CN113919924A - Method for detecting crime of money laundering in underground money bank based on big data - Google Patents
Method for detecting crime of money laundering in underground money bank based on big data Download PDFInfo
- Publication number
- CN113919924A CN113919924A CN202111052390.3A CN202111052390A CN113919924A CN 113919924 A CN113919924 A CN 113919924A CN 202111052390 A CN202111052390 A CN 202111052390A CN 113919924 A CN113919924 A CN 113919924A
- Authority
- CN
- China
- Prior art keywords
- rule
- calculator
- model
- calculation
- money laundering
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Abstract
The invention discloses a method for detecting crime of money laundering in an underground bank based on big data, which comprises a data budgeting device, an operator calculator, a rule calculator, a model calculator and an early warning generator, wherein the operator calculator is used for calculating the rule according to the rule; the invention supports mass data calculation; supporting multi-dimensional data statistical analysis and supporting rule expansion investigation points; constructing an underground money bank money laundering crime fund network, tracking fund flow direction, presenting a fund link, and positioning initial fund departure and final fund departure; complementing the missing customer information elements, constructing complete transaction information, and restoring a real transaction scene; the efficiency of investigation of the crime of money laundering in underground money bank is improved, the money laundering activity in underground money bank is discovered and monitored in time, the crime of money laundering and the crime of the upper reaches thereof are suppressed, and financial security is maintained.
Description
Technical Field
The invention relates to the technical field of computer software application, in particular to a method for detecting crime of money laundering in an underground money bank based on big data.
Background
With the arrival of the big data era, the social economy is diversified, the economic structure taking an individual as a base number is more discrete and complex, and the economic expression forms are diversified. Based on the background of big data era, the economic crime form is more and more diversified and informationized, and the early warning and prevention of money laundering crime in underground money bank is particularly challenging. Underground money bank plays an important intermediary service role in money laundering crimes, is in a key link in legal treatment of crimes, runs out of national financial management order, provides a platform for money laundering, and makes drug crimes, smuggling, black social crimes, bribery crimes and the like rampant more rampant. However, in the background of the big data era, the detection of money laundering crime of underground money bank by financial institutions faces the following problems: (1) the traditional underground money bank money laundering crime investigation mode based on a single main body gradually highlights various limitations in terms of time and space; (2) the detection of a fund network among multiple main bodies of an underground money bank is lacked, and the fund flow direction cannot be accurately tracked; (3) the suspicious transaction is difficult to obtain evidence when the suspicious transaction is committed across regions, banks and countries.
Based on the background, by analyzing the recent cases of the crime of the underground money bank money laundering by early-stage financial institution service personnel, the activity characteristics and the activity rules of the crime of the underground money bank money laundering under the background of a big data era are found out, and the method for detecting the crime of the underground money bank money laundering based on the big data is designed, so that the detection efficiency of the crime of the underground money bank money laundering is improved, the money laundering activity of the underground money bank is timely found and monitored, the crime of money laundering and the upstream crime thereof are suppressed, and the financial safety is maintained.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method for detecting crime of money laundering in an underground money bank based on big data.
The invention provides the following technical scheme:
the invention provides a method for detecting crime of money laundering in an underground money bank based on big data, which comprises a data budgeting device, an operator calculator, a rule calculator, a model calculator and an early warning generator, wherein the operator calculator is used for calculating the rule according to the rule; the data of an upstream source platform is accessed to the anti-money laundering platform in a T +1 mode (T is a transaction occurrence date), and a data budgeting device is responsible for cleaning, converting and processing the source data, adjusting external interfaces (such as enterprise investigation and credit investigation interfaces) for online checking and completing missing customer information elements; the operator calculator is responsible for calculating the dimensionalities of data such as aggregation, grouping, duplicate removal, increment, decrement, variance, standard deviation and the like, and provides an API (application program interface) for external calling; the rule calculator is responsible for suspicious feature calculation, can call operators, realize the calculation and logic judgment of data, can flexibly set a suspicious transaction review period according to the configuration of rule parameters, and can set detection points in multiple dimensions; the model calculator is responsible for money laundering model calculation and capital network calculation, an initial model instance is established according to customer dimensions according to rule evidences (customers, accounts and transaction information meeting the rules) under the model, then capital network networking calculation is carried out on the transaction evidences corresponding to the rules under the same money laundering scene to generate a capital network, and the model instance and the capital network are combined to generate the model evidences; the early warning generator is responsible for generating suspicious early warning for the crime model evidence of the underground money bank money laundering; the details are as follows:
(1) a data budgeter: the data budgeting device is a script program developed by a Scala language, and adopts an open-source Spark calculation engine to realize cleaning and processing of mass data and generate data such as clients, accounts, transactions and the like under a standard interface; aiming at a client: marking the attribute of the client list, and adjusting an external interface (such as an enterprise check interface, a credit investigation interface and the like) to complement the contact way, the address, the certificate expiration date, the legal information, the beneficiary information and the like of the client; for an account: complementing information such as account names, account opening financial institutions and the like; for a transaction: analyzing a transaction occurrence area through a transaction ip address, matching login equipment information and terminal information, and performing networking check on identity information of a main body and an opponent client and the like to construct complete client, account and transaction information;
(2) an operator calculator: the operator calculator is a basic function interface developed by Java language, can realize the calculation of dimensionalities such as summation, counting, averaging, maximum value, minimum value, tree statistics, list acquisition, object replacement, grouping, duplicate removal, discontinuous increment, continuous increment, discontinuous decrement, continuous decrement, variance, standard deviation and the like of data, provides an API interface for external calling, can transmit parameters and can return a calculation result value;
(3) a rule calculator: the rule calculator is a script program developed by a Scala language, an open-source Spark calculation engine is adopted to realize rule calculation, and calculation results (rule evidence) are written into a database; each suspicious identification point is defined as a rule, the rule is designed in a layered mode, the rules of the same layer can be executed in parallel, and the rules of different layers are executed in series; the rule calculator can call an operator to realize the calculation and logic judgment of the data; the rule calculator can flexibly set a suspicious transaction review period according to the configuration of rule parameters, can set detection points in multiple dimensions, such as customer dimension, ip dimension, area dimension, enterprise site dimension and the like, and can monitor suspicious transactions in all dimensions;
(4) a model calculator: the model calculator is a program developed by Java language, realizes money laundering model calculation and capital network calculation, and writes calculation results (model evidence) into a database; a model is a money laundering type, which reflects a money laundering scene, the model comprises a plurality of rules downward, each rule is equivalent to a small feature of money laundering, and the plurality of small features reflect the money laundering scene; according to rule evidences under the model, an initial model instance is established according to customer dimensions, then fund network networking calculation is carried out on transaction evidences corresponding to the rules under the same money laundering scene, a fund network is generated, and the model instance and the fund network are combined to generate the model evidences;
(5) an early warning generator: the early warning generator is a program developed by Java language, and is mainly used for generating suspicious early warning based on the evidence of the underground money bank money laundering crime model and writing the suspicious early warning and the early warning evidence thereof into a database.
Compared with the prior art, the invention has the following beneficial effects:
1. a Spark calculation engine is introduced to support mass data calculation;
2. applying a series of operators such as summation, counting, averaging, maximum value, minimum value, tree statistics, list acquisition, object replacement, grouping, duplicate removal, discontinuous increment, continuous increment, discontinuous decrement, continuous decrement, variance, standard deviation and the like to suspicious rule calculation, supporting multi-dimensional data statistical analysis, and supporting rule expansion investigation points;
3. constructing an underground money bank money laundering crime fund network, tracking fund flow direction, presenting a fund link, and positioning initial fund departure and final fund departure;
4. supporting calling external interfaces (such as enterprise investigation and credit investigation interfaces) for networking inspection, complementing missing customer information elements, constructing complete transaction information and restoring a real transaction scene;
5. the efficiency of investigation of the crime of money laundering in underground money bank is improved, the money laundering activity in underground money bank is discovered and monitored in time, the crime of money laundering and the crime of the upper reaches thereof are suppressed, and financial security is maintained.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of the warning generation of the present invention;
fig. 2 is a flow chart of the method of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation. Wherein like reference numerals refer to like parts throughout.
Example 1
As shown in fig. 1-2. The core of the invention is to provide a method for detecting crime of money laundering in underground money bank based on big data, which can improve the detection efficiency of financial institutions on crime of money laundering in underground money bank, discover and monitor money laundering activities in underground money bank in time, suppress crime of money laundering and crime upstream thereof, and maintain financial security. A method for detecting crime of money laundering in underground money bank based on big data comprises a data budgeting device, an operator calculator, a rule calculator, a model calculator and an early warning generator. The specific implementation steps are as follows:
s11, data budgeting device: the data budgeter is a script program developed by a Scala language and adopts an open-source Spark calculation engine. The data of the upstream source platform is accessed to the money laundering platform in a mode of T +1 (T is the transaction occurrence date), and after the data budgeting device cleans and processes the original data, the data of clients, accounts, transactions and the like under a standard interface are generated. Aiming at a client: marking the attribute of the client list, and adjusting an external interface (such as an enterprise check interface, a credit investigation interface and the like) to complement the contact way, the address, the certificate expiration date, the legal information, the beneficiary information and the like of the client; for an account: complementing information such as account names, account opening financial institutions and the like; for a transaction: the transaction occurrence area is analyzed through the transaction ip address, login equipment information and terminal information are matched, identity information of a main body and an opponent client is checked in a networking mode, and therefore complete client, account and transaction information is constructed.
S12, operator calculator: the operators are basic interface functions developed by Java language, and the common operators comprise summation, counting, average, maximum value, minimum value, tree statistics, list acquisition, object replacement, grouping, duplicate removal, discontinuous increment, continuous increment, discontinuous decrement, continuous decrement, variance, standard deviation and the like. The operator calculator provides an API interface for external calling, can transmit parameters and can return a calculation result value.
S13, rule calculator: the rule calculator is a script program developed by a Scala language, and adopts an open source Spark calculation engine, the rules are calculated in layers, the rules of the same layer are executed in parallel, the rules of different layers are executed in series, and calculation results (rule evidence) are written into a database. The rule calculator can call operators to realize data calculation and logic judgment, can flexibly set a suspicious transaction review period according to the configuration of rule parameters, can set detection points in multiple dimensions, such as customer dimension, ip dimension, area dimension, mechanism website dimension and the like, and can monitor suspicious transactions in all directions.
S14, model calculator: the model calculator is a program developed by Java language, realizes money laundering model calculation and capital network calculation, and writes calculation results (model evidence) into a database. According to rule evidences (customers, accounts and transaction information meeting the rules) under the model, an initial model instance is established according to customer dimensions, then fund network networking calculation is carried out on the transaction evidences corresponding to the rules under the same money laundering scene, a fund network is generated, and the model instance and the fund network are combined to generate the model evidences.
S15, early warning generator: the early warning generator is a program developed by Java language, and is mainly used for generating suspicious early warning based on the evidence of the underground money bank money laundering crime model and writing the suspicious early warning and the early warning evidence thereof into a database.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (1)
1. A method for detecting crime of money laundering in underground money bank based on big data is characterized by comprising a data budgeting device, an operator calculator, a rule calculator, a model calculator and an early warning generator; the data of an upstream source platform is accessed to the anti-money laundering platform in a T +1 mode (T is a transaction occurrence date), and a data budgeting device is responsible for cleaning, converting and processing the source data, adjusting external interfaces (such as enterprise investigation and credit investigation interfaces) for online checking and completing missing customer information elements; the operator calculator is responsible for calculating the dimensionalities of data such as aggregation, grouping, duplicate removal, increment, decrement, variance, standard deviation and the like, and provides an API (application program interface) for external calling; the rule calculator is responsible for suspicious feature calculation, can call operators, realize the calculation and logic judgment of data, can flexibly set a suspicious transaction review period according to the configuration of rule parameters, and can set detection points in multiple dimensions; the model calculator is responsible for money laundering model calculation and capital network calculation, an initial model instance is established according to customer dimensions according to rule evidences (customers, accounts and transaction information meeting the rules) under the model, then capital network networking calculation is carried out on the transaction evidences corresponding to the rules under the same money laundering scene to generate a capital network, and the model instance and the capital network are combined to generate the model evidences; the early warning generator is responsible for generating suspicious early warning for the crime model evidence of the underground money bank money laundering; the details are as follows:
(1) a data budgeter: the data budgeting device is a script program developed by a Scala language, and adopts an open-source Spark calculation engine to realize cleaning and processing of mass data and generate data such as clients, accounts, transactions and the like under a standard interface; aiming at a client: marking the attribute of the client list, and adjusting an external interface (such as an enterprise check interface, a credit investigation interface and the like) to complement the contact way, the address, the certificate expiration date, the legal information, the beneficiary information and the like of the client; for an account: complementing information such as account names, account opening financial institutions and the like; for a transaction: analyzing a transaction occurrence area through a transaction ip address, matching login equipment information and terminal information, and performing networking check on identity information of a main body and an opponent client and the like to construct complete client, account and transaction information;
(2) an operator calculator: the operator calculator is a basic function interface developed by Java language, can realize the calculation of dimensionalities such as summation, counting, averaging, maximum value, minimum value, tree statistics, list acquisition, object replacement, grouping, duplicate removal, discontinuous increment, continuous increment, discontinuous decrement, continuous decrement, variance, standard deviation and the like of data, provides an API interface for external calling, can transmit parameters and can return a calculation result value;
(3) a rule calculator: the rule calculator is a script program developed by a Scala language, an open-source Spark calculation engine is adopted to realize rule calculation, and calculation results (rule evidence) are written into a database; each suspicious identification point is defined as a rule, the rule is designed in a layered mode, the rules of the same layer can be executed in parallel, and the rules of different layers are executed in series; the rule calculator can call an operator to realize the calculation and logic judgment of the data; the rule calculator can flexibly set a suspicious transaction review period according to the configuration of rule parameters, can set detection points in multiple dimensions, such as customer dimension, ip dimension, area dimension, enterprise site dimension and the like, and can monitor suspicious transactions in all dimensions;
(4) a model calculator: the model calculator is a program developed by Java language, realizes money laundering model calculation and capital network calculation, and writes calculation results (model evidence) into a database; a model is a money laundering type, which reflects a money laundering scene, the model comprises a plurality of rules downward, each rule is equivalent to a small feature of money laundering, and the plurality of small features reflect the money laundering scene; according to rule evidences under the model, an initial model instance is established according to customer dimensions, then fund network networking calculation is carried out on transaction evidences corresponding to the rules under the same money laundering scene, a fund network is generated, and the model instance and the fund network are combined to generate the model evidences;
(5) an early warning generator: the early warning generator is a program developed by Java language, and is mainly used for generating suspicious early warning based on the evidence of the underground money bank money laundering crime model and writing the suspicious early warning and the early warning evidence thereof into a database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111052390.3A CN113919924A (en) | 2021-09-08 | 2021-09-08 | Method for detecting crime of money laundering in underground money bank based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111052390.3A CN113919924A (en) | 2021-09-08 | 2021-09-08 | Method for detecting crime of money laundering in underground money bank based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113919924A true CN113919924A (en) | 2022-01-11 |
Family
ID=79234285
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111052390.3A Pending CN113919924A (en) | 2021-09-08 | 2021-09-08 | Method for detecting crime of money laundering in underground money bank based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113919924A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114726592A (en) * | 2022-03-21 | 2022-07-08 | 中国电信股份有限公司广州分公司 | Method, device and equipment for detecting broadband attribute and storage medium |
| CN116955967A (en) * | 2023-09-20 | 2023-10-27 | 成都无糖信息技术有限公司 | System and method for simulating investigation and adjustment in network target range |
-
2021
- 2021-09-08 CN CN202111052390.3A patent/CN113919924A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114726592A (en) * | 2022-03-21 | 2022-07-08 | 中国电信股份有限公司广州分公司 | Method, device and equipment for detecting broadband attribute and storage medium |
| CN114726592B (en) * | 2022-03-21 | 2024-04-05 | 中国电信股份有限公司广州分公司 | Broadband attribute detection method, device, equipment and storage medium |
| CN116955967A (en) * | 2023-09-20 | 2023-10-27 | 成都无糖信息技术有限公司 | System and method for simulating investigation and adjustment in network target range |
| CN116955967B (en) * | 2023-09-20 | 2023-12-08 | 成都无糖信息技术有限公司 | System and method for simulating investigation and adjustment in network target range |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020253358A1 (en) | Service data risk control analysis processing method, apparatus and computer device | |
| Moore et al. | The postmodern Ponzi scheme: Empirical analysis of high-yield investment programs | |
| EP2555153A1 (en) | Financial activity monitoring system | |
| US11037229B2 (en) | Fraud detection system for the faster payments system | |
| CN111382150B (en) | Real-time computing method and system based on Flink | |
| US20140012724A1 (en) | Automated fraud detection method and system | |
| US20110087495A1 (en) | Suspicious entity investigation and related monitoring in a business enterprise environment | |
| CN113919924A (en) | Method for detecting crime of money laundering in underground money bank based on big data | |
| CN112215616B (en) | Method and system for automatically identifying abnormal fund transaction based on network | |
| Kim et al. | A model to detect potentially fraudulent/abnormal wires of an insurance company: An unsupervised rule-based approach | |
| US20170255995A1 (en) | Fraud detection system | |
| Singh et al. | Design and implementation of continuous monitoring and auditing in SAP enterprise resource planning | |
| Dzhaparov | Application of blockchain and artificial intelligence in bank risk management | |
| CN111915316A (en) | Suspicious transaction monitoring method and device, computer equipment and storage medium | |
| Berdyugin et al. | Approaches to measuring the risk of cyberattacks in remote banking services of Russia | |
| Min et al. | Behavior language processing with graph based feature generation for fraud detection in online lending | |
| CN104599174A (en) | Personal finance credit evaluation method based on big data | |
| Breslow et al. | The new frontier in anti–money laundering | |
| Ni et al. | A Victim-Based Framework for Telecom Fraud Analysis: A Bayesian Network Model | |
| CN115879548B (en) | Knowledge graph construction method and system for customer identity recognition | |
| Kanhere et al. | A methodology for outlier detection in audit logs for financial transactions | |
| JP2023081325A (en) | Computer mounting method, computer mounting system, and non-temporary computer readable medium (system and method for performing governance on suspicious activity detection pipeline in risk network) | |
| CN112669039B (en) | Knowledge graph-based customer risk management and control system and method | |
| CN114820158A (en) | Method and device for monitoring security data by bank based on rule engine | |
| Kapoor | Deception Detection And Vulnerability Analysis Using A Multi-Level Clustering Machine Learning Algorithm In Business Transactions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |