CN108734567A - A kind of asset management system and its appraisal procedure based on big data artificial intelligence air control - Google Patents
A kind of asset management system and its appraisal procedure based on big data artificial intelligence air control Download PDFInfo
- Publication number
- CN108734567A CN108734567A CN201810289057.6A CN201810289057A CN108734567A CN 108734567 A CN108734567 A CN 108734567A CN 201810289057 A CN201810289057 A CN 201810289057A CN 108734567 A CN108734567 A CN 108734567A
- Authority
- CN
- China
- Prior art keywords
- user
- index
- credit
- assets
- data
- 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
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
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Technology Law (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention belongs to assets credit evaluation areas, and in particular to a kind of asset management system and its appraisal procedure based on big data artificial intelligence air control.The present invention includes user's asset information database, user information processing subsystem, user's assets credit grade quantitative assessment subsystem, user's assets credit qualitative evaluation subsystem, assets credit grade synthesis result evaluation subsystem.The independence of system module effectively increases the maintainability and autgmentability of system, and also to which each commercial undertaking is facilitated to carry out personalized index Design according to actual conditions, the independence of evaluation index module has been fully considered when carrying out Software for Design.
Description
Technical field
The invention belongs to assets credit evaluation areas, and in particular to a kind of Assets Reorganization Taking based on big data artificial intelligence air control
Reason system and its appraisal procedure.
Background technology
Assets Management assesses main core business work as commercial credit, in the daily operation system of business
In highly important status.Under existing conditions, the quality of a commercial system whole economic efficiency, an area finance
The height of asset quality is heavily dependent on the height of asset management level.In order to strengthen asset management, realize intensive
It manages, scientific management, specification business operation flow, increases the supervision of assets, reduce asset risk, improve financial asset
The science of prediction and decision needs to design asset risk and evaluation for credit degree system based on user.
The evaluation for credit degree system of user's assets is one of current primary computer business application system of business system, and
And it will contain the information of diversification that is more increasingly complex than front desk service, more having break-up value.From the point of view of financial business angle, use
Family assets credit grade assessment system management is data that are traditional, being also main profitable business means at present, involved
Risk, also attract attention in the business of commercial credit.Therefore, it in business system information work have it is special and
Extremely important status.
The asset quality of the current solely state-owned commercial credit in China allows of no optimist.Four big solely stated-owned commercial bank of China is not
Good lending ratio is about 15.37%.And Bank of America's non-performing asset ratio is currently only 0.67%.Meanwhile some enterprises
Although assets meet the condition of credit on surface, actually management state is bad, causes bank's account receivable that cannot withdraw for a long time,
Potential risks are brought to bank portfolio.At home, the major business system in China is just embarking the risk management practice of oneself,
But mostly it is the management of preliminary assets operation, is not carried out the intelligence of risk management, the decision support system of informationization, networking
System.With business role and duty conversion of energy, loan transaction is growing day by day, and the risk by establishing assets is commented with credit grade
Estimate system, quick obtaining decision information analyses in depth loan quality, improves risk control and be ready for the challenge, improve competitiveness
Advantageous manner.
Currently, being completed some asset risks and evaluation for credit degree system, such as：Central Bank's credit registration management system,
Comprehensive business system, comprehensive credit line system and credit card management system etc., and sent out in different financial department application sites
Wave important role.The structure and main implementation technique means for analyzing these systems, are broadly divided into following several：
Application of the Component- Based Development method in DSS
The method comes from the thought of software reuse.It is substantially to already present software development knowledge and software development
The reuse of each phase results.Software component technology provides advantageous branch for realization Distributed Calculation inside application program
It holds.The versatility of DSS, flexibility are poor, are always the major reason for hindering it to be widely used.By software structure
The method of part is applied in the exploitation of decision system, contribute to solve DSS versatility and flexibility it is poor these
Problem.User completes the description to decision problem first, then systematically to problem analyze/identify, establishes model：User
After carrying out model selection/optimization by interactive means, implementation model simplifies operation to evaluate model, finally completes mould
The solution of type exports result.Complete model object COM components realize, and by these components carry out structure example when it is required
In structural information data and the storage to model library of the essential information of component itself.
The application of Realizing Bank Decision Support System based on data warehouse
The method establishes the intelligent decision system of business bank based on data warehouse, for supporting in management
Decision process.Usual DW and data mining (Data Mining) cooperate, and utilize data mining technology going through from data warehouse
Seek and explore useful information in history data, the development and decision to future provide branch.DW leads to the data of basic database
Cross extraction, conversion, by decision need each theme reorganize, for support decision (risk analysis, data mining, online point
Analysis is handled) best data format is provided.OLAP (On.1ine Analysis Processing) can be from multi-level, multi-angle
The rule for investigating data, shows result with diversified forms.DM is supported to carry out data mining from user from multi-level, multi-angle, be visited
Rope rule.Knowledge is excavated from data warehouse, and is put into the knowledge base of expert system as new knowledge, by knowing
The expert system for knowing reasoning carries out qualitative analysis aid decision.
The application MAS (Multi-Agent System) of the decision system of intelligent agent based on multi-Agent is to improve
The efficiency and effect of completion task are coupled or by Software Agent by the Agent of different function in certain hardware in a network environment
It is constituted in the environment of support, serves the system cooperated with each other between the same target, each Agent.In credit evaluation,
Expert largely from different fields such as finance, finance, management, statistics, predictions needs collaboration, parallel work.Different Agent
Between cooperate, be by what groupware expert system, information and knowledge system and computer hardware technique were constituted by building one
System the integration environment, " wisdom " of " intelligence " of machine and people is organically combined, is made from different field by coordination mechanism
Expert's effectively concurrent working overcomes individual behavior under bounded rationality to a certain extent by communication mode as blackboard
Defect, to ensure that the validity of credit evaluation system.
The application of decision system based on inference engine of expert system
Expert system is a system containing knowledge type program, it makes computer have human expert is such to solve to ask
The ability of topic, it is by a large amount of special knowledge to solve the challenge of specific area.It can carry out the work of certain mankind's solutions
Make, indicates knowledge in the form of rule or frame, dialogue can be interacted with people, can consider multiple hypothesis simultaneously.It is general
Using in artificial intelligence the representation of knowledge and knowledge reasoning technology simulate the challenge that common expert could solve, reach
With the level with the same ability to solve problem of expert.In general, it is suitable for completing the theory and method, number that those are not generally acknowledged
Diagnosis imperfect according to inaccurate or information, human expert is short or special knowledge is sufficiently expensive, explanation, monitoring, prediction, planning
With design etc. tasks.
These methods meet the needs of user and enterprise to a certain extent, further analysis compare these methods can
To find out：Component- Based Development method is a kind of effective implementation method in decision system exploitation, by using Reusable Components
Construct the method started all over again from the beginning that new system is used than most software developer much faster, and make establishment it is big, it is high
The software systems of quality are possibly realized.But this scheme is at present at home still without good component technology and product support；It is based on
Data warehouse and data mining realize that DSS has preferable effect, but the speed of service is slower, the efficiency of decision-making compared with
It is low, the support of a large amount of historical datas and the delay of decision-making time are needed, simultaneously because the complexity and data of data warehouse structure
The efficiency and effect problem of excavation so that the difficulty of exploitation, period and cost are higher.The country has realized several practical applications at present
Case, but effect unobvious, generally sensory adaption are poor, and system development cycle is longer, bring that system applies when
Ductility；Agent system can realize expert's collaboration from different fields such as finance, finance, management, statistics, predictions, parallel
Work, by building a system collection being made of groupware expert system, information and knowledge system and computer hardware technique
At environment, " wisdom " of " intelligence " of machine and people is organically combined, is overcome to a certain extent individual under bounded rationality
The defect of behavior, to ensure that the validity of system.But the program equally exists that the development cycle is longer, development difficulty compared with
Greatly, the higher drawback of cost；Decision system based on expert system can be directed to specific application field, establish the special of the field
Family's system knowledge base, and can realize Dynamic Maintenance and the growth of knowledge, providing reasoning for inference engine of expert system supports, enhancing system
The adaptability of system, while expert system makes inferences for common model in specific industry, can obtain in a short period of time
To the reasoning results and decision support, there is certain high efficiency and convenience.But evaluation index is difficult to objective and fair, is unfavorable for
The accuracy of decision judges.
Invention content
The purpose of the present invention is to provide a kind of asset management systems based on big data artificial intelligence air control.
The present invention also aims to provide a kind of asset management appraisal procedure based on big data artificial intelligence air control.
The object of the present invention is achieved like this：
A kind of asset management system based on big data artificial intelligence air control, including user's asset information database, user
Information processing subsystem, user's assets credit grade quantitative assessment subsystem, user's assets credit qualitative evaluation subsystem, assets
Credit grade synthesis result evaluation subsystem.
User's asset information database, which is searched for by network big data, extracted and sent, supports user information processing
System, user's assets credit grade quantitative assessment subsystem, user's assets credit qualitative evaluation subsystem and assets credit grade
The initial data of synthesis result evaluation subsystem；Storage is by user's assets credit grade quantitative assessment subsystem, user respectively
Assets credit qualitative evaluation subsystem is integrated according to the intermediate ephemeral data library file and assets credit grade for carrying out processing conversion
Intermediate result data after the credit evaluation model operation of outcome evaluation subsystem, with assessment report and credit evaluation result table
It is single.
The initial data that user information processing subsystem extraction user's asset information database provides carries out user
The typing of the typing of basic document and logical relation automatic Verification, user's basic document includes by the base of business personnel's craft typing
The basic information that plinth information, the basic information imported from standard electronic document and network big data are searched for, it is described
Logical relation automatic Verification refer to the verification of the logical relation in user's basic document of user information processing subsystem typing, and
Project to not meeting logical relation wherein gives warning prompt.
User's assets credit grade quantitative assessment subsystem completes the financial analysis to user according to initial data
Ephemeral data library file among user's assets credit grade quantitative assessment subsystem is obtained, user's assets credit grade is fixed
Ephemeral data library file includes transaction with credit financial analysis data, financial structure analysis data, payment of debts among amount Evaluation subsystem
Capability analysis data, management ability and performance analysis data, analysis of cash flow and developing ability analyze data.
The big number of network that user's assets credit qualitative evaluation subsystem is searched for by user's asset information database
The evaluation information of user is assessed in obtain ephemeral data library text among user's assets credit qualitative evaluation subsystem
Part.
The assets credit grade synthesis result evaluation subsystem is completed to user's assets credit grade quantitative assessment
Ephemeral data library file and user's assets credit grade quantitative assessment subsystem centre ephemeral data library file carry out among system
Ranking operation, and determine according to the quantitative model of user credit risk the assets credit grading index of user to be appraised, output by
The assets credit grading index of user is commented to export assets credit assessment report, credit evaluation result list.
The basic information includes user's lifetime, average education degree, marriage ratio, average health status, gender
Ratio, social relationships index；The transaction with credit financial analysis data include the current promise breaking index of current debt, debt early period
Promise breaking index；The financial structure analysis data include guaranty, collateral value ratio, the length of maturity, the amount of the loan；It is described
Analysis of clearing off debts ability data to include that average income is horizontal, total income is horizontal, monthly repayments principal and interest is shared take in proportion, other debts
Business index；The management ability and performance analysis data includes industry described in user, the average operation time limit, academic title's ratio, warp
Seek risk return profile；The analysis of cash flow and developing ability analysis data include amount of fixed assets evidence, average local inhabitation
The time limit, index is paid in insurance, common reserve fund pays index；Financial user's basic condition information, financial user's trade information, finance are used
Family debt paying ability index, financial user's stability indicator, financial user's reference index, credit product essential information index.
The basic information, transaction with credit financial analysis data, financial structure analysis data, analysis of clearing off debts ability number
Data constitutive characteristic index set is analyzed according to, management ability and performance analysis data, analysis of cash flow and developing ability
Y=[Y1、Y2、Y3…Yn]
YnThe characteristic index obtained by big data analysis according to the preset range of system for specific targets；
ylFor corresponding event YnFirst of numerical value of the big data extracted, αlFor ylThe power in corresponding big data source
Value, α0The basis estimation weights of database where big data.
To YnCarry out accuracy detection, detected value
For the preliminary setting parameter of place event index；
When U is in default threshold value σ, then Y is assertnAccuracy meets index request, based on adopting.
The assets credit grading index of the user to be appraised is Z, and Z=1 is user's promise breaking, Z=0 is that user does not break a contract,
By Z values according to being equally divided into 8 grades between 0 to 1, and Z ∈ [0-0.125) it is AAA grade, Z ∈ [0.125-0.25) it is AA grades, Z ∈ [0-
0.375) it is A grades, and Z ∈ [0.375-0.5) it is BBB grades, Z ∈ [0.5-0.625) it is BB grades, Z ∈ [0.625-0.75) it is B grades, Z
∈ [0.75-0.875) it is C grades, [0.875-1] is D grades；
Wherein, YnIt is characterized index, δnIt is characterized the corresponding weight vectors of index, εnIt is characterized the standard deviation of index, δ0For
The basic weight vector of characteristic index, ε0The basic standard for being characterized index is poor.
The characteristic index YnIncluding m section, section xn1 arrives xnM, wherein section xn1 includes pn1 value, section xnm
Including pnM is worth, then the entropy of this feature index
E=Kln Ω, K is characterized index coefficient,
Calculate the Y of characteristic indexnUnit entropy：
I is the arbitrary value of a value in m, and j is the arbitrary value in n；
qj=1-ej
α is characterized the average value of index.
The assets credit grade synthesis result evaluation subsystem carries out the assets credit grading index Z of user to be appraised
Efficiency rating obtains efficiency rating value F,
θnFor YnFor the contribution rate of system evaluation；
When F is in system evaluation metrics-thresholds D, then corresponding assets credit grade synthesis result evaluation subsystem to by
It comments the assets credit grading index Z of user to give to adopt.
A kind of asset management appraisal procedure based on big data artificial intelligence air control, includes the following steps：
(1) user's asset information database, which is searched for by network big data, extracted and sent, supports user information processing
System, user's assets credit grade quantitative assessment subsystem, user's assets credit qualitative evaluation subsystem and assets credit grade
The initial data of synthesis result evaluation subsystem；Storage is by user's assets credit grade quantitative assessment subsystem, user respectively
Assets credit qualitative evaluation subsystem is integrated according to the intermediate ephemeral data library file and assets credit grade for carrying out processing conversion
Intermediate result data after the credit evaluation model operation of outcome evaluation subsystem, with assessment report and credit evaluation result table
It is single；
(2) it is basic to carry out user for the initial data that user information processing subsystem extraction user's asset information database provides
The typing of data and logical relation automatic Verification, the typing of user's basic document include the basis letter by business personnel's craft typing
The basic information that breath, the basic information imported from standard electronic document and network big data are searched for, described patrols
Volume relationship automatic Verification refers to the verification of the logical relation in user's basic document of user information processing subsystem typing, and to it
In do not meet the project of logical relation and give warning prompt；
(3) user's assets credit grade quantitative assessment subsystem obtains the financial analysis of user according to initial data completion
Ephemeral data library file among user's assets credit grade quantitative assessment subsystem, user's assets credit grade are quantitatively commented
Ephemeral data library file includes transaction with credit financial analysis data, financial structure analysis data, debt paying ability among valence subsystem
It analyzes data, management ability and performance analysis data, analysis of cash flow and developing ability and analyzes data；
(5) in the network big data that user's assets credit qualitative evaluation subsystem is searched for by user's asset information database
The evaluation information of user is assessed to obtain ephemeral data library file among user's assets credit qualitative evaluation subsystem；
(6) assets credit grade synthesis result evaluation subsystem is completed to user's assets credit grade quantitative assessment subsystem
Ephemeral data library file is weighted among intermediate ephemeral data library file and user's assets credit grade quantitative assessment subsystem
Operation, and determine according to the quantitative model of user credit risk the assets credit grading index of user to be appraised, export use to be appraised
Assets credit grading index output assets credit assessment report, the credit evaluation result list at family.
The basic information includes user's lifetime, average education degree, marriage ratio, average health status, gender
Ratio, social relationships index；The transaction with credit financial analysis data include the current promise breaking index of current debt, debt early period
Promise breaking index；The financial structure analysis data include guaranty, collateral value ratio, the length of maturity, the amount of the loan；It is described
Analysis of clearing off debts ability data to include that average income is horizontal, total income is horizontal, monthly repayments principal and interest is shared take in proportion, other debts
Business index；The management ability and performance analysis data includes industry described in user, the average operation time limit, academic title's ratio, warp
Seek risk return profile；The analysis of cash flow and developing ability analysis data include amount of fixed assets evidence, average local inhabitation
The time limit, index is paid in insurance, common reserve fund pays index；Financial user's basic condition information, financial user's trade information, finance are used
Family debt paying ability index, financial user's stability indicator, financial user's reference index, credit product essential information index.
The basic information, transaction with credit financial analysis data, financial structure analysis data, analysis of clearing off debts ability number
Data constitutive characteristic index set is analyzed according to, management ability and performance analysis data, analysis of cash flow and developing ability
Y=[Y1、Y2、Y3…Yn]
YnThe characteristic index obtained by big data analysis according to the preset range of system for specific targets；
ylFor corresponding event YnFirst of numerical value of the big data extracted, αlFor ylThe power in corresponding big data source
Value, α0The basis estimation weights of database where big data；
To YnCarry out accuracy detection, detected value
For the preliminary setting parameter of place event index；
When U is in default threshold value σ, then Y is assertnAccuracy meets index request, based on adopting.
The assets credit grading index of the user to be appraised is Z, and Z=1 is user's promise breaking, Z=0 is that user does not break a contract,
By Z values according to being equally divided into 8 grades between 0 to 1, and Z ∈ [0-0.125) it is AAA grade, Z ∈ [0.125-0.25) it is AA grades, Z ∈ [0-
0.375) it is A grades, and Z ∈ [0.375-0.5) it is BBB grades, Z ∈ [0.5-0.625) it is BB grades, Z ∈ [0.625-0.75) it is B grades, Z
∈ [0.75-0.875) it is C grades, [0.875-1] is D grades；
Wherein, YnIt is characterized index, δnIt is characterized the corresponding weight vectors of index, εnIt is characterized the standard deviation of index, δ0For
The basic weight vector of characteristic index, ε0The basic standard for being characterized index is poor；
The characteristic index YnIncluding m section, section xn1 arrives xnM, wherein section xn1 includes pn1 value, section xnm
Including pnM is worth, then the entropy of this feature index
E=Kln Ω, K is characterized index coefficient,
Calculate the Y of characteristic indexnUnit entropy：
I is the arbitrary value of a value in m, and j is the arbitrary value in n；
qj=1-ej
α is characterized the average value of index.
The assets credit grade synthesis result evaluation subsystem carries out the assets credit grading index Z of user to be appraised
Efficiency rating obtains efficiency rating value F
θnFor YnFor the contribution rate of system evaluation；
When F is in system evaluation metrics-thresholds D, then corresponding assets credit grade synthesis result evaluation subsystem to by
It comments the assets credit grading index Z of user to give to adopt.
The beneficial effects of the present invention are：
(1) independence of system module effectively increases the maintainability and autgmentability of system, and also to convenient each
Commercial undertaking carries out personalized index Design according to actual conditions, and evaluation index module has been fully considered when carrying out Software for Design
Independence.That is, when adjusting evaluation index, does not have to modification program code, only need to adjust the arrange parameter of software i.e.
It can.
(2) relative independentability high-precision big, the gradually development with national economy and the industry knot of credit evaluation standard value
The continuous adjustment and upgrading of structure, some industries are larger in the fund performance difference in different years, therefore it is corresponding to be necessary to adjustment
Credit evaluation standard value.User credit assessment system has fully considered this characteristic, when this system is installed, can fill in advance
Upper credit evaluation standard value, when standard value needs adjustment, it is only necessary to be packed into standard value floppy disk or the new standard value of typing, no
Software must be reinstalled.
(3) in order to meet the needs of all types of user, system design has one for the personalization and flexibility of system and applicability
Fixed flexibility, applicability and personalization.It is mainly reflected in：The flexibility for evaluating data source, provides a variety of importings and export
Interface solves Data Integration, dynamic statement and management inquiry for credit department and provides means.
Description of the drawings
Fig. 1 is the schematic diagram of present system structure；
Fig. 2 is the method for the present invention general flow chart.
Specific implementation mode
The present invention is described further below in conjunction with the accompanying drawings.
As shown in Figure 1, a kind of asset management system based on big data artificial intelligence air control, including user's assets information number
According to library, user information processing subsystem, user's assets credit grade quantitative assessment subsystem, user's assets credit qualitative evaluation
System, assets credit grade synthesis result evaluation subsystem.
User's asset information database, which is searched for by network big data, extracted and sent, supports user information processing
System, user's assets credit grade quantitative assessment subsystem, user's assets credit qualitative evaluation subsystem and assets credit grade
The initial data of synthesis result evaluation subsystem；Storage is by user's assets credit grade quantitative assessment subsystem, user respectively
Assets credit qualitative evaluation subsystem is integrated according to the intermediate ephemeral data library file and assets credit grade for carrying out processing conversion
Intermediate result data after the credit evaluation model operation of outcome evaluation subsystem, with assessment report and credit evaluation result table
It is single.
The initial data that user information processing subsystem extraction user's asset information database provides carries out user
The typing of the typing of basic document and logical relation automatic Verification, user's basic document includes by the base of business personnel's craft typing
The basic information that plinth information, the basic information imported from standard electronic document and network big data are searched for, it is described
Logical relation automatic Verification refer to the verification of the logical relation in user's basic document of user information processing subsystem typing, and
Project to not meeting logical relation wherein gives warning prompt.
User's assets credit grade quantitative assessment subsystem completes the financial analysis to user according to initial data
Ephemeral data library file among user's assets credit grade quantitative assessment subsystem is obtained, user's assets credit grade is fixed
Ephemeral data library file includes transaction with credit financial analysis data, financial structure analysis data, payment of debts among amount Evaluation subsystem
Capability analysis data, management ability and performance analysis data, analysis of cash flow and developing ability analyze data.
The big number of network that user's assets credit qualitative evaluation subsystem is searched for by user's asset information database
The evaluation information of user is assessed in obtain ephemeral data library text among user's assets credit qualitative evaluation subsystem
Part.
The assets credit grade synthesis result evaluation subsystem is completed to user's assets credit grade quantitative assessment
Ephemeral data library file and user's assets credit grade quantitative assessment subsystem centre ephemeral data library file carry out among system
Ranking operation, and determine according to the quantitative model of user credit risk the assets credit grading index of user to be appraised, output by
The assets credit grading index of user is commented to export assets credit assessment report, credit evaluation result list.
The basic information includes user's lifetime, average education degree, marriage ratio, average health status, gender
Ratio, social relationships index；The transaction with credit financial analysis data include the current promise breaking index of current debt, debt early period
Promise breaking index；The financial structure analysis data include guaranty, collateral value ratio, the length of maturity, the amount of the loan；It is described
Analysis of clearing off debts ability data to include that average income is horizontal, total income is horizontal, monthly repayments principal and interest is shared take in proportion, other debts
Business index；The management ability and performance analysis data includes industry described in user, the average operation time limit, academic title's ratio, warp
Seek risk return profile；The analysis of cash flow and developing ability analysis data include amount of fixed assets evidence, average local inhabitation
The time limit, index is paid in insurance, common reserve fund pays index；Financial user's basic condition information, financial user's trade information, finance are used
Family debt paying ability index, financial user's stability indicator, financial user's reference index, credit product essential information index.
The system of the present invention allows independent variable and dependent variable, and there are errors, and structural equation model is compared with traditional statistical method
Biggest advantage, exactly allows between studied variable that there are specific error ranges.It is much difficult to directly calculate in reality
Go out the latent variable of result, such as business risk, customer satisfaction, employee's royalty, this just needs to go indirectly using certain methods
Estimation, and structural equation model provides for this method, introduces observational variable as the medium for measuring latent variable, this is biography
System statistical method is not accomplished.
The basic information, transaction with credit financial analysis data, financial structure analysis data, analysis of clearing off debts ability number
Data constitutive characteristic index set is analyzed according to, management ability and performance analysis data, analysis of cash flow and developing ability
Y=[Y1、Y2、Y3…Yn]
YnThe characteristic index obtained by big data analysis according to the preset range of system for specific targets；
ylFor corresponding event YnFirst of numerical value of the big data extracted, αlFor ylThe power in corresponding big data source
Value, α0The basis estimation weights of database where big data.
To YnCarry out accuracy detection, detected value
For the preliminary setting parameter of place event index；
When U is in default threshold value σ, then Y is assertnAccuracy meets index request, based on adopting.
The present invention provides diversified with suitable index, and whether traditional statistical method generally only sees desired value in output facet
Significantly, it once significantly just declaring refusal null hypothesis, but in research, as long as sample number is as many, even if influencing very little, can still reach
To significant effect.Therefore, structural equation model also provides two kinds of models and matches suitable index, each refers to other than assessed value
Mark indicates the characteristic of certain part of model specification, and the adaptability of judgment models can be carried out according to different indexs and is judged.
The assets credit grading index of the user to be appraised is Z, and Z=1 is user's promise breaking, Z=0 is that user does not break a contract,
By Z values according to being equally divided into 8 grades between 0 to 1, and Z ∈ [0-0.125) it is AAA grade, Z ∈ [0.125-0.25) it is AA grades, Z ∈ [0-
0.375) it is A grades, and Z ∈ [0.375-0.5) it is BBB grades, Z ∈ [0.5-0.625) it is BB grades, Z ∈ [0.625-0.75) it is B grades, Z
∈ [0.75-0.875) it is C grades, [0.875-1] is D grades；
Wherein, YnIt is characterized index, δnIt is characterized the corresponding weight vectors of index, εnIt is characterized the standard deviation of index, δ0For
The basic weight vector of characteristic index, ε0The basic standard for being characterized index is poor.
The characteristic index YnIncluding m section, section xn1 arrives xnM, wherein section xn1 includes pn1 value, section xnm
Including pnM is worth, then the entropy of this feature index
E=Kln Ω, K is characterized index coefficient,
Calculate the Y of characteristic indexnUnit entropy：
I is the arbitrary value of a value in m, and j is the arbitrary value in n；
qj=1-ej
α is characterized the average value of index.
The assets credit grade synthesis result evaluation subsystem carries out the assets credit grading index Z of user to be appraised
Efficiency rating obtains efficiency rating value F,
θnFor YnFor the contribution rate of system evaluation；
When F is in system evaluation metrics-thresholds D, then corresponding assets credit grade synthesis result evaluation subsystem to by
It comments the assets credit grading index Z of user to give to adopt.
By above-mentioned assessment system, the present invention can carry out the assessment of complex model.There are many dimension, Mei Gewei for one model
Degree can include more topic item, and the model of this complexity is very universal situation in fields such as education, psychology, management.It is passing
In the analysis of system, may analyze could repeatedly finish interpretation of result, during separated analysis, often have ignored variable
Between influence each other, cause structure inaccurate.And structural equation model can there are complex relationships in the calculating of same time
Variable deeply excavates the relationship between each variable, and more thinking spaces are provided to researcher.
A kind of asset management appraisal procedure based on big data artificial intelligence air control, includes the following steps：
(1) user's asset information database, which is searched for by network big data, extracted and sent, supports user information processing
System, user's assets credit grade quantitative assessment subsystem, user's assets credit qualitative evaluation subsystem and assets credit grade
The initial data of synthesis result evaluation subsystem；Storage is by user's assets credit grade quantitative assessment subsystem, user respectively
Assets credit qualitative evaluation subsystem is integrated according to the intermediate ephemeral data library file and assets credit grade for carrying out processing conversion
Intermediate result data after the credit evaluation model operation of outcome evaluation subsystem, with assessment report and credit evaluation result table
It is single；
(2) it is basic to carry out user for the initial data that user information processing subsystem extraction user's asset information database provides
The typing of data and logical relation automatic Verification, the typing of user's basic document include the basis letter by business personnel's craft typing
The basic information that breath, the basic information imported from standard electronic document and network big data are searched for, described patrols
Volume relationship automatic Verification refers to the verification of the logical relation in user's basic document of user information processing subsystem typing, and to it
In do not meet the project of logical relation and give warning prompt；
(3) user's assets credit grade quantitative assessment subsystem obtains the financial analysis of user according to initial data completion
Ephemeral data library file among user's assets credit grade quantitative assessment subsystem, user's assets credit grade are quantitatively commented
Ephemeral data library file includes transaction with credit financial analysis data, financial structure analysis data, debt paying ability among valence subsystem
It analyzes data, management ability and performance analysis data, analysis of cash flow and developing ability and analyzes data；
(5) in the network big data that user's assets credit qualitative evaluation subsystem is searched for by user's asset information database
The evaluation information of user is assessed to obtain ephemeral data library file among user's assets credit qualitative evaluation subsystem；
(6) assets credit grade synthesis result evaluation subsystem is completed to user's assets credit grade quantitative assessment subsystem
Ephemeral data library file is weighted among intermediate ephemeral data library file and user's assets credit grade quantitative assessment subsystem
Operation, and determine according to the quantitative model of user credit risk the assets credit grading index of user to be appraised, export use to be appraised
Assets credit grading index output assets credit assessment report, the credit evaluation result list at family.
The basic information includes user's lifetime, average education degree, marriage ratio, average health status, gender
Ratio, social relationships index；The transaction with credit financial analysis data include the current promise breaking index of current debt, debt early period
Promise breaking index；The financial structure analysis data include guaranty, collateral value ratio, the length of maturity, the amount of the loan；It is described
Analysis of clearing off debts ability data to include that average income is horizontal, total income is horizontal, monthly repayments principal and interest is shared take in proportion, other debts
Business index；The management ability and performance analysis data includes industry described in user, the average operation time limit, academic title's ratio, warp
Seek risk return profile；The analysis of cash flow and developing ability analysis data include amount of fixed assets evidence, average local inhabitation
The time limit, index is paid in insurance, common reserve fund pays index；Financial user's basic condition information, financial user's trade information, finance are used
Family debt paying ability index, financial user's stability indicator, financial user's reference index, credit product essential information index.
The basic information, transaction with credit financial analysis data, financial structure analysis data, analysis of clearing off debts ability number
Data constitutive characteristic index set is analyzed according to, management ability and performance analysis data, analysis of cash flow and developing ability
Y=[Y1、Y2、Y3…Yn]
YnThe characteristic index obtained by big data analysis according to the preset range of system for specific targets；
ylFor corresponding event YnFirst of numerical value of the big data extracted, αlFor ylThe power in corresponding big data source
Value, α0The basis estimation weights of database where big data；
To YnCarry out accuracy detection, detected value
For the preliminary setting parameter of place event index；
When U is in default threshold value σ, then Y is assertnAccuracy meets index request, based on adopting.
The assets credit grading index of the user to be appraised is Z, and Z=1 is user's promise breaking, Z=0 is that user does not break a contract,
By Z values according to being equally divided into 8 grades between 0 to 1, and Z ∈ [0-0.125) it is AAA grade, Z ∈ [0.125-0.25) it is AA grades, Z ∈ [0-
0.375) it is A grades, and Z ∈ [0.375-0.5) it is BBB grades, Z ∈ [0.5-0.625) it is BB grades, Z ∈ [0.625-0.75) it is B grades, Z
∈ [0.75-0.875) it is C grades, [0.875-1] is D grades；
Wherein, YnIt is characterized index, δnIt is characterized the corresponding weight vectors of index, εnIt is characterized the standard deviation of index, δ0For
The basic weight vector of characteristic index, ε0The basic standard for being characterized index is poor；
The characteristic index YnIncluding m section, section xn1 arrives xnM, wherein section xn1 includes pn1 value, section xnm
Including pnM is worth, then the entropy of this feature index
E=Kln Ω, K is characterized index coefficient,
Calculate the Y of characteristic indexnUnit entropy：
I is the arbitrary value of a value in m, and j is the arbitrary value in n；
qj=1-ej
α is characterized the average value of index.
The assets credit grade synthesis result evaluation subsystem carries out the assets credit grading index Z of user to be appraised
Efficiency rating obtains efficiency rating value F
θnFor YnFor the contribution rate of system evaluation；
When F is in system evaluation metrics-thresholds D, then corresponding assets credit grade synthesis result evaluation subsystem to by
It comments the assets credit grading index Z of user to give to adopt.
This method of assessment in conjunction with to(for) user credit grade finds this method when carrying out credit scoring to user, such as
The credit grade of fruit user is forward, then usual Default Probability is also relatively small, credit risk is also smaller.If the credit of user
Grade ranks behind, then user also can not necessarily break a contract, can only illustrate in selected user combines, the letter of credit of user
Condition is not so good as other users, user can be divided into loan class user with caution, this result is also to be consistent with reality.This explanation
Model selected by the present invention has carried out complementation in the selection of index, emphasizes particularly on different fields, and models coupling can be measured more comprehensively
The assets credit risk of user.
In conclusion the present invention acquires number by artificial intelligence analysis's technology based on big data in network information flow
According to being analyzed, generally by commenting realizing the credit risk that can meet financial institution's application demand to tally with the national condition
Estimate decision system；Establishing, there is dynamic can safeguard and the credit database of more new function, Credit Model library and knowledge base；It will research
Achievement carries out applied analysis in the financial institution of cooperation, the industrialization promotion for realizing product, constantly improve letter is needed in conjunction with market
With assessment models and credit database.
Here it must be noted that other unaccounted structures that the present invention provides are because be all the known knot of this field
Structure, title or function according to the present invention, those skilled in the art can find the document of related record, therefore not do
It further illustrates.The technical means disclosed in the embodiments of the present invention is not limited only to the technological means disclosed in the above embodiment, also
Include by the above technical characteristic arbitrarily the formed technical solution of combination.
Claims (10)
1. a kind of asset management system based on big data artificial intelligence air control, including user's asset information database, Yong Huxin
Cease processing subsystem, user's assets credit grade quantitative assessment subsystem, user's assets credit qualitative evaluation subsystem, assets letter
With grade synthesis result evaluation subsystem；It is characterized in that：
User's asset information database, which is searched for by network big data, extracted and sent, supports user information to handle subsystem
System, user's assets credit grade quantitative assessment subsystem, user's assets credit qualitative evaluation subsystem and assets credit grade are comprehensive
Close the initial data of outcome evaluation subsystem；Storage is by user's assets credit grade quantitative assessment subsystem, Yong Huzi respectively
Production credit qualitative evaluation subsystem is according to the intermediate ephemeral data library file and assets credit grade synthesis knot for carrying out processing conversion
Intermediate result data after the credit evaluation model operation of fruit evaluation subsystem, with assessment report and credit evaluation result list；
It is basic that the initial data that user information processing subsystem extraction user's asset information database provides carries out user
The typing of data and logical relation automatic Verification, the typing of user's basic document include the basis letter by business personnel's craft typing
The basic information that breath, the basic information imported from standard electronic document and network big data are searched for, described patrols
Volume relationship automatic Verification refers to the verification of the logical relation in user's basic document of user information processing subsystem typing, and to it
In do not meet the project of logical relation and give warning prompt；
User's assets credit grade quantitative assessment subsystem obtains the financial analysis of user according to initial data completion
Ephemeral data library file among user's assets credit grade quantitative assessment subsystem, user's assets credit grade are quantitatively commented
Ephemeral data library file includes transaction with credit financial analysis data, financial structure analysis data, debt paying ability among valence subsystem
It analyzes data, management ability and performance analysis data, analysis of cash flow and developing ability and analyzes data；
In the network big data that user's assets credit qualitative evaluation subsystem is searched for by user's asset information database
The evaluation information of user is assessed to obtain ephemeral data library file among user's assets credit qualitative evaluation subsystem；
The assets credit grade synthesis result evaluation subsystem is completed to user's assets credit grade quantitative assessment subsystem
Ephemeral data library file is weighted among intermediate ephemeral data library file and user's assets credit grade quantitative assessment subsystem
Operation, and determine according to the quantitative model of user credit risk the assets credit grading index of user to be appraised, export use to be appraised
Assets credit grading index output assets credit assessment report, the credit evaluation result list at family.
2. a kind of asset management system based on big data artificial intelligence air control according to claim 1, it is characterised in that：
The basic information includes user's lifetime, average education degree, marriage ratio, average health status, sex ratio, society
Relationship index；The transaction with credit financial analysis data include the current promise breaking index of current debt, debt promise breaking early period index；
The financial structure analysis data include guaranty, collateral value ratio, the length of maturity, the amount of the loan；The payment of debts energy
Power analysis data include that average income is horizontal, total income is horizontal, the shared income proportion of monthly repayment principal and interest, other debt indexs；
The management ability and performance analysis data includes industry described in user, the average operation time limit, academic title's ratio, operating income shape
Condition；The analysis of cash flow and developing ability analysis data include amount of fixed assets evidence, the average local inhabitation time limit, insurance
Pay index, common reserve fund pays index；Financial user's basic condition information, financial user's trade information, financial user's payment of debts energy
Power index, financial user's stability indicator, financial user's reference index, credit product essential information index.
3. a kind of asset management system based on big data artificial intelligence air control according to claim 2, it is characterised in that：
The basic information, financial structure analysis data, analysis of clearing off debts ability data, manages energy at transaction with credit financial analysis data
Power and performance analysis data, analysis of cash flow and developing ability analyze data constitutive characteristic index set
Y=[Y1、Y2、Y3…Yn]
YnThe characteristic index obtained by big data analysis according to the preset range of system for specific targets；
ylFor corresponding event YnFirst of numerical value of the big data extracted, αlFor ylThe weights in corresponding big data source, α0For
The basis estimation weights of database where big data；
To YnCarry out accuracy detection, detected value
For the preliminary setting parameter of place event index；
When U is in default threshold value σ, then Y is assertnAccuracy meets index request, based on adopting.
4. a kind of asset management system based on big data artificial intelligence air control according to claim 1, it is characterised in that：
The assets credit grading index of the user to be appraised be Z, Z=1 be user promise breaking, Z=0 be that user does not break a contract, by Z values according to
It is equally divided into 8 grades between 0 to 1, and Z ∈ [0-0.125) it is AAA grade, Z ∈ [0.125-0.25) it is AA grades, Z ∈ [0-0.375) for A
Grade, and Z ∈ [0.375-0.5) it is BBB grades, Z ∈ [0.5-0.625) it is BB grades, Z ∈ [0.625-0.75) it is B grades, Z ∈ [0.75-
0.875) it is C grades, [0.875-1] is D grades；
Wherein, YnIt is characterized index, δnIt is characterized the corresponding weight vectors of index, εnIt is characterized the standard deviation of index, δ0It is characterized
The basic weight vector of index, ε0The basic standard for being characterized index is poor；
The characteristic index YnIncluding m section, section xn1 arrives xnM, wherein section xn1 includes pn1 value, section xnM includes
pnM is worth, then the entropy of this feature index
E=Kln Ω, K is characterized index coefficient,
Calculate the Y of characteristic indexnUnit entropy：
I is the arbitrary value of a value in m, and j is the arbitrary value in n；
qj=1-ej
α is characterized the average value of index.
5. a kind of asset management system based on big data artificial intelligence air control according to claim 4, it is characterised in that：
The assets credit grade synthesis result evaluation subsystem carries out efficiency rating to the assets credit grading index Z of user to be appraised
Obtain efficiency rating value F
θnFor YnFor the contribution rate of system evaluation；
When F is in system evaluation metrics-thresholds D, then corresponding assets credit grade synthesis result evaluation subsystem is to use to be appraised
The assets credit grading index Z at family, which gives, to be adopted.
6. a kind of asset management appraisal procedure based on big data artificial intelligence air control, which is characterized in that include the following steps：
(1) user's asset information database by the search of network big data, extract and send support user information processing subsystem,
User's assets credit grade quantitative assessment subsystem, user's assets credit qualitative evaluation subsystem and assets credit grade synthesis knot
The initial data of fruit evaluation subsystem；Storage is believed by user's assets credit grade quantitative assessment subsystem, user's assets respectively
It is commented according to the intermediate ephemeral data library file and assets credit grade synthesis result for carrying out processing conversion with qualitative evaluation subsystem
Estimate the intermediate result data after the credit evaluation model operation of subsystem, with assessment report and credit evaluation result list；
(2) initial data that user information processing subsystem extraction user's asset information database provides carries out user's basic document
Typing and logical relation automatic Verification, the typing of user's basic document include by business personnel's craft typing basic information,
The basic information that the basic information and network big data imported from standard electronic document is searched for, the logic are closed
It is the verification for the logical relation that automatic Verification refers in user's basic document of user information processing subsystem typing, and to wherein not
The project for meeting logical relation gives warning prompt；
(3) user's assets credit grade quantitative assessment subsystem obtains user according to initial data completion to the financial analysis of user
Ephemeral data library file among assets credit grade quantitative assessment subsystem, user's assets credit grade quantitative assessment
Ephemeral data library file includes transaction with credit financial analysis data, financial structure analysis data, analysis of clearing off debts ability among system
Data, management ability and performance analysis data, analysis of cash flow and developing ability analyze data；
(5) in the network big data that user's assets credit qualitative evaluation subsystem is searched for by user's asset information database for
The evaluation information of user is assessed to obtain ephemeral data library file among user's assets credit qualitative evaluation subsystem；
(6) assets credit grade synthesis result evaluation subsystem is completed among to user's assets credit grade quantitative assessment subsystem
Ephemeral data library file is weighted among ephemeral data library file and user's assets credit grade quantitative assessment subsystem,
And the assets credit grading index of user to be appraised is determined according to the quantitative model of user credit risk, export the money of user to be appraised
Produce credit grade index output assets credit assessment report, credit evaluation result list.
7. a kind of asset management system based on big data artificial intelligence air control according to claim 6, it is characterised in that：
The basic information includes user's lifetime, average education degree, marriage ratio, average health status, sex ratio, society
Relationship index；The transaction with credit financial analysis data include the current promise breaking index of current debt, debt promise breaking early period index；
The financial structure analysis data include guaranty, collateral value ratio, the length of maturity, the amount of the loan；The payment of debts energy
Power analysis data include that average income is horizontal, total income is horizontal, the shared income proportion of monthly repayment principal and interest, other debt indexs；
The management ability and performance analysis data includes industry described in user, the average operation time limit, academic title's ratio, operating income shape
Condition；The analysis of cash flow and developing ability analysis data include amount of fixed assets evidence, the average local inhabitation time limit, insurance
Pay index, common reserve fund pays index；Financial user's basic condition information, financial user's trade information, financial user's payment of debts energy
Power index, financial user's stability indicator, financial user's reference index, credit product essential information index.
8. a kind of asset management system based on big data artificial intelligence air control according to claim 7, it is characterised in that：
The basic information, financial structure analysis data, analysis of clearing off debts ability data, manages energy at transaction with credit financial analysis data
Power and performance analysis data, analysis of cash flow and developing ability analyze data constitutive characteristic index set
Y=[Y1、Y2、Y3…Yn]
YnThe characteristic index obtained by big data analysis according to the preset range of system for specific targets；
ylFor corresponding event YnFirst of numerical value of the big data extracted, αlFor ylThe weights in corresponding big data source, α0For
The basis estimation weights of database where big data；
To YnCarry out accuracy detection, detected value
For the preliminary setting parameter of place event index；
When U is in default threshold value σ, then Y is assertnAccuracy meets index request, based on adopting.
9. a kind of asset management system based on big data artificial intelligence air control according to claim 8, it is characterised in that：
The assets credit grading index of the user to be appraised be Z, Z=1 be user promise breaking, Z=0 be that user does not break a contract, by Z values according to
It is equally divided into 8 grades between 0 to 1, and Z ∈ [0-0.125) it is AAA grade, Z ∈ [0.125-0.25) it is AA grades, Z ∈ [0-0.375) for A
Grade, and Z ∈ [0.375-0.5) it is BBB grades, Z ∈ [0.5-0.625) it is BB grades, Z ∈ [0.625-0.75) it is B grades, Z ∈ [0.75-
0.875) it is C grades, [0.875-1] is D grades；
Wherein, YnIt is characterized index, δnIt is characterized the corresponding weight vectors of index, εnIt is characterized the standard deviation of index, δ0It is characterized
The basic weight vector of index, ε0The basic standard for being characterized index is poor；
The characteristic index YnIncluding m section, section xn1 arrives xnM, wherein section xn1 includes pn1 value, section xnM includes
pnM is worth, then the entropy of this feature index
E=Kln Ω, K is characterized index coefficient,
Calculate the Y of characteristic indexnUnit entropy：
I is the arbitrary value of a value in m, and j is the arbitrary value in n；
qj=1-ej
α is characterized the average value of index.
10. a kind of asset management system based on big data artificial intelligence air control according to claim 9, feature exist
In：The assets credit grade synthesis result evaluation subsystem is to the assets credit grading index Z of user to be appraised into line efficiency
Evaluation obtains efficiency rating value F
θnFor YnFor the contribution rate of system evaluation；
When F is in system evaluation metrics-thresholds D, then corresponding assets credit grade synthesis result evaluation subsystem is to use to be appraised
The assets credit grading index Z at family, which gives, to be adopted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810289057.6A CN108734567A (en) | 2018-04-03 | 2018-04-03 | A kind of asset management system and its appraisal procedure based on big data artificial intelligence air control |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810289057.6A CN108734567A (en) | 2018-04-03 | 2018-04-03 | A kind of asset management system and its appraisal procedure based on big data artificial intelligence air control |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108734567A true CN108734567A (en) | 2018-11-02 |
Family
ID=63941173
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810289057.6A Pending CN108734567A (en) | 2018-04-03 | 2018-04-03 | A kind of asset management system and its appraisal procedure based on big data artificial intelligence air control |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108734567A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109598605A (en) * | 2018-11-26 | 2019-04-09 | 格锐科技有限公司 | A kind of long-distance intelligent assessment and loan self-aid system based on entity guaranty |
| CN111160783A (en) * | 2019-12-30 | 2020-05-15 | 北京阿尔山区块链联盟科技有限公司 | Method and system for evaluating digital asset value and electronic equipment |
| CN111581296A (en) * | 2020-04-02 | 2020-08-25 | 深圳壹账通智能科技有限公司 | Data correlation analysis method and device, computer system and readable storage medium |
| CN114548820A (en) * | 2022-03-07 | 2022-05-27 | 济南数聚计算机科技有限公司 | Big data wind control method and server for distance education service |
| CN115907956A (en) * | 2022-09-27 | 2023-04-04 | 睿智合创(北京)科技有限公司 | Simulation early warning method and system for asset risk |
| CN118628235A (en) * | 2024-08-14 | 2024-09-10 | 无锡锡商银行股份有限公司 | Risk assessment method for house mortgage loan |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101667266A (en) * | 2008-09-03 | 2010-03-10 | 山东征信信用管理咨询有限公司 | Credit rating management consultation system |
| CN105069701A (en) * | 2015-08-10 | 2015-11-18 | 国网上海市电力公司 | Monte Carlo method based risk evaluation method for power transmission system |
| CN105303311A (en) * | 2015-10-21 | 2016-02-03 | 中国人民解放军装甲兵工程学院 | Assessment index selection method and device based on data envelopment analysis |
-
2018
- 2018-04-03 CN CN201810289057.6A patent/CN108734567A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101667266A (en) * | 2008-09-03 | 2010-03-10 | 山东征信信用管理咨询有限公司 | Credit rating management consultation system |
| CN105069701A (en) * | 2015-08-10 | 2015-11-18 | 国网上海市电力公司 | Monte Carlo method based risk evaluation method for power transmission system |
| CN105303311A (en) * | 2015-10-21 | 2016-02-03 | 中国人民解放军装甲兵工程学院 | Assessment index selection method and device based on data envelopment analysis |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109598605A (en) * | 2018-11-26 | 2019-04-09 | 格锐科技有限公司 | A kind of long-distance intelligent assessment and loan self-aid system based on entity guaranty |
| CN111160783A (en) * | 2019-12-30 | 2020-05-15 | 北京阿尔山区块链联盟科技有限公司 | Method and system for evaluating digital asset value and electronic equipment |
| CN111160783B (en) * | 2019-12-30 | 2023-10-24 | 北京阿尔山区块链联盟科技有限公司 | Digital asset value evaluation method and system and electronic equipment |
| CN111581296A (en) * | 2020-04-02 | 2020-08-25 | 深圳壹账通智能科技有限公司 | Data correlation analysis method and device, computer system and readable storage medium |
| CN111581296B (en) * | 2020-04-02 | 2022-08-16 | 深圳壹账通智能科技有限公司 | Data correlation analysis method and device, computer system and readable storage medium |
| CN114548820A (en) * | 2022-03-07 | 2022-05-27 | 济南数聚计算机科技有限公司 | Big data wind control method and server for distance education service |
| CN114548820B (en) * | 2022-03-07 | 2022-11-01 | 极客邦控股(北京)有限公司 | Big data wind control method and server for distance education service |
| CN115907956A (en) * | 2022-09-27 | 2023-04-04 | 睿智合创(北京)科技有限公司 | Simulation early warning method and system for asset risk |
| CN118628235A (en) * | 2024-08-14 | 2024-09-10 | 无锡锡商银行股份有限公司 | Risk assessment method for house mortgage loan |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bose et al. | Big data, data analytics and artificial intelligence in accounting: An overview | |
| CN108734567A (en) | A kind of asset management system and its appraisal procedure based on big data artificial intelligence air control | |
| WO2021088499A1 (en) | False invoice issuing identification method and system based on dynamic network representation | |
| CN101714273A (en) | Rule engine-based method and system for monitoring exceptional service of bank | |
| US8065177B2 (en) | Project management system and method | |
| Gao | The use of machine learning combined with data mining technology in financial risk prevention | |
| CN109685651A (en) | The credit risk monitoring method and device of current assets mortgage | |
| CN110472815A (en) | To the risk control method and system of financing enterprise in a kind of supply chain financial business | |
| CN105259816A (en) | Bank dynamic credit monitoring system based on wireless sensing network and method | |
| CN114048436A (en) | Construction method and construction device for forecasting enterprise financial data model | |
| CN117670056A (en) | Data analysis system for financial management | |
| CN115145993A (en) | Railway freight big data visualization display platform based on self-learning rule operation | |
| CN112668822A (en) | Scientific and technological achievement transformation platform sharing system, method, storage medium and mobile phone APP | |
| CN110689437A (en) | Communication construction project financial risk prediction method based on random forest | |
| Scherer et al. | On the practical art of state definitions for Markov decision process construction | |
| Zeng | Neural Network Technology‐Based Optimization Framework of Financial and Management Accounting Model | |
| Biswas et al. | Stock Market Prediction: A Survey and Evaluation | |
| Pavelková et al. | Passenger car sales projections: Measuring the accuracy of a sales forecasting model | |
| Zhang et al. | Dynamic time warp-based clustering: Application of machine learning algorithms to simulation input modelling | |
| Sun | Intelligent data mining based on market circulation of production factors | |
| Qiang et al. | [Retracted] Relationship Model between Human Resource Management Activities and Performance Based on LMBP Algorithm | |
| US20170004521A1 (en) | Systems and methods for generating industry outlook scores | |
| CN117132383A (en) | Credit data processing method, device, equipment and readable storage medium | |
| Moubariki et al. | Enhancing cash management using machine learning | |
| Xu et al. | Research on Multistage Dynamic Trading Model Based on Gray Model and Auto‐Regressive Integrated Moving Average Model |
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 |