group consisting of: identifying loans in a set of candidate loans; compiling a combined offer; compiling a merging plan; compiling content conveying the consolidated offer; arranging for a combined offer; communicating a consolidated offer; negotiating a merge offer modification; compiling a merging protocol; executing a merge protocol; modifying the collateral for a set of loans; processing a merged application workflow; managing and checking; management evaluation; setting interest rate; a deferred payment requirement; setting a payment plan; or to achieve a merge agreement.
An example method may also include: at least one of the entities is a party to at least one of the set of loan merge transactions.
An example method may also include: wherein the principal is at least one principal selected from the group consisting of: primary borrower, secondary borrower, lending bank, corporate borrower, government borrower, bank borrower, secured borrower, bond issuer, bond purchaser, unsecured lender, secured supplier, borrower, debtor, insured carrier, inspector, evaluator, auditor, valuation professional, government officer, or accountant.
An example method may also include: determining that a consolidated negotiation for at least one loan in the subset of the set of loans is complete; and modifying the intelligent merged contract based on the negotiation result.
An example method may also include: determining at least one of a result and a negotiation event associated with a merger of at least a subset of the set of loans; and recording at least one of the results and negotiation events associated with the merge in a distributed ledger associated with a subset of the set of loans.
In an embodiment, a system for adaptive intelligence and robotic process automation capabilities for trading, financial and market support is provided herein.
An example apparatus or system may include: data collection circuitry configured to collect information about entities involved in a set of warranty loans and a training set of interactions between entities for a set of warranty loan transactions. The apparatus or system may further comprise: an artificial intelligence circuit configured to classify entities involved in the set of warranty loans, wherein the artificial intelligence circuit is trained based on the training set of interactions; and a robotic process automation circuit configured to manage the warranty loan, wherein the robotic process automation circuit is trained based on the set of warranty loan interactions.
Certain additional aspects of the example systems or apparatus are described below, any one or more of which may be present in certain embodiments.
An example apparatus or system may include: wherein the data collection circuit comprises at least one of: the system of Internet of things is used for monitoring the entity; a set of cameras for monitoring the entity; a set of software services for obtaining information related to an entity from an open information website; a set of mobile devices for reporting information related to an entity; a set of wearable devices for wearing by a human entity; a set of user interfaces through which entities provide information about the entities; and a set of crowdsourcing services for requesting and reporting information related to the entity.
An example apparatus or system may include: wherein the artificial intelligence circuit is further configured to use a model that processes attributes of entities involved in the set of warranty loans; and wherein the at least one attribute is selected from the group consisting of: assets for warranty, identity of the party, interest rate, payment balance, payment terms, payment plan, loan type, collateral type, financial status of the party, payment status, collateral status, or collateral value.
An example apparatus or system may include: wherein the at least one administrative warranty loan comprises managing items selected from the group consisting of: managing at least one of a set of warranty assets; identifying a warranty loan in a set of candidate loans; compiling a warranty offer; compiling a warranty plan; compiling content conveying warranty offers; arranging a warranty offer; communicating a warranty offer; negotiating a warranty offer modification; compiling a warranty protocol; executing a warranty protocol; modifying a set of mortgages of a warranty loan; processing a set of receivables transfers; processing a warranty application workflow; managing and checking; managing an evaluation of a set of assets to be warranted; setting interest rate; a deferred payment requirement; setting a payment plan; or to reach a warranty agreement.
An example apparatus or system may include: wherein the assets for the warranty comprise a set of accounts receivable.
An example apparatus or system may include: wherein the at least one administrative warranty loan comprises managing items selected from the group consisting of: managing at least one of a set of warranty assets; identifying a warranty loan in a set of candidate loans; compiling a warranty offer; compiling a warranty plan; compiling content conveying warranty offers; arranging a warranty offer; communicating a warranty offer; negotiating a warranty offer modification; compiling a warranty protocol; executing a warranty protocol; modifying a set of mortgages of a warranty loan; processing a set of receivables transfers; processing a warranty application workflow; managing and checking; managing an evaluation of a set of assets to be warranted; setting interest rate; a deferred payment requirement; setting a payment plan; or to achieve warranty agreements.
An example apparatus or system may include: at least one of the entities is a party to at least one of the set of warranty loan transactions.
An example apparatus or system may include: wherein the principal is at least one principal selected from the following: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, and accountants.
An example apparatus or system may include: wherein the artificial intelligence circuit comprises at least one of: a machine learning system, a model-based system, a rule-based system, a deep learning system, a hybrid system, a neural network, a convolutional neural network, a feed-forward neural network, a feedback neural network, a self-organizing map, a fuzzy logic system, a random walk system, a random forest system, a probabilistic system, a bayesian system, or a simulation system.
An example apparatus or system may further include: an interface circuit configured to receive an interaction from at least one of the entities, and wherein the robotic process automation circuit is further trained based on the interaction.
An example apparatus or system may further include: and intelligent contract circuitry configured to determine that the warranty loan negotiation is complete and modify the intelligent warranty loan contract based on the result of the negotiation.
An example apparatus or system may further include: a distributed ledger circuit configured to determine at least one of a result associated with a warranty loan negotiation and a negotiation event; and recording at least one of the results and negotiation events associated with the warranty loan in a distributed ledger associated with the warranty loan.
In an embodiment, a method for adaptive intelligence and robotic process automation capabilities for trading, financial and market support is provided herein. An example method may include: collecting information about entities involved in a set of warranty loans, and a training set of interactions between entities transacting the set of warranty loans; classifying entities involved in the set of cover loans based at least in part on the training set of interactions; and managing the warranty loan based at least in part on the set of warranty loan interactions.
Certain additional aspects of the example systems will be described below, any one or more of which may be present in certain embodiments. An example method may also include: wherein the at least one administrative warranty loan comprises managing items selected from the group consisting of: managing at least one of a set of warranty assets; identifying a warranty loan in a set of candidate loans; compiling a warranty offer; compiling a warranty plan; compiling content conveying warranty offers; arranging a warranty offer; communicating a warranty offer; negotiating a warranty offer modification; compiling a warranty protocol; executing a warranty protocol; modifying a set of mortgages of a warranty loan; processing a set of receivables transfers; processing a warranty application workflow; managing and checking; managing an evaluation of a set of assets to be warranted; setting interest rate; a deferred payment requirement; setting a payment plan; or to achieve warranty agreements.
An example method may also include: wherein at least one of the entities is a party to at least one of the set of financial loan transactions.
An example method may include: wherein the principal is at least one principal selected from the group consisting of: primary borrower, secondary borrower, lending bank, corporate borrower, government borrower, bank borrower, secured borrower, bond issuer, bond purchaser, unsecured lender, secured supplier, borrower, debtor, insured carrier, inspector, evaluator, auditor, valuation professional, government officer, or accountant.
An example method may also include: determining that the insurance loan negotiation is completed; and modifying the intelligent insurance policy based on the negotiation result.
An example method may also include: determining at least one of a result associated with a warranty loan negotiation and a negotiation event; and recording at least one of the results and negotiation events associated with the warranty loan in a distributed ledger associated with the warranty loan.
In an embodiment, a system for adaptive intelligence and robotic process automation capabilities for trading, financial and market support is provided herein.
An example apparatus or system may include: a data collection circuit configured to collect information about entities involved in a set of mortgage activities and a training set of interactions between entities for the set of mortgage transactions. The apparatus or system may further comprise: an artificial intelligence circuit configured to classify entities involved in the set of mortgage activities, wherein the artificial intelligence circuit is trained based on the training set of interactions; and a robotic process automation circuit configured to broker the mortgage, wherein the robotic process automation circuit is trained based on at least one of the set of mortgage activities and the interactive training set.
Certain additional aspects of example systems or apparatus will be described below, any one or more of which may be present in certain embodiments. An example apparatus or system may include: wherein at least one of the set of mortgage activities and the set of mortgage transactions includes an activity selected from the group consisting of: a marketing campaign; identifying a set of potential borrowers; identifying property; identifying a collateral; ensuring that the borrower obtains the qualification; searching for property rights; verifying the property right; evaluating the property; checking property; evaluating the property; verifying income; performing a demographic analysis on the borrower; identifying a patron; determining an available interest rate; determining available payment terms and conditions; analyzing the existing mortgage; performing comparative analysis on the existing mortgage terms and the new mortgage terms; completing the application workflow; filling in an application field; compiling a mortgage protocol; completing the collateral protocol attached table; negotiating mortgage terms and conditions with the patron; negotiating mortgage terms and conditions with the borrower; transferring property rights; setting a lien right; or to achieve a mortgage agreement.
An example apparatus or system may include: wherein the data collection circuit comprises at least one of: the system of Internet of things is used for monitoring the entity; a set of cameras for monitoring the entity; a set of software services for obtaining information related to an entity from an open information website; a set of mobile devices for reporting information related to an entity; a set of wearable devices for wearing by a human entity; a set of user interfaces through which entities provide information about the entities; and a set of crowdsourcing services for requesting and reporting information related to the entity.
An example apparatus or system may include: wherein the artificial intelligence circuit is further configured to use a model that processes attributes of entities involved in the set of mortgage activities; and wherein the at least one attribute is selected from the group consisting of: mortgage property, an asset for mortgage, the identity of a party, interest rate, payment balance, payment terms, payment plan, type of mortgage, type of property, financial condition of a party, payment status, condition of property or value of a property.
An example apparatus or system may include: wherein the proxy mortgage includes at least one activity selected from the group consisting of: managing at least one of the mortgage assets; identifying candidate mortgages according to the current status of a group of borrowers; compiling a mortgage offer; compiling content conveying the mortgage offer; arranging a mortgage offer; communicating a mortgage offer; negotiating a mortgage offer modification; compiling a mortgage protocol; executing a mortgage protocol; modifying a set of mortgages of a mortgage loan; processing the lien transfer; processing an application workflow; managing and checking; managing an evaluation of a set of assets to be collated; setting interest rate; a deferred payment requirement; setting a payment plan; or to achieve a mortgage agreement.
An example apparatus or system may include: wherein at least one of the entities is a party to at least one mortgage transaction in the set of mortgage transactions.
An example apparatus or system may include: wherein the principal is at least one principal selected from the following: primary borrowers, secondary borrowers, lending banks, corporate borrowers, government borrowers, bank borrowers, secured borrowers, bond issuers, bond purchasers, unsecured lenders, secured providers, borrowers, debtors, insurers, inspectors, evaluators, auditors, valuation professionals, government officers, and accountants.
An example apparatus or system may include: wherein the artificial intelligence circuit comprises at least one of: a machine learning system, a model-based system, a rule-based system, a deep learning system, a hybrid system, a neural network, a convolutional neural network, a feed-forward neural network, a feedback neural network, a self-organizing map, a fuzzy logic system, a random walk system, a random forest system, a probabilistic system, a bayesian system, or a simulation system.
An example apparatus or system may further include: an interface circuit configured to receive an interaction from at least one of the entities, and wherein the robotic process automation circuit is further trained based on the interaction.
An example apparatus or system may further include: intelligent contract circuitry configured to determine that a mortgage loan negotiation is complete; and modifying the intelligent insurance policy based on the result of the negotiation.
An example apparatus or system may further include: a distributed ledger circuit configured to determine at least one of a result associated with a mortgage negotiation and a negotiation event; and recording at least one of the results and negotiation events associated with the mortgage in a distributed ledger associated with the mortgage.
In an embodiment, a method for adaptive intelligence and robotic process automation capabilities for trading, financial and market support is provided herein. An example method may include: collecting information about a set of entities involved in a mortgage loan activity, and a training set of interactions between a set of entities transacting the mortgage loan; classifying entities involved in the set of mortgage activities based at least in part on the training set of interactions; and brokering the mortgage based at least in part on at least one of the set of mortgage activities and the interactive training set.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example method may also include: classifying the entities involved in the set of mortgage activities based on a model that processes attributes of the entities involved in the set of mortgage activities; and wherein the at least one attribute is selected from the group consisting of: mortgage property, assets for mortgage, identity of a party, interest rate, payment balance, payment terms, payment plan, type of mortgage, type of property, financial condition of a party, payment status, condition of property or and value of property.
An example method may also include: wherein the at least one proxy mortgage includes an activity selected from the group consisting of: managing at least one of the mortgage assets; identifying candidate mortgages according to the current status of a group of borrowers; compiling a mortgage offer; compiling content conveying a mortgage offer; arranging a mortgage offer; communicating a mortgage offer; negotiating a mortgage offer modification; compiling a mortgage protocol; executing a mortgage protocol; modifying a set of mortgages of a mortgage loan; processing the lien transfer; processing an application workflow; managing and checking; managing an evaluation of a set of assets to be mortgage; setting interest rate; a deferred payment requirement; setting a payment plan; or to achieve a mortgage agreement.
An example method may include: wherein at least one of the entities is a party to at least one mortgage transaction in the set of mortgage transactions.
An example method may include: wherein the principal is at least one principal selected from the group consisting of: primary borrower, secondary borrower, lending bank, corporate borrower, government borrower, bank borrower, secured borrower, bond issuer, bond purchaser, unsecured lender, secured supplier, borrower, debtor, insured carrier, inspector, evaluator, auditor, valuation professional, government officer, or accountant.
An example method may also include: determining that the mortgage loan negotiation is complete; and modifying the intelligent insurance policy based on the negotiation result.
An example method may also include: determining at least one of a result associated with the mortgage negotiation and a negotiation event; and recording at least one of the results and negotiation events associated with the mortgage in a distributed ledger associated with the mortgage.
In an embodiment, a system for adaptive intelligence and robotic process automation capabilities for trading, financial and market support is provided herein.
An example system: the method can comprise the following steps: data collection circuitry configured to collect information about entities involved in a set of liability transactions, a training data set of outcomes related to the entities, and a training set of liability management activities. The system may further comprise: a condition classification circuit configured to classify a condition of at least one of the entities, wherein the condition classification circuit comprises a model and a set of artificial intelligence circuits, and wherein the model is trained using a training data set of results associated with the entities; and an automatic debt management circuit configured to manage debt related actions, wherein the automatic debt management circuit is trained based on the training set of debt management activities.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein the data collection circuit comprises at least one system selected from the group consisting of: the system comprises an internet of things device, a set of environmental condition sensors, a set of crowdsourcing services, a set of social network analysis services or a set of network domain query algorithms.
An example system may include: wherein at least one debt transaction of the set of debt transactions is selected from the group consisting of: an automobile loan, an inventory loan, a capital equipment loan, a performance bond, a capital improvement loan, a construction loan, an account receivable warranty loan, an invoice financing arrangement, a warranty arrangement, a payday loan, a refund prospective loan, a school-aid loan, a banking loan, a property loan, a house loan, a risk debt loan, an intellectual property loan, a contractual obligation loan, a floating fund loan, a small business loan, an agricultural loan, a municipal bond, or a subsidy loan.
An example system may include: wherein the entities involved in the set of debt transactions include at least one of a set of parties and a set of assets.
An example system may include: wherein at least one asset of the set of assets comprises an asset selected from the group consisting of: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, or personal property.
An example system, may further include: a set of sensors disposed on at least one asset of the set of assets, on a container of at least one asset of the set of assets, and on a packaging of at least one asset of the set of assets, wherein the set of sensors is to associate sensor information sensed by the set of sensors with a unique identifier of at least one asset of the set of assets; and a set of blockchain circuitry configured to receive information from the data collection circuitry and the set of sensors and store the information in the blockchain, wherein the principal of the debt transaction involving at least one asset of the set of assets is provided access to the blockchain through the secure access control interface circuitry.
An example system may include: wherein at least one sensor of the set of sensors is selected from the group consisting of: image, temperature, pressure, humidity, velocity, acceleration, rotation, torque, weight, chemical, magnetic, electric or position sensors.
An example system may include: an automated agent circuit configured to process events related to at least one of value, status, and ownership of at least one asset in the set of assets, and further configured to take a set of actions related to a debt transaction involving the asset.
An example system, may further include: wherein at least one action of the set of actions is selected from the group consisting of: an offer debt transaction; underwriting debt transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notification that the providing is required; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; a joint debt; or to consolidate debts.
An example system may also include: wherein at least one artificial intelligence circuit of the set of artificial intelligence circuits comprises at least one system selected from the group consisting of: a machine learning system, a model-based system, a rule-based system, a deep learning system, a hybrid system, a neural network, a convolutional neural network, a feed-forward neural network, a feedback neural network, a self-organizing map, a fuzzy logic system, a random walk system, a random forest system, a probabilistic system, a bayesian system, or a simulation system.
An example system may also include: an interface circuit configured to receive an interaction from at least one of the entities, and wherein the automatic liability management circuit is further trained based on the interaction.
An example system, may further include: wherein at least one debt management activity in the training set of debt management activities comprises an activity selected from the group consisting of: an offer debt transaction; underwriting debt transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notification requiring provisioning; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; a joint debt; or to consolidate debts.
An example system may also include: market value data collection circuitry configured to monitor and report market information related to a value of at least one asset of a set of assets.
An example system may also include: wherein at least one asset of the set of assets is selected from the group consisting of: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, or personal property.
An example system, may further include: wherein the market value data collection circuitry is further configured to monitor at least one of pricing and financial data for items in the at least one public market that are similar to at least one asset in the set of assets.
An example system, may further include: wherein a set of similar items for valuing at least one asset in the set of assets is constructed using a similarity clustering algorithm based on attributes of the assets.
An example system, may further include: wherein at least one of the asset attributes is selected from the group consisting of: asset class, asset age, asset condition, asset history, asset storage, or geographic location of the asset.
An example system, may further include: intelligent contract circuitry configured to manage intelligent contracts for debt transactions.
An example system, may further include: the intelligent contract circuit is further configured to establish a set of terms and conditions for the debt transaction.
An example system, may further include: wherein at least one of the set of terms and conditions of the debt transaction is selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, last minute best effort plan, collateral description, collateral substitutability description, party, insured person, guarantor, collateral, personal guaranty, lien, term, contract, redemption condition, default condition, or result of default.
In an embodiment, a method for adaptive intelligence and robotic process automation capabilities for trading, financial and market support is provided herein. An example method may include: collecting information about entities involved in a set of debt transactions, a training data set of results related to the entities, and a training set of debt management activities; classifying a condition of at least one of the entities based at least in part on a training dataset of results related to the entities; and managing an action related to the debt based at least in part on the training set of debt management activities.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example method may also include: wherein the entities involved in the set of debt transactions include a set of parties and a set of assets.
An example method may also include: receiving information from a set of sensors disposed on at least one asset, wherein the set of sensors are to associate sensor information sensed by the set of sensors with a unique identifier of at least one asset in the set of assets, and wherein the set of sensors are disposed on at least one asset in the set of assets, on a container of at least one asset in the set of assets, and on a package of at least one asset in the set of assets; and storing the information in the blockchain, wherein the principal of the debt transaction involving at least one asset of the set of assets is provided access to the blockchain through the secure access control interface.
An example method may include: processing an event related to at least one of a value, a status, and an ownership of at least one asset in the set of assets; and processing a set of actions related to the debt transaction to which the asset relates.
An example method may include: an interaction from at least one of the entities is received.
An example method may also include: market information relating to the value of at least one asset in a set of assets is monitored and reported.
An example method may also include: at least one pricing and financial data for items in at least one public market that are similar to at least one asset in the set of assets is monitored.
An example method may also include: a set of similar items for valuing at least one asset in the set of assets is constructed using a similarity clustering algorithm based on attributes of the assets.
An example method may also include: an intelligent contract for managing debt transactions.
An example method may also include: a set of terms and conditions of a smart contract for a debt transaction is established.
In an embodiment, a system for adaptive intelligence and robotic process automation capabilities for trading, financial and market support is provided herein.
An example system may include: a crowd-sourced data collection circuit configured to collect a training data set of information about entities involved in a set of bond transactions and results related to the entities. The system may further comprise: a situation classification circuit configured to classify a situation of a group of publishers using a model and information from the crowdsourcing data collection circuit, wherein the model is trained using a training data set of results associated with the group of publishers.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein at least one of the entities is selected from the group consisting of: a set of entities includes the following entities: a set of publishers, a set of bonds, a set of parties, or a set of assets.
An example system may include: wherein at least one issuer of the set of issuers is selected from the group consisting of: municipalities, companies, contractors, government entities, non-government entities or non-profit entities.
An example system may include: wherein at least one of the set of bonds is selected from the group consisting of: municipal bonds, government bonds, treasury bonds, asset security bonds, or corporate bonds.
An example system may include: wherein the conditions classified by the condition classification circuit are selected from the group consisting of: a breach condition, a redemption-out condition, a condition indicative of a breach of a contract, a financial risk condition, a behavioral risk condition, a policy risk condition, a financial health condition, a physical defect condition, a physical health condition, an entity risk condition, or an entity health condition.
An example system may include: wherein the crowdsourcing data collection circuit is structured to support a user interface through which a user can configure a crowdsourcing request for information related to a condition about the group of publishers.
An example system, may further include: a configurable data collection and monitoring circuit configured to monitor at least one publisher of the set of publishers, wherein the configurable data collection and monitoring circuit includes a system selected from the group consisting of: the system comprises the Internet of things equipment, a set of environmental condition sensors, a set of social network analysis services or a set of network domain query algorithms.
An example system may include: wherein the configurable data collection and monitoring circuitry is configured to monitor at least one environment selected from the group consisting of: a municipal environment, a corporate environment, a securities trading environment, a property environment, a commercial facility, a warehousing facility, a transportation environment, a manufacturing environment, a storage environment, a house or a vehicle.
An example system may include: wherein a set of bonds associated with the set of bond transactions is vouched for by a set of assets.
An example system may include: wherein at least one asset of the set of assets is selected from the group consisting of: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, or personal property.
An example system may include: an automated agent circuit configured to process events related to at least one of value, status, and ownership of at least one asset in the set of assets, and wherein the automated agent circuit is further configured to perform actions related to liability transactions involving the assets.
An example system may include: wherein the action is selected from the group consisting of: an offer debt transaction; underwriting debt transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; urging to loan payment; ending the transaction; setting terms and conditions of the transaction; providing a notification requiring provisioning; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; a joint debt; or to consolidate debts.
An example system may include: wherein the condition classification circuit comprises a system selected from the group consisting of: a machine learning system, a model-based system, a rule-based system, a deep learning system, a hybrid system, a neural network, a convolutional neural network, a feed-forward neural network, a feedback neural network, a self-organizing map, a fuzzy logic system, a random walk system, a random forest system, a probabilistic system, a bayesian system, or a simulation system.
An example system, may further include: an automatic bond management circuit configured to manage actions related to bonds, wherein the automatic bond management circuit is trained based on a training set of bond management activities.
An example system may include: wherein the automated bond management circuitry is trained based on a set of interactions of a party with a set of user interfaces involved in a set of bond transactions.
An example system may include: wherein at least one bond transaction of the set of bond transactions comprises an activity selected from the group consisting of: an offer debt transaction; underwriting debt transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the assets; urging to loan payment; ending the transaction; setting terms and conditions of the transaction; providing a notification requiring provisioning; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; a joint debt; or to consolidate debts.
An example system, may further include: market value data collection circuitry configured to monitor and report market information relating to the value of at least one of the issuer and the set of assets.
An example system may include: wherein reporting at least one asset from a set of assets selected from the group consisting of: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, unexplored land, farms, crops, municipal facilities, warehouses, a set of inventory, goods, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, or personal property.
An example system may include: wherein the market value data collection circuit is configured to monitor pricing or financial data for items similar to the property in at least one public market.
An example system may include: a set of similar items for valuing the property is constructed using a similarity clustering algorithm based on the property of the property.
An example system may include: wherein at least one of the attributes is selected from the group consisting of: asset class, asset age, asset condition, asset history, asset storage, or asset geographic location.
An example system, may further include: intelligent contract circuitry configured to manage intelligent contracts for bond transactions.
An example system may include: wherein the smart contract circuit is further configured to determine terms and conditions of the bond.
An example system may include: wherein at least one of a set of terms and conditions of the debt transaction specified and managed by the set of intelligent contract circuitry is selected from the group consisting of: principal amount of the debt, balance of the debt, fixed interest rate, variable interest rate, payment amount, payment plan, top-end grand return plan, guaranteed asset description of the debt, asset substitutability description, party, issuer, purchaser, insured person, guarantor, collateral, personal guaranty, lien, deadline, obligation, redemption condition, default condition, or result of breach.
In an embodiment, a method for adaptive intelligence and robotic process automation capabilities for trading, financial and market support is provided herein. An example method may include: collecting a training data set of information about an entity involved in a set of bond transactions for a set of bonds and results related to the entity; and classifying a set of publisher conditions using the collected information and a model, wherein the model is trained using a training data set of results associated with the set of publishers.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example method may also include: processing an event related to at least one of a value, a status, and an ownership of at least one asset in the set of assets; and performing an action related to the liability transaction to which the asset relates.
An example method may also include: managing actions related to the bond based at least in part on the training set of bond management activities.
An example method may also include: market information relating to the value of at least one of the issuer and the set of assets is monitored and reported.
An example method may also include: an intelligent contract for managing bond transactions.
An example method may also include: terms and conditions of a smart contract for at least one bond are determined.
In an embodiment, a system for monitoring the condition of a bond issuer is provided herein. An example platform, system, or apparatus may include: social network data collection circuitry configured to collect information about at least one entity involved in at least one transaction comprising at least one bond; a condition classification circuit configured to classify a condition of the at least one entity according to a model and based on information from the social network data collection circuit, wherein the model is trained using a training data set of a plurality of results related to the at least one entity; and automatic bond management circuitry configured to manage actions related to at least one bond in response to the sorting conditions of at least one entity.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein at least one entity is selected from the following entities: bond issuers, bonds, parties and assets.
An example system may include: wherein the at least one entity comprises a bond issuer selected from the group consisting of: municipalities, companies, contractors, government entities, non-government entities, and non-profit entities.
An example system may include: wherein the bond is selected from the following entities: municipal bonds, government bonds, treasury bonds, asset security bonds, and corporate bonds.
An example system may include: wherein the conditions classified by the condition classification circuit include at least one of the following conditions: a default condition, a redemption-out condition, a condition indicative of a breach of a contract, a financial risk condition, a behavioral risk condition, a policy risk condition, a financial health condition, a physical defect condition, a physical health condition, an entity risk condition, or an entity health condition.
An example system may include: wherein the social network data collection circuit further comprises a social network input circuit configured to receive an input from a user, the input for configuring a query for information about at least one entity in response to the received input.
An example system, may further include: a data collection circuit configured to monitor at least one of an internet of things device, an environmental condition sensor, a crowdsourcing request circuit, a crowdsourcing communication circuit, a crowdsourcing issue circuit, and an algorithm for querying a network domain.
An example system, may further include: wherein the condition classification circuit is further configured to classify the condition in response to information from the data collection circuit.
An example system may include: wherein the data collection circuit is further configured to monitor an environment selected from the group consisting of: a municipal environment, a corporate environment, a securities trading environment, a property environment, a commercial facility, a warehousing facility, a transportation environment, a manufacturing environment, a storage environment, a house, and a vehicle.
An example system, may further include: wherein the condition classification circuit is further configured to classify the condition in response to the monitored environment.
An example system may include: wherein at least one bond is vouched for by at least one asset.
An example system may include: wherein at least one asset is selected from the following assets: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
An example system, may further include: event processing circuitry configured to process events related to at least one of value, status, and ownership of the at least one asset and take actions related to the at least one transaction in response to the events.
An example system may include: wherein the action is selected from the following actions: an offer bond transaction; underwriting bond transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notification requiring provisioning; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; a joint bond; and merging the bonds.
An example system may include: wherein the condition classification circuit comprises one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
An example system, may further include: an automatic bond management circuit configured to manage actions related to at least one bond, wherein the automatic bond management circuit is trained based on a training dataset of a plurality of bond management activities.
An example system may include: wherein the automated bond management circuitry is trained based on a plurality of interactions of the principal with a plurality of user interfaces involved in a plurality of bond transactions.
An example system may include: wherein the plurality of bond transaction campaigns are selected from the following bond transaction campaigns: an offer bond transaction; underwriting bond transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notification requiring provisioning; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; a joint bond; and merging the bonds.
An example system, may further include: market value data collection circuitry configured to monitor and report market information related to a value of at least one of the bond issuer, the at least one bond, and the asset related to the at least one bond.
An example system may include: wherein the assets are selected from the following: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
An example system may include: wherein the market value data collection circuit is further configured to monitor pricing or financial data of the offsetting assets in the at least one public market.
An example system, may further include: clustering circuitry configured to use the clustering circuitry to construct a set of cancellation collateral for valuing the asset based on the attributes of the asset.
An example system may include: wherein the attributes are selected from the following: category, age of asset, status of asset, history of asset, storage of asset, and geographic location.
An example system, may further include: intelligent contract circuitry configured to manage an intelligent contract for at least one transaction.
An example system may include: wherein the smart contract circuitry is further configured to determine terms and conditions of the at least one bond.
An example system may include: wherein the terms and conditions are selected from the group consisting of: principal amount of the debt, balance of the debt, fixed interest rate, variable interest rate, payment amount, payment plan, end-most grand hold plan, guaranteed asset description of at least one debt, asset exchangeability description, party, issuer, purchaser, insured person, guarantor, collateral, personal guaranty, lien, term, contract, redemption status, breach status, and breach outcome. In an embodiment, a method for monitoring the condition of a bond issuer is provided herein. An example method may include: collecting social network information about at least one entity involved in at least one transaction comprising at least one bond; classifying a condition of the at least one entity according to a model and based on social network information, wherein the model is trained using a training dataset of a plurality of results related to the at least one entity; managing at least one bond-related action in response to the classification status of at least one entity.
Certain additional aspects of the example methods are described below, any one or more of which may be present in certain embodiments. An example method may also include: processing events related to at least one of value, status, and ownership of at least one asset related to at least one bond; and taking an action related to the at least one transaction in response to the event. An example method may also include: training an automatic bond management circuit based on a training set of a plurality of bond management activities to manage an action related to at least one bond, and wherein managing the action comprises operating the automatic bond management circuit. An example method may also include: market information relating to the value of at least one of the bond issuer, the at least one bond, and the asset is monitored and reported.
In an embodiment, a system for monitoring the condition of a bond issuer is provided herein. An example platform, system, or apparatus may include: an internet of things data collection circuit configured to collect information about at least one entity involved in at least one transaction comprising at least one bond; a condition classification circuit configured to classify a condition of the at least one entity according to a model and based on information from the internet of things data collection circuit, wherein the model is trained using a training data set of a plurality of results related to the at least one entity; event processing circuitry configured to take an action related to at least one transaction in response to the classification condition of at least one entity.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein at least one entity is selected from the following entities: bond issuers, bonds, parties and assets.
An example system may include: wherein the bond issuer is selected from the group consisting of: municipalities, companies, contractors, government entities, non-government entities, and non-profit entities.
An example system may include: wherein the bond is selected from the following entities: municipal bonds, government bonds, treasury bonds, asset security bonds, and corporate bonds.
An example system may include: wherein the conditions classified by the condition classification circuit include at least one of: a breach condition, a redemption-out condition, a condition indicative of a breach of a contract, a financial risk condition, a behavioral risk condition, a policy risk condition, a financial health condition, a physical defect condition, a physical health condition, an entity risk condition, or an entity health condition.
An example system may include: wherein the internet of things data collection circuit further comprises an internet of things input circuit configured to receive an input from a user for configuring a query for information about at least one entity.
An example system, may further include: a data collection circuit configured to monitor at least one of an internet of things device, an environmental condition sensor, a crowdsourcing request circuit, a crowdsourcing communication circuit, a crowdsourcing issue circuit, and an algorithm for querying a network domain.
An example system, may further include: wherein the condition classification circuit is further configured to classify the condition in response to information from the data collection circuit.
An example system may include: wherein the data collection circuit is further configured to monitor an environment selected from the group consisting of: a municipal environment, a corporate environment, a securities trading environment, a property environment, a commercial facility, a warehousing facility, a transportation environment, a manufacturing environment, a storage environment, a house, and a vehicle.
An example system may include: wherein the condition classification circuit is further configured to classify the condition in response to the monitored environment.
An example system may include: wherein at least one bond is vouched for by at least one asset.
An example system may include: wherein at least one asset is selected from the following assets: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
An example system, may further include: event processing circuitry configured to process events related to at least one of value, status, and ownership of the at least one asset and take actions related to the at least one transaction to further respond to the events.
An example system may include: wherein the action may be selected from the following actions: an offer bond transaction; underwriting bond transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notification requiring provisioning; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; a joint bond; and merging the bonds.
An example system may include: wherein the condition classification circuit comprises one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
An example system, may further include: an automatic bond management circuit configured to manage actions related to at least one bond, wherein the automatic bond management circuit is trained based on a training dataset of a plurality of bond management activities.
An example system may include: wherein the automated bond management circuitry is trained based on a plurality of interactions of the principal with a plurality of user interfaces involved in a plurality of bond transactions.
An example system may include: wherein the plurality of bond transaction campaigns are selected from the following bond transaction campaigns: an offer bond transaction; underwriting bond transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notification that the providing is required; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; a joint bond; and merging the bonds.
An example system may also include: market value data collection circuitry configured to monitor and report market information related to a value of at least one of the bond issuer, the at least one bond, and the asset related to the at least one bond.
An example system may include: wherein the assets are selected from the following: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
An example system may include: wherein the market value data collection circuit is further configured to monitor pricing or financial data of the offsetting assets in the at least one public market.
An example system may also include: clustering circuitry configured to use the clustering circuitry to construct a set of cancellation mortgages for valuing the asset based on the attributes of the asset.
An example system may include: wherein the attributes are selected from the following: category, age of asset, status of asset, history of asset, storage of asset, and geographic location.
An example system, may further include: intelligent contract circuitry configured to manage an intelligent contract for at least one transaction.
An example system may include: wherein the smart contract circuitry is further configured to determine terms and conditions of the at least one bond.
An example system may include: wherein the terms and conditions are selected from the group consisting of: principal amount of the debt, balance of the debt, fixed interest rate, variable interest rate, payment amount, payment plan, end-most grand hold plan, guaranteed asset description of at least one debt, asset exchangeability description, party, issuer, purchaser, insured person, guarantor, collateral, personal guaranty, lien, term, contract, redemption status, breach status, and breach outcome.
In an embodiment, a method for monitoring the condition of a bond issuer is provided herein. An example method may include: collecting internet of things information about at least one entity involved in at least one transaction comprising at least one bond; classifying a condition of the at least one entity according to a model and based on the internet of things information, wherein the model is trained using a training dataset of a plurality of results related to the at least one entity; taking an action related to at least one transaction in response to the classification condition of at least one entity.
Certain additional aspects of the example methods are described below, any one or more of which may be present in certain embodiments. An example method may also include: processing an event related to at least one of a value, a status, and an ownership of at least one asset; and taking an action related to the at least one transaction in response to the event. An example method may also include: an automatic bond management circuit is trained based on a training set of a plurality of bond management activities to manage actions related to at least one bond. An example method may also include: market information relating to the value of at least one of the bond issuer, the at least one bond, and the asset is monitored and reported.
In an embodiment, an example platform or system may include: an internet of things data collection circuit configured to collect information about at least one entity involved in at least one subsidy loan transaction; a condition classification circuit comprising a model configured to classify at least one parameter of at least one subsidy involved in at least one subsidy loan transaction based on information from the internet of things data collection circuit, wherein the model is trained using a training dataset of a plurality of results related to the at least one subsidy loan; and intelligent contract circuitry configured to automatically modify terms and conditions of at least one subsidized loan based on the classification parameters of the condition classification circuitry.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein at least one entity is selected from the following entities: at least one subsidy loan, a different at least one subsidy loan involved in the at least one subsidy loan transaction, the party, the subsidy, the guarantor, the party to the subsidy, and the collateral.
An example system may include: wherein the at least one entity comprises a principal selected from the following: municipalities, companies, contractors, government entities, non-government entities, and non-profit entities.
An example system may include: wherein the at least one subsidy loan comprises at least one of: a municipal subsidy loan, a government subsidy loan, an assisted study loan, an asset guarantee subsidy loan, or a corporate subsidy loan.
An example system may include: wherein the condition classified by the condition classification circuit is selected from the following conditions: a default condition, a redemption-up condition, a condition indicating a breach of a contract, a financial risk condition, a behavioral risk condition, a contract performance condition, a policy risk condition, a financial health condition, a physical defect condition, a physical health condition, an entity risk condition, and an entity health condition.
An example system may include: wherein the at least one subsidy loan is a study aid loan and the status classification circuit classifies at least one of: the student gains academic progress, the student participates in non-profit activities and the student participates in public welfare activities.
An example system may include: also included is a user interface of the internet of things data collection circuit configured to enable a user to configure a query for information about at least one entity.
An example system may include: wherein further comprising at least one configurable data collection and circuitry configured to monitor at least one entity selected from the group consisting of: social network analysis circuitry, environmental condition circuitry, crowdsourcing circuitry, and algorithms to query network domains.
An example system may include: wherein the at least one configurable data collection and circuitry monitors the following environment: municipal environments, educational environments, enterprise environments, securities trading environments, real estate environments, commercial facilities, warehousing facilities, transportation environments, manufacturing environments, storage environments, houses, and vehicles.
An example system may include: wherein the at least one subsidy is secured by the at least one property.
An example system may include: wherein at least one asset is selected from the following assets: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, unexplored land, farms, crops, municipal facilities, warehouses, a group of inventory, goods, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
An example system may include: also included is an automated agent configured to process at least one event related to at least one of value, status, and ownership of the at least one property and take an action related to at least one subsidy loan transaction to which the at least one property relates.
An example system may include: wherein the action is selected from: a loan transaction to be tendered; underwriting subsidy loan transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; urging to loan payment; ending the transaction; setting terms and conditions of the transaction; providing a notice requiring the provision, stopping the redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; jointly subsidizing a loan; and merging subsidy loans.
An example system may include: wherein the condition classification circuit comprises one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
An example system may include: further included is an automatic subsidy loan management circuit configured to manage actions related to at least one subsidized loan, wherein the automatic subsidy loan management circuit is trained based on a training set of subsidized loan management activities.
An example system may include: wherein the automated subsidy management circuit is trained based on a plurality of interactions of the party with a plurality of user interfaces involved in a plurality of subsidy loan transactions.
An example system may include: wherein the plurality of subsidized loan transaction activities are selected from the following subsidized loan transaction activities: a loan transaction to be tendered; underwriting subsidy loan transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a notification requiring provisioning; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; jointly subsidizing a loan; and merging subsidy loans.
An example system may include: further included is blockchain service circuitry configured to record the modified set of terms and conditions of the at least one subsidy in the distributed ledger.
An example system may include: further included is a market value data collection circuit configured to monitor and report market information related to the value of at least one of the issuer, the at least one subsidy, and the at least one property.
An example system may include: wherein at least one asset selected from the following assets is reported: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
An example system may include: wherein the market value data collection circuit is further configured to monitor pricing or financial data of the offsetting assets in the at least one public market.
An example system may include: a clustering circuit configured to use the clustering circuit to construct a set of offset collateral for valuation of the at least one asset based on the attributes of the at least one asset.
An example system may include: wherein the attributes are selected from the following: category, age of asset, status of asset, history of asset, storage of asset, and geographic location.
An example system may include: also included is intelligent contract circuitry configured to manage at least one intelligent contract for subsidizing a loan transaction.
An example system may include: wherein the intelligent contract is further configured to modify the intelligent contract in response to the classification parameter of the at least one subsidized loan.
An example system may include: wherein the terms and conditions of the at least one subsidy loan automatically modified by the intelligent contract circuitry are selected from the group consisting of: principal amount of the debt, balance of the debt, fixed interest rate, variable interest rate, payment amount, payment plan, end-most grand payback plan, guaranteed asset description of at least one subsidy, asset exchangeability description, party, issuer, purchaser, insured person, collateral, personal guarantee, lien, term, contract, redemption-out condition, default condition, and default outcome.
In an embodiment, an example method may include: collecting information about at least one entity involved in at least one subsidy loan transaction; classifying at least one parameter of at least one subsidy loan involved in the at least one subsidy loan transaction based on the information using a model trained based on a training dataset for a plurality of results associated with the at least one subsidy loan; and automatically modifying the terms and conditions of the at least one subsidy loan based on the classification parameters.
Certain additional aspects of the example methods are described below, any one or more of which may be present in certain embodiments. An example method may include: further comprising processing at least one event relating to at least one of a value, a status, and an ownership of at least one property relating to the at least one subsidy and taking action relating to at least one subsidy loan transaction to which the at least one property relates.
An example method may include: further comprising recording the modified set of terms and conditions for the at least one subsidy in the distributed ledger.
An example method may include: which also includes monitoring and reporting market information related to the value of the issuer, the at least one subsidy loan, or the at least one property associated with the at least one subsidy loan.
In an embodiment, an example platform or system may include: a social network analytics data collection circuit configured to collect social network information about at least one entity involved in at least one subsidy loan transaction; a condition classification circuit comprising a model configured to classify at least one parameter of at least one subsidy loan involved in at least one subsidy loan transaction based on social network information from the social network analysis data collection circuit, wherein the model is trained using a training dataset of results related to the at least one subsidy loan; and intelligent contract circuitry configured to automatically modify terms and conditions of at least one subsidized loan based on at least one parameter of the classification.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein at least one entity is selected from the following entities: at least one subsidy loan, a different at least one subsidy loan involved in the at least one subsidy loan transaction, the party, the subsidy, the guarantor, the party to the subsidy, and the collateral.
An example system may include: wherein the party subsidizing the at least one subsidy is selected from the group consisting of: municipalities, companies, contractors, government entities, non-government entities, and non-profit entities.
An example system may include: wherein the at least one subsidy loan comprises at least one of: municipal subsidy loans, government subsidy loans, school-aid loans, asset guarantee subsidy loans, or corporate subsidy loans.
An example system may include: wherein the at least one parameter classified by the condition classification circuit is selected from the following conditions: a default condition, a redemption-out condition, a condition indicative of a breach of a contract, a financial risk condition, a behavioral risk condition, a contract performance condition, a policy risk condition, a financial health condition, a physical defect condition, a physical health condition, an entity risk condition, and an entity health condition.
An example system may include: wherein the at least one subsidy loan is a study aid loan and the status classification circuit classifies at least one of: the student gains the progress of the academic degree, the student participates in the non-profit activities or the student participates in the public welfare activities.
An example system may include: wherein a user interface of the social network analysis data collection circuit is further included, the user interface being structured to enable a user to configure a query for information about at least one entity, wherein the social network analysis data collection circuit initiates at least one algorithm in response to the query, the at least one algorithm searches for and retrieves data from at least one social network in response to the query.
An example system may include: wherein further comprising at least one configurable data collection and circuitry configured to monitor at least one entity and selected from the group consisting of: social network analysis circuitry, environmental condition circuitry, crowdsourcing circuitry, and algorithms to query network domains.
An example system may include: wherein the at least one configurable data collection and circuitry monitors the following environment: municipal environments, educational environments, enterprise environments, securities trading environments, real estate environments, commercial facilities, warehousing facilities, transportation environments, manufacturing environments, storage environments, houses, and vehicles.
An example system may include: wherein the at least one subsidy is secured by the at least one property.
An example system may include: wherein at least one asset is selected from the following assets: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
An example system may include: further included is an automated agent configured to process at least one event related to at least one of a value, status, or ownership of at least one property and take an action related to at least one subsidy loan transaction related to the at least one property.
An example system may include: wherein the action is selected from: a loan transaction to be tendered; underwriting subsidy loan transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a request for a notice to offer, stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; jointly subsidizing a loan; and merging subsidy loans.
An example system may include: wherein the condition classification circuit comprises one of the following systems: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
An example system may include: wherein further comprising an automatic subsidy loan management circuit configured to manage actions related to at least one subsidized loan, and wherein the automatic subsidy loan management circuit is trained based on a training set of subsidized loan management activities.
An example system may include: wherein the automated subsidy management circuit is trained based on a plurality of interactions of the party with a plurality of user interfaces involved in a plurality of subsidy loan transactions.
An example system may include: wherein the plurality of subsidy loan transaction activities are selected from the following subsidy loan transaction activities: a loan transaction to be tendered; underwriting subsidy loan transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; urging to loan payment; ending the transaction; setting terms and conditions of the transaction; providing a notification requiring provisioning; stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; jointly subsidizing a loan; and incorporate subsidy loans.
An example system may include: further included is blockchain service circuitry configured to record the modified set of terms and conditions of the at least one subsidy in the distributed ledger.
An example system may include: further included is a market value data collection circuit configured to monitor and report market information related to the value of at least one of the issuer, the at least one subsidy, or the at least one property.
An example system may include: wherein at least one asset selected from the following assets is reported: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
An example system may include: wherein the market value data collection circuit is further configured to monitor pricing or financial data of the offsetting assets in the at least one public market.
An example system, may further include: a clustering circuit configured to use the clustering circuit to construct a set of offset collateral for valuation of the at least one asset based on the attributes of the at least one asset.
An example system may include: wherein the attributes are selected from the following: category, age of asset, status of asset, history of asset, storage of asset, and geographic location.
An example system may include: also included is intelligent contract circuitry configured to manage at least one intelligent contract for subsidizing a loan transaction.
An example system may include: wherein the intelligent contract circuitry sets at least one of terms and conditions for subsidizing the loan.
An example system may include: wherein the terms and conditions of the at least one subsidy loan specified and managed by the intelligent contract circuitry are selected from the group consisting of: principal amount of the debt, balance of the debt, fixed interest rate, variable interest rate, payment amount, payment plan, end-most grand payback plan, guaranteed asset description of at least one subsidy, asset exchangeability description, party, issuer, purchaser, insured person, collateral, personal guarantee, lien, term, contract, redemption-out condition, default condition, and default outcome.
In an embodiment, an example method may include: collecting social network information about at least one entity involved in at least one subsidy loan transaction; classifying at least one parameter of at least one subsidy loan involved in the at least one subsidy loan transaction based on the social network information using a model trained based on a training dataset of results related to the at least one subsidy loan; and automatically modifying the terms and conditions of at least one subsidized loan based on at least one parameter of the classification.
Certain additional aspects of the example methods are described below, any one or more of which may be present in certain embodiments. An example method may include: further comprising processing at least one event related to at least one of value, status, and ownership of the at least one property and taking an action related to at least one subsidy loan transaction to which the at least one property relates.
An example method may include: further comprising recording the modified set of terms and conditions for the at least one subsidy in the distributed ledger.
An example method may include: which also includes monitoring and reporting market information related to the value of at least one of the issuer, the at least one subsidy, or the at least one property.
In an embodiment, a system for automatically processing a subsidy loan is provided herein. An example platform or system may include: a crowdsourcing service circuit configured to collect information relating to a set of entities involved in a set of subsidy loan transactions; a condition classification circuit comprising a model and an artificial intelligence service circuit configured to classify a set of parameters of a set of subsidies involved in the transaction based on information from the crowdsourcing service circuit, wherein the model is trained using a training dataset of results related to the subsidies; and intelligent contract circuitry for automatically modifying the terms and conditions of the subsidized loan based on a set of classification parameters from the condition classification circuitry.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein the set of entities includes the following entities: a set of subsidies, a set of parties, a set of subsidies, a set of guarantors, a set of subsidizing parties, and a set of collateral.
An example system may include: wherein each entity of the set of entities comprises an entity selected from the list consisting of: a subsidy in a set of subsidized loans corresponding to a set of subsidized loan transactions, a principal associated with at least one of the set of subsidized loan transactions, a subsidy corresponding to a set of subsidized loans corresponding to a set of subsidized loan transactions, a subsidized principal associated with at least one of the set of subsidized loan transactions, a subsidy corresponding to a set of subsidized loans corresponding to a set of subsidized loan transactions, a collateral associated with at least one of the set of subsidized loan transactions, and a subsidy corresponding to a set of subsidized loans corresponding to a set of subsidized loan transactions.
An example system may include: at least one entity of the set of entities comprises a principal of subsidy related to at least one of the set of subsidy loan transactions, wherein the principal of subsidy comprises at least one of: municipalities, companies, contractors, government entities, non-government entities or non-profit entities.
An example system may include: wherein each loan in a set of subsidized loans corresponding to the set of loan transactions comprises at least one of: municipal subsidy loans, government subsidy loans, school-aid loans, asset guarantee subsidy loans, or corporate subsidy loans.
An example system may include: wherein the condition classified by the condition classification circuit is among a default condition, a redemption-stop condition, a condition indicative of a breach of contract, a financial risk condition, a behavioral risk condition, a contract performance condition, a policy risk condition, a financial health condition, a physical defect condition, a physical health condition, an entity risk condition, and an entity health condition.
An example system may include: wherein the subsidy loan is a study aid loan and the status classification circuit classifies at least one of: the student gains academic progress, the student participates in non-profit activities and the student participates in public welfare activities.
An example system may include: wherein the crowdsourcing service circuitry is further configured to have a user interface through which a user can configure a query for information about a set of entities, and the crowdsourcing service circuitry automatically configures the crowdsourcing request based on the query.
An example system, may further include: a configurable data collection and monitoring service circuit for monitoring the entity, wherein the configurable data collection and monitoring service circuit comprises at least one of the group consisting of: the system comprises an internet of things service, a set of environmental condition sensors, a set of social network analysis services and a set of algorithms for querying network domains.
An example system may include: wherein the configurable data collection and monitoring service circuit is further configured to monitor an environment selected from the group consisting of: municipal environments, educational environments, corporate environments, securities trading environments, real estate environments, commercial facilities, warehousing facilities, transportation environments, manufacturing environments, storage environments, houses, and vehicles.
An example system may include: wherein the set of subsidy loans is guaranteed by a set of properties.
An example system may include: wherein each of the group of assets is selected from: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, and personal property.
An example system, may further include: automatic agent circuitry configured to process events related to at least one of value, status, or ownership of at least one property of the set of properties and take actions related to a subsidized loan transaction involving the at least one property.
An example system may include: wherein the action is selected from: a loan transaction to be tendered; underwriting subsidy loan transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; the loan is collected; ending the transaction; setting terms and conditions of the transaction; providing a request for a notice to offer, stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; jointly subsidizing a loan; or incorporate subsidy loans.
An example system may include: wherein the artificial intelligence service circuit comprises at least one of: machine learning systems, model-based systems, rule-based systems, deep learning systems, hybrid systems, neural networks, convolutional neural networks, feed-forward neural networks, feedback neural networks, self-organizing maps, fuzzy logic systems, random walk systems, random forest systems, probabilistic systems, bayesian systems, and simulation systems.
An example system may include: also included is an automatic subsidy loan management circuit configured to manage actions related to subsidizing loans, wherein the automatic subsidy loan management circuit is trained based on a training set of subsidy loan management activities.
An example system may include: wherein the automatic subsidy loan management circuitry is further trained based on a set of interactions of a party with a set of user interfaces, wherein the party is involved in a set of subsidy loan transactions.
An example system may include: wherein each of the set of subsidized loan transactions is selected from the group consisting of: a loan transaction to be tendered; underwriting subsidy loan transactions; setting interest rate; a deferred payment requirement; modifying interest rate; verifying the property right; managing and checking; recording the change of property rights; evaluating the value of the asset; urging to loan payment; ending the transaction; setting terms and conditions of the transaction; providing a request for a notice to offer, stopping redemption of a set of assets; modifying the terms and conditions; setting a rating of the entity; jointly subsidizing a loan; or incorporate subsidy loans.
An example system may include: further included is blockchain service circuitry configured to record a modified set of terms and conditions of a set of subsidies corresponding to the set of subsidized loan transactions in a distributed ledger.
An example system may include: further included is a market value data collection service circuit configured to monitor and report market information related to the value of at least one of the party associated with the subsidy, a set of subsidy loans corresponding to the set of subsidy loan transactions, and a set of assets.
An example system may include: wherein a set of assets is reported, the set of assets including at least one of: municipal assets, vehicles, ships, airplanes, buildings, houses, real estate, undeveloped land, farms, crops, municipal facilities, warehouses, a group of inventory, commodities, securities, currency, value tokens, tickets, cryptocurrency, consumables, edible items, beverages, precious metals, jewelry accessories, gemstones, intellectual property items, intellectual property rights, contractual rights, antiques, fixtures, furniture, equipment, tools, machinery, or personal property.
An example system may include: wherein the market value data collection service circuitry is further configured to monitor pricing or financial data for items in the at least one public market that are similar to assets in the set of assets.
An example system may include: wherein a set of similar items for valuing assets in the set of assets is constructed using a similarity clustering algorithm based on attributes of the assets.
An example system may include: wherein the attributes are selected from the following: asset class, asset age, asset condition, asset history, asset storage, or asset geographic location.
An example system may include: the intelligent contract service circuit is used for managing the intelligent contract for subsidizing the loan.
An example system may include: wherein the intelligent contract service circuit is further configured to set a set of terms and conditions for subsidizing the loan.
An example system may include: wherein the terms and conditions of the debt transaction specified and managed by the intelligent contract service circuit are selected from the group consisting of: principal amount of debt, balance of debt, fixed interest rate, variable interest rate, payment amount, payment plan, end-most big payback plan, guaranteed property description of subsidized loan, property substitutability description, party, issuer, purchaser, insured person, collateral, personal guarantee, lien, term, contract, redemption status, default status, or result of default.
In an embodiment, a method is provided herein that facilitates automatically processing a subsidy loan. An example method may include: collecting information relating to a set of entities involved in a set of subsidy loan transactions; classifying a set of parameters of a set of subsidies involved in the transaction of the subsidy loan based on an artificial intelligence service, a model and information from a crowdsourcing service, wherein the model is trained based on a training dataset of results related to the subsidy loan; and modifying the terms and conditions of the subsidized loan based on a set of classification parameters.
Certain additional aspects of the example methods are described below, any one or more of which may be present in certain embodiments. An example method may include: wherein a group of entities is selected from: a set of subsidies, a set of parties, a set of subsidies, a set of guarantors, a set of subsidizing parties, or a set of collateral.
An example method may include: wherein the set of entities comprises a set of subsidizing parties, and wherein each party in the set of subsidizing parties comprises at least one of: municipalities, companies, contractors, government entities, non-government entities or non-profit entities.
An example method may include: wherein a set of subsidy loans includes at least one of: municipal subsidy loans, government subsidy loans, school-aid loans, asset guarantee subsidy loans, and corporate subsidy loans.
An example method may include: wherein the subsidized loan is a school loan, wherein said classification is based on at least one of: the student gains academic progress, the student participates in non-profit activities and the student participates in public welfare activities.
In an embodiment, an example platform or system may include: an asset identification service circuit configured to interpret a plurality of assets corresponding to a financial entity for taking over the plurality of assets; identity management service circuitry configured to authenticate a plurality of identifiers corresponding to executable action entities entitled to take actions with respect to a plurality of assets, wherein the plurality of identifiers includes at least one credential; a blockchain service circuit configured to store a plurality of asset control features in a blockchain structure, wherein the blockchain structure includes a distributed ledger configuration; and financial management circuitry configured to communicate the interpreted plurality of assets and the authenticated plurality of identifiers to blockchain service circuitry for storage in a blockchain structure as asset control features, and wherein the blockchain service circuitry is further configured to record the asset control features in a distributed ledger configuration as asset events.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein the at least one credential includes at least one of an owner credential, a proxy credential, a beneficiary credential, a delegate credential, or a custodian credential.
An example system may include: wherein the asset events include the following events: transferring property, owner death, owner disability, owner bankruptcy, stopping redemption, setting liens, using property as a collateral, designating beneficiary, loan on property, providing notice about property, reviewing property, evaluating property, reporting property for tax purposes, assigning property ownership, disposing of property, selling property, purchasing property, or designating ownership status.
An example system may include: data collection circuitry configured to monitor at least one of interpretation of the plurality of assets, authentication of the plurality of identifiers, and recording of asset events.
An example system may include: wherein each of the executable action entities comprises at least one of an owner, beneficiary, agent, delegate, or custodian.
An example system may include: an intelligent contract circuit configured to manage custody of a plurality of assets, and wherein at least one asset event related to the plurality of assets is managed by the intelligent contract circuit based on a plurality of terms and conditions implemented in an intelligent contract configuration and based on data collected by the data collection service circuit.
An example system may include: wherein the at least one asset event related to the plurality of assets comprises at least one event selected from: transferring property, owner death, owner disability, owner bankruptcy, stopping redemption, setting liens, using property as a collateral, designating beneficiary, lending with property as a collateral, providing notice about property, reviewing property, evaluating property, reporting property for tax purposes, assigning property ownership, disposing of property, selling property, purchasing property, and designating ownership status.
An example system may include: wherein the data collection circuit further comprises at least one of: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and an interactive crowdsourcing system.
An example system may include: wherein each of the asset identification service circuit, the identity management service circuit, the blockchain service circuit, and the financial management circuit further comprises a corresponding Application Programming Interface (API) component configured to facilitate communication between the system circuits. The corresponding API component of the circuit also includes a user interface configured to interact with a plurality of users of the system.
An example system may include: block chain service circuitry further structured to share and distribute asset events with the plurality of executable action entities.
In an embodiment, an example method may include: interpreting a plurality of assets corresponding to a financial entity for taking over the plurality of assets; authenticating a plurality of identifiers corresponding to executable action entities having authority to take actions with respect to a plurality of assets, wherein the plurality of identifiers includes at least one credential; storing a plurality of asset control features in a block-chaining structure, wherein the block-chaining structure comprises a distributed ledger configuration; and communicating the interpreted plurality of assets and the authenticated plurality of identifiers for storage in the blockchain structure as asset control features, wherein the asset control features are recorded in the distributed ledger configuration as asset events.
An example method may include: wherein the at least one credential includes at least one of an owner credential, a proxy credential, a beneficiary credential, a delegate credential, or a custodian credential.
An example method may include: wherein each of the asset events comprises at least one event selected from: transferring property, owner death, owner disability, owner bankruptcy, stopping redemption, setting liens, using property as a collateral, designating beneficiary, loan on property, providing notice about property, reviewing property, evaluating property, reporting property for tax purposes, assigning property ownership, disposing of property, selling property, purchasing property, or designating ownership status.
An example method may include: at least one of an interpretation of the plurality of assets, an authentication of the plurality of identifiers, or a record of asset events is monitored.
An example method may include: wherein each of the executable action entities comprises at least one of an owner, beneficiary, agent, delegate, or custodian.
An example method may include: custody of a plurality of assets is managed, wherein at least one asset event related to the plurality of assets is based on a plurality of terms and conditions implemented in an intelligent contract configuration and based on data collected by data regarding the plurality of assets.
An example method may include: wherein each asset event related to the plurality of assets comprises at least one event selected from: transferring property, owner death, owner disability, owner bankruptcy, stopping redemption, setting liens, using property as a collateral, designating beneficiary, loan on property, providing notice about property, reviewing property, evaluating property, reporting property for tax purposes, assigning property ownership, disposing of property, selling property, purchasing property, or designating ownership status.
An example method may include: wherein the monitoring is performed by at least one of the following systems: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, or an interactive crowdsourcing system.
An example method may include: an asset event is shared and distributed with a plurality of executable action entities.
An example method may include: wherein interpreting the plurality of assets comprises identifying a plurality of assets that the financial entity is responsible for taking over.
An example method may include: wherein authenticating the plurality of identifiers comprises authorizing the plurality of identifiers corresponding to the executable action entity to take action with respect to the plurality of assets.
An example method may include: wherein the block chain structure is provided in association with the block chain market.
An example method may include: the blockchain marketplace utilizes an automated blockchain based trading application.
An example method may include: asset transaction data is stored in a block chain structure based on interactions between executable action entities.
An example method may include: wherein the block-link structure is a distributed block-link structure spanning multiple asset nodes.
An example method may include: wherein at least one of the plurality of assets is a virtual asset tag and interpreting the plurality of assets includes identifying the virtual asset tag.
An example method may include: wherein storing the plurality of asset control features comprises storing virtual asset tag data.
An example method may include: wherein the virtual asset tag data is at least one of location data or tracking data.
An example method may include: wherein the identifier corresponding to at least one of the financial entity or the action-executable entity is stored as virtual asset tag data.
In an embodiment, a system that facilitates redemption of collateral is provided herein. An example platform or system may include: a loan protocol storage circuit configured to store a plurality of loan protocol data including at least one loan protocol, wherein the at least one loan protocol includes loan condition data including terms and condition data of the at least one loan protocol, the terms and condition data of the at least one loan protocol relating to a redemption-stopping condition of the at least one asset, the redemption-stopping condition of the at least one asset providing a collateral condition associated with the collateral asset for providing a guarantee for a repayment obligation of the at least one loan protocol; a data collection service circuit configured to monitor the loan condition data and detect a default condition based on a change in the loan condition data; and intelligent contract service circuitry configured to, when the data collection service circuitry detects a breach condition, interpret the breach condition and communicate an indication of the breach condition that initiates a redemption process based on the collateral condition and the breach condition.
Certain additional aspects of the example systems are described below, any one or more of which may be present in certain embodiments. An example system may include: wherein the smart contract service circuit is further configured to communicate that the detected breach condition indication is communicated to at least one of the smart lock and the smart container to lock the mortgage asset.
An example system may include: wherein the redemption process configures and initiates a listing of mortgage assets on the public auction website.
An example system may include: wherein the redemption process configures and transmits a set of shipping instructions for the mortgage asset.
An example system may include: wherein the redemption process configures the set of instructions for the drone to transport the mortgage asset.
An example system may include: wherein the redemption process configures the robotic device with a set of instructions to transport the mortgage asset.
An example system may include: wherein the redemption process initiates a process for automatically replacing a set of substitute collateral.
An example system may include: wherein the redemption process initiates a collateral tracking process.
An example system may include: wherein the redemption process initiates a collateral valuation process.
An example system may include: wherein the redemption-out process initiates a message to the borrower to initiate a negotiation regarding redemption-out.
An example system may include: wherein the negotiation is managed by a robotic process automation system that is trained based on a training set of redemption-out negotiations.
An example system may include: wherein the negotiation involves modifying at least one of interest rates, payment terms, and collateral of at least one loan agreement.
An example system may include: wherein the data collection service circuit further comprises at least one of: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, and an interactive crowdsourcing system.
An example system may include: wherein each of the loan protocol storage circuit, the data collection service circuit, and the intelligent contract service circuit further includes a corresponding Application Programming Interface (API) component configured to facilitate communication between the system circuits.
An example system may include: wherein the corresponding API component of the circuit further comprises a user interface configured to interact with a plurality of users of the system.
In an embodiment, a method of facilitating redemption of a collateral is provided herein. An example method may include: storing a plurality of loan protocol data comprising at least one loan protocol, wherein the at least one loan protocol comprises loan condition data, the loan condition data comprising terms and condition data of the at least one loan protocol, the terms and condition data of the at least one loan protocol being related to a redemption-out condition of at least one asset, the redemption-out condition of the at least one asset providing a collateral condition related to the collateral asset for securing a repayment obligation of the at least one loan protocol; monitoring the loan condition data and detecting a default condition based on a change in the loan condition data; interpreting the default condition; and communicating an indication of the breach condition to initiate a redemption process based on the collateral condition.
Certain additional aspects of the example methods are described below, any one or more of which may be present in certain embodiments. An example method may include: wherein the detected breach condition indication is communicated to at least one of the smart lock and the smart container to lock the mortgage asset.
An example method may include: wherein the redemption process configures and initiates a listing of mortgage assets on the public auction website.
An example method may include: wherein the redemption process configures and transmits a set of shipping instructions for the mortgage asset.
An example method may include: wherein the redemption process configures the set of instructions for the drone to transport the mortgage asset.
An example method may include: wherein the redemption process configures the robotic device with a set of instructions to transport the mortgage asset.
An example method may include: wherein the redemption process initiates a process for automatically replacing a set of substitute collateral.
An example method may include: wherein the redemption process initiates a collateral tracking process.
An example method may include: wherein the redemption process initiates a collateral valuation process.
An example method may include: wherein the redemption-stop process initiates a message to the borrower, thereby initiating a negotiation regarding redemption-stop.
An example method may include: wherein the negotiation is managed by a robotic process automation system that is trained based on a training set of redemption-stop negotiations.
An example method may include: wherein the negotiation involves modifying at least one of interest rates, payment terms, or collateral of at least one of the loan agreements.
An example method may include: wherein the monitoring is provided by at least one of the following systems: an internet of things system, a camera system, a networked monitoring system, an internet monitoring system, a mobile device system, a wearable device system, a user interface system, or an interactive crowdsourcing system.
An example method may include; wherein communications for monitoring, interpretation and communication are provided through an Application Programming Interface (API).
An example method may include: wherein a user interface comprising an API is provided for interacting with a plurality of users.
Referring to fig. 111, the adaptive intelligence system 11104 may include an artificial intelligence system 11148, a digital twin system 11120, and an adaptive device (or edge) intelligence system 11130. The artificial intelligence system 11148 may define a machine learning model 11102 for performing analysis, simulation, decision-making, and prediction related to data processing, data analysis, simulation creation, and simulation analysis of one or more of the trading entities. The machine learning model 11102 is an algorithmic and/or statistical model that does not use explicit instructions but relies on patterns and reasoning to perform specific tasks. Machine learning model 11102 builds one or more mathematical models based on training data to make predictions and/or decisions without being explicitly programmed to perform specific tasks. The machine learning model 11102 may receive sensor data inputs as training data, including event data 11124 and status data 11172 related to one or more of the trading entities, through the data collection system 11118 and the monitoring system 11106 and the connection facility 11116. Event data 11124 and state data 11172 may be stored in data storage system 11110. The sensor data input to the machine learning model 11102 may be used to train the machine learning model 11102 to perform analysis, simulation, decision-making, and prediction related to data processing, data analysis, simulation creation, and simulation analysis of one or more of the trading entities. The machine learning model 11102 may also use input data from one or more users of the information technology system. The machine learning model 11102 may include an artificial neural network, a decision tree, a support vector machine, a bayesian network, a genetic algorithm, any other suitable form of machine learning model, or a combination thereof. The machine learning model 11102 may be used to learn by supervised learning, unsupervised learning, reinforcement learning, self-learning, feature learning, sparse dictionary learning, anomaly detection, association rules, combinations thereof, or any other suitable learning algorithm.
The artificial intelligence system 11148 may also define a digital twin system 11120 to create a digital copy of one or more of the trading entities. The digital copy of one or more of the transaction entities may use the substantially real-time sensor data to provide a substantially real-time virtual representation of the transaction entities and to provide a simulation of one or more possible future states of the one or more transaction entities. The digital copy is present concurrently with the one or more transaction entities being copied. The digital copy provides one or more simulations of physical elements and attributes of the one or more transacting entities being copied and their dynamics in embodiments throughout the lifestyle of the one or more transacting entities being copied. The digital copy may provide a hypothetical simulation of the one or more trading entities by allowing hypothetical extrapolation of sensor data to simulate the state of the one or more trading entities, such as during high stress, after a period of time that component wear may have been an issue, during maximum throughput operation, after one or more hypothetical or planned improvements have been made to the one or more manufacturing entities, or in any other suitable hypothetical situation, such as during a design phase prior to construction or manufacture of the one or more trading entities, or during or after construction or manufacture of the one or more trading entities. In some embodiments, the machine learning model 11102 may automatically predict hypothetical situations for simulation using the digital replica, for example by predicting possible improvements to one or more transaction entities, predicting when one or more components of one or more transaction entities may fail, and/or suggesting possible improvements to one or more transaction entities, such as changes to time settings, arrangements, components, or any other suitable changes to transaction entities. The digital copy allows for simulation of the one or more transaction entities during the design and operational phase of the one or more transaction entities, as well as simulation of assumed operational conditions and configurations of the one or more transaction entities. By enabling convenient observation and measurement of virtually any type of metric, including temperature, wear, light, vibration, etc., not only in, on, and around each component of the one or more transaction entities, but in some embodiments also within the one or more transaction entities, the digital copy enables very valuable analysis and simulation of the one or more transaction entities. In some embodiments, the machine learning model 11102 may process sensor data including event data 11124 and state data 11172 to define analog data for use by the digital twin system 11120. For example, the machine learning model 11102 may receive state data 11172 and event data 11124 related to a particular trading entity of a plurality of trading entities and perform a series of operations on the state data 11172 and event data 11124 to format the state data 11172 and event data 11124 into a format suitable for use by the digital twin system 11120 in creating a digital copy of the trading entity. For example, one or more of the transaction entities may include a robot for enhancing products on adjacent assembly lines. The machine learning model 11102 may collect data from one or more sensors located on, near, in, and/or around the robot. The machine learning model 11102 may perform operations on the sensor data to process the sensor data into analog data and output the analog data to the digital twin system 11120. The digital twin system 11120 simulation may use the simulated data to create one or more digital copies of the robot, the simulation including measurements, etc., including temperature, wear, speed, rotation, and vibration of the robot and components of the robot. The simulation may be a substantially real-time simulation such that a human user of the information technology may view the simulation of the robot, the metrics related to the robot, and the metrics related to the components of the robot in substantially real-time. The simulation may be a predicted or hypothetical situation such that a human user of the information technology can view the predicted or hypothetical simulation of the robot, the metrics related to the robot, and the metrics related to the components of the robot.
In some embodiments, the machine learning model 11102 and the digital twin system 11120 may process the sensor data and create digital copies of a set of transaction entities of the plurality of transaction entities to facilitate design, real-time simulation, predictive simulation, and/or hypothetical simulation of the set of related transaction entities. The digital copy of the set of transaction entities may use the substantially real-time sensor data to provide a substantially real-time virtual representation of the set of transaction entities and to provide a simulation of one or more possible future states of the set of transaction entities. The digital copy is present concurrently with the set of transaction entities being copied. The digital copy provides one or more simulations of physical elements and attributes of the set of transacting entities being copied and their dynamics in embodiments throughout the life style of the set of transacting entities being copied. The one or more simulations may include a visual simulation, such as a wireframe virtual representation of one or more transaction entities that may be viewed on a display using an Augmented Reality (AR) device or using a Virtual Reality (VR) device. The visual simulation may be manipulated by a human user of the information technology system, such as zooming or highlighting the simulated components and/or providing an exploded view of one or more transaction entities. The digital copy may provide a hypothetical simulation of the set of trading entities by allowing hypothetical extrapolation of sensor data to simulate the state of the set of trading entities, such as during high stress, after a period of time has elapsed in which component wear may be a problem, during maximum throughput operation, after one or more hypothetical or planned improvements have been made to the set of trading entities, or under any other suitable hypothetical scenario, such as during a design phase prior to construction or manufacture of one or more trading entities, or during or after construction or manufacture of one or more trading entities. In some embodiments, the machine learning model 11102 may automatically predict hypothetical situations for simulation using the digital replicas, such as by predicting possible improvements to the set of transactional entities, predicting when one or more components of the set of transactional entities may fail, and/or suggesting possible improvements to the set of transactional entities, such as changes to time settings, arrangements, components, or any other suitable changes to the transactional entities. The digital copy allows for simulation of the set of transaction entities during the design and operational phases of the set of transaction entities, as well as simulation of assumed operational conditions and configurations of the set of transaction entities. The digital copy enables highly valuable analysis and simulation of one or more transaction entities by enabling convenient observation and measurement of virtually any type of metric, including temperature, wear, light, vibration, etc., not only in, on, and around each component of the set of transaction entities, but also within the set of transaction entities in some embodiments. In some embodiments, the machine learning model 11102 may process sensor data including event data 11124 and state data 11172 to define analog data for use by the digital twin system 11120. For example, the machine learning model 11102 may receive state data 11172 and event data 11124 related to a particular transactional entity of a plurality of transactional entities and perform a series of operations on the state data 11172 and event data 11124 to format the state data 11172 and event data 11124 into a format suitable for use by the digital twin system 11120 in creating a digital copy of the set of transactional entities. For example, a set of transaction entities may include: a die stamping machine for placing the product on a conveyor belt; the conveyor belt, the die stamping machine is used for placing the product on the conveyor belt; a plurality of robots to add parts to the products as they move along an assembly line. The machine learning model 11102 may collect data from one or more sensors located on, near, in and/or around the die press, the conveyor belt, and each of the plurality of robots. The machine learning model 11102 may perform operations on the sensor data to process the sensor data into analog data and output the analog data to the digital twin system 11120. The digital twinning system 11120 simulation may use these simulated data to create one or more digital copies of the die-stamping machine, the conveyor belt, and the plurality of robots, the simulation including measurements, etc., of the temperature, wear, speed, rotation, and vibration of the die-stamping machine, the conveyor belt, and the plurality of robots and their components. The simulation may be a substantially real-time simulation such that a human user of information technology may view the simulation of the die machine, the conveyor belt, and the plurality of robots, the metrics related thereto, and the metrics related to the components thereof substantially in real-time. The simulation may be a predicted or hypothetical situation such that a human user of information technology can view predicted or hypothetical simulations of the die machine, the conveyor belt, and the plurality of robots, metrics related thereto, and metrics related to components thereof.
In some embodiments, the machine learning model 11102 may preferentially collect sensor data for digital replica simulation of one or more of the trading entities. The machine learning model 11102 may be trained using sensor data and user input to learn which types of sensor data are most effective for creating a digital replica simulation of one or more of the transaction entities. For example, the machine learning model 11102 may discover that a particular transaction entity has dynamic properties such as component wear and throughput that are affected by temperature, humidity, and load. The machine learning model 11102 may preferentially collect sensor data related to temperature, humidity, and load through machine learning, and may preferentially process sensor data of a preferential type into analog data to output to the digital twin system 11120. In some embodiments, the machine learning model 11102 may suggest to a user of the information technology system to implement more and/or different priority type sensors near and around the transacting entity being simulated in the information technology, so that more and/or better priority type data may be used in the simulation of the transacting entity through its digital copy.
In some embodiments, the machine learning model 11102 may be used to learn based on modeling goals and one or both of the quality or type of sensor data to determine which types of sensor data are to be processed as analog data for transmission to the digital twin system 11120. The modeling objective may be an objective set by a user of the information technology system, or may be predicted or learned by the machine learning model 11102. Examples of modeling objectives include creating digital replicas capable of displaying throughput dynamics on an assembly line, which may include collecting, simulating, and modeling thermal, electrical, component wear and other metrics of a conveyor belt, assembly machine, one or more product and other components of a transaction ecosystem, and the like. The machine learning model 111102 may be used to learn to determine which types of sensor data need to be processed as analog data for transmission to the digital twin system 11120 to implement such a model. In some embodiments, the machine learning model 11102 may analyze which types of sensor data are being collected, the quality and quantity of sensor data being collected, and what the sensor data being collected represents; decisions, predictions, analyses, and/or determinations may be made as to which types of sensor data are relevant and/or irrelevant to achieving the modeling objective; decisions, predictions, analyses, and/or determinations may be made to prioritize, improve, and/or achieve the quality and quantity of sensor data processed as analog data for use by digital twin system 11120 to achieve modeling goals.
In some embodiments, a user of the information technology system may input modeling targets into the machine learning model 11102. The machine learning model 11102 may learn to analyze the training data to output suggestions to a user of the information technology system as to which types of sensor data are most relevant to achieving the modeling objective, e.g., one or more types of sensors located in, on, or near a business entity or multiple business entities that are relevant to achieving the modeling objective are sufficient and/or insufficient to achieve the modeling objective, and how different configurations of the types of sensors (e.g., by adding, removing, or repositioning sensors) better facilitate the machine learning model 11102 and the digital twin system 11120 achieving the modeling objective. In some embodiments, the machine learning model 11102 may automatically increase or decrease the collection rate, processing, storage, sampling rate, bandwidth allocation, bit rate, and other attributes of sensor data collection to achieve or better achieve modeling goals. In some embodiments, the machine learning model 11102 may suggest or predict to a user of the information technology system regarding: the collection rate, processing, storage, sampling rate, bandwidth allocation, bit rate, and other attributes of sensor data collection are increased or decreased to achieve or better achieve the modeling goals. In some embodiments, the machine learning model 11102 may automatically create and/or propose modeling targets using sensor data, simulation data, previous, current, and/or future digital replica simulations of one or more of the plurality of business entities. In some embodiments, the modeling goals automatically created by the machine learning model 11102 may be automatically implemented by the machine learning model 11102. In some embodiments, the modeling goals automatically created by the machine learning model 11102 may be proposed to a user of the information technology system and only implemented after acceptance and/or partial acceptance by the user, e.g., after modification of the proposed modeling goals by the user.
In some embodiments, the user may enter one or more modeling targets by entering one or more modeling commands, or the like, into the information technology system. The one or more modeling commands may include, for example: commands for the machine learning model 11102 and the digital twin system 11120 to create a digital replica simulation of a trading entity or a group of trading entities; the digital replica simulation is set to be a command of one or more of real-time simulation and hypothetical simulation. The modeling commands may also include, for example, parameters regarding what type of sensor data should be used, the sampling rate of the sensor data, and other parameters regarding the sensor data used in one or more digital replica simulations. In some embodiments, the machine learning model 11102 may be used to predict modeling commands, for example, by using previous modeling commands as training data. The machine learning model 11102 may present predictive modeling commands to users of the information technology system to facilitate simulation, etc., of one or more of the transaction entities, which may be useful for management of the transaction entities and/or to enable users to easily identify potential problems or possible improvements to the transaction entities. The system shown in FIG. 111 may include a transaction management platform and an application.
In some embodiments, the machine learning model 11102 may be used to evaluate a set of hypothesis simulations of one or more of the trading entities. The set of hypothetical simulations may be created by the machine learning model 11102 and the digital twin system 11120 due to: one or more modeling commands; one or more modeling objectives, one or more modeling commands, predictions of the machine learning model 11102, or a combination thereof. The machine learning model 11102 may evaluate the set of hypothesis simulations based on one or more metrics defined by the user, one or more metrics defined by the machine learning model 11102, or a combination thereof. In some embodiments, the machine learning model 11102 may evaluate each hypothesis simulation in the set of hypothesis simulations independently of each other. In some embodiments, the machine learning model 11102 may evaluate one or more hypothesis simulations in the set of hypothesis simulations relative to each other, such as by ranking the hypothesis simulations or creating a hierarchy of hypothesis simulations based on one or more metrics.
In some embodiments, the machine learning model 11102 may include one or more model interpretable systems to facilitate human understanding of the outputs of the machine learning model 11102, as well as information and insights related to the cognition and processes of the machine learning model 11102, i.e., the one or more model interpretable systems enable a human to understand not only what the machine learning model 11102 is outputting, but also why the machine learning model 11102 will output its outputs, and what processes cause the machine learning model 11102 to form these outputs. The one or more model interpretable systems may also be used by a human user to improve and guide the training of the machine learning model 11102 to help debug the machine learning model 11102 to help identify deviations in the machine learning model 11102. The one or more model interpretable systems may include one or more of: linear regression, logistic regression, generalized Linear Model (GLM), generalized Additive Model (GAM), decision trees, decision rules, ruleFit, naive bayes classifier, K nearest neighbor algorithm, partial dependency graph, individual condition expectation graph (ICE), cumulative local effect (ALE) graph, feature interaction, permuted feature importance, global surrogate model, local surrogate (LIME) model, scope rules (i.e., anchor points), sharley values, sharley additive interpretation (SHAP), feature visualization, web-based or any other suitable profiling machine learning interpretable implementation. In some embodiments, the one or more model interpretable systems may include a model dataset visualization system. The model dataset visualization system is used to automatically provide visual analysis to a human user of the information technology system regarding the sensor data, simulation data, and value distributions of the data nodes of the machine learning model 11102.
In some embodiments, the machine learning model 11102 may include and/or implement an embedded model interpretable system, such as a Bayesian Case Model (BCM) or a glass box model. The bayesian case model uses bayesian case based reasoning, prototype classification, and clustering to help humans understand sensor data, simulation data, and data nodes, etc. of the machine learning model 11102. In some embodiments, the model interpretability system may include and/or implement a glass-box interpretability approach, such as a gaussian process, to help humans understand sensor data, simulation data, and data nodes, etc., of the machine learning model 11102.
In some embodiments, the machine learning model 11102 may include and/or implement testing using concept activation vectors (TCAV). TCAV allows the machine learning model 11102 to learn human-interpretable concepts such as "running," "not running," "powered," "unpowered," "robot," "human," "truck," or "ship" from examples through a process that includes defining concepts, determining concept activation vectors, and computing directional derivatives. By learning human-interpretable concepts, objects, states, etc., TCAV can allow the machine learning model 11102 to output useful information related to the transacting entity and data collected therefrom in a format that is easily understood by human users of the information technology system.
In some embodiments, the machine learning model 11102 may be and/or include an artificial neural network, e.g., a connection-aware system, for "learning" to perform a task by considering examples without explicit programming with task-specific rules. The machine learning model 11102 may be based on a collection of connected units and/or nodes that may behave like artificial neurons, in some respects simulating neurons in the biological brain. These units and/or nodes may each have one or more connections to other units and/or nodes. These units and/or nodes may be used to transmit information (e.g., one or more signals) to other units and/or nodes, process signals received from other units and/or nodes, and forward processed signals to other units and/or nodes. One or more of these units and/or nodes and the connections between them may have one or more digital "weights" assigned. The assigned weights may be used to facilitate learning, i.e., training, of the machine learning model 11102. The assigned weights may increase and/or decrease one or more signals between one or more units and/or nodes, and in some embodiments may have one or more thresholds associated with one or more of the weights. The one or more thresholds may be configured such that: signals are only sent between one or more units and/or nodes if the signals and/or the aggregated signal exceed a threshold. In some embodiments, the units and/or nodes may be assigned to multiple layers, each layer having one or both of an input and an output. The first layer may be configured to receive training data, convert at least a portion of the training data, and transmit signals related to the training data and its conversion to the second layer. The final layer may be used to output estimates, conclusions, artifacts, or other results of the machine learning model 11102 processing one or more inputs. Each layer may perform one or more types of conversion, and one or more signals may pass through one or more layers one or more times. In some embodiments, the machine learning model 11102 may employ deep learning and be modeled and/or configured at least in part as a deep neural network, a deep belief network, a recurrent neural network, and/or a convolutional neural network, such as by being configured to include one or more hidden layers.
In some embodiments, the machine learning model 11102 may be and/or include a decision tree, e.g., a tree-based predictive model, for identifying one or more observations and determining one or more conclusions based on input. These observations can be modeled as one or more "branches" of the decision tree, and these conclusions can be modeled as one or more "branches and leaves" of the decision tree. In some embodiments, the decision tree may be a classification tree that may include one or more branches representing one or more class labels and one or more branches representing one or more feature combinations for directing to the class labels. In some embodiments, the decision tree may be a regression tree. The regression tree may be configured such that one or more target variables may take on continuous values.
In some embodiments, the machine learning model 11102 may be and/or include a support vector machine, e.g., a set of related supervised learning methods, configured for one or both of classification and regression modeling of data. The support vector machine may be used to predict whether a new instance belongs to one or more categories that are configured during training of the support vector machine.
In some embodiments, the machine learning model 11102 may be used to perform regression analysis to determine and/or estimate relationships between one or more inputs and one or more features of the one or more inputs. The regression analysis may include a linear regression in which the machine learning model 11102 may compute a single line according to one or more mathematical criteria to best fit the input data.
In embodiments, inputs to the machine learning model 11102 (e.g., a regression model, a bayesian network, a supervised model, or other type of model) may be tested, for example, by using a set of test data that is independent of the data set used to create and/or train the machine learning model, to test the impact of various inputs on the accuracy of the model 11102, and so forth. For example, inputs to the regression model, including single inputs, pairs of inputs, triples of inputs, etc., may be removed to determine whether none of these inputs would severely impact the success of the model 11102. This can help identify inputs that are actually related (e.g., are linear combinations of the same underlying data), overlapping, etc. The comparison of model success may assist in selection among alternative input data sets that provide similar information, e.g., to identify the input (among several similar inputs) that produces the least "noise" in the model, provides the greatest impact on model effectiveness at the lowest cost, etc. Thus, the impact of input changes and test input changes on model validity may be used to curtail or enhance the model performance of any machine learning system described in this disclosure.
In some embodiments, the machine learning model 11102 may be and/or include a bayesian network. The bayesian network can be a probabilistic graph model for representing a set of random variables and conditional independence of the set of random variables. The bayesian network can be used to represent the random variables and the conditional independence by directed acyclic graphs. The bayesian network can include one or both of a dynamic bayesian network and an influence graph.
In some embodiments, the machine learning model 11102 may be defined by supervised learning, i.e., one or more algorithms for building a mathematical model of a set of training data containing one or more inputs and desired outputs. The training data may comprise a set of training examples, each training example having one or more inputs and a desired output, i.e. a supervisory signal. Each training example may be represented in the machine learning model 11102 by an array and/or a vector (i.e., a feature vector). The training data may be represented in a matrix in the machine learning model 11102. The machine learning model 11102 may learn one or more functions by iteratively optimizing an objective function to learn to predict outputs associated with new inputs. After optimization, the objective function enables the machine learning model 11102 to accurately determine the output of inputs other than those contained in the training data. In some embodiments, the machine learning model 11102 may be defined by one or more supervised learning algorithms (e.g., active learning, statistical classification, regression analysis, and similarity learning). Active learning may include interactively querying a user and/or information source through the machine learning model 11102 to tag new data points with desired outputs. Statistical classification may include identifying, by the machine learning model 11102, a set of sub-categories, i.e., sub-populations, to which a new observation belongs based on a training data set containing observations having known categories. The regression analysis may include estimating, by the machine learning model 11102, the relationship between the dependent variable (i.e., the outcome variable) and one or more independent variables (i.e., the predictor, covariates, and/or features). Similarity learning may include learning from examples by the machine learning model 11102 using a similarity function designed to measure the degree of similarity or correlation of two objects.
In some embodiments, the machine learning model 11102 may be defined by unsupervised learning, i.e., one or more algorithms for building a mathematical model that contains only one set of data of the input by looking for structures in the data (e.g., groupings or clusters of data points). In some embodiments, the machine learning model 11102 may learn from test data (i.e., training data) that has not been labeled, classified, or categorized. Unsupervised learning algorithms may include identifying commonalities in training data through the machine learning model 11102 and learning by reacting to commonalities identified by the presence or absence of new data. In some embodiments, the machine learning model 11102 may generate one or more probability density functions. In some embodiments, the machine learning model 11102 may learn by performing a cluster analysis, such as by assigning a set of observations into subsets (i.e., clusters) according to one or more pre-specified criteria (e.g., according to similarity measures in which internal compactness, separation, estimated density, and/or graph connectivity are factors).
In some embodiments, the machine learning model 11102 may be defined by semi-supervised learning, i.e., using one or more algorithms of training data, some of which may lack training labels. Semi-supervised learning may be weakly supervised learning, where training labels may be noisy, limited, and/or inaccurate. The generation of noisy, limited, and/or inaccurate training labels may be less costly and/or less labor intensive, thereby enabling the machine learning model 11102 to be trained based on a larger training data set at less cost and/or effort.
In some embodiments, the machine learning model 11102 may be defined by reinforcement learning, e.g., one or more algorithms using dynamic programming techniques, such that the machine learning model 11102 may be trained to maximize the cumulative reward by taking action in the environment. In some embodiments, the training data is represented as a Markov decision process.
In some embodiments, the machine learning model 11102 may be defined by self-learning, where the machine learning model 11102 is used to train using training data without external rewards and without external teaching, for example, by employing a Cross Adaptive Array (CAA). CAA may compute decisions about the actions and/or emotions of the resulting situation in an interleaved manner, driving the teaching of the machine learning model 11102 through interactions between cognition and emotion.
In some embodiments, the machine learning model 11102 may be defined by feature learning, i.e., one or more algorithms for discovering increasingly accurate and/or appropriate representations of one or more inputs (e.g., training data) provided during training. Feature learning may include training by principal component analysis and/or cluster analysis. The feature learning algorithm may include attempting to retain the input training data by the machine learning model 11102 while also transforming the input training data so that the transformed input training data is useful. In some embodiments, the machine learning model 11102 may be used to transform input training data prior to performing one or more classifications and/or predictions of the input training data. Thus, the machine learning model 11102 may be used to reconstruct input training data from one or more unknown data generation distributions without having to conform to an unreasonable configuration of the input training data from the distributions. In some embodiments, the feature learning algorithm may be performed by the machine learning model 11102 in a supervised, unsupervised, or semi-supervised manner.
In some embodiments, the machine learning model 11102 may be defined by anomaly detection, i.e., by identifying rare and/or outlier instances of one or more items, events, and/or observations. These rare and/or outlier instances may be identified by instances that are significantly different from the patterns and/or attributes of most training data. Unsupervised anomaly detection may include detecting anomalies in the unlabeled training data set by the machine learning model 11102 under the assumption that most of the training data is "normal". Supervising the anomaly detection may include training a data set, wherein at least a portion of the training data has been labeled as "normal" and/or "anomalous".
In some embodiments, the machine learning model 11102 may be defined by robotic learning. Robot learning may include generating one or more courses through the machine learning model 11102, which are a sequence of learning experiences, and cumulatively acquiring new skills through exploration guided by the machine learning model 11102 and social interaction of the machine learning model 11102 with humans. Acquisition of new skills may be facilitated by one or more guidance mechanisms (e.g., active learning, maturation, motor coordination, and/or simulation).
In some embodiments, the machine learning model 11102 may be defined by association rule learning. Association rule learning may include discovering relationships between variables in the database through the machine learning model 11102 to identify strengths using some "interestingness" metric. Association rule learning may include identifying, learning, and/or evolving rules to store, manipulate, and/or apply knowledge. The machine learning model 11102 may be used to learn by identifying and/or utilizing a set of relationship rules that collectively represent the knowledge captured by the machine learning model 11102. Association rule learning may include learning one or more of a classifier system, inductive logic programming, and artificial immune system. A learning classifier system is an algorithm that can combine a discovery component (e.g., one or more genetic algorithms) with a learning component (e.g., one or more algorithms for supervised learning, reinforcement learning, or unsupervised learning). Inductive logic programming may include the machine learning model 11102 using logic programming to represent rule learning of one or more of input examples, background knowledge, and assumptions determined by the machine learning model 11102 during training. The machine learning model 11102 may be used to derive a hypothetical logic program that contains all the positive examples, given the encoding of known background knowledge and a set of examples represented as a logical database of facts.
Referring to FIG. 112, a compliance system 11200 that facilitates using a distributed ledger and cryptographic monetary license check rights is depicted. As used herein, personality may refer to an entity's ability to control the use of its identity for business purposes. The term entity as used herein may refer to an individual or organization (e.g., university, school, sports team, company, etc.) who agrees to grant their personality rights unless the context dictates otherwise. This may include the ability of an entity to control the use of its name, image, similarity, sound, etc. For example, individuals exercising their personality for business purposes may include appearing in businesses, television programs, or movies, making sponsored social media posts (e.g., instagram posts, facebook posts, twitter tweets, etc.), appearing their names on clothing (e.g., jerseys, shirt, jersey, etc.) or other merchandise, appearing in video games, and so forth. In an embodiment, an individual may refer to a student athlete or a professional athlete, but may also include other categories of individuals. While the present description makes reference to NCAA, the system may be used to monitor and facilitate transactions involving other individuals and organizations. For example, the system may be used in the context of professional sports, where organizations may utilize sponsorship and other licensing agreements to circumvent payroll caps or other tournament rules (e.g., international equity competitive rules).
In an embodiment, the compliance system 11200 maintains one or more digital ledgers that record transactions relating to personality license of an entity. In embodiments, the digital ledger may be a distributed ledger distributed among a set of computing devices 11270, 11280, 11290 (also referred to as nodes), and/or may be encrypted. In other words, each participating node may store a copy of the distributed ledger. An example of a digital ledger is a blockchain ledger. In some embodiments, the distributed ledger is stored on a set of common nodes. In other embodiments, the distributed ledger is stored on a set of white-listed participant nodes (e.g., on servers participating in a university or sports team). In some embodiments, the digital ledger is maintained privately via a compliance system 11200. The digital ledger maintenance means provided by the latter configuration is more energy-efficient; while the former configuration (e.g., distributed ledger) provides a digital ledger maintenance means that is more secure/verifiable.
In an embodiment, the distributed ledger may store tokens. The token may be a cryptocurrency token that is transferrable to the licensor and the licensee. In some embodiments, the distributed ledger may store ownership data for each token. Tokens (or portions thereof) may be owned by a compliance system, an administrative organization (e.g., NCAA), a licensor, a licensee, a sports team, an institution, an individual, and so forth. In an embodiment, the distributed ledger may store event records. The event record may store information about events associated with entities related to the compliance system. For example, the event record may record an agreement the two parties have signed, a situation where the licensor has fulfilled an obligation, a situation where the licensor has allocated funds to the licensor based on the licence, a situation where the licensor has not fulfilled an obligation, allocation of funds to an entity associated with the licensee (e.g., a teammate, organization, sports team, etc.), and the like.
In an embodiment, the digital ledger may store intelligent contracts that govern agreements between licensees and licensees. As described herein, a licensee may be an organization or individual wishing to enter into a licensor personality license agreement. Examples of licensees may include, but are not limited to: an automobile dealer wishing to show a star student athlete in a printed advertisement, a company wishing to show a likeness of a licensor (e.g., athlete and/or team) in a commercial, a video game production company wishing to use a team name, team clothing, athlete name and/or number in a video game, a company wishing to use a team name, athlete name or number in a game, a shoe maker wishing to speak a sports shoe for the athlete, a television show maker wishing to show an athlete in a television show, etc. In an embodiment, compliance system 11200 generates intelligent contracts that record agreements between individuals and licensees and facilitate the transfer of consideration (e.g., funds) each time an incident approves an individual for fulfilling its requirements set forth in the agreement. For example, the athlete may agree to appear in the advertisement on behalf of a local car dealer. The smart contract in this example may include an identifier of the athlete (e.g., a personal ID and/or a personal account ID), an identifier of an organization (e.g., an organization ID and/or an organization account ID), a requirement of the individual (e.g., appearing in a commercial, making a sponsored social media post, appearing at an in-person signature, etc.), and a consideration (e.g., a monetary amount). In an embodiment, the smart contract may include additional terms. In an embodiment, the additional terms may include an allocation rule defining a manner of allocating the consideration to the athlete and one or more other parties (e.g., agents, managers, universities, sports teams, teammates, etc.). For example, in the case of student athletes, a smart contract may define a division between a licensed athlete, a sports system for the student athlete to learn about, and a teammate for the student athlete. In a particular example, a university may have a policy that requires players appearing in any advertisement to divide funds in a 60/20/20 division, where 60% of the funds are allocated to students ' players appearing in the advertisement, 20% of the funds are allocated to the sports department, and 20% of the funds are allocated to the students ' players ' teammates. When the smart contract verifies that the athlete has performed his duties about the smart contract (e.g., presented in an advertisement), the smart contract may transfer the contracted amount from the licensee's account to the athlete's account and any other entities that may allocate a proportion of the funds in the smart contract (e.g., the sports department and teammates).
In an embodiment, compliance system 11200 facilitates the transfer of funds using a cryptographic currency. In embodiments, the cryptocurrency is mined by the participant nodes and/or generated by the compliance system. The cryptocurrency may be an established type of cryptocurrency (e.g., bitcoin, ethercurrency, lexest, etc.), or may be a proprietary cryptocurrency. In some embodiments, the cryptocurrency is a hook cryptocurrency that hooks into a particular legal currency (e.g., hooks into U.S. dollars, pounds, euros, etc.). For example, a single unit of cryptocurrency (also referred to as a "coin") may be hooked up with a single unit of legal currency (e.g., U.S. dollars). In an embodiment, the licensee may exchange the fiat currency for a corresponding amount of cryptocurrency. For example, if the cryptocurrency is hooked up to U.S. dollars, the licensee may exchange a certain amount of U.S. dollars for a corresponding amount of cryptocurrency. In an embodiment, the compliance system 11200 may maintain a percentage of real-world currency as a transaction fee (e.g., 5%). For example, in exchange for $ 10000, the compliance system 11200 may allocate $ 9500 worth of cryptocurrency to the licensee's account and may charge $ 5000 as the transaction fee. Once the cryptocurrency is deposited into the account of the licensee, the licensee can conduct a transaction with the person.
In an embodiment, compliance system 11200 may allow an organization to create an intelligent contract template that defines one or more conditions/restrictions for a contract. For example, an organization may predefine the allocation between licensees, organizations, and any other individuals (e.g., coaches, teammates, representatives). Additionally or alternatively, the organization may contract for a minimum and/or maximum amount of money. Additionally or alternatively, an organization may place restrictions on when a protocol may be signed and/or executed. For example, an athlete may be restricted from appearing in a commercial or advertising campaign during a season and/or during an examination. These details may be stored in organization data store 11256A, and the organization may set other conditions/restrictions in the smart contracts. In these embodiments, individuals and licensees wishing to enter into an agreement must use intelligent contract templates provided by the organization to which the individual belongs. In other words, if the smart contract is defined or otherwise approved by an organization, the compliance system 11200 may allow only individuals having an active relationship with the organization (e.g., racing in a college's sports team) to participate in the smart contract.
In an embodiment, the compliance system 11200 manages clearing house flows that approve potential licensees. The licensee may provide information related to the licensee before the licensee can participate in the agreement facilitated by the compliance system 11200. This may include tax ID numbers, entity names, company information (e.g., presence and type), lists of key people (e.g., board of directors, high administration, board members, approved decisionmakers, etc.), and any other suitable information. In an embodiment, a potential licensee may be required to sign (e.g., electronically or ink) a document indicating that the organization will be reluctant to use compliance system 11200 to circumvent any rules, laws, or regulations (e.g., they will not circumvent the NCAA regulations). In an embodiment, the compliance system 11200 or another entity (e.g., NCAA) may verify the licensee. Once verified, this information is stored in the licensee data store 11256B, and the licensee can participate in the transaction.
In an embodiment, once a licensor joins an organization (e.g., signs a sports award with a university), the compliance system 11200 may create an account for the licensor. Once the licensor is verified as being associated with the organization, the compliance system 11200 may create an account for the licensor and may create a relationship between the individual and the organization, whereby the licensor may be required to use the intelligent contracts approved or provided by the organization. If the licensor joins another organization (e.g., goes to another school), the compliance system 11200 may terminate the relationship with the previous organization and may create a new relationship with the other organization. Similarly, once the approver is no longer associated with any organization (e.g., athlete graduation, entry into a professional tournament, retirement, etc.), the compliance system 11200 may prevent the approver from engaging in transactions on the compliance system 11200.
In an embodiment, the compliance system 11200 may provide a graphical user interface that allows a user to create smart contracts that manage personal rights permissions. In these embodiments, the compliance system allows a user (e.g., a licensor) to select an intelligent contract template. In some embodiments, the compliance system 11200 may restrict the user from selecting only smart contract templates associated with the licensor's organization. In embodiments, the graphical user interface allows the user to define certain terms (e.g., one or more types of obligations imposed on the licensor, the amount to be paid, the date the licensor obligation must be completed, the location where the obligation is completed, and/or other suitable terms). When a user provides input for parameterizing an intelligent contract template, the compliance system 11200 may generate an intelligent contract by parameterizing one or more variables in the intelligent contract using the provided input. Upon parameterizing an instance of an intelligent contract, the compliance system 11200 may deploy the intelligent contract. In some embodiments, the compliance system 11200 may deploy the intelligent contracts by broadcasting parameterized intelligent contracts to participant nodes, which in turn may update each respective instance of the distributed ledger with the new intelligent contracts. In some embodiments, the licensor's authority must approve the parameterized smart contract before it can be deployed to the distributed ledger.
In an embodiment, the compliance system 11200 may provide a graphical user interface to verify the fulfillment of the obligation by the licensor. In some of these embodiments, the compliance system 11200 may include an application program accessed by the licensor that allows the licensor to prove that it is fulfilling obligations. In some of these embodiments, the application may allow the user to record the location to which the licensor goes (e.g., the location where a movie or photo was taken), upload a record (e.g., a screenshot of a social media post), or provide other corroborative evidence that the licensor has carried out his obligations related to licensing the transaction. In this way, the licensor can prove that it completed the tasks required by the license agreement. In some embodiments, the application may interact with the wearable device, or may capture other digital information, such as social media posts of the user (e.g., licensor) to collect evidence that the licensor supports or refutes purporting that it fulfills obligations under the transaction agreement. In an embodiment, the witness evidence collected by the application may be recorded by the application and stored on a distributed ledger as a licensor data store 11256C.
In an embodiment, the compliance system 11200 (or a smart contract issued in conjunction with the compliance system 11200) may complete a transaction related to a smart contract that governs the licensing of the licensing authority after verifying that the licensing authority has fulfilled its obligation defined in the agreement. As previously described, the licensor may use an application to provide evidence of fulfillment of the obligation of the present agreement. Further, the licensee may provide proof that the licensor has fulfilled his obligation (e.g., using an application). In an embodiment, a smart contract for a management agreement may receive a verification that a licensor has fulfilled its obligations defined by the agreement. In response, the smart contract may release (or initiate release of) the cryptocurrency amount defined in the smart contract. The cryptocurrency amount may be allocated to the account of the licensor and any other party defined in the agreement (e.g., the licensor's teammate, the licensor's plan, the regulatory body, etc.).
In an embodiment, the compliance system 11200 is used to perform the analysis and provide reports to regulatory agencies and/or other entities (e.g., other organizations). In these embodiments, the analysis may be used to identify individuals who potentially circumvent the rules and regulations of the regulatory body. Further, in some embodiments, transaction records may be maintained on a distributed ledger, whereby different organizations may be able to view agreements that individuals have signed in with other organizations, such that increased levels of transparency and oversight may prevent individuals, organizations, and/or licensees from circumventing rules and regulations.
In an embodiment, the compliance system 11200 may train and/or utilize machine learning models to identify potential instances of avoidance rules or ordinances. In these embodiments, the compliance system 11200 may train the machine learning model using the result data. Examples of result data may include data related to a set of transactions where an organization (e.g., a sports team or university), a licensee (e.g., a company), and/or a licensor (e.g., an athlete) are determined to avoid rules or regulations, and data related to a set of transactions, and/or a licensee is found to comply with rules and regulations. Examples of machine learning models include neural networks, regression-based models, decision trees, random forests, hidden markov models, bayesian models, and the like. In an embodiment, the compliance system 11200 may utilize the machine learning model by obtaining a set of records from a distributed ledger related to transactions by licensees, and/or organizations (e.g., sports teams or universities). The compliance system may extract relevant features such as the amount paid by the licensee to a particular licensor, the amount paid by other licensees in other sports teams, the affiliations of the licensees, the amount paid by other licensees to the licensee, etc., and may feed the features back to the machine learning model. The machine learning model may issue a score indicating the likelihood that the transaction is legitimate (or illegitimate) based on the extracted features. In an embodiment, the compliance system 11200 may provide a notification to the interested party (e.g., a regulatory agency) when the output of the machine learning model indicates that the transaction may be illegal.
Figure 113 illustrates an example system 11300 for electronically facilitating licensing of one or more personality rights of a licensor in accordance with some embodiments of the present disclosure. In some embodiments, system 11300 may include one or more computing platforms 11302. Computing platform 11302 may be utilized to communicate with one or more remote platforms 11304 in accordance with a client/server architecture, a peer-to-peer architecture, and/or other architectures. Remote platform 11304 may be used to communicate with other remote platforms via computing platform 11302 and/or according to a client/server architecture, peer-to-peer architecture, and/or other architectures. A user may access the system 11300 via a remote platform 11304.
In an embodiment, computing platform 11302 may be configured by machine-readable instructions 11306. The machine-readable instructions 11306 may include one or more instruction modules. The instruction modules may include computer program modules. The instruction modules may include one or more of an access module 11208, a funds management module 11212, a ledger management module 11216, a verification module 11218, an analysis module 11220, and/or other instruction modules.
In an embodiment, the access module 11208 may be configured to receive an access request from a licensee to obtain approval of the permission checkers rights from a set of available licensees. In an embodiment, the access module 11208 may be configured to selectively grant access to a licensee based on the access request. For example, the access module 11208 may receive a name of a potential licensee (e.g., a company name), a list of principals of the potential licensee (e.g., high-master and/or owner), a location of the licensee, affiliations of the licensee and its principals, and the like. In embodiments, the access module 11208 may provide this information to the access grantor and/or may feed this information into an artificial intelligence system that reviews potential licensee. In an embodiment, the access module 11208 may selectively grant access to a licensor by verifying that the licensee is allowed to associate with a set of licensees, including the licensor, based on the set of dependencies. Selectively granting access to the licensor may include approving the licensee to associate with the set of licensees in response to verifying that the licensee is allowed to associate with the set of licensees. The set of affiliations of the licensee may include an organization to which the licensee belongs or an organization donated to or owned by a party associated with the licensee.
In an embodiment, the funds management module 11212 may be operable to receive a deposit confirmation of the amount of funds from the licensee. In some embodiments, the funds management module 11212 may be operable to issue to an account of the licensee an amount of cryptocurrency corresponding to the amount of funds deposited by the licensee. In an embodiment, the funds management system 11212 may be used to escrow the value amount of the cryptocurrency from the account of the licensee until the funds are released by the smart contract.
In an embodiment, the ledger management module 11216 may be operable to receive an intelligent contract request to create an intelligent contract that manages the licensee's permissions to one or more personalities of the licensor. In an embodiment, the ledger management module 11216 may be operable to generate an intelligent contract based on the intelligent contract request. The smart contract may be generated using a smart contract template provided by a third party of interest (e.g., a university, a regulatory agency, etc.) and one or more parameters provided by a user (e.g., a licensor's team, an organization, and/or a licensee). By way of non-limiting example, the third party of interest may be a university, sports team, or university sports governing organization. The smart contract request may indicate one or more terms including a bid amount of cryptocurrency to be paid to the licensor in exchange for one or more obligations of the licensor. In an embodiment, the ledger management module 11216 may be used to deploy intelligent contracts to distributed ledgers. The distributed ledger can be audited by a set of third parties, including interested third parties. The distributed ledger can be a public ledger. The distributed ledger can be a specialized ledger that is only kept on computing devices associated with third parties of interest. In an embodiment, the distributed ledger can be a blockchain.
In embodiments, the verification module 11218 may be used to verify that the licensor has fulfilled one or more obligations. In some embodiments, verifying that the licensor has fulfilled the one or more obligations may include receiving location data from a wearable device associated with the licensor, and verifying that the licensor has fulfilled the one or more obligations based on the location data, whereby the location may be used to display that the licensor is in a particular location at a particular time (e.g., taking a picture or photography). In an embodiment, verifying that the licensor may have fulfilled the one or more obligations includes receiving social media data from a social media website, and verifying that the licensor has fulfilled the one or more obligations based on the social media data, whereby the social media data may be used to indicate that the licensor has made the desired social media post. In an embodiment, verifying that the licensor may have fulfilled the one or more obligations includes receiving media content from an external data source, and verifying that the licensor has fulfilled the one or more obligations based on the media content, whereby the licensor and/or licensee may upload the media content to prove that the licensor has appeared in the media content. By way of non-limiting example, the media content may be one of a video recording, a photograph, or an audio recording. In embodiments, the verification module 11218 may generate and output an event record to the participating node when the licensor is verified to have fulfilled its obligations. In embodiments, the verification module 11218 may generate and output to the participating nodes an event record indicating that the compliance system 11200 has received corroborative evidence (e.g., social media data, location data, and/or media content) that the licensor has fulfilled its obligations. In an embodiment, the validation module 11218 may be operable to output an event record to the distributed ledger indicating completion of the approval transaction defined by the smart contract.
In an embodiment, the verification module 11218 may be operable to verify, via the smart contract, that the licensor has fulfilled the one or more obligations. In embodiments, the verification module 11218 and/or the smart contract may be operable to release at least a portion of the cryptocurrency bid amount into the licensor account of the licensor in response to receiving verification that the licensor has fulfilled the one or more obligations. Releasing at least a portion of the consideration amount of the cryptocurrency into the licensee account of the licensee may include identifying an allocation smart contract associated with the licensee and allocating the cryptocurrency consideration amount according to allocation rules. As non-limiting examples, the additional entities may include one or more of a teammate of the licensor, a coach of the licensor, a team of the licensee, a university of the licensee, and a regulatory agency (e.g., NCAA).
In an embodiment, the analysis module 11220 may be configured to obtain a set of records from the distributed ledger indicating completion of a set of respective transactions. The set of records may include a record indicating that a transaction defined by the smart contract was completed. The analysis module 11220 may determine whether an organization associated with the licensor may violate one or more regulations based on the set of records and the fraud detection model. The fraud detection model may be trained using training data indicative of transactions allowed and fraudulent transactions.
In some embodiments, a distribution intelligence contract may define distribution rules governing the manner in which funds resulting from the licensing of one or more personalities are to be distributed between a licensor and one or more additional entities.
In some embodiments, the specification may be provided by one of NCAA, FIFA, NBA, MLB, NFL, MLS, NHL, and the like, as non-limiting examples.
In some embodiments, computing platforms 11302, remote platforms 11304, and/or external resources 11334 may be operably linked via one or more electronic communication links. Such electronic communication links may be established, for example, at least in part via a network such as the internet and/or other networks. It should be understood that this is not intended to be limiting, and that the scope of the present disclosure includes implementations in which computing platform 11302, remote platforms 11304, and/or external resources 11334 may be operatively linked via some other communications medium.
A given remote platform 11304 may include one or more processors for executing computer program modules. Computer program modules may be used to enable an expert or user associated with a given remote platform 11304 to connect with compliance system 11200 and/or external resources 11334 and/or provide other functionality attributed herein to the remote platform. 11304. As non-limiting examples, a given remote platform 11304 and/or a given computing platform 11302 may include one or more of a server, a desktop computer, a laptop computer, a handheld computer, a tablet computing platform, a netbook, a smartphone, a gaming console, and/or other computing platform.
The external resources 11334 may include sources of information outside of the compliance system 11200, external entities participating in the compliance system 11200, and/or other resources. In some embodiments, some or all of the functionality attributed herein to external resource 11334 may be provided by resources included in compliance system 11200.
Electronic storage 11336 may include non-transitory storage media that electronically stores information. The electronic storage media of electronic storage 11336 may include one or both of system memory that is integrated with (i.e., substantially non-removable) computing platform 11302 and/or removable storage that is removably connectable to computing platform 11302 via, for example, a port (e.g., a USB port, a firewire port, etc.) or a drive (e.g., a disk drive, etc.). Electronic storage 11336 may include one or more of optically readable storage media (e.g., optical disks, etc.), magnetically readable storage media (e.g., magnetic tape, hard disk drive, floppy disk drive, etc.), electrical charge-based storage media (e.g., EEPROM, RAM, etc.), solid-state storage media (e.g., flash memory disks, etc.), and/or other electronically readable storage media. Electronic storage 11336 can include one or more virtual storage resources (e.g., cloud storage, virtual private networks, and/or other virtual storage resources). Electronic storage 11336 may store software algorithms, information determined by processor 11338, information received from computing platform 11302, information received from remote platform 11304, and/or other information that enables computing platform 11302 to function as described herein.
Processor 11338 may be used to provide information processing capabilities in computing platform 11302. Thus, processor 11338 may include one or more of a digital processor, an analog processor, a digital circuit designed to process information, an analog circuit designed to process information, a state machine, and/or other mechanisms for electronically processing information. Although processor 11338 is shown in fig. 113 as a single entity, this is for illustration purposes only. In some embodiments, processor 11338 may include multiple processing units. These processing units may be physically located within the same device, or processor 11338 may represent processing functionality of multiple devices operating in coordination. Processor 11338 may be used to execute modules 11208, 11212, 11216, 11218, 11220, and/or other modules. The processor 11338 may be used to process data via software; hardware firmware; some combination of software, hardware, and/or firmware; and/or other mechanisms for configuring processing capabilities on processor 11338 execute modules 11208, 11212, 11216, 11218, 11220, and/or other modules. As used herein, the term "module" may refer to any component or collection of components that perform the function attributed to the module. This may include one or more physical processors, processor-readable instructions, circuitry, hardware, storage media, or any other component during execution of the processor-readable instructions.
It should be understood that although modules 11208, 11212, 11216, 11218, and 11220 are shown in fig. 113 as being implemented within a single processing unit, in implementations in which processor 11338 includes multiple processing units, one or more of modules 11208, 11212, 11216, 11218, and 11220 may be implemented remotely from the other modules. The description of the functionality provided by the different modules 11208, 11212, 11216, 11218, and 11220 described below is for illustrative purposes, and is not intended to be limiting, as any of modules 11208, 11212, 11216, 11218, and/or 11220 may provide more or less functionality than is described. For example, one or more of modules 11208, 11212, 11216, 11218, and/or 11220 may be eliminated, and some or all of its functionality may be provided by other ones of modules 11208, 11212, 11216, 11218, and/or 11220. As another example, processor 11338 may be used to execute one or more additional modules that may perform some or all of the functionality attributed below to one of modules 11208, 11212, 11216, 11218, and/or 11220.
Fig. 114 and/or 115 illustrate an example method 11400 for electronically facilitating licensing of one or more personality rights of a licensor in accordance with some embodiments of the present disclosure. The operation of method 11400 presented below is for illustrative purposes. In some embodiments, method 11400 may be implemented using one or more additional operations not described and/or without one or more of the operations discussed. Further, the order in which the operations of method 11400 are illustrated in fig. 114 and/or 115 and described below is not intended to be limiting.
In some embodiments, method 11400 may be implemented in one or more processing devices (e.g., a digital processor, an analog processor, a digital circuit designed to process information, an analog circuit designed to process information, a state machine, and/or other mechanisms for electronically processing information).
The one or more processing devices may include one or more devices that perform some or all of the operations of method 11400 in response to instructions stored electronically on an electronic storage medium. The one or more processing devices may include one or more devices configured via hardware, firmware, and/or software, which are specifically designed to perform one or more operations of method 11400.
Fig. 114 shows a method 11400 according to one or more embodiments of the present disclosure.
At 11402, the method may include receiving an access request from a licensee to obtain approval of the permission check right from a set of available licensees. In accordance with one or more embodiments, operation 11402 may be performed by one or more hardware processors configured according to machine-readable instructions, the one or more hardware processors including a module that is the same as or similar to access module 11208.
At 11404, the method includes selectively granting access to the licensee based on the access request. In accordance with one or more embodiments, operation 11404 may be performed by one or more hardware processors configured according to machine-readable instructions, the one or more hardware processors including a module that is the same as or similar to access module 11208.
At 11406, the method includes receiving a deposit confirmation of the amount of funds from the licensee. In accordance with one or more embodiments, operation 11406 may be performed by one or more hardware processors configured according to machine-readable instructions, the one or more hardware processors comprising the same or similar modules as the funds management module 11212.
At 11408, the method includes issuing to an account of the licensee an amount of cryptocurrency corresponding to the amount of funds deposited by the licensee. In accordance with one or more embodiments, the operation 11408 may be performed by one or more hardware processors configured according to machine-readable instructions, the one or more hardware processors comprising the same or similar modules as the funds management module 11212.
Fig. 115 shows a method 11500 according to one or more embodiments of the present disclosure.
At 11522, the method includes receiving a smart contract request to create a smart contract that manages permissions of a licensee for one or more personalities of a licensor. The smart contract request may indicate one or more terms including a bid amount of cryptocurrency to be paid to the licensor in exchange for one or more obligations of the licensor. In accordance with one or more embodiments, operation 11522 may be performed by one or more hardware processors configured according to machine-readable instructions, the one or more hardware processors comprising the same or similar modules as ledger management module 11216.
At 11524, the method includes generating the intelligent contract based on the intelligent contract request. In accordance with one or more embodiments, operation 11524 may be performed by one or more hardware processors configured according to machine-readable instructions, the one or more hardware processors comprising the same or similar modules as ledger management module 11216.
At 11526, the method includes escrowing a consideration amount of cryptocurrency from the account of the licensee. In accordance with one or more embodiments, the operation 11526 may be performed by one or more hardware processors configured according to machine-readable instructions, the one or more hardware processors comprising the same or similar modules as the funds management module 11212.
At 11528, the method includes deploying the smart contract to a distributed ledger. In accordance with one or more embodiments, operation 11528 may be performed by one or more hardware processors configured according to machine-readable instructions, the one or more hardware processors comprising the same or similar modules as ledger management module 11216.
At 11530, the method includes verifying, by the smart contract, that the licensor has fulfilled the one or more obligations. In accordance with one or more embodiments, operation 11530 may be performed by one or more hardware processors configured according to machine-readable instructions, the one or more hardware processors comprising the same or similar modules as verification module 11218.
At 11532, the method includes releasing at least a portion of the cryptocurrency bid amount into a licensor account of the licensor in response to receiving verification that the licensor has fulfilled the one or more obligations. In accordance with one or more embodiments, operation 11532 may be performed by one or more hardware processors configured according to machine-readable instructions, the one or more hardware processors comprising the same or similar modules as verification module 11218.
At 11534, the method includes outputting a record to the distributed ledger indicating completion of the license transaction defined by the smart contract. In accordance with one or more embodiments, operation 11534 may be performed by one or more hardware processors configured according to machine-readable instructions, the one or more hardware processors comprising the same or similar modules as validation module 11218 and/or ledger management module 11216.
Fig. 116 illustrates a method 11600 according to one or more embodiments.
At 11602, the method includes obtaining a set of records from the distributed ledger indicating that a set of respective transactions has been completed. The set of records may include a record indicating that a transaction defined by the smart contract was completed. According to one or more embodiments, operation 11602 may be performed by one or more hardware processors configured according to machine-readable instructions, the one or more hardware processors including the same or similar modules as analysis module 11220.
At 11604, the method includes determining whether an organization associated with the licensor may violate one or more regulations based on the set of records and the fraud detection model. In accordance with one or more embodiments, operation 11604 may be performed by one or more hardware processors configured according to machine-readable instructions, the one or more hardware processors including a module that is the same as or similar to analysis module 11220.
Referring to fig. 117, a computer-implemented method 11700 for selecting an AI solution for use in a robotic or automated process is described. A computer-implemented method may include receiving one or more functional media 11702. The functional media may include information indicative of brain activity of a worker involved in a task to be automated. The functional medium may be functional imaging, such as MRI, FMRI, etc., from which neocortical active regions may be identified. The functional media may be images, video streams, audio streams, etc., from which the type of brain activity may be inferred. The functional media may be acquired while the worker is performing work or while performing a simulation of work, such as in an augmented reality, virtual reality environment, or on a model of the device and/or environment. Upon receipt, functional media is analyzed 11704 to identify activity levels in at least one brain region 11706. Based on the activity level, brain region parameters and/or activity parameters 11708 are identified. The brain region parameters may represent specific regions of the neocortex, such as the frontal, parietal, occipital and temporal lobes of the neocortex (including the primary visual and auditory cortex), or subdivisions of the neocortex include the ventral prefrontal cortex (broaca region) and the orbital prefrontal cortex. The activity parameters may represent functional areas of the brain, such as visual processing, inductive reasoning, audio processing, olfactory processing, muscle control, and the like. The activity parameter may represent the type of activity in which the worker is involved, e.g. visual processing (watching), audio processing (listening), olfactory processing (sniffing), motor activity, listening to the sound of a device, observing another negotiator, etc. The activity level may represent the intensity or level of activity, e.g. the extent of the brain region involved, the signal strength, whether the brain region is engaged, etc.
Based on one or more of the brain region parameters, the activity parameters, or the activity level, the action parameters may be identified 11710. The action parameters may provide additional information about the activity parameters. For example, the activity parameter indicates motion, and the motion parameter may describe a range of motion, a speed of motion, a repetition of motion, a utilization of muscle memory, smoothness of motion, a flow of motion, a timing of motion, and the like. Based on one or more of the brain region parameters, activity parameters, or activity levels, a component 11712 may be selected to be incorporated into the final AI solution. The components may include one or more of a model, an expert system, a neural network, and the like. After selecting a component of the AI solution, 11714 configuration parameters may be determined. The configuration parameters may be based in part on the type of component selected, brain region parameters, activity level, or action parameters. Configuring and configuring parameters may include selecting an input of a machine learning process, identifying an output to be provided by the machine learning process, identifying an input of an operational solution process 11716, identifying an output of an operational solution process, adjusting a learning parameter, identifying a rate of change, identifying a weighting factor, identifying a parameter for inclusion, identifying a parameter for exclusion of a parameter, setting a threshold for input data, setting an output threshold for operating a robotic process, or setting a parameter threshold. Further, the analysis of functional media 11704 may include identifying a second brain region parameter or a second activity parameter 11718. A component 11720 of the AI solution may be modified based on the second brain region parameter or the second activity parameter. A second component of the 11722AI solution may be selected based on the second brain region parameter or the second activity parameter. The final AI solution can be assembled from the component 11724 or the second component 11726. In an embodiment, the final AI solution may be assembled from the first and second components, optionally with any standard or mandatory components to achieve operation.
Referring to fig. 118, a computer-implemented method 11800 for selecting an AI solution for use in a robotic or automated process is depicted. The method may include receiving a user-related input (11802) including a timestamp and analyzing the user-related input (11804). The user-related inputs may include audio feeds, motion sensors, video feeds, heartbeat monitors, eye trackers, biosensors (e.g., galvanic skin responses), and the like. The analysis may enable identification of a series of user actions and associated activity parameters (11806). A component of the AI solution may be selected based on a user action in a series of user actions (11808). The analysis may enable identification of a second user action (11810) of the series of user actions. Based on the second user action, the selected component for the AI solution may be modified (11812). A second component for the AI solution may be selected based on the second user action (11814). An action parameter may be identified based on the user action and/or the associated activity parameter (11816). For example, if the user action is motion, the action parameters may include range of motion, speed of motion, repetition of motion, utilization of muscle memory, smoothness of motion, flow of motion, timing of motion, and the like. Selected components of the AI solution may be configured based on the action parameters (11818). In an embodiment, at least one device input performed by a user may be received (11820). The device input may be synchronized with the user action based on the timestamp and a correlation between the device input and the determined user action (11819). The component may be modified based on the correlation (11823). Selection of a component of the AI solution may be based in part on a correlation between the device input and the user-related input (11821). The AI solution may be assembled 11822 from the components. The AI solution can be assembled from the second component (11824). In an embodiment, the AI can be assembled from the component and the second component, optionally with any standard or mandatory components to achieve operation.
Referring to fig. 119, an illustrative and non-limiting example of assembling the AI solution 11902 is depicted. Assembled AI solution 11902 may include selected component 11904 and second selected component 11906, as well as other components 11908. Configuration data 11914 for a first selected component and setup data 11912 for a second selected component may be provided. Runtime input data 11910 may be specified as part of a component configuration process. The components may be configured to operate in series (e.g., selected component 11904 and second selected component 11906 receiving inputs from selected component 11904) or in parallel (e.g., second component 11906 and other components 11908). Some components may provide input for other components (e.g., a selection component 11904 that provides input to a second selection component 11906). Multiple components may provide various portions of the overall AI solution output 11918 (e.g., the second selected component 11906 and other components 11908). The description is not meant to be limiting and the final solution may include a different number of components, configuration data and inputs, as well as other components (e.g., sensors, voice modulators, etc.), and may be interconnected in various configurations.
Referring to fig. 120-121, a computer-implemented method for selecting an AI solution for a robotic or automated process is described. The method may include receiving temporal biometric data (12002) of a worker performing a task, and receiving spatiotemporal environmental data (12004) experienced by the worker performing the task. Using the received data, spatiotemporal activity patterns may be identified (12006). Based on the spatiotemporal activity pattern, an activity region of the worker's neocortex may be identified (12008). The type of inference used when performing the task may be identified based on active regions of neocortex and/or biometric data or spatio-temporal environmental data (12010). The components used in the AI solution may be selected 12012 to replicate the inference type. Components of the AI solution may be configured based on the spatiotemporal environment input (12014). It may be determined whether the serial or parallel AI solution is optimal (12016). A set of configuration inputs for the components may be identified (12018), and an ordered input for the components of the AI solution may be identified (12020). Training the machine may include providing various subsets of spatio-temporal environmental inputs to determine appropriate input weights and identify efficiencies from combinations of spatio-temporal environmental inputs (12022). Desired or undesired combinations of spatiotemporal environmental data may also be identified (12024). Based on the identified desired input, the input environmental data may be processed to reduce input noise (e.g., improve the signal-to-noise ratio of the signal of interest), filtered to provide an appropriate input signal to the component, etc. (12026).
With continued reference to fig. 121, a second time biometric data of the same worker performing the task may be received 12102 and a plurality of performed tasks identified from the biometric measurements 12104. Performance parameters may be extracted from biometric measurements (12106), such as worker heart rate, skin current response, etc. In some embodiments, the components may be configured based on the performance parameters (12107). In some embodiments, the second temporal biometric measurement may be provided to the configuration module as a training set (12109). Result data related to the task may be received 12108, and the second temporal biometric data may be correlated 12110 with the received result data. In some embodiments, the component may be selected based at least in part on the relevance (12111). A series of time intervals between each of the plurality of performed tasks may be identified (12112), and a component of the AI solution is configured based on at least one of the time intervals (12114). For example, if a worker checks an object for a long time before moving to the next action, this may indicate complex visual processing as well as psychological processing, and may indicate that the corresponding component of the task is used for depth, fine detail processing, and the like.
Referring to fig. 122, an AI solution selection and configuration system 12202 is depicted. Example selection and configuration system 12202 may include a media input module 12204 structured to receive user-related functionality media 12214. User-related function media 12214 may include images, audio recordings, video feeds, biometric data (e.g., heartbeat data, galvanic skin response data, etc.), motion data, etc., of persons participating in a task to be automated. The media analysis module 12206 may analyze the received media and identify action parameters. The action parameter may represent the type of activity that the person appears to be involved in, such as watching, listening, moving, thinking, etc. In some embodiments, the functional media indicates a type of brain activity of a person participating in a task to be automated, and media analysis module 122206 identifies an activity level in at least one brain region and provides brain region parameters corresponding to the identified activity level in the brain region. The media analysis module may also identify an activity parameter indicative of the level of engagement, such as engagement, non-engagement, activity level, activity type, and the like. The solution selection module 12208 can be configured to select at least one component of the AI solution for the automated process based at least in part on the action parameter, the brain region parameter, or the activity parameter. The brain region parameter or the action parameter may suggest the type of component to be selected, and the activity parameter may suggest the level of processing required by the component. For example, the viewed action parameters would suggest selecting components suitable for visual processing. If the activity parameter represents olfactory processes, the input specification module may identify at least one chemical sensor as an input. If the activity parameter represents a visual process, the input specification module 11216 may identify at least one visual sensor as a robotic input. In some embodiments, the visual sensor may be selected to be sensitive to a portion of the visible spectrum having a wavelength between about 380 and 700 nanometers. If the activity parameter represents auditory processing, the input specification module 11216 may identify at least one microphone as a robotic input. If the activity parameter represents a very high concentration level, the solution selection module 12208 may suggest a level of treatment that will be needed, a location where treatment may occur, and the like. The component configuration module 12210 may configure the components 12212. The configuration component may include: selecting an input of a machine learning process for a selected component, identifying an output to be provided by the machine learning process, identifying an input of an operational solution process, identifying an output of an operational solution process, adjusting a learning parameter, identifying a rate of change, identifying a weighting factor, identifying a parameter for inclusion, identifying a parameter for exclusion of a parameter, setting a threshold for input data, setting an output threshold for operating a robotic process or setting a parameter threshold. The solution assembly module 12218 can assemble the final AI solution based on the one or more selected components, the configuration components, and the desired runtime. Input specification module 12216 may suggest input sources based on selected components, action parameters, brain region parameters, activity parameters, and the like.
Referring to fig. 123, an AI solution selection and configuration system 12302 is depicted. The exemplary selection system 12302 may include an image input module 12304 structured to receive a functional image 12314 of the brain, such as a functional MRI or other magnetic imaging, electroencephalogram (EEG), or other imaging, such as by identifying extensive brain activity (e.g., active wavelength bands, such as delta, theta, alpha, and gamma waves), by identifying a set of brain regions that have been activated and/or deactivated while the worker is performing one of the tasks to be automated. The image input module 12304 can provide a subset of the functional images 12314 to the image analysis module 12306. In some embodiments, the image input module 12304 may perform some pre-processing, such as noise reduction, histogram adjustment, filtering, etc., on the subset of functional images 12314 before providing the subset of functional images 12314 to the image analysis module 12306. The image analysis module 12306 can identify activity levels in at least one brain region and provide brain region parameters based on a subset of the functional images. The brain region parameters may represent specific regions of the neocortex, such as the frontal, parietal, occipital and temporal lobes of the neocortex (including primary visual and auditory cortices), or subdivision of the neocortex (including ventral prefrontal cortex (broucard region) and orbital prefrontal cortex. Brain region parameters may represent functional regions of the brain, such as visual processing, inductive reasoning, audio processing, olfactory processing, muscle control, etc. solution selection module 12308 may select components for an AI solution based on brain region parameters and provide inputs to component configuration module (e.g., select inputs to a machine learning process, identify outputs to be provided by the machine learning process, identify inputs to an operational solution process, identify outputs to operate solution process, adjust learning parameters, identify rates of change, identify weighting factors, identify parameters for inclusion, identify parameters for exclusion, set thresholds for input data, set thresholds for output data or set parameter thresholds for operating a robot process, etc.) component configuration module 12310 may use the inputs to configure component 8978 solution, the specification 8978 may provide a specification to the input module 12308 to create a multiple AI solution assembly module 12316, which may be configured to display a solution assembly module 12308, although it may receive a multiple input solution selection module 12316, which may also receive input solutions, and display a solution selection module 12316, which may display a solution selection module
Referring to fig. 124-125, an AI solution selection and configuration system 12402 is depicted. The example AI solution selection and configuration system 12402 may include an input module 12404 configured to receive various user-related inputs, such as video, audio recordings, heartbeat monitors, galvanic skin response data, motion data, and the like. There may be temporal data associated with the user-related input. The input module 12404 can provide a subset of the user-related input data 12414 to the input analysis module 12406. The analysis module 12406 can include a time analysis module 12418 to identify timing of user-related actions. The time analysis module 12418 may enable identifying timing of user actions. In some embodiments, the input module 12404 may perform some pre-processing on the subset of user-related input information 12414, such as noise reduction, correlation between input data types, etc., before providing the subset of user-related input data 12414 to the input analysis module 12406. Input analysis module 12406 can identify the type of brain activity (e.g., visual processing, auditory processing, olfactory processing, motor control, etc.) and activity intensity level being engaged in based on data of heartbeat data, skin current response data, etc. The component selection module 12408, which may select components for use in the AI solution based on the type of brain activity and provide inputs to the component configuration module 12410, may include an ML input selection module 12502 for selecting inputs to the machine learning process, an MP output recognition module 12504 for recognizing outputs to be provided by the machine learning process, a runtime input selection module 12506 for recognizing inputs to the operational solution process, a runtime output identification module 12508 for recognizing outputs of the components, a setting module 12510 for recognizing a rate of change, recognizing a weighting factor, setting a threshold of input data, setting an output threshold of the operational robotic process, etc., a parameter setting module 12512 for tuning learning parameters, recognizing parameters to be included, recognizing parameters to be excluded, setting parameter thresholds, etc. The component configuration module 12410 may configure the selected component 12412. Component selection module 12408 can also provide data to input specification module 12416. The AI solution assembly module 12420 can combine the configured components with other components and any standard or mandatory components to create an AI solution. The AI solution can be configured to receive input specified by the input specification module 12416. Although one iteration of selecting a component is shown in this figure, it is contemplated that multiple components may be selected, configured, and assembled as part of the AI solution.
In an embodiment, referring to fig. 126, an AI solution selection and configuration system 12602 is depicted. The example AI solution selection and configuration system 12602 may include a data input module 12604 to receive an input stream including temporary user-related data 12614, the temporary user-related data 12614 may include a video stream, an audio stream, device interactions (e.g., mouse clicks, mouse movements, physical inputs to a machine), user biometrics such as heart beats, galvanic skin responses, eye tracking, and the like. Data input module 12604 may also receive temporal environmental input data 12620 indicative of environmental inputs the user is receiving, such as visual environments, auditory environments, olfactory environments, device displays, device user interfaces, and the like. Data input module 12604 may also receive time result input data 12603. Data input module 12604 may provide a subset of received data 12614, 12620, 12603 to input analysis module 12616. Data input module 12604 may process received data 12614, 12620, 12603 to reduce noise, compress data, correlate some data, and the like. The analysis module 12616 may identify a plurality of user actions to provide to the component selection module 12608. The image analysis module 12616 may include a time analysis module 12618 to identify the timing of user actions. Temporal analysis module 12618 may allow correlation between temporal user-related data 12614, environmental data 12620, and result data 12603. Based on the user actions, the component selection module 12608 may select components that will simulate one or more psychological processes of the user that are required to perform at least one of the plurality of user actions. Factors that identify the selected component may include the required level of computational intensity, time sensitivity, and the like. This may specify the type of component, the location of the component (onboard, in the cloud, edge computing, etc.). The input analysis module 12616 may also provide information regarding user actions and environmental data to the component configuration module 12610. This data can be used by the component configuration module with the result data as input to a machine learning algorithm to identify which inputs are favorable and which inputs are unfavorable, thereby enabling the component to achieve a desired result, and to identify appropriate weighting, parameter settings, etc. of the inputs. The component configuration module 12610 configures the component 12612, and the component 12612 is provided with the configuration information to the entire AI solution 12624.
As described elsewhere herein, the present disclosure relates to systems and methods for discovering opportunities to increase automation and intelligence, including solutions to domain-specific problems. In addition, the present disclosure also relates to selecting and configuring artificial intelligence solutions (e.g., neural networks, machine learning systems, expert systems, etc.) after discovery opportunities.
Referring now to fig. 127, controller 12708 includes opportunity-mining module 153, artificial intelligence configuration module 12704, and artificial intelligence search engine 12710, optionally with collaborative filter 12728 and clustering engine 12730. Opportunity mining module 153 receives input 12702, such as attribute input for attributes of a task, domain, or domain-related issue.
If it is determined that the artificial intelligence system is applicable to a task or domain, an output 12712 regarding this determination may be used to trigger the artificial intelligence search engine 12710 to perform a search of the artificial intelligence storage 157. The artificial intelligence storage 157 can include a plurality of domain-specific and general artificial intelligence models 12718, and a component of the domain-specific and general artificial intelligence models 12718. The artificial intelligence storage 157 may be organized by category. The categories may be at least one of artificial intelligence model component types, domains, input types, process types, output types, computational requirements, computational power, costs, training states, or energy usage. The artificial intelligence storage can include at least one e-commerce feature. The at least one e-commerce feature may include at least one of a rating, a review, a link to related content, a provisioning mechanism, a licensing mechanism, a delivery mechanism, or a payment mechanism. The model 12718 may be pre-trained, or may be used for training. The components of the domain-specific and generic artificial intelligence model 12718 may include artificial intelligence building blocks, such as components that detect and translate languages, or components that provide highly personalized customer recommendations. One or more models 12718 and/or components of model 12718 may be identified in a search of artificial intelligence storage 157. Components of model 12718 may be identified as separate elements for use in custom AI model 12718 assembly, or as complete, optionally pre-trained model 12718 components.
The artificial intelligence storage 157 can include metadata 12724 or other descriptive material that indicates applicability of the artificial intelligence system to at least one of solving a particular type of problem or operating on domain-specific inputs, data, or other entities. The metadata 12724 or other descriptive material, category, or e-commerce feature may be searched using attribute input 12702 and/or other selection criteria 12714. For example, the artificial intelligence storage 157 and its metadata 12724 may be searched for attributes of tasks related to 2D object classification to reveal an artificial intelligence model 12718 that is appropriate for tasks related to 2D object classes may be a convolutional neural network. Continuing with this example, there may be model diversity even in the Convolutional Neural Network (CNN) class in the artificial intelligence memory 157, such as a CNN calibrated to a particular type of 2D object identification (e.g., a straight side) and another CNN calibrated to another type of 2D object identification (e.g., a combination of curved and straight sides). In this example, if another edge of the 2D object type and the curved property are searched, the artificial intelligence memory 157 will present the CNN that is best suited for the 2D object to be classified.
In an embodiment, in addition to input 12702, artificial intelligence search engine 12710 may use at least one selection criterion 12714 to search artificial intelligence model 12718 and/or components thereof in artificial intelligence storage 157. The selection criteria used in recommending an artificial intelligence model 12718 or model component may include at least one of: whether the model is pre-trained, availability of at least one artificial intelligence model 12718 or model component to execute in a user environment, availability of at least one artificial intelligence model 12718 or model component to a user, governance guidelines, governance policies, computational factors, network factors, data availability, task specific factors, performance factors, quality of service factors, model deployment considerations, security considerations, or human machine interfaces, as may be described elsewhere herein. For example, governance principles, such as requirements for anti-bias review of a pedestrian accident avoidance system, may be used to search the artificial intelligence store 157 for artificial intelligence models to apply to autonomous driving tasks. In another example, the selection criteria to be used for an artificial intelligence solution for use with an air traffic control system may be a requirement that a antagonistic attack and spoofing input training have been accepted. In another example, the selection criteria for an artificial intelligence solution to be used for stock trading tasks may be human supervision, in particular based on the requirements of a human final decision.
The artificial intelligence search engine 12710 can rank one or more results of a search according to the advantages or disadvantages of at least one artificial intelligence model 12718 or a model component relative to at least one selection criterion 12714. The ranked search results may be presented to the user for evaluation and consideration, and ultimately selection. In embodiments, the artificial intelligence search engine 12710 can further include a collaborative filter 12728, the collaborative filter 12728 receiving an indication of at least one artificial intelligence model 12718, or an element of a model component, from a user, the indication for filtering search results. In an embodiment, the artificial intelligence search engine 12710 can further comprise a clustering engine 12730, the clustering engine 12730 configured to cluster search results comprising at least one artificial intelligence model 12718 or model component. The clustering engine 12730 may be at least one of a similarity matrix or a k-means cluster. The clustering engine 12730 may correlate at least one of similar developers, similar domain-specific problems, or similar artificial intelligence solutions in the search results.
Once the artificial intelligence search engine 12710 identifies an artificial intelligence model 12718 or a component thereof by searching using input 12702 alone or through both input 12702 and selection criteria 12714, artificial intelligence configuration module 12704 can configure one or more data inputs 12720 for use with at least one artificial intelligence model 12718 or model component. In some embodiments, artificial intelligence configuration module 12704 may be used to discover and select which inputs 12720 may enable artificial intelligence to be used effectively and efficiently for a given problem. In an embodiment, the artificial intelligence configuration module 12704 may further configure at least one artificial intelligence model 12718 or model component according to at least one configuration standard 12722. In embodiments, a single data input and model component may be configured via one or more configuration standards, while in other embodiments a single configuration standard manages the configuration of data inputs, AI component assembly, and the like.
In an embodiment, the at least one configuration criterion 12722 may include at least one of: availability of at least one artificial intelligence model 12718 or model component to execute in a user environment, availability of at least one artificial intelligence model 12718 or model component to a user, governance principles, governance policies, computational factors, network factors, data availability, task specific factors, performance factors, quality of service factors, model deployment considerations, security considerations, or human-machine interfaces. In an embodiment, the at least one configuration criterion may comprise at least one of: identifying a desired output, identifying training data, identifying parameters for exclusion from or inclusion in training or operation of a model, an input data threshold, an output data threshold, selection of a neural network type, selection of an input model type, setting of initial model weights, setting of a model size, selection of a computing deployment environment, selection of an input data source for training, selection of an input data source for operation, selection of a feedback function/outcome metric, selection of a data integration language for input and output, configuration of an API11214 for model training, configuration of an API11214 for model input, setting of an API for output, configuration of access control, configuration of security parameters, configuration of network protocols, configuration of storage parameters, configuration of economic factors, configuration of data streams, configuration of high-speed, one or more fault-tolerant environments, price-based data acquisition strategies, heuristic methods, decision-making for decision models, or coordination of massively parallel decision environments. In embodiments, the at least one configuration standard may include parameters for assembling an AI solution from a plurality of identified model components, optionally together with other standards or mandatory model components. For example, the model components may be used in parallel operation, serial operation, or a combination of serial and parallel.
For example, the artificial intelligence configuration module 12704 may configure the artificial intelligence model 12718 such that one data input 12720 is weighted more heavily than the other. For example, in rain, an autonomous driving solution may weight the inputs from the traction control system and the forward radar system more than sensors that are targeted to improve fuel efficiency (e.g., sensors that measure road grade and vehicle speed). After rain, the weights may be reversed.
In another example, the artificial intelligence configuration module 12704 may configure the artificial intelligence model 12718 to operate within a particular threshold of the data input 12720. For example, the artificial intelligence model 12718 may be used to combine drawing tasks. When only two clear ideas are provided to model 12718, model 12718 may not be triggered to run. However, once model 12718 receives the third clarified idea, the process of combining its clarified ideas can begin.
The artificial intelligence configuration module 12704 can configure which sensors are used as data inputs 12720, the frequency at which data is sampled, the frequency at which outputs are transmitted, the weighting of various data inputs 12720, the thresholds applied to the data from the data inputs 12720, whether the output of one component of the model 12718 is used as an input to another component of the model 12718, the order of operation of the components of the model 12718, the positioning of model components within the model workflow, and the like.
The artificial intelligence configuration module 12704 can configure the artificial intelligence model 12718 according to one or more model components identified by the artificial intelligence search engine 12710. If the search results consist of only model components, for example, the AI configuration module 12704 can configure locations where the identified 127 components are placed in association with each other,
such as in a workflow or data flow, and other components needed for the model 12718 to operate.
In embodiments, artificial intelligence storage 157 may include a set of interfaces to artificial intelligence systems, e.g., to enable downloading of relevant artificial intelligence applications, establishing links or other connections to artificial intelligence systems (e.g., links to cloud-deployed artificial intelligence systems through APIs, ports, connectors, or other interfaces), and so forth.
Referring now to FIG. 128, a method of artificial intelligence model identification and selection can include receiving input regarding attributes of a task or domain (12802), and processing the input to determine whether an artificial intelligence system can be applied to the task or domain (12804); performing a search of an artificial intelligence memory of a plurality of domain-specific and generic artificial intelligence models and model components using the input and at least one selection criterion to identify at least one of an artificial intelligence model or model component to be applied to the task or domain (12808); configuring one or more data inputs for the at least one artificial intelligence model or model component (12810). The artificial intelligence storage can include metadata or other descriptive material that indicates applicability of the artificial intelligence system to at least one of solving a particular type of problem or operating on domain-specific inputs, data, or other entities.
The method may also include ranking the one or more results of the search according to a benefit or a benefit of the at least one artificial intelligence model relative to the at least one selection criterion (12812). The method may also include configuring at least one artificial intelligence model or model component according to at least one configuration criterion (12814). The method may also include collaborative filtering of search results including at least one artificial intelligence model using elements of the at least one artificial intelligence model or model component selected by the user (12816). The method may also include clustering the search results including the at least one artificial intelligence model or model component using a clustering engine (12818).
In embodiments, one or more of the controllers, circuits, systems, data collectors, storage systems, network elements, etc. described in this disclosure may be implemented in or on an integrated circuit, e.g., an analog, digital, or mixed-signal circuit, such as a microprocessor, programmable logic controller, application specific integrated circuit, field programmable gate array, or other circuit, e.g., on one or more chips disposed on one or more circuit boards, e.g., in hardware (with possibly accelerated speed, power performance, input-output performance, etc.) to provide one or more of the functions described herein. This may include placing circuits with up to billions of logic gates, flip-flops, multiplexers, and other circuits in a small space, facilitating high speed processing, low power consumption, and reduced manufacturing costs compared to board level integration. In embodiments, digital ICs (typically microprocessors, digital signal processors, microcontrollers, etc.) may process digital signals using Boolean (Boolean) algebra to embody complex logic, such as is involved in the circuits, controllers, and other systems described herein. In embodiments, the data collector, expert system, storage system, etc. may be implemented as a digital integrated circuit, such as a logic IC, memory chip, interface IC (e.g., level shifter, serializer, deserializer, etc.), power management IC, and/or a programmable device; analog integrated circuits such as linear ICs, RFICs, etc., or mixed signal ICs such as data acquisition ICs (including a/D converters, D/a converters, digital potentiometers) and/or clock/timing ICs.
Although only a few embodiments of the present invention have been shown and described, it would be obvious to those skilled in the art that various changes and modifications can be made without departing from the spirit and scope of the invention as described in the following claims. All patent applications and patents (including foreign and domestic) and all other publications cited herein are incorporated herein by reference in their entirety to the full extent permitted by law.
The present disclosure makes reference to one or more elements, such as controllers, circuits, modules, engines, processors, etc. (a "control element"), that are configured and/or operative to perform certain operations and/or processes to illustrate embodiments of the present disclosure. For clarity of description, a given control element may be described as a single device, but the control element may be a single device, or distributed across multiple devices, with aspects of the control element being implemented as all or part of the given device. Without limiting any aspect of the disclosure, a control element may be implemented as and/or may be communicatively or operatively coupled to any one or more of: a sensor; an actuator; a user interface; computing resources (e.g., processors, networks, and/or memory); and/or as executable instructions on a computer-readable medium.
The methods and systems described herein may be deployed, in part or in whole, by a machine executing computer software, program code, and/or instructions on a processor. The present invention may be implemented as a method on a machine, a system or apparatus associated with the machine or as a computer program product in a computer readable medium for execution on one or more machines. In embodiments, the processor may be part of a server, cloud server, client, network infrastructure, mobile computing platform, fixed computing platform, or other computing platform. The processor may be any type of computing or processing device capable of executing program instructions, code, binary instructions, and the like. The processor may be or include a signal processor, a digital processor, an embedded processor, a microprocessor, or any variant, such as a coprocessor (math coprocessor, graphics coprocessor, communications coprocessor, etc.), or the like, which may directly or indirectly facilitate the execution of program code or program instructions stored thereon. Further, the processor may enable execution of multiple programs, threads, and codes. Threads may be executed concurrently to enhance performance of the processor and to facilitate concurrent execution of applications. As an implementation, the methods, program code, program instructions, etc. described herein may be implemented in one or more threads. A thread may spawn other threads, which may have assigned priorities associated with them; the processor may execute these threads based on priority or based on any other order of instructions provided in the program code. The processor, or any machine utilizing it, may include non-transitory memory that stores methods, code, instructions, and programs as described herein and elsewhere. The processor may access the non-transitory storage medium through an interface that may store the methods, codes, and instructions as described herein and elsewhere. The storage medium associated with the processor for storing methods, programs, code, program instructions or other types of instructions capable of being executed by a computing or processing device may include, but is not limited to, one or more of CD-ROM, DVD, memory, hard disk, flash drive, RAM, ROM, cache, etc.
The processor may include one or more cores that may enhance the speed and performance of the multiprocessor. In embodiments, the processor may be a dual-core processor, a quad-core processor, other chip-scale multiprocessor combining two or more independent cores (referred to as a wafer volume), or the like.
The methods and systems described herein may be deployed in part or in whole by a machine executing computer software on a server, client, firewall, gateway, hub, router, or other such computer and/or network hardware. The software programs may be associated with servers that may include file servers, print servers, domain servers, internet servers, intranet servers, cloud servers, and other variations such as auxiliary servers, mainframe servers, distributed servers, and the like. The server may include one or more of a memory, a processor, a computer readable medium, a storage medium, ports (physical and virtual), a communication device, and an interface capable of accessing other servers, clients, machines, and devices through a wired or wireless medium, and the like. The methods, programs, or code described herein and elsewhere may be executed by a server. In addition, other devices required to perform the methods described herein can be considered part of the infrastructure associated with the server.
Servers may provide interfaces to other devices, including but not limited to clients, other servers, printers, database servers, print servers, file servers, communication servers, distributed servers, social networks, and the like. Additionally, such coupling and/or connections may facilitate remote execution of programs across a network. Networking of some or all of these devices may facilitate parallel processing of programs or methods at one or more locations without departing from the scope of the present disclosure. Additionally, any device attached to the server through an interface may include at least one storage medium capable of storing methods, programs, code, and/or instructions. The central repository may provide program instructions to be executed on different devices. In this embodiment, the remote store may serve as a storage medium for program code, instructions, and programs.
The software programs may be associated with clients, which may include file clients, print clients, domain clients, internet clients, intranet clients, and other variations such as secondary clients, host clients, distributed clients, and the like. The client may include one or more of a memory, processor, computer readable medium, storage medium, ports (physical and virtual), communication devices, and interfaces capable of accessing other clients, servers, machines, and devices through a wired or wireless medium, etc. The methods, programs, or code described herein and elsewhere may be executed by a client. In addition, other devices required to perform the methods described herein may be considered part of the infrastructure associated with the client.
Clients may provide interfaces to other devices, including, but not limited to, servers, other clients, printers, database servers, print servers, file servers, communication servers, distributed servers, and the like. Additionally, such coupling and/or connections may facilitate remote execution of programs across a network. Networking of some or all of these devices may facilitate parallel processing of programs or methods at one or more locations without departing from the scope of the present disclosure. Additionally, any device attached to the client through an interface may include at least one storage medium capable of storing methods, programs, applications, code, and/or instructions. The central repository may provide program instructions to be executed on different devices. In this embodiment, the remote store may serve as a storage medium for program code, instructions, and programs.
The methods and systems described herein may be deployed in part or in whole via a network infrastructure. The network infrastructure may include elements such as computing devices, servers, routers, hubs, firewalls, clients, personal computers, communication devices, routing devices, and other active and passive devices, modules, and/or components known in the art. Computing and/or non-computing devices associated with the network infrastructure may include storage media such as flash memory, buffers, stacks, RAM, ROM, etc., among other components. The processes, methods, program code, instructions described herein and elsewhere may be executed by one or more network infrastructure elements. The methods and systems described herein may be used with any type of private, community, or hybrid cloud computing network or cloud computing environment, including those involving features of software as a service (SaaS), platform as a service (PaaS), and/or infrastructure as a service (IaaS).
The methods, program codes, and instructions described herein and elsewhere may be implemented on a cellular network having a plurality of cells. The cellular network may be a Frequency Division Multiple Access (FDMA) network or a Code Division Multiple Access (CDMA) network. The cellular network may include mobile devices, cell sites, base stations, repeaters, antennas, towers, and the like. The cellular network may be GSM, GPRS, 3G, EVDO, mesh, or other network types.
The methods, program codes, and instructions described herein and elsewhere may be implemented on or by a mobile device. The mobile device may include a navigation device, a cellular telephone, a mobile personal digital assistant, a laptop computer, a palmtop computer, a netbook, a pager, an e-book reader, a music player, etc. These devices may include storage media such as flash memory, buffers, RAM, ROM, and one or more computing devices, among other components. Computing devices associated with the mobile devices may be enabled to execute the program code, methods, and instructions stored thereon. Alternatively, the mobile device may be used to execute instructions in cooperation with other devices. The mobile device can communicate with a base station that interfaces with a server and is used to execute program code. The mobile device may communicate over a peer-to-peer network, a mesh network, or other communication network. The program code may be stored on a storage medium associated with the server and executed by a computing device embedded within the server. A base station may include a computing device and a storage medium. The storage device may store program code and instructions for execution by a computing device associated with a base station.
Computer software, program code, and/or instructions may be stored and/or accessed on a machine-readable medium, which may include: computer components, devices and recording media that retain calculated digital data for certain time intervals; semiconductor memory, referred to as random access memory ("RAM"); mass storage, typically for more permanent storage, such as in the form of optical disks, magnetic storage (e.g., hard disks, tapes, drums, cards, and other types); processor registers, cache memory, volatile memory, non-volatile memory; optical storage, such as CD, DVD; removable media such as flash memory (e.g., a USB flash disk or a key), a floppy disk, a magnetic tape, paper tape, punch cards, a separate RAM disk, a zip drive, removable mass storage, offline storage, and the like; other computer memory such as dynamic memory, static memory, read/write memory, alterable memory, read only memory, random access memory, sequential access memory, location addressable memory, file addressable memory, content addressable memory, network attached storage, storage area networks, barcodes, magnetic ink, and the like.
The methods and systems described herein may transform a physical and/or intangible article from one state to another. The methods and systems described herein may also transform data representing physical and/or intangible items from one state to another.
The elements depicted and described herein, including flow diagrams and block diagrams throughout the figures, imply logical boundaries between elements. However, in accordance with software or hardware engineering practices, the illustrated elements and their functions may be implemented on a machine having a processor capable of executing program instructions stored thereon as a single-chip software structure, as stand-alone software modules, or as modules employing external routines, code, services, etc., or any combination of these, and all such implementations may be within the scope of the present invention. Examples of such machines may include, but are not limited to, personal digital assistants, laptop computers, personal computers, mobile phones, other handheld computing devices, medical devices, wired or wireless communication devices, transducers, chips, calculators, satellites, tablets, electronic books, gadgets, electronic devices, devices employing artificial intelligence, computing devices, network devices, servers, routers, and so forth. Furthermore, the elements depicted in the flow diagrams and block diagrams, or any other logical components, may be implemented on a machine capable of executing program instructions. Accordingly, while the foregoing figures and description set forth functional aspects of the disclosed systems, no particular arrangement of software for implementing these functional aspects should be inferred from this description unless explicitly stated or otherwise clear from the context. Similarly, it should be understood that the various steps identified and described above may be varied, and the order of the steps may be adapted to specific applications of the techniques disclosed herein. All such variations and modifications are intended to fall within the scope of the present invention. Thus, the order in which the steps are illustrated and/or described should not be construed as requiring that the steps be performed in a particular order unless required by a particular application or otherwise explicitly stated or otherwise clear from the context.
The methods and/or processes described above, and the steps associated therewith, may be implemented in hardware, software, or any combination of hardware and software as appropriate for a particular application. The hardware may include a general purpose computer, and/or a special purpose computing device, or a particular aspect or component of a particular computing device. The processes may be implemented in one or more microprocessors, microcontrollers, embedded microcontrollers, programmable digital signal processors or other programmable devices, and internal and/or external memory. These processes may also or alternatively be embodied in an application specific integrated circuit, a programmable gate array, programmable array logic, or any other device or combination of devices that may be used to process electronic signals. It should also be understood that one or more of the processes may be implemented as computer executable code capable of being executed on a machine-readable medium.
Computer executable code may be created using a structured programming language such as C, an object oriented programming language such as C + +, or any other high-level or low-level programming language including assembly, hardware description, and database programming languages, which may be stored, compiled, or interpreted to run on one of the above devices, as well as a heterogeneous combination of processors, processor architectures, or a combination of different hardware and software, or any other machine capable of executing program instructions.
Thus, in one aspect, the above-described methods and combinations thereof may be embodied in computer-executable code that, when executed on one or more computing devices, performs the steps thereof. In another aspect, the method may be embodied in a system that performs its steps and may be distributed across devices in a variety of ways, or all functions may be integrated into a dedicated, stand-alone device or other hardware. In another aspect, the means for performing the steps associated with the processes described above may comprise any of the hardware and/or software described above. All such permutations and combinations are intended to fall within the scope of the present invention.
While the present invention has been disclosed in conjunction with the preferred embodiments shown and described in detail, various modifications and improvements will become apparent to those skilled in the art. Thus, the spirit and scope of the present invention is not limited by the foregoing examples, but should be understood in the broadest sense allowable by law.
The use of the terms "a" and "an" and "the" and similar referents in the context of describing the disclosure (especially in the context of the following claims) is to be construed to cover both the singular and the plural, unless otherwise indicated herein or clearly contradicted by context. The terms "comprising," "having," "including," and "containing" are to be construed as open-ended terms (i.e., meaning "including, but not limited to,") unless otherwise noted. Recitation of ranges of values herein are merely intended to serve as a shorthand method of referring individually to each separate value falling within the range, unless otherwise indicated herein, and each separate value is incorporated into the specification as if it were individually recited herein. All methods described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The use of any and all examples, or exemplary language (e.g., "such as") provided herein, is intended merely to better illuminate the disclosure and does not pose a limitation on the scope of the disclosure unless otherwise claimed. The term "group" may include groups having a single member. No language in the specification should be construed as indicating any non-claimed element as essential to the practice of the invention.
While the foregoing written description enables one of ordinary skill to make and use what is presently considered to be the best mode thereof, those of ordinary skill will understand and appreciate the existence of variations, combinations, and equivalents of the specific embodiments, methods, and examples herein. Accordingly, the present invention should not be limited by the above-described embodiments, methods and examples, but by all embodiments and methods within the scope and spirit of the invention.
All documents incorporated herein by reference are incorporated herein in their entirety as if fully set forth herein.
Claims (115)
1. A system, comprising:
an opportunity mining module configured to receive input regarding attributes of a task or domain and process the input to determine whether an artificial intelligence system can be applied to the task or the domain;
an artificial intelligence search engine configured to receive the input and perform a search of an artificial intelligence memory of a plurality of domain-specific and generic artificial intelligence models and model components using the input and at least one selection criterion to identify at least one of an artificial intelligence model or model component to be applied to the task or the domain;
An artificial intelligence configuration module structured to configure one or more data inputs for the at least one of the artificial intelligence model or the model component.
2. The system of claim 1, wherein the artificial intelligence search engine ranks one or more results of the search according to a superiority or inferiority of the at least one of the artificial intelligence model or the model component relative to the at least one selection criterion.
3. The system of claim 1, wherein the at least one of the artificial intelligence model or the model component is at least one of a neural network, a machine learning system, or an expert system.
4. The system of claim 1, wherein the at least one selection criterion comprises at least one of: availability of the at least one of the artificial intelligence model or the model component to execute in a user environment, availability of the at least one of the artificial intelligence model or the model component to at least one user, abatement principles, abatement policies, computational factors, network factors, data availability, task-specific factors, performance factors, quality of service factors, model deployment considerations, security considerations, or human-machine interfaces.
5. The system of claim 1, wherein the artificial intelligence configuration module is further configured to configure the at least one of the artificial intelligence model or the model component according to at least one configuration criterion.
6. The system of claim 5, wherein the at least one configuration criterion comprises at least one of: availability of the at least one of the artificial intelligence model or the model component to execute in a user environment, availability of the at least one of the artificial intelligence model or the model component to a user, abatement principles, abatement policies, computational factors, network factors, data availability, task specific factors, performance factors, quality of service factors, model deployment considerations, security considerations, or human-machine interfaces.
7. The system of claim 5, wherein the at least one configuration criterion comprises at least one of: selection of a neural network type, selection of an input model type, setting of initial model weights, setting of model sizes, selection of a computing deployment environment, selection of input data sources for training, selection of input data sources for operations, selection of feedback functions/outcome metrics, selection of one or more data integration languages for input and output, configuration of an Application Programming Interface (API) for model training, configuration of an API for model input, configuration of an API for output, configuration of access control, configuration of security parameters, configuration of network protocols, configuration of storage parameters, configuration of economic factors, configuration of data streams, configuration of high availability, one or more fault tolerance environments, price-based data acquisition strategies, heuristics, decision-making for decision models, or coordination of massively parallel decision-making environments.
8. The system of claim 1, wherein the artificial intelligence store comprises metadata or other descriptive material indicating applicability of an artificial intelligence model or model component to at least one of solving a particular type of problem or operating on domain-specific inputs, data, or other entities.
9. The system of claim 8, wherein the problem is at least one of prediction, NLP, image recognition, pattern recognition, motion detection, or route optimization.
10. The system of claim 1, wherein the artificial intelligence store is organized by category.
11. The system of claim 10, wherein the categories are at least one of artificial intelligence model component types, domains, input types, process types, output types, computational requirements, computational power, cost, or energy usage.
12. The system of claim 1, wherein the artificial intelligence search engine further comprises a collaborative filter configured to receive an indication of elements of the at least one artificial intelligence model or model component from a user, the indication for filtering search results that include the at least one artificial intelligence model or model component.
13. The system of claim 1, wherein the artificial intelligence search engine further comprises a clustering engine configured to cluster search results comprising the at least one artificial intelligence model or model component.
14. The system of claim 13, wherein the clustering engine is at least one of a similarity matrix or a k-means cluster.
15. The system of claim 13, wherein the clustering engine associates at least one of similar developers, similar domain-specific problems, or similar artificial intelligence solutions in the search results.
16. The system of claim 1, wherein the artificial intelligence memory comprises at least one e-commerce feature.
17. The system of claim 16, wherein the at least one e-commerce feature comprises at least one of: rating, review, link to related content, provisioning mechanism, licensing mechanism, delivery mechanism, or payment mechanism.
18. A method, comprising:
receiving input regarding attributes of a task or a domain, and processing the input to determine whether an artificial intelligence system can be applied to the task or the domain;
Performing a search of an artificial intelligence memory of a plurality of domain-specific and generic artificial intelligence models and model components using the input and at least one selection criterion to identify at least one of an artificial intelligence model or model component to be applied to the task or the domain;
configuring one or more data inputs for the at least one of the artificial intelligence model or the model component.
19. The method of claim 18, further comprising ranking one or more results of the search according to a benefit or a benefit of the at least one of the artificial intelligence model or the model component over the at least one selection criterion.
20. The method of claim 18, further comprising configuring the at least one of the artificial intelligence model or the model component in accordance with at least one configuration criterion.
21. The method of claim 18, wherein the artificial intelligence storage includes metadata or other descriptive material indicating applicability of the artificial intelligence system to at least one of solving a particular type of problem or operating on domain-specific inputs, data, or other entities.
22. The method of claim 18, further comprising collaborative filtering search results that include the at least one of the artificial intelligence model or the model component using an element of the at least one of the artificial intelligence model or the model component selected by a user.
23. The method of claim 18, further comprising clustering search results that include the at least one of the artificial intelligence model or the model component using a clustering engine.
24. A system, comprising:
an opportunity mining module that receives input regarding attributes of a task or domain and processes the input to determine whether an artificial intelligence system can be applied to the task or the domain;
an artificial intelligence search engine that receives the input and performs a search on artificial intelligence storage of a plurality of domain-specific and generic artificial intelligence models and model components using the input to identify at least one of an artificial intelligence model or model component to be applied to the task or the domain;
an artificial intelligence configuration module that configures one or more data inputs for the at least one of the artificial intelligence model or the model component.
25. The system of claim 24, further comprising identifying the at least one of the artificial intelligence model or the model component using at least one selection criterion.
26. The system of claim 25, wherein the artificial intelligence search engine ranks one or more results of the search according to a dominance or a disadvantage of the at least one artificial intelligence model or model component relative to the at least one selection criterion.
27. The system of claim 24, wherein the at least one artificial intelligence model or model component is at least one of a neural network, a machine learning system, or an expert system.
28. The system of claim 25, wherein the at least one selection criterion comprises at least one of: availability of the at least one artificial intelligence model or model component to execute in the user environment, availability of the at least one artificial intelligence model or model component to the user, governance guidelines, governance policies, computational factors, network factors, data availability, task specific factors, performance factors, quality of service factors, model deployment considerations, security considerations, or human-machine interfaces.
29. The system of claim 24, wherein the artificial intelligence configuration module further configures the at least one artificial intelligence model or model component according to at least one configuration standard.
30. The system of claim 29, wherein the at least one configuration criterion comprises at least one of: availability of the at least one artificial intelligence model or model component to execute in the user environment, availability of the at least one artificial intelligence model or model component to the user, governance guidelines, governance policies, computational factors, network factors, data availability, task specific factors, performance factors, quality of service factors, model deployment considerations, security considerations, or human-machine interfaces.
31. The system of claim 29, wherein the at least one configuration criterion comprises at least one of: selection of a neural network type, selection of an input model type, setting of initial model weights, setting of model sizes, selection of a computing deployment environment, selection of input data sources for training, selection of input data sources for operations, selection of feedback functions/outcome metrics, selection of one or more data integration languages for input and output, configuration of APIs for model training, configuration of APIs for model input, configuration of APIs for output, configuration of access controls, configuration of security parameters, configuration of network protocols, configuration of storage parameters, configuration of economic factors, configuration of data flows, configuration of high availability, configuration of one or more fault tolerance environments, price-based data acquisition strategies, heuristic methods, decision-making for decision models, or coordination of massively parallel decision environments.
32. The system of claim 24, wherein the artificial intelligence storage includes metadata or other descriptive material indicating applicability of the artificial intelligence system to at least one of solving a particular type of problem or operating on domain-specific inputs, data, or other entities.
33. The system of claim 32, wherein the problem is at least one of prediction, NLP, image recognition, pattern recognition, motion detection, or route optimization.
34. The system of claim 24, wherein the artificial intelligence store is organized by category.
35. The system of claim 34, wherein the categories are at least one of artificial intelligence model component types, domains, input types, process types, output types, computational requirements, computational power, cost, or energy usage.
36. The system of claim 24, wherein the artificial intelligence search engine further comprises a collaborative filter that receives an indication of elements of the at least one artificial intelligence model or model component from a user, the indication for filtering search results that include the at least one artificial intelligence model or model component.
37. The system of claim 24, wherein the artificial intelligence search engine further comprises a clustering engine that clusters search results comprising the at least one artificial intelligence model or model component.
38. The system of claim 37, wherein the clustering engine is at least one of a similarity matrix or a k-means cluster.
39. The system of claim 37, wherein the clustering engine associates at least one of similar developers, similar domain-specific problems, or similar artificial intelligence solutions in the search results.
40. The system of claim 24, wherein the artificial intelligence memory comprises at least one e-commerce feature.
41. The system of claim 40, wherein the at least one e-commerce feature comprises at least one of: rating, review, link to related content, provisioning mechanism, licensing mechanism, delivery mechanism, or payment mechanism.
42. A method, comprising:
receiving input regarding attributes of a task or a domain, and processing the input to determine whether an artificial intelligence system can be applied to the task or the domain;
Performing a search on artificial intelligence storage of a plurality of domain-specific and generic artificial intelligence models using the input to identify at least one artificial intelligence model or model component to be applied to the task or the domain;
configuring one or more data inputs for the at least one artificial intelligence model or model component.
43. The method of claim 42, further comprising identifying the at least one artificial intelligence model or model component using at least one selection criterion.
44. The method of claim 43, further comprising ranking one or more results of the search according to a benefit or a benefit of the at least one artificial intelligence model or model component relative to the at least one selection criterion.
45. The method of claim 42, further comprising configuring the at least one artificial intelligence model or model component in accordance with at least one configuration criterion.
46. The method of claim 42, wherein the artificial intelligence storage includes metadata or other descriptive material indicating applicability of the artificial intelligence system to at least one of solving a particular type of problem or operating on domain-specific inputs, data, or other entities.
47. The method of claim 42, further comprising collaborative filtering of search results including the at least one artificial intelligence model or model component using elements of the at least one artificial intelligence model or model component selected by a user.
48. The method of claim 42, further comprising clustering search results including the at least one artificial intelligence model or model component using a clustering engine.
49. A system for selecting and configuring automated robotic processes, the system comprising:
a media input module configured to receive at least one functional media;
a media analysis module configured to analyze the at least one functional media and identify an action parameter;
a solution selection module configured to select at least one component of an AI solution for an automated robotic process, wherein the selection is based at least in part on the action parameters.
50. The system of claim 49, wherein:
the at least one functional media includes media indicative of brain activity of a person participating in a task of interest;
the media analysis module is further configured to identify an activity level in at least one brain region and provide brain region parameters corresponding to the activity level in the at least one brain region.
51. The system of claim 50, wherein the solution selection module is further structured to select the at least one component of the AI solution based at least in part on the brain region parameters.
52. The system of claim 50, wherein:
the media analysis module is further configured to provide activity parameters related to a human participating task of interest and corresponding to the brain region parameters;
the solution selection module is further configured to select at least one component of the AI solution based at least in part on the activity parameter.
53. The system of claim 52, wherein the activity parameter is selected from an activity parameter list comprising at least one of participation, non-participation, activity level, or activity type.
54. The system of claim 52, further comprising a component configuration module configured to set configuration parameters based at least in part on at least one of the activity parameters or the brain region parameters.
55. The system of claim 50, wherein the solution selection module is further configured to identify a runtime input based at least in part on the brain region parameters.
56. The system of claim 50, wherein the brain region parameter indicates a neocortical region comprising at least one of Fp1, F7, F3, T3, C3, T5, P3, O1, fp2, F8, F4, T4, C4, T6, P4, or O2.
57. The system of claim 50, wherein the at least one selected component of the AI solution simulates processing activities similar to the activities of the brain region indicated by the brain region parameters.
58. The system of claim 52, wherein the activity parameter represents an activity comprising at least one of an olfactory process, a visual process, an auditory process, or a motion.
59. The system of claim 58, wherein when the activity parameter represents the olfactory process, input specification module is further configured to identify at least one chemical sensor as a robotic input.
60. The system of claim 58, wherein when the activity parameter represents the visual process, the input specification module is further configured to identify at least one visual sensor as a robotic input.
61. The system of claim 60, wherein the sensitivity of the at least one vision sensor comprises a portion of a wavelength range between about 380 nanometers to about 700 nanometers.
62. The system of claim 58, wherein when the activity parameter represents the auditory process, the input specification module is further configured to identify at least one microphone as a robotic input.
63. The system of claim 50, wherein the media analysis module is further configured to identify a second brain region parameter.
64. The system according to claim 63, wherein the second brain region parameter is indicative of at least one of: a resolution of the at least one functional media, an intensity of an engagement signal, a relative intensity of an engagement signal between the brain region parameter and the second brain region parameter, or a degree of brain region engagement.
65. The system of claim 49, wherein the selected at least one component of the AI solution comprises at least one of: models, expert systems, neural network types, specific machine learning algorithms, configuration specifications, specified inputs, specified outputs, learning parameters, rates of change, weights, or thresholds.
66. The system of claim 49, wherein:
the at least one functional media comprises a video feed of a person participating in a task of interest;
the action parameter represents an action that includes at least one of auditory, visual, olfactory, or tactile.
67. The system of claim 49, wherein:
the action parameters comprise an ordered series of actions;
the solution selection module is further structured to select a plurality of components of the AI solution, the selection based at least in part on the ordered series of actions.
68. A system for selecting and configuring automated robotic processes, the system comprising:
an input module configured to receive at least one user-related input;
an input analysis module configured to analyze the at least one user-related input and identify an action parameter;
a component selection module configured to select a component in an AI solution for an automated robotic process, wherein the selection is based at least in part on the action parameters.
69. The system of claim 68, wherein the user-related input comprises at least one of: an audio feed, a motion sensor, a heartbeat monitor, a biosensor, or an eye tracker.
70. The system of claim 68, wherein the analysis of the at least one user-related input includes a temporal analysis that produces a plurality of temporal parameters.
71. The system of claim 70, wherein the selection of the component of the AI solution is further based at least in part on the plurality of time parameters.
72. The system of claim 68, further comprising a component configuration module structured to configure the component of the AI solution based at least in part on the action parameters, wherein a manner of configuration of the component of the AI solution comprises at least one of: selecting an input for a machine learning process; identifying an output to be provided by the machine learning process; identifying an input to operate a solution process; identifying an output of an operational solution process; adjusting learning parameters; identifying a rate of change; identifying a weighting factor; identifying parameters for inclusion; identifying a parameter for excluding the parameter; setting a threshold value of input data; setting an output threshold for operating the robotic process; or set parameter thresholds.
73. The system of claim 70, wherein the components of the AI solution include at least one of a model, an expert system, or a neural network.
74. A system for selecting and configuring a robotic process, the system comprising:
A data input module configured to receive an input stream relating to a user participating in a task of interest;
an input analysis module configured to analyze the input stream and provide a series of actions and associated action parameters, wherein each action in the series of actions is time stamped;
a component selection module configured to select a component in an AI solution for an automated robotic process, wherein the selection is based at least in part on at least one of an action in the series of actions and the associated action parameter;
wherein the component of the AI solution is selected based at least in part on its ability to simulate one or more of the actions in the series of actions.
75. The system of claim 74, wherein the component selection module is further configured to select a second component of the AI solution based on a second action in the series of actions, wherein the component of the AI solution and the second component of the AI solution occur at different locations.
76. The system of claim 75, wherein at least one of the component or the second component of the AI solution requires at least one of: computationally intensive processing; a quick decision is made with minimal input.
77. The system of claim 75, wherein at least one of the component or the second component comprises a neural network having multiple layers operating in a cloud environment.
78. The system of claim 74, wherein each component is at least one of a specific model, expert system, neural network, or algorithm.
79. A computer-implemented method for selecting an AI solution for an automated robotic process, the method comprising:
receiving at least one functional media, wherein the functional media includes information indicative of brain activity of a person participating in a task of interest;
analyzing the at least one functional media;
identifying an activity level in at least one brain region;
identifying brain region parameters and activity parameters;
identifying an action parameter based at least in part on at least one of the brain region parameter and the activity parameter;
selecting a component of the AI solution based at least in part on at least one of the brain region parameters, the activity parameters, or the action parameters.
80. The method of claim 79, further comprising determining a configuration parameter based at least in part on at least one of the selected component of the AI solution, the brain region parameter, the activity parameter, or the action parameter.
81. The method of claim 79, further comprising recognizing a robotic input based at least in part on at least one of the brain region parameters or the activity parameters.
82. The method of claim 79, wherein the selected component of the AI solution simulates processing activity similar to activity of the at least one brain region indicated by the brain region parameters.
83. The method of claim 79, wherein at least one of the brain region parameters or the activity parameters represents an activity comprising at least one of an olfactory process, a visual process, an auditory process, or a motor activity.
84. The method of claim 79, further comprising:
identifying at least one of a second brain region parameter or a second activity parameter;
modifying selected components of the AI solution based at least in part on at least one of the second brain region parameter or the second activity parameter.
85. The method of claim 84, further comprising:
identifying a second component of the AI solution based in part on the second brain region parameter or the second activity parameter.
86. The method of claim 79, further comprising:
identifying at least one of a second brain region parameter or a second activity parameter;
Selecting a second component of the AI solution based at least in part on at least one of the second brain region parameter or the second activity parameter.
87. The method of claim 86, further comprising assembling the AI solution, the AI solution including at least the selected components.
88. The method of claim 87, wherein the assembled AI solution further includes a second selected component.
89. A computer-implemented method for selecting and configuring automated robotic processes, the method comprising:
receiving a user-related input comprising a timestamp;
analyzing the user-related input;
identifying a series of user actions and associated activity parameters;
selecting a component in the AI solution for the automated robotic process based at least in part on a user action in the series of user actions.
90. The method of claim 89, wherein the user-related input is at least one of: an audio feed, a motion sensor, a video feed, a heartbeat monitor, an eye tracker, or a biosensor.
91. The method of claim 89, further comprising identifying a second user action from the series of user actions.
92. The method of claim 91, further comprising modifying selected components of the AI solution based on the second user action.
93. The method of claim 92, further comprising selecting a second component as the AI solution based on the second user action.
94. The method of claim 89, further comprising:
identifying an action parameter based at least in part on at least one of the user action or the associated activity parameter;
configuring selected components of the AI solution based on the action parameters.
95. The method of claim 94, wherein the user action is motion and the associated action parameter is at least one of range of motion, speed of motion, repetition of motion, utilization of muscle memory, smoothness of motion, flow of motion, or timing of motion.
96. The method of claim 89, further comprising:
receiving at least one device input performed by the user,
wherein the device input of the user is synchronized with the user-related input.
97. The method of claim 96, wherein the selection of the component of the AI solution is based at least in part on a correlation between at least one of the device inputs and the user-related input.
98. A computer-implemented method for selecting and configuring automated robotic processes, the method comprising:
receiving a temporal biometric measurement of a worker performing a task;
receiving a spatiotemporal environment input provided to the worker;
identifying a type of inference to use in performing the task based at least in part on the temporal biometric measurement of the worker;
selecting a component of an AI solution to replicate the inference type;
configuring the components of the AI solution based on the spatiotemporal environment input,
wherein the temporal biometric measurements comprise a set of spatiotemporal imaging data of a brain of the worker;
wherein identifying the inference type further comprises identifying a set of spatiotemporal neocortical activity patterns of the worker and identifying an activity region of neocortex of the worker;
wherein the component that selects the AI solution is based at least in part on the identified active region of the neocortex.
99. The method of claim 98, wherein the identified active region of the neocortex comprises an O1 neocortex region, and a selected AI component is optimized for visual processing.
100. The method of claim 99, wherein configuring the component of the AI solution further comprises identifying a visual input for the component based on the spatiotemporal environment input.
101. The method of claim 98, wherein the identified active region of the neocortex comprises a C3 neocortex region, and the selected component is optimized for at least one of data storage or retrieval.
102. The method of claim 98, wherein the selected component comprises a block chain based distributed ledger.
103. The method of claim 98, further comprising identifying whether a serial or parallel processing AI component is optimal based at least in part on the spatio-temporal neocortical activity pattern.
104. The method of claim 98, wherein configuring the selected component of the AI solution further comprises identifying an ordered set of inputs to the component of the AI solution.
105. The method of claim 98, wherein configuring the selected component of the AI solution further comprises identifying an efficiency from the combination of spatiotemporal environment inputs.
106. The method of claim 98, wherein configuring the selected component of the AI solution further comprises identifying an undesirable portion of the spatiotemporal environment input that is detrimental to an aggressive solution; and configuring inputs to a portion of the AI solution to limit undesired inputs to the AI solution.
107. The method of claim 106, wherein limiting undesired inputs to the AI solution further comprises removing input noise.
108. The method of claim 98, wherein the spatiotemporal environment comprises at least one of an auditory environment, a visual environment, an olfactory environment, or a device user interface.
109. The method of claim 98, further comprising:
receiving a second temporal biometric measurement of the worker performing the task;
wherein the second temporal biometric measurement comprises at least one of: an image of the worker, a video feed of the worker, an audio feed from the worker, a motion of the worker, a heartbeat of the worker, a galvanic skin response of the worker, or an eye motion of the worker.
110. The method of claim 98, comprising:
identifying a plurality of performance tasks from the biometric measurements;
extracting a performance parameter from the biometric measurement;
wherein the selected component to configure the AI solution is based at least in part on the performance parameter.
111. The method of claim 109, wherein the second temporal biometric measurement is provided in a training set for the component of the AI solution.
112. The method of claim 109, further comprising:
receiving result data related to the task;
associating the second temporal biometric measurement with the received result data;
wherein the component that selects the AI solution is further based at least in part on at least one of the result data or the correlation.
113. The method of claim 98, further comprising:
identifying a plurality of time intervals between each of a plurality of executing tasks;
configuring the selected component of the AI solution based on at least one of the time intervals.
114. An information technology system for trading artificial intelligence with digital twins, comprising:
an adaptive intelligence system comprising:
an artificial intelligence system, wherein the artificial intelligence system comprises a machine learning system;
a digital twinning system; and
a self-adaptive edge intelligence system;
wherein the adaptive intelligence system defines a machine learning model configured to receive at least one of state data or event data from a data storage system;
wherein the adaptive intelligence system defines the digital twin system to create a digital copy of one or more of the transactional (ecosystem) entities that communicate over a connection facility.
A monitoring system and a data collection system;
a transaction management platform and an application.
115. A computer-implemented method for electronically facilitating licensing of one or more personality rights of a licensor, the method comprising:
receiving an access request from a licensee to obtain approval of a license personality from a set of available licensees;
selectively granting access to the licensee based on the access request;
receiving a deposit confirmation of the amount of funds from the licensee;
issuing an encrypted monetary amount corresponding to the monetary amount deposited by the licensee to an account of the licensee;
receiving a smart contract request to create a smart contract that manages the licensing of the one or more personalities of the licensee by the licensee, wherein the smart contract request indicates one or more terms including a cryptocurrency price pair amount to be paid to the licensee in exchange for one or more obligations of the licensee;
generating the intelligent contract based on the intelligent contract request;
escrowing the cryptocurrency counter-value amount from the account of the licensee;
Deploying the smart contract to a distributed ledger;
verifying, by the smart contract, that the licensor has fulfilled the one or more obligations;
releasing at least a portion of the cryptocurrency counter amount into a licensor account of the licensor in response to receiving verification that the licensor has fulfilled the one or more obligations;
outputting a record to the distributed ledger indicating that a permissible transaction defined by the smart contract has been completed.
Applications Claiming Priority (9)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US16/780,519 US11669914B2 (en) | 2018-05-06 | 2020-02-03 | Adaptive intelligence and shared infrastructure lending transaction enablement platform responsive to crowd sourced information |
| US16/780,519 | 2020-02-03 | ||
| US202062994581P | 2020-03-25 | 2020-03-25 | |
| US62/994,581 | 2020-03-25 | ||
| US202063069542P | 2020-08-24 | 2020-08-24 | |
| US63/069,542 | 2020-08-24 | ||
| US202063127980P | 2020-12-18 | 2020-12-18 | |
| US63/127,980 | 2020-12-18 | ||
| PCT/US2021/016473 WO2021158702A1 (en) | 2020-02-03 | 2021-02-03 | Artificial intelligence selection and configuration |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115413346A true CN115413346A (en) | 2022-11-29 |
Family
ID=77200570
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202180026383.8A Pending CN115413346A (en) | 2020-02-03 | 2021-02-03 | Artificial intelligence selection and configuration |
Country Status (6)
| Country | Link |
|---|---|
| EP (1) | EP4100893A4 (en) |
| JP (1) | JP2023513146A (en) |
| CN (1) | CN115413346A (en) |
| AU (1) | AU2021216391A1 (en) |
| CA (1) | CA3169998A1 (en) |
| WO (1) | WO2021158702A1 (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116186594A (en) * | 2023-04-26 | 2023-05-30 | 成都市环境应急指挥保障中心 | Method for realizing intelligent detection of environment change trend based on decision network combined with big data |
| CN116956747A (en) * | 2023-08-28 | 2023-10-27 | 西湾智慧(广东)信息科技有限公司 | Method for building machine learning modeling platform based on AI (advanced technology attachment) capability |
| CN117708681A (en) * | 2024-02-06 | 2024-03-15 | 南京邮电大学 | Personalized federal electroencephalogram signal classification method and system based on structural diagram guidance |
| CN117708681B (en) * | 2024-02-06 | 2024-04-26 | 南京邮电大学 | Personalized federal electroencephalogram signal classification method and system based on structural diagram guidance |
Families Citing this family (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11550299B2 (en) | 2020-02-03 | 2023-01-10 | Strong Force TX Portfolio 2018, LLC | Automated robotic process selection and configuration |
| US11669914B2 (en) | 2018-05-06 | 2023-06-06 | Strong Force TX Portfolio 2018, LLC | Adaptive intelligence and shared infrastructure lending transaction enablement platform responsive to crowd sourced information |
| US11544782B2 (en) | 2018-05-06 | 2023-01-03 | Strong Force TX Portfolio 2018, LLC | System and method of a smart contract and distributed ledger platform with blockchain custody service |
| WO2019217323A1 (en) | 2018-05-06 | 2019-11-14 | Strong Force TX Portfolio 2018, LLC | Methods and systems for improving machines and systems that automate execution of distributed ledger and other transactions in spot and forward markets for energy, compute, storage and other resources |
| US11416926B1 (en) * | 2019-02-27 | 2022-08-16 | Candor Technology Inc. | Intelligent data matching and validation system |
| CA3123465A1 (en) * | 2019-03-01 | 2020-09-10 | Conquest Planning Inc. | Strategic advice manager for financial plans |
| US20220318902A1 (en) * | 2021-04-06 | 2022-10-06 | David B. Coulter | Loan Access System and Method |
| US11468519B1 (en) | 2021-06-24 | 2022-10-11 | Square, Inc. | Automatic tax account management |
| US11393026B1 (en) * | 2021-06-24 | 2022-07-19 | Block, Inc. | Tax refund loan management platform |
| WO2023033199A1 (en) * | 2021-08-31 | 2023-03-09 | Stratio | Methods for automatically identifying a match between a product image and a reference drawing based on artificial intelligence |
| CN114218809B (en) * | 2021-12-29 | 2022-06-03 | 中国科学技术大学 | Automatic and formal protocol modeling method and system for Ether house intelligent contract |
| US20230252477A1 (en) * | 2022-02-08 | 2023-08-10 | Actimize Ltd. | Automated rule generation system and methods |
| CN114661010B (en) * | 2022-03-17 | 2023-05-09 | 北京合思信息技术有限公司 | Driving detection processing method based on artificial intelligence and cloud platform |
| WO2023182693A1 (en) * | 2022-03-24 | 2023-09-28 | 메이즈 주식회사 | Cafe curation device and cafe curation method |
| JP2023148287A (en) * | 2022-03-30 | 2023-10-13 | ソニーセミコンダクタソリューションズ株式会社 | Information processing device, and information processing system |
| CN115016960B (en) * | 2022-08-08 | 2022-11-11 | 杭州实在智能科技有限公司 | Configurable RPA robot full-flow information notification processing method and system |
| CN116912444B (en) * | 2023-08-04 | 2024-02-23 | 深圳市固有色数码技术有限公司 | Meta-universe model generation system and method based on artificial intelligence |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7519452B2 (en) * | 2004-04-15 | 2009-04-14 | Neurosciences Research Foundation, Inc. | Mobile brain-based device for use in a real world environment |
| US20140214730A9 (en) * | 2007-02-05 | 2014-07-31 | Goded Shahaf | System and method for neural modeling of neurophysiological data |
| EP3441896B1 (en) * | 2012-09-14 | 2021-04-21 | InteraXon Inc. | Systems and methods for collecting, analyzing, and sharing bio-signal and non-bio-signal data |
| US20160358099A1 (en) * | 2015-06-04 | 2016-12-08 | The Boeing Company | Advanced analytical infrastructure for machine learning |
| US10324457B2 (en) * | 2017-05-11 | 2019-06-18 | Global Eprocure | Robotic process automation for supply chain management operations |
-
2021
- 2021-02-03 JP JP2022547295A patent/JP2023513146A/en active Pending
- 2021-02-03 CA CA3169998A patent/CA3169998A1/en active Pending
- 2021-02-03 WO PCT/US2021/016473 patent/WO2021158702A1/en unknown
- 2021-02-03 CN CN202180026383.8A patent/CN115413346A/en active Pending
- 2021-02-03 EP EP21750846.4A patent/EP4100893A4/en active Pending
- 2021-02-03 AU AU2021216391A patent/AU2021216391A1/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116186594A (en) * | 2023-04-26 | 2023-05-30 | 成都市环境应急指挥保障中心 | Method for realizing intelligent detection of environment change trend based on decision network combined with big data |
| CN116956747A (en) * | 2023-08-28 | 2023-10-27 | 西湾智慧(广东)信息科技有限公司 | Method for building machine learning modeling platform based on AI (advanced technology attachment) capability |
| CN117708681A (en) * | 2024-02-06 | 2024-03-15 | 南京邮电大学 | Personalized federal electroencephalogram signal classification method and system based on structural diagram guidance |
| CN117708681B (en) * | 2024-02-06 | 2024-04-26 | 南京邮电大学 | Personalized federal electroencephalogram signal classification method and system based on structural diagram guidance |
Also Published As
| Publication number | Publication date |
|---|---|
| AU2021216391A1 (en) | 2022-09-01 |
| JP2023513146A (en) | 2023-03-30 |
| WO2021158702A1 (en) | 2021-08-12 |
| EP4100893A4 (en) | 2024-03-20 |
| EP4100893A1 (en) | 2022-12-14 |
| CA3169998A1 (en) | 2021-08-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11567478B2 (en) | Selection and configuration of an automated robotic process | |
| US11669914B2 (en) | Adaptive intelligence and shared infrastructure lending transaction enablement platform responsive to crowd sourced information | |
| US20220198562A1 (en) | Market orchestration system for facilitating electronic marketplace transactions | |
| US20210248514A1 (en) | Artificial intelligence selection and configuration | |
| CN115413346A (en) | Artificial intelligence selection and configuration | |
| CN113272850A (en) | Adaptive intelligent shared infrastructure loan transaction support platform | |
| US20220291666A1 (en) | Ai solution selection for an automated robotic process | |
| CN116113967A (en) | System and method for controlling digital knowledge dependent rights |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |