CN110046993A - Illicit gain legalizes behavior monitoring method, system, computer installation and medium - Google Patents
Illicit gain legalizes behavior monitoring method, system, computer installation and medium Download PDFInfo
- Publication number
- CN110046993A CN110046993A CN201811537506.0A CN201811537506A CN110046993A CN 110046993 A CN110046993 A CN 110046993A CN 201811537506 A CN201811537506 A CN 201811537506A CN 110046993 A CN110046993 A CN 110046993A
- Authority
- CN
- China
- Prior art keywords
- money laundering
- account
- money
- model
- identification
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000009434 installation Methods 0.000 title claims abstract description 29
- 238000004900 laundering Methods 0.000 claims abstract description 213
- 238000005406 washing Methods 0.000 claims abstract description 60
- 238000003860 storage Methods 0.000 claims abstract description 39
- 238000003062 neural network model Methods 0.000 claims description 43
- 238000012549 training Methods 0.000 claims description 40
- 238000004590 computer program Methods 0.000 claims description 22
- 238000012550 audit Methods 0.000 claims description 17
- 238000012795 verification Methods 0.000 claims description 8
- 210000002569 neuron Anatomy 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 8
- 238000012790 confirmation Methods 0.000 description 5
- 238000012546 transfer Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 235000013399 edible fruits Nutrition 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- -1 6 months) Chemical compound 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 2
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 230000014759 maintenance of location Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 239000002574 poison Substances 0.000 description 1
- 231100000614 poison Toxicity 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The present invention provides a kind of illicit gain and legalizes behavior monitoring method, system, computer installation and computer readable storage medium.The illicit gain legalize behavior monitoring method include: obtain history anti money washing record data；The money laundering identification model that data establish different Account Types for identification is recorded according to the history anti money washing；Money laundering Monitoring instruction is received, and reads the online stream data of Account Type information and account trading generation from transaction system database according to the Monitoring instruction；By the online stream data read and Account Type information input to the money laundering identification model, to carry out money laundering risks identification；Classification storage is carried out to the recognition result that the money laundering identification model exports according to default classifying rules, and exports the account information with money laundering suspicion.The present invention is based on neural networks to establish money laundering identification model, it can be achieved that carrying out money laundering identification to online transaction stream data, and anti money washing behavior monitoring timeliness is high.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of money laundering monitoring method, system, computer installation and meters
Calculation machine readable storage medium storing program for executing.
Background technique
Money laundering is a kind of behavior that illicit gain legalizes, and generally refers to cover up by various modes, conceals such as poison
Product crime, terrorist activity crime, smuggling offences, crime of embezzlement and bribery, destroys Financial Management at crimes with gangster connections and characteristics
The money-laundering in the source and property of the crime such as order crime gained and its income, common money laundering approach relate generally to silver
The various fields such as row, insurance, security, real estate.Anti money washing is that government employs legislation, judicial strength, transfer related tissue and
Commercial undertaking identifies possible money-laundering, is disposed to related fund, is punished associated mechanisms and personage
It penalizes, to reach the systematic engineering of business for preventing criminal activity purpose.In the prior art, anti money washing system mainly passes through pre-
If analysis rule it is for statistical analysis to off-line trading data, to obtain corresponding off-line analysis result.This kind of mode lacks
The ability of weary online recognition cannot analyze in time online transaction data, so cause to be monitored anti money washing behavior
Timeliness it is not high, be unfavorable for anti money washing business personnel and find money laundering account in time and take relevant management and control measures.
Summary of the invention
In view of above-mentioned, the present invention provides a kind of money laundering monitoring method, system, computer installation and computer-readable storage medium
Matter may be implemented to analyze online transaction data in time, and monitoring timeliness is high.
One embodiment of the application provides a kind of money laundering monitoring method, which comprises
It obtains history anti money washing and records data, wherein history anti money washing record data include money laundering account transactional data
And non-money laundering account transactional data；
The money laundering identification model that data establish different Account Types for identification is recorded according to the history anti money washing；
Money laundering Monitoring instruction is received, and Account Type information is read from transaction system database according to the Monitoring instruction
And the online stream data that account trading generates；
By the online stream data read and Account Type information input to the money laundering identification model, to carry out
Money laundering risks identification；And
Classification storage is carried out to the recognition result that the money laundering identification model exports according to default classifying rules, and exports tool
There is the account information of money laundering suspicion.
Preferably, described that the money laundering knowledge that data establish different Account Types for identification is recorded according to the history anti money washing
The step of other model includes:
A neural network model is established, the neural network model includes input layer, multiple hidden layers and output layer；And
The neural network model is trained using history anti money washing record data to obtain the money laundering identification
Model.
Preferably, described that the neural network model is trained to obtain institute using history anti money washing record data
The step of stating money laundering identification model include:
History anti money washing record data are divided into training set and verifying collection；
The neural network model is trained using the training set；
The neural network model after training is verified using verifying collection, and is counted according to each verification result
To a model prediction accuracy rate；
Judge whether the model prediction accuracy rate is less than preset threshold；And
When the model prediction accuracy rate is not less than the preset threshold, by the neural network model of training completion
As the money laundering identification model.
Preferably, it is described judge the step of whether the model prediction accuracy rate is less than preset threshold after further include:
When the model prediction accuracy rate is less than the preset threshold, the parameter of the neural network model is adjusted, and
Neural network model adjusted is trained again using the training set；
The neural network model of re -training is verified using verifying collection, and again according to each verification result
Statistics obtains a model prediction accuracy rate, and judges whether the model prediction accuracy rate counted again is less than preset threshold；
When the model prediction accuracy rate counted again is not less than the preset threshold, by the re -training
Obtained neural network model is as the money laundering identification model；And
When the model prediction accuracy rate counted again be less than the preset threshold when, repeat the above steps until
The model prediction accuracy rate obtained by the verifying collection verifying is not less than the preset threshold；
Wherein, the parameter of the neural network model includes the neuron number of total number of plies, each layer.
Preferably, described to read Account Type information and account friendship from transaction system database according to the Monitoring instruction
Include: after the step of online stream data being also easy to produce
The online stream data that the Account Type information read and account trading generate is stored to a buffer area.
Preferably, the recognition result that the basis presets that classifying rules exports the money laundering identification model carries out classification and deposits
The step of storage includes:
Classify according to the recognition result that default classifying rules exports the money laundering identification model, and by same category
Recognition result saved in a manner of sparse storage；
Wherein, the default classifying rules includes carrying out classifying according to Account Type and/or being divided according to recognition result
Class.
Preferably, after the output has the step of account information of money laundering suspicion further include:
The account information with money laundering suspicion is sent to rear end audit platform, is examined with carrying out account money laundering risks
Core.
One embodiment of the application provides a kind of money laundering monitoring system, the system comprises:
Module is obtained, for obtaining history anti money washing record data, wherein history anti money washing record data include washing
Money account transactional data and non-money laundering account transactional data；
Module is established, for recording the money laundering that data establish different Account Types for identification according to the history anti money washing
Identification model；
Read module is read from transaction system database for receiving money laundering Monitoring instruction, and according to the Monitoring instruction
The online stream data for taking Account Type information and account trading to generate；
Identification module, for knowing the online stream data read and Account Type information input to the money laundering
Other model, to carry out money laundering risks identification；And
Storage and output module, for according to preset recognition result that classifying rules exports the money laundering identification model into
Row classification storage, and export the account information with money laundering suspicion.
One embodiment of the application provides a kind of computer installation, and the computer installation includes processor and memory,
Several computer programs are stored on the memory, the processor is for when executing the computer program stored in memory
The step of realizing money laundering monitoring method as elucidated before.
One embodiment of the application provides a kind of computer readable storage medium, is stored thereon with computer program, described
The step of money laundering monitoring method as elucidated before is realized when computer program is executed by processor.
Above-mentioned money laundering monitoring method, system, computer installation and computer readable storage medium, based on neural network with go through
History anti money washing record data are established and train to obtain money laundering identification model, by the acquisition online stream data of transaction system and defeated
Enter to money laundering identification model to identify the trading account with money laundering suspicion, and model can also be identified to suspicion transaction account
Family is sent to backstage and carries out audit confirmation again, and anti money washing identifies that accuracy is high, may be implemented to carry out online transaction data and
When analyze, monitoring timeliness is high.
Detailed description of the invention
It, below will be to required in embodiment description in order to illustrate more clearly of the technical solution of embodiment of the present invention
The attached drawing used is briefly described, it should be apparent that, the accompanying drawings in the following description is some embodiments of the present invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is the step flow chart of money laundering monitoring method in one embodiment of the invention.
Fig. 2 is the functional block diagram that money laundering monitors system in one embodiment of the invention.
Fig. 3 is computer schematic device in one embodiment of the invention.
Specific embodiment
To better understand the objects, features and advantages of the present invention, with reference to the accompanying drawing and specific real
Applying mode, the present invention will be described in detail.It should be noted that in the absence of conflict, presently filed embodiment and reality
The feature applied in mode can be combined with each other.
In the following description, numerous specific details are set forth in order to facilitate a full understanding of the present invention, described embodiment
Only some embodiments of the invention, rather than whole embodiments.Based on the embodiment in the present invention, this field
Those of ordinary skill's every other embodiment obtained without making creative work, belongs to guarantor of the present invention
The range of shield.
Unless otherwise defined, all technical and scientific terms used herein and belong to technical field of the invention
The normally understood meaning of technical staff is identical.Term as used herein in the specification of the present invention is intended merely to description tool
The purpose of the embodiment of body, it is not intended that in the limitation present invention.
Preferably, money laundering monitoring method of the invention is applied in one or more computer installation.The computer
Device is that one kind can be according to the instruction for being previously set or storing, the automatic equipment for carrying out numerical value calculating and/or information processing,
Hardware includes but is not limited to microprocessor, specific integrated circuit (Application Specific Integrated
Circuit, ASIC), programmable gate array (Field-Programmable Gate Array, FPGA), digital processing unit
(Digital Signal Processor, DSP), embedded device etc..
The computer installation can be the calculating such as desktop PC, laptop, tablet computer, server and set
It is standby.The computer installation can carry out people by modes such as keyboard, mouse, remote controler, touch tablet or voice-operated devices with user
Machine interaction.
Embodiment one:
Fig. 1 is the step flow chart of money laundering monitoring method preferred embodiment of the present invention.The process according to different requirements,
The sequence of step can change in figure, and certain steps can be omitted.
As shown in fig.1, the money laundering monitoring method specifically includes following steps.
Step S11, it obtains history anti money washing and records data, wherein history anti money washing record data include money laundering account
Transaction data and non-money laundering account transactional data.
In one embodiment, the history anti money washing record data, which can be, is collected and is existed by big data to one in advance
If in database, can be communicated to connect by being established with the presetting database, and then to obtain history from presetting database
Anti money washing records data.The history anti money washing record data are also possible to the Historical Monitoring data of anti money washing monitoring department.Institute
Stating history anti money washing record data includes money laundering account transactional data and non-money laundering account transactional data.
In one embodiment, the history anti money washing in an available designated time period records data, for example obtains most
Nearly 1 year money laundering account transactional data and non-money laundering account transactional data.
Step S12, the money laundering identification that data establish different Account Types for identification is recorded according to the history anti money washing
Model.
In one embodiment, the money laundering identification model can be one based on neural network model and a large amount of money laundering account
Family, non-money laundering account historical trading data train come disaggregated model.Money laundering identification model after training can have
There is a plurality of money laundering recognition rule, and money laundering identification can be carried out to different Account Types.
The different types of account trading amount of money differs greatly, corresponding for different Account Types to be different money laundering identification
Rule.Account Type may include personal account, individual industrial and commercial account, business account, and wherein business account can also be according to enterprise
Industry scale, affiliated industry, registion time etc. are further segmented.
In one embodiment, the neural network model includes input layer, multiple hidden layers and output layer.Input layer is used
In receiving training data (history anti money washing records data), each hidden layer includes corresponding multiple nodes (neuron), Mei Yiyin
Each node in hiding layer is configured to the output at least one node of the adjacent lower in the model and executes line
Property or nonlinear transformation.Wherein, the input of the node of upper layer hidden layer can be based on a node in adjacent lower or several
The output of node.Each hidden layer has corresponding weight, and wherein the weight is obtained based on training data.To model into
When row training, the initial of each hidden layer can be obtained by carrying out the pre-training of model using there is the learning process of supervision
Weight.It, can be by using back-propagation (Back propagation, BP) algorithm to fine-tuning for the weight of each hidden layer
It carries out, output layer is for receiving the output signal from the last layer hidden layer.
In one embodiment, the history anti money washing record data are divided into training set and verifying collection.Wherein,
Training set is for being trained neural network model, and verifying collection is for verifying the neural network model after training.Tool
Body, neural network model is trained first with the training set to obtain a mid-module, the account that the verifying is concentrated
Family type and account transactional data are input in the mid-module progress money laundering suspicion verifying, can be with according to each verification result
Statistics obtains a model prediction accuracy rate, judges whether the model prediction accuracy rate is less than preset threshold.
When the model prediction accuracy rate is not less than the preset threshold, show that this mid-module classifying quality is preferable, it is full
Sufficient use demand, can be using the mid-module as the money laundering identification model.When model prediction accuracy rate is less than described pre-
If when threshold value, showing that this mid-module classifying quality is bad, being improved, adjust the ginseng of the neural network model at this time
Number, and neural network model adjusted is trained again using the training set to obtain a new mid-module, then
Again the mid-module retrieved is verified to obtain a new model prediction accuracy rate using verifying collection, and is judged
Whether the model prediction accuracy rate counted again is less than preset threshold；When the model prediction counted again is accurate
When rate is not less than the preset threshold, the neural network model that the re -training is obtained is as the money laundering identification model；
When the model prediction accuracy rate counted again is less than the preset threshold, repeat the above steps until by described
The model prediction accuracy rate that verifying collection verifying obtains is not less than the preset threshold.
In one embodiment, the parameter of the adjustment neural network model can be adjustment neural network model
Total number of plies and/or the neuron number etc. of each layer of adjustment.The preset threshold can be set according to actual use demand, example
Such as it is set as 95%.
For example, the money laundering identification model can identify the doubtful money laundering account with following transaction: a. client
Same day funds stream transfinites volume, and cash flow includes gathering, pay the bill and withdraws deposit that (such as personal industrial and commercial account surpasses 2,000,000 limits, enterprise's account
Family surpasses 9,000,000 limits)；B. before client's first three days cash flow reaches first threshold (such as 2,000,000), and rear three days cash flows are
3 times or more of three days, and trading frequency is the 2 times or more of first three days；(such as N=10) is personal or individual in c.N consecutive days
Industrial and commercial account is greater than 10 in period in morning (1:00-5:00) transaction stroke count, and cumulative transaction amount is greater than 20W；D.N certainly
In the right moon (such as 6 months), individual industry and commerce account is greater than in the improper transaction accounting for managing time (such as 23:00-08:00)
50%；In e.N calendar month (such as 6 months), transaction amount is that the transaction accounting of 100 integral multiples is greater than 70%.
Step S13 receives money laundering Monitoring instruction, and reads account from transaction system database according to the Monitoring instruction
The online stream data that type information and account trading generate.
In one embodiment, the money laundering Monitoring instruction can be anti money washing monitoring device, software exports after triggering
Instruction.Realization can be fetched when receiving money laundering Monitoring instruction by establishing communication link with transaction system, referred to according to the monitoring
Enable the online stream data that Account Type information and account trading generation are read from transaction system database.Transaction system can be with
For the operation system of the financial institutions such as bank, securities broker company, insurance company, transaction system is used to handle and record the storage of user
The various financial business such as store, transfer accounts, investing, the transaction data that transaction system generates will be stored in transaction system database.
In one embodiment, by taking the transaction system of bank as an example, since the daily number of transaction of bank is very huge,
The savings of bank account, the related services information-distribution type such as transfer accounts, remit money are stored in multiple storages including a transaction system
In equipment, so guarantee the business datum of storage magnanimity.Binlog log can be read from transaction system, and is sent to
Apache Kafka message queue, to obtain online stream data.Wherein, Apache Kafka, that is, distributed post-subscription
Message system, mainly for the treatment of active online stream data, Apache Kafka has following compared with conventional message system
Different: Apache Kafka is designed to a distributed system, is easy to extend to the outside, and can mention simultaneously for publication and subscription
For high-throughput, support more subscribers, when failure can autobalance consumer, can be by message duration to disk, therefore can
For consuming in batches.In other embodiments of the invention, transaction system can also be read by other distributed information systems
The systems such as the online stream data, such as RabbitMQ, Apache ActiveMQ that system generates.
In one embodiment, first the Account Type information and account that read from transaction system database can be handed over
The online stream data being also easy to produce is stored to a buffer area, and subsequent step takes out data from buffer area again, is handed over to avoid occupying
Easy system resource prompts data-handling efficiency.
The online stream data read and Account Type information input to the money laundering are identified mould by step S14
Type, to carry out money laundering risks identification.
In one embodiment, the online stream data read and Account Type information input to training are completed
Money laundering identification model so that may be implemented money laundering risks identification.If recognizing an account A1 to meet in money laundering identification model
Money laundering rule, then money laundering identification model will export the recognition result that account A1 is suspicious money laundering account, if recognizing an account
Family A2 is unsatisfactory for the rule of the money laundering in money laundering identification model, then money laundering identification model will export the knowledge that account A2 is normal account
Other result.For example, the money laundering identification model includes a following rule after training: client's same day funds stream transfinites
Volume, cash flow includes gathering, pay the bill and withdraws deposit that (such as personal industrial and commercial account surpasses 2,000,000 limits, business account surpasses 9,000,000 limits
Volume).If detecting, some artificial quotient's account A odd-numbered day cash flow was 2,200,000 (being greater than 2,000,000), can export personal industry and commerce
Account A has the recognition result of money laundering risks, if detecting, the odd-numbered day cash flow of a business account B is that 1000W (is greater than 900
Ten thousand) recognition result that business account B has money laundering risks can, then be exported.
Step S15 carries out classification storage to the recognition result that the money laundering identification model exports according to default classifying rules,
And export the account information with money laundering suspicion.
In one embodiment, since online stream data amount is huge, corresponding money laundering recognition result data also will
It is very huge, to save storage resource, knot can be identified to the money laundering of money laundering identification model output by the way of sparse storage
Fruit is saved.It can classify according to default classifying rules to money laundering risks recognition result, and by same category of identification
As a result it is saved in a manner of sparse storage.Wherein, the default classifying rules can be configured according to actual needs, than
If the default classifying rules includes carrying out classifying and/or classifying according to recognition result according to Account Type, can also incite somebody to action
Account Type is different but type of service and the identical result of money laundering risks are divided into same class.
In one embodiment, the account information with money laundering suspicion, the account without money laundering suspicion can only be exported
Information can be without output and be summarized and exported the account information with money laundering suspicion in a manner of a list.
For example, the recognition result of the money laundering identification model output is as shown in table 1:
Table 1
It,, can be identical by this part when Va value high concentration under the combination for finding some Le+It in an analysis time
Data be recorded in additional table, former table only record other Va distribution record.The following table 2 be table 1 sparse analysis as a result, its
Middle Cnt indicates to be in same account levels, same type of service, and has the recognition result item number of same Va value, passes through statistics
Obtain in sparse analysis result comprising two major classes: account levels L1, type of service are Item 1, and Value value is the Cnt value of V1
It is 5, proportion 0.833, and account levels are L1, type of service is Item 1, and the Cnt value that Value value is V2 is 1, institute
Accounting example is 0.167.
Table 2
Since account levels are L1, type of service is Item 1, and Va value compares concentration for the record of V1, therefore can be by this
The identical data in part are recorded in table 3.
Table 3
The account information with money laundering suspicion is sent to rear end audit platform, to carry out account money laundering by step S16
Risk audit.
In one embodiment, when detecting the account of money laundering suspicion by the money laundering identification model, by the tool
There are the account trading flowing water of money laundering suspicion and account essential information to be sent to rear end audit platform, is examined with carrying out account money laundering risks
Core, such as rear end audit platform are provided with manual examination and verification mechanism, anti money washing business personnel can account to the money laundering suspicion into
Row audit confirmation again, to judge whether to improve money laundering with money laundering suspicion and identify accuracy.
Above-mentioned money laundering monitoring method is established based on neural network and history anti money washing record data and trains to obtain money laundering knowledge
Other model is identified by obtaining the online stream data of transaction system and being input to money laundering identification model with money laundering suspicion
Trading account, and model can also be identified suspicion trading account be sent to backstage carry out again audit confirmation, anti money washing
It identifies that accuracy is high, may be implemented to analyze online transaction data in time, monitoring timeliness is high.
Embodiment two:
Fig. 2 is the functional block diagram that money laundering of the present invention monitors system preferred embodiment.
As shown in fig.2, the money laundering monitoring system 10 may include obtaining module 101, establishing module 102, read mould
Block 103, identification module 104, storage and output module 105 and sending module 106.
The acquisition module 101 is for obtaining history anti money washing record data, wherein the history anti money washing records data
Including money laundering account transactional data and non-money laundering account transactional data.
In one embodiment, the history anti money washing record data, which can be, is collected and is existed by big data to one in advance
If in database, can be communicated to connect by being established with the presetting database, and then to obtain history from presetting database
Anti money washing records data.The history anti money washing record data are also possible to the Historical Monitoring data of anti money washing monitoring department.Institute
Stating history anti money washing record data includes money laundering account transactional data and non-money laundering account transactional data.
In one embodiment, the history anti money washing record obtained in the available designated time period of module 101
Data, for example obtain nearest 1 year money laundering account transactional data and non-money laundering account transactional data.
The module 102 of establishing is for recording data foundation different Account Types for identification according to the history anti money washing
Money laundering identification model.
In one embodiment, the money laundering identification model can be one based on neural network model and a large amount of money laundering account
Family, non-money laundering account historical trading data train come disaggregated model.Money laundering identification model after training can have
There is a plurality of money laundering recognition rule, and money laundering identification can be carried out to different Account Types.
The different types of account trading amount of money differs greatly, corresponding for different Account Types to be different money laundering identification
Rule.Account Type may include personal account, individual industrial and commercial account, business account, and wherein business account can also be according to enterprise
Industry scale, affiliated industry, registion time etc. are further segmented.
In one embodiment, the neural network model includes input layer, multiple hidden layers and output layer.Input layer is used
In receiving training data (history anti money washing records data), each hidden layer includes corresponding multiple nodes (neuron), Mei Yiyin
Each node in hiding layer is configured to the output at least one node of the adjacent lower in the model and executes line
Property or nonlinear transformation.Wherein, the input of the node of upper layer hidden layer can be based on a node in adjacent lower or several
The output of node.Each hidden layer has corresponding weight, and wherein the weight is obtained based on training data.To model into
When row training, the initial of each hidden layer can be obtained by carrying out the pre-training of model using there is the learning process of supervision
Weight.It, can be by using back-propagation (Back propagation, BP) algorithm to fine-tuning for the weight of each hidden layer
It carries out, output layer is for receiving the output signal from the last layer hidden layer.
In one embodiment, the history anti money washing record data are divided into training set and verifying collection.Wherein,
Training set is for being trained neural network model, and verifying collection is for verifying the neural network model after training.Tool
Body, the module 102 of establishing is trained neural network model first with the training set to obtain a mid-module, by institute
The Account Type and account transactional data for stating verifying concentration are input to progress money laundering suspicion verifying in the mid-module, according to every
One verification result can count to obtain a model prediction accuracy rate, judge whether the model prediction accuracy rate is less than default threshold
Value.
When the model prediction accuracy rate is not less than the preset threshold, show that this mid-module classifying quality is preferable, it is full
Sufficient use demand, can be using the mid-module as the money laundering identification model.When model prediction accuracy rate is less than described pre-
If when threshold value, showing that this mid-module classifying quality is bad, being improved, adjust the ginseng of the neural network model at this time
Number, and neural network model adjusted is trained again using the training set to obtain a new mid-module, then
Again the mid-module retrieved is verified to obtain a new model prediction accuracy rate using verifying collection, and is judged
Whether the model prediction accuracy rate counted again is less than preset threshold；When the model prediction counted again is accurate
When rate is not less than the preset threshold, the neural network model that the re -training is obtained is as the money laundering identification model；
When the model prediction accuracy rate counted again is less than the preset threshold, repeat the above steps until by described
The model prediction accuracy rate that verifying collection verifying obtains is not less than the preset threshold.
In one embodiment, it is described establish module 102 adjust the neural network model parameter can be adjustment mind
The neuron number etc. of total number of plies and/or each layer of adjustment through network model.The preset threshold can be according to actual use need
It asks and is set, such as be set as 95%.
For example, the money laundering identification model can identify the doubtful money laundering account with following transaction: a. client
Same day funds stream transfinites volume, and cash flow includes gathering, pay the bill and withdraws deposit that (such as personal industrial and commercial account surpasses 2,000,000 limits, enterprise's account
Family surpasses 9,000,000 limits)；B. before client's first three days cash flow reaches first threshold (such as 2,000,000), and rear three days cash flows are
3 times or more of three days, and trading frequency is the 2 times or more of first three days；(such as N=10) is personal or individual in c.N consecutive days
Industrial and commercial account is greater than 10 in period in morning (1:00-5:00) transaction stroke count, and cumulative transaction amount is greater than 20W；D.N certainly
In the right moon (such as 6 months), individual industry and commerce account is greater than in the improper transaction accounting for managing time (such as 23:00-08:00)
50%；In e.N calendar month (such as 6 months), transaction amount is that the transaction accounting of 100 integral multiples is greater than 70%.
The read module 103 is for receiving money laundering Monitoring instruction, and according to the Monitoring instruction from transaction system data
The online stream data of Account Type information and account trading generation is read in library.
In one embodiment, the money laundering Monitoring instruction can be anti money washing monitoring device, software exports after triggering
Instruction.The read module 103 can fetch realization when receiving money laundering Monitoring instruction by establishing communication link with transaction system,
The online streaming number of Account Type information and account trading generation is read from transaction system database according to the Monitoring instruction
According to.Transaction system can be the operation system of the financial institutions such as bank, securities broker company, insurance company, and transaction system is for handling
And the various financial business such as the savings of user are recorded, transfers accounts, invest, the transaction data that transaction system generates will be stored in transaction
In system database.
In one embodiment, by taking the transaction system of bank as an example, since the daily number of transaction of bank is very huge,
The savings of bank account, the related services information-distribution type such as transfer accounts, remit money are stored in multiple storages including a transaction system
In equipment, so guarantee the business datum of storage magnanimity.Binlog log can be read from transaction system, and is sent to
Apache Kafka message queue, to obtain online stream data.Wherein, Apache Kafka, that is, distributed post-subscription
Message system, mainly for the treatment of active online stream data, Apache Kafka has following compared with conventional message system
Different: Apache Kafka is designed to a distributed system, is easy to extend to the outside, and can mention simultaneously for publication and subscription
For high-throughput, support more subscribers, when failure can autobalance consumer, can be by message duration to disk, therefore can
For consuming in batches.In other embodiments of the invention, transaction system can also be read by other distributed information systems
The systems such as the online stream data, such as RabbitMQ, Apache ActiveMQ that system generates.
In one embodiment, the account that the read module 103 will first can be read from transaction system database
The online stream data that type information and account trading generate is stored to a buffer area, and subsequent step takes out number from buffer area again
According to avoid transaction system resource, prompt data-handling efficiency is occupied.
The identification module 104 is used for the online stream data read and Account Type information input to described
Money laundering identification model, to carry out money laundering risks identification.
In one embodiment, the identification module 104 believes the online stream data read and Account Type
Breath is input to the money laundering identification model of training completion and then money laundering risks identification may be implemented.If recognizing account A1 satisfaction
Money laundering rule in money laundering identification model, then money laundering identification model will export the identification knot that account A1 is suspicious money laundering account
Fruit, if recognizing the money laundering rule that an account A2 is unsatisfactory in money laundering identification model, money laundering identification model will export account
Family A2 is the recognition result of normal account.For example, the money laundering identification model includes a following rule: visitor after training
Family same day funds stream transfinites volume, and cash flow includes gathering, pay the bill and withdraws deposit that (such as personal industrial and commercial account surpasses 2,000,000 limits, enterprise
Account surpasses 9,000,000 limits).If detecting, some artificial quotient's account A odd-numbered day cash flow was 2,200,000 (are greater than 2,000,000), can be with
The recognition result that individual industry and commerce account A has money laundering risks is exported, the odd-numbered day cash flow of a business account B is if detecting
1000W (is greater than 9,000,000), then can export the recognition result that business account B has money laundering risks.
The identification that the storage is used to export the money laundering identification model according to classifying rules is preset with output module 105
As a result classification storage is carried out, and exports the account information with money laundering suspicion.
In one embodiment, since online stream data amount is huge, corresponding money laundering recognition result data also will
It is very huge, to save storage resource, knot can be identified to the money laundering of money laundering identification model output by the way of sparse storage
Fruit is saved.The storage can divide money laundering risks recognition result according to default classifying rules with output module 105
Class, and same category of recognition result is saved in a manner of sparse storage.Wherein, the default classifying rules can root
It is configured according to actual demand, for example the default classifying rules includes classification being carried out according to Account Type and/or according to identification
As a result classify, can also Account Type is different but type of service and the identical result of money laundering risks be divided into same class.
In one embodiment, the storage can only export the account information with money laundering suspicion with output module 105,
Account information without money laundering suspicion can be without output and be summarized in a manner of a list and exported with money laundering suspicion
Account information.
For example, the recognition result of the money laundering identification model output is as shown in table 1:
Table 1
It,, can be identical by this part when Va value high concentration under the combination for finding some Le+It in an analysis time
Data be recorded in additional table, former table only record other Va distribution record.The following table 2 be table 1 sparse analysis as a result, its
Middle Cnt indicates to be in same account levels, same type of service, and has the recognition result item number of same Va value, passes through statistics
Obtain in sparse analysis result comprising two major classes: account levels L1, type of service are Item 1, and Value value is the Cnt value of V1
It is 5, proportion 0.833, and account levels are L1, type of service is Item 1, and the Cnt value that Value value is V2 is 1, institute
Accounting example is 0.167.
Table 2
Since account levels are L1, type of service is Item 1, and Va value compares concentration for the record of V1, therefore can be by this
The identical data in part are recorded in table 3.
Table 3
The sending module 106 is used to for the account information with money laundering suspicion being sent to rear end audit platform, with
Carry out the audit of account money laundering risks.
In one embodiment, when detecting the account of money laundering suspicion by the money laundering identification model, the hair
Send module 106 by the account trading flowing water and account essential information with money laundering suspicion be sent to rear end audit platform, with into
The audit of row account money laundering risks, such as rear end audit platform are provided with manual examination and verification mechanism, and anti money washing business personnel can be to this
The account of money laundering suspicion carries out audit confirmation again, to judge whether to improve money laundering with money laundering suspicion and identify accuracy.
Above-mentioned money laundering monitors system, is established based on neural network and history anti money washing record data and trains to obtain money laundering knowledge
Other model is identified by obtaining the online stream data of transaction system and being input to money laundering identification model with money laundering suspicion
Trading account, and model can also be identified suspicion trading account be sent to backstage carry out again audit confirmation, anti money washing
It identifies that accuracy is high, may be implemented to analyze online transaction data in time, monitoring timeliness is high.
Fig. 3 is the schematic diagram of computer installation preferred embodiment of the present invention.
The computer installation 1 includes memory 20, processor 30 and is stored in the memory 20 and can be in institute
State the computer program 40 run on processor 30, such as money laundering monitoring program.The processor 30 executes the computer journey
The step in above-mentioned money laundering monitoring method embodiment, such as step S11~S16 shown in FIG. 1 are realized when sequence 40.Alternatively, described
Processor 30 realizes the function of each module in above-mentioned money laundering monitoring system embodiment when executing the computer program 40, such as schemes
Module 101~106 in 2.
Illustratively, the computer program 40 can be divided into one or more module/units, it is one or
Multiple module/the units of person are stored in the memory 20, and are executed by the processor 30, to complete the present invention.It is described
One or more module/units can be the series of computation machine program instruction section that can complete specific function, described instruction section
For describing implementation procedure of the computer program 40 in the computer installation 1.For example, the computer program 40 can
Be divided into Fig. 2 acquisition module 101, establish module 102, read module 103, identification module 104, storage and output
Module 105 and sending module 106.Each module concrete function is referring to embodiment two.
The computer installation 1 can be the calculating such as desktop PC, notebook, palm PC and cloud server and set
It is standby.It will be understood by those skilled in the art that the schematic diagram is only the example of computer installation 1, do not constitute to computer
The restriction of device 1 may include perhaps combining certain components or different components, example than illustrating more or fewer components
Such as described computer installation 1 can also include input-output equipment, network access equipment, bus.
Alleged processor 30 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic device
Part, discrete hardware components etc..General processor can be microprocessor or the processor 30 be also possible to it is any conventional
Processor etc., the processor 30 is the control centre of the computer installation 1, entire using various interfaces and connection
The various pieces of computer installation 1.
The memory 20 can be used for storing the computer program 40 and/or module/unit, and the processor 30 passes through
Operation executes the computer program and/or module/unit being stored in the memory 20, and calls and be stored in memory
Data in 20 realize the various functions of the computer installation 1.The memory 20 can mainly include storing program area and deposit
Store up data field, wherein storing program area can application program needed for storage program area, at least one function (for example sound is broadcast
Playing function, image player function etc.) etc.；Storage data area, which can be stored, uses created data according to computer installation 1
(such as audio data, phone directory etc.) etc..In addition, memory 20 may include high-speed random access memory, can also include
Nonvolatile memory, such as hard disk, memory, plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), safety
Digital (Secure Digital, SD) card, flash card (Flash Card), at least one disk memory, flush memory device or
Other volatile solid-state parts.
If the integrated module/unit of the computer installation 1 is realized in the form of SFU software functional unit and as independence
Product when selling or using, can store in a computer readable storage medium.Based on this understanding, of the invention
It realizes all or part of the process in above-described embodiment method, can also instruct relevant hardware come complete by computer program
At the computer program can be stored in a computer readable storage medium, and the computer program is held by processor
When row, it can be achieved that the step of above-mentioned each embodiment of the method.Wherein, the computer program includes computer program code, institute
Stating computer program code can be source code form, object identification code form, executable file or certain intermediate forms etc..It is described
Computer-readable medium may include: any entity or device, recording medium, U that can carry the computer program code
Disk, mobile hard disk, magnetic disk, CD, computer storage, read-only memory (ROM, Read-Only Memory), arbitrary access
Memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It needs
It is bright, the content that the computer-readable medium includes can according in jurisdiction make laws and patent practice requirement into
Row increase and decrease appropriate, such as do not include electric load according to legislation and patent practice, computer-readable medium in certain jurisdictions
Wave signal and telecommunication signal.
In several embodiments provided by the present invention, it should be understood that disclosed computer installation and method, it can be with
It realizes by another way.For example, computer installation embodiment described above is only schematical, for example, described
The division of unit, only a kind of logical function partition, there may be another division manner in actual implementation.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in same treatment unit
It is that each unit physically exists alone, can also be integrated in same unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of hardware adds software function module.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included in the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.This
Outside, it is clear that one word of " comprising " does not exclude other units or steps, and odd number is not excluded for plural number.It is stated in computer installation claim
Multiple units or computer installation can also be implemented through software or hardware by the same unit or computer installation.The
One, the second equal words are used to indicate names, and are not indicated any particular order.
Finally it should be noted that the above examples are only used to illustrate the technical scheme of the present invention and are not limiting, although reference
Preferred embodiment describes the invention in detail, those skilled in the art should understand that, it can be to of the invention
Technical solution is modified or equivalent replacement, without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. a kind of money laundering monitoring method, which is characterized in that the described method includes:
It obtains history anti money washing and records data, wherein history anti money washing record data include money laundering account transactional data and non-
Money laundering account transactional data；
The money laundering identification model that data establish different Account Types for identification is recorded according to the history anti money washing；
Money laundering Monitoring instruction is received, and Account Type information and account are read from transaction system database according to the Monitoring instruction
The online stream data that family transaction generates；
By the online stream data read and Account Type information input to the money laundering identification model, to carry out money laundering
Risk identification；And
Classification storage is carried out to the recognition result that the money laundering identification model exports according to default classifying rules, and exports to have and wash
The account information of money suspicion.
2. money laundering monitoring method as described in claim 1, which is characterized in that described to record data according to the history anti money washing
The step of establishing the money laundering identification model of different Account Types for identification include:
A neural network model is established, the neural network model includes input layer, multiple hidden layers and output layer；And
The neural network model is trained to obtain the money laundering identification model using history anti money washing record data.
3. money laundering monitoring method as claimed in claim 2, which is characterized in that described to record data using the history anti money washing
Being trained the step of obtaining the money laundering identification model to the neural network model includes:
History anti money washing record data are divided into training set and verifying collection；
The neural network model is trained using the training set；
The neural network model after training is verified using verifying collection, and counts to obtain one according to each verification result
Model prediction accuracy rate；
Judge whether the model prediction accuracy rate is less than preset threshold；And
When the model prediction accuracy rate be not less than the preset threshold when, will training complete the neural network model as
The money laundering identification model.
4. money laundering monitoring method as claimed in claim 3, which is characterized in that described whether to judge the model prediction accuracy rate
After the step of less than preset threshold further include:
When the model prediction accuracy rate is less than the preset threshold, the parameter of the neural network model is adjusted, and utilize
The training set is again trained neural network model adjusted；
The neural network model of re -training is verified using verifying collection, and is counted again according to each verification result
A model prediction accuracy rate is obtained, and judges whether the model prediction accuracy rate counted again is less than preset threshold；
When the model prediction accuracy rate counted again is not less than the preset threshold, the re -training is obtained
Neural network model as the money laundering identification model；And
When the model prediction accuracy rate counted again is less than the preset threshold, repeat the above steps until passing through
The model prediction accuracy rate that the verifying collection verifying obtains is not less than the preset threshold；
Wherein, the parameter of the neural network model includes the neuron number of total number of plies, each layer.
5. money laundering monitoring method as described in claim 1, which is characterized in that it is described according to the Monitoring instruction from transaction system
Include: after the step of online stream data that reading Account Type information and account trading generate in database
The online stream data that the Account Type information read and account trading generate is stored to a buffer area.
6. money laundering monitoring method as claimed in claim 1 or 5, which is characterized in that the basis presets classifying rules to described
Money laundering identification model output recognition result carry out classification storage the step of include:
Classify according to the recognition result that default classifying rules exports the money laundering identification model, and by same category of knowledge
Other result is saved in a manner of sparse storage；
Wherein, the default classifying rules includes carrying out classifying and/or classifying according to recognition result according to Account Type.
7. money laundering monitoring method as claimed in claim 1 or 5, which is characterized in that the output has the account of money laundering suspicion
After the step of information further include:
The account information with money laundering suspicion is sent to rear end audit platform, to carry out account money laundering risks audit.
8. a kind of money laundering monitors system, which is characterized in that the system comprises:
Module is obtained, for obtaining history anti money washing record data, wherein history anti money washing record data include money laundering account
Family transaction data and non-money laundering account transactional data；
Module is established, for recording the money laundering identification that data establish different Account Types for identification according to the history anti money washing
Model；
Read module reads account from transaction system database for receiving money laundering Monitoring instruction, and according to the Monitoring instruction
The online stream data that family type information and account trading generate；
Identification module, for the online stream data read and Account Type information input to the money laundering to be identified mould
Type, to carry out money laundering risks identification；And
Storage and output module, the recognition result for being exported according to default classifying rules to the money laundering identification model divide
Class storage, and export the account information with money laundering suspicion.
9. a kind of computer installation, the computer installation includes processor and memory, is stored on the memory several
Computer program, which is characterized in that such as right is realized when the processor is for executing the computer program stored in memory
It is required that described in any one of 1-7 the step of money laundering monitoring method.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of money laundering monitoring method as described in any one of claim 1-7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811537506.0A CN110046993A (en) | 2018-12-15 | 2018-12-15 | Illicit gain legalizes behavior monitoring method, system, computer installation and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811537506.0A CN110046993A (en) | 2018-12-15 | 2018-12-15 | Illicit gain legalizes behavior monitoring method, system, computer installation and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110046993A true CN110046993A (en) | 2019-07-23 |
Family
ID=67273745
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811537506.0A Pending CN110046993A (en) | 2018-12-15 | 2018-12-15 | Illicit gain legalizes behavior monitoring method, system, computer installation and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110046993A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110659989A (en) * | 2019-09-10 | 2020-01-07 | 马洪富 | Active exploration type compliance anti-money laundering method, device, system and storage medium |
| CN110852884A (en) * | 2019-11-15 | 2020-02-28 | 成都数联铭品科技有限公司 | Data processing system and method for anti-money laundering recognition |
| CN111127200A (en) * | 2019-11-25 | 2020-05-08 | 中国建设银行股份有限公司 | Method and device for monitoring suspicious transactions of anti-money laundering |
| CN111160745A (en) * | 2019-12-23 | 2020-05-15 | 中国建设银行股份有限公司 | User account data processing method and device |
| CN111292195A (en) * | 2020-02-28 | 2020-06-16 | 中国工商银行股份有限公司 | Risk account identification method and device |
| CN111709844A (en) * | 2020-05-13 | 2020-09-25 | 北京明略软件系统有限公司 | Insurance money laundering personnel detection method and device and computer readable storage medium |
| CN111738868A (en) * | 2020-06-11 | 2020-10-02 | 北京向上一心科技有限公司 | Anti-money laundering anti-terrorist financing risk monitoring method, device, computer equipment and storage medium |
| CN112132693A (en) * | 2020-09-28 | 2020-12-25 | 平安养老保险股份有限公司 | Transaction verification method, transaction verification device, computer equipment and computer-readable storage medium |
| CN112184238A (en) * | 2020-09-23 | 2021-01-05 | 中国建设银行股份有限公司 | Anti-money laundering monitoring method and device for financial leasing industry, electronic equipment and medium |
| CN112329862A (en) * | 2020-11-09 | 2021-02-05 | 杭州安恒信息技术股份有限公司 | Decision tree-based anti-money laundering method and system |
| CN112418933A (en) * | 2020-11-24 | 2021-02-26 | 深圳市新系区块链技术有限公司 | Transaction data processing method, system and related equipment |
| CN112508705A (en) * | 2020-12-18 | 2021-03-16 | 北京航空航天大学 | Method and system for detecting money laundering transaction in complex association transaction |
| CN112906765A (en) * | 2021-02-01 | 2021-06-04 | 中国建设银行股份有限公司 | RBF neural network-based customer money laundering risk grading method and system |
| CN113240425A (en) * | 2021-04-27 | 2021-08-10 | 湖南大学 | Financial anti-money laundering transaction method, device and storage medium based on deep learning |
| CN113379540A (en) * | 2020-11-09 | 2021-09-10 | 中科金审(北京)科技有限公司 | Capital data analysis system |
| CN113469816A (en) * | 2021-09-03 | 2021-10-01 | 浙江中科华知科技股份有限公司 | Digital currency identification method, system and storage medium based on multigroup technology |
| CN113592505A (en) * | 2021-08-25 | 2021-11-02 | 国泰君安证券股份有限公司 | System, method, device, processor and storage medium for realizing suspicious transaction scene model identification processing based on combined construction |
| CN113592499A (en) * | 2021-01-29 | 2021-11-02 | 微梦创科网络科技（中国）有限公司 | Internet money laundering confrontation method and device |
| CN118037298A (en) * | 2024-02-21 | 2024-05-14 | 湖北经济学院 | Anti-money laundering suspicious transaction monitoring system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101599165A (en) * | 2009-07-07 | 2009-12-09 | 华中科技大学 | A kind of dynamic financial network monitoring analytical method |
| US20100004981A1 (en) * | 2002-07-12 | 2010-01-07 | Elazar Katz | Dynamic anti-money laundering system and methodology for providing situational-specific risk assessment determinations |
| JP2010225040A (en) * | 2009-03-25 | 2010-10-07 | Mizuho Information & Research Institute Inc | Money laundering determination assistance system, method, and program |
| CN106156795A (en) * | 2016-07-05 | 2016-11-23 | 中国银联股份有限公司 | A kind of determination method and device of suspicious money laundering account |
| CN108053087A (en) * | 2017-10-20 | 2018-05-18 | 深圳前海微众银行股份有限公司 | Anti money washing monitoring method, equipment and computer readable storage medium |
| CN108280755A (en) * | 2018-02-28 | 2018-07-13 | 阿里巴巴集团控股有限公司 | The recognition methods of suspicious money laundering clique and identification device |
-
2018
- 2018-12-15 CN CN201811537506.0A patent/CN110046993A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100004981A1 (en) * | 2002-07-12 | 2010-01-07 | Elazar Katz | Dynamic anti-money laundering system and methodology for providing situational-specific risk assessment determinations |
| JP2010225040A (en) * | 2009-03-25 | 2010-10-07 | Mizuho Information & Research Institute Inc | Money laundering determination assistance system, method, and program |
| CN101599165A (en) * | 2009-07-07 | 2009-12-09 | 华中科技大学 | A kind of dynamic financial network monitoring analytical method |
| CN106156795A (en) * | 2016-07-05 | 2016-11-23 | 中国银联股份有限公司 | A kind of determination method and device of suspicious money laundering account |
| CN108053087A (en) * | 2017-10-20 | 2018-05-18 | 深圳前海微众银行股份有限公司 | Anti money washing monitoring method, equipment and computer readable storage medium |
| CN108280755A (en) * | 2018-02-28 | 2018-07-13 | 阿里巴巴集团控股有限公司 | The recognition methods of suspicious money laundering clique and identification device |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110659989A (en) * | 2019-09-10 | 2020-01-07 | 马洪富 | Active exploration type compliance anti-money laundering method, device, system and storage medium |
| CN110852884A (en) * | 2019-11-15 | 2020-02-28 | 成都数联铭品科技有限公司 | Data processing system and method for anti-money laundering recognition |
| CN111127200A (en) * | 2019-11-25 | 2020-05-08 | 中国建设银行股份有限公司 | Method and device for monitoring suspicious transactions of anti-money laundering |
| CN111160745A (en) * | 2019-12-23 | 2020-05-15 | 中国建设银行股份有限公司 | User account data processing method and device |
| CN111292195A (en) * | 2020-02-28 | 2020-06-16 | 中国工商银行股份有限公司 | Risk account identification method and device |
| CN111709844A (en) * | 2020-05-13 | 2020-09-25 | 北京明略软件系统有限公司 | Insurance money laundering personnel detection method and device and computer readable storage medium |
| CN111738868A (en) * | 2020-06-11 | 2020-10-02 | 北京向上一心科技有限公司 | Anti-money laundering anti-terrorist financing risk monitoring method, device, computer equipment and storage medium |
| CN112184238A (en) * | 2020-09-23 | 2021-01-05 | 中国建设银行股份有限公司 | Anti-money laundering monitoring method and device for financial leasing industry, electronic equipment and medium |
| CN112132693A (en) * | 2020-09-28 | 2020-12-25 | 平安养老保险股份有限公司 | Transaction verification method, transaction verification device, computer equipment and computer-readable storage medium |
| CN113379540A (en) * | 2020-11-09 | 2021-09-10 | 中科金审(北京)科技有限公司 | Capital data analysis system |
| CN112329862A (en) * | 2020-11-09 | 2021-02-05 | 杭州安恒信息技术股份有限公司 | Decision tree-based anti-money laundering method and system |
| CN112418933A (en) * | 2020-11-24 | 2021-02-26 | 深圳市新系区块链技术有限公司 | Transaction data processing method, system and related equipment |
| CN112508705A (en) * | 2020-12-18 | 2021-03-16 | 北京航空航天大学 | Method and system for detecting money laundering transaction in complex association transaction |
| CN113592499A (en) * | 2021-01-29 | 2021-11-02 | 微梦创科网络科技（中国）有限公司 | Internet money laundering confrontation method and device |
| CN113592499B (en) * | 2021-01-29 | 2023-08-25 | 微梦创科网络科技（中国）有限公司 | Internet money laundering countermeasure method and device |
| CN112906765A (en) * | 2021-02-01 | 2021-06-04 | 中国建设银行股份有限公司 | RBF neural network-based customer money laundering risk grading method and system |
| CN113240425A (en) * | 2021-04-27 | 2021-08-10 | 湖南大学 | Financial anti-money laundering transaction method, device and storage medium based on deep learning |
| CN113592505A (en) * | 2021-08-25 | 2021-11-02 | 国泰君安证券股份有限公司 | System, method, device, processor and storage medium for realizing suspicious transaction scene model identification processing based on combined construction |
| CN113592505B (en) * | 2021-08-25 | 2024-01-19 | 国泰君安证券股份有限公司 | System for realizing suspicious transaction scene model identification processing based on combination construction |
| CN113469816A (en) * | 2021-09-03 | 2021-10-01 | 浙江中科华知科技股份有限公司 | Digital currency identification method, system and storage medium based on multigroup technology |
| CN118037298A (en) * | 2024-02-21 | 2024-05-14 | 湖北经济学院 | Anti-money laundering suspicious transaction monitoring system |
| CN118037298B (en) * | 2024-02-21 | 2024-09-24 | 湖北经济学院 | Anti-money laundering suspicious transaction monitoring system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110046993A (en) | Illicit gain legalizes behavior monitoring method, system, computer installation and medium | |
| Sun et al. | Predicting credit card delinquencies: An application of deep neural networks | |
| Wu et al. | Credit rating prediction through supply chains: A machine learning approach | |
| Paleologo et al. | Subagging for credit scoring models | |
| US10552735B1 (en) | Applied artificial intelligence technology for processing trade data to detect patterns indicative of potential trade spoofing | |
| US8296205B2 (en) | Connecting decisions through customer transaction profiles | |
| US20150142713A1 (en) | Real-Time Adaptive Decision System And Method Using Predictive Modeling | |
| Vanini et al. | Online payment fraud: from anomaly detection to risk management | |
| CN106952159A (en) | A kind of real security risk control method, system and storage medium | |
| WO2022155740A1 (en) | Systems and methods for outlier detection of transactions | |
| CN113657901B (en) | Method, system, terminal and medium for managing fee owed users | |
| WO2022143431A1 (en) | Method and apparatus for training anti-money laundering model | |
| US20210133017A1 (en) | Approach to predicting entity failures through decision tree modeling | |
| CN111612606A (en) | Merchant fraud risk monitoring system and data mining method | |
| CN112419030A (en) | Method, system and equipment for evaluating financial fraud risk | |
| CN110866821A (en) | Financing method and system based on block chain and product life cycle, and storage medium | |
| CN112037013A (en) | Pedestrian credit variable derivation method and device | |
| CN112766814A (en) | Training method, device and equipment for credit risk pressure test model | |
| CN116361542A (en) | Product recommendation method, device, computer equipment and storage medium | |
| CN110458684A (en) | A kind of anti-fraud detection method of finance based on two-way shot and long term Memory Neural Networks | |
| Gruszczyński et al. | Modeling financial distress and bankruptcy | |
| Achsan et al. | The Demographic and Behavior Determinant of Credit Card Default in Indonesia | |
| CN113850609A (en) | Customer management system, method, computer equipment and storage medium | |
| Edelstein et al. | Bank branch grouping strategy, an unusual DEA application | |
| US20230032963A1 (en) | Method and system for validating financial events and security events |
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 |