CN109461078B - Abnormal transaction identification method and system based on fund transaction network - Google Patents
Abnormal transaction identification method and system based on fund transaction network Download PDFInfo
- Publication number
- CN109461078B CN109461078B CN201811227516.4A CN201811227516A CN109461078B CN 109461078 B CN109461078 B CN 109461078B CN 201811227516 A CN201811227516 A CN 201811227516A CN 109461078 B CN109461078 B CN 109461078B
- Authority
- CN
- China
- Prior art keywords
- transaction
- data
- risk
- fund
- abnormal
- 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.)
- Active
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 83
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000004900 laundering Methods 0.000 claims abstract description 83
- 230000008569 process Effects 0.000 claims abstract description 21
- 238000012216 screening Methods 0.000 claims abstract description 15
- 238000005065 mining Methods 0.000 claims abstract description 7
- 230000006399 behavior Effects 0.000 claims description 32
- 238000012545 processing Methods 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000010276 construction Methods 0.000 claims description 7
- 238000007418 data mining Methods 0.000 claims description 7
- 238000011002 quantification Methods 0.000 claims description 7
- 206010000117 Abnormal behaviour Diseases 0.000 claims description 6
- 238000005406 washing Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000002452 interceptive effect Effects 0.000 claims description 3
- 238000011835 investigation Methods 0.000 abstract description 6
- 230000000875 corresponding effect Effects 0.000 description 23
- 238000013139 quantization Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000002547 anomalous effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Economics (AREA)
- Accounting & Taxation (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses an abnormal transaction identification method and system based on a fund transaction network, wherein the abnormal transaction identification method comprises the following steps: the method comprises the steps of constructing a data mart through multi-class theme data, determining basic index data, generating first risk characteristic data, establishing a plurality of fund transaction networks formed based on transaction data, generating abnormal transaction suspicious cases and generating suspicious screening reports; the abnormal transaction identification system includes: the system comprises a data market building module, a basic index mining module, a risk characteristic generating module, a transaction network building module, a suspicious case generating module and a discrimination report generating module. Based on the established fund transaction network and transaction risk model, the money laundering process and the money laundering scene can be thoroughly restored, and powerful support and help are provided for money laundering behavior investigation; the invention also has the outstanding advantages of high precision, good comprehensiveness, strong objectivity and the like.
Description
Technical Field
The invention relates to the technical field of transaction data processing, in particular to an abnormal transaction identification method and system based on a fund transaction network.
Background
Anti-money laundering, often refer to in order to prevent through various ways to hide, hide drugs crime, organization crime of black social nature, terrorism crime, smuggly crime, bribery crime and destroy financial management order crime etc. crime and its income source and nature money laundering activities, the main activities of money laundering are all realized through financial transaction basically, so can find money laundering phenomenon through checking up financial transaction, but if only rely on manpower to manually check up massive financial transaction data, find money laundering behavior, it is impossible to realize; in view of this, the prior art adopts the modes of database, index calculation or stored process coding calculation, etc. to identify abnormal transactions and try to find money laundering behaviors, and a great deal of practice shows that: the above method still cannot accurately and comprehensively identify abnormal transactions, the effect is not ideal, and the investigation of money laundering behaviors in the later period still has great difficulty.
Therefore, how to accurately and comprehensively identify abnormal transactions and provide powerful data support for money laundering behavior research becomes a key point for technical problems to be solved and research in the past by technical personnel in the field.
Disclosure of Invention
In order to solve the problems that abnormal transactions cannot be found accurately and comprehensively and the money laundering behavior investigation work is less assisted in the prior art, the invention innovatively provides an abnormal transaction identification method and system based on a fund transaction network.
In order to achieve the technical purpose, the invention discloses an abnormal transaction identification method based on a fund transaction network, which comprises the following steps of;
carrying out standardization processing on the acquired transaction related data so as to convert the transaction related data into multi-class theme data, and constructing a data mart through the multi-class theme data;
processing various types of subject data in the data marts in a data mining mode based on the data marts to obtain basic index data serving as abnormal behavior comparison standards;
performing characteristic calculation on data in the data mart by taking the basic index data as a basis, so as to generate first risk characteristic data;
all transaction data related to the first risk characteristic data are used as data bases, and a plurality of fund transaction networks formed on the basis of the transaction data are established according to fund transfer-in and transfer-out relations;
and respectively carrying out risk characteristic matching on each fund transaction network and a transaction risk model established in advance to calculate the matching degree of each fund transaction network and the transaction risk model, and taking the fund transaction network with the matching degree reaching a risk threshold as an abnormal transaction suspicious case.
Based on the technical scheme, the method can find abnormal transaction conditions from a large amount of transaction related data, accurately and comprehensively determine abnormal transactions, completely restore the money laundering process and the money laundering scene, provide clues and evidences for money laundering behavior investigation work, and effectively solve the problems in the prior art.
Further, in the process of establishing the fund transaction network, the following steps are included;
extracting all transaction data associated with the first risk characteristic data, and constructing a temporary risk data mart by using all transaction data;
grouping all transaction data in the temporary risk data mart according to the transferring-in and transferring-out relationship of funds; wherein, the transaction data in the same group has a transfer-in or transfer-out relationship;
and all the transaction data in the same group are established into a fund transaction network with a transfer-in or transfer-out relationship among network nodes, wherein the network nodes are at least one of users, accounts and equipment.
Based on the improved technical scheme, the invention can clearly express the fund exchange relationship among suspicious transactions, money laundering risk characteristics contained in each network and related personnel, and provides great help for abnormal transaction identification and money laundering prevention work.
Further, a transaction risk model is established in the following way;
carrying out scene definition on money laundering case data, and classifying the money laundering case data subjected to scene definition, so that the money laundering case data belonging to the same scene are in the same scene category;
under any scene category, second risk characteristic data in money washing case data in the scene are extracted, and a transaction risk model is established based on the second risk characteristic data; wherein one scene category corresponds to one transaction risk model.
Based on the improved technical scheme, the money laundering behavior recognition is performed in a scenario-based manner, so that an accurate and comprehensive transaction risk model is established, the workload of manual parameter configuration is effectively reduced, and abnormal transaction behaviors and money laundering behaviors are recognized more accurately.
Further, when the risk characteristics of the fund transaction network are matched with the risk characteristics of the transaction risk model, the risk characteristics of the first risk characteristic data corresponding to the fund transaction network and the second risk characteristic data corresponding to the transaction risk model are matched.
Further, quantifying a risk characteristic matching result of the first risk characteristic data and the second risk characteristic data, and enabling a quantification result to be an accumulated total score or a logical expression;
if the quantification result is an accumulated total score, comparing the accumulated total score with a preset threshold score corresponding to a risk threshold, and taking a fund transaction network corresponding to the accumulated total score which is greater than or equal to the preset threshold score as an abnormal transaction suspicious case;
and if the quantitative result is a logic expression, matching the logic expression with a preset expression corresponding to the risk threshold, and taking the fund transaction network corresponding to the logic expression matched with the preset expression as the abnormal transaction suspicious case.
Further, the transaction risk model is an anti-money laundering model.
Further, when the feature calculation is carried out on the data in the data mart, the method comprises the following steps;
and defining risk event characteristics by referring to basic index data, screening and analyzing data in the data mart according to the risk event characteristics, and taking an analysis result as first risk characteristic data.
Further, the risk event feature is used to describe a risk event, the risk event comprising: legal representatives or high-level management of different enterprises are the same, the different enterprises have the same company accounting, related transactions occur among multiple enterprises, the industry to which the enterprises belong is a specific industry, the transaction frequency and the transaction scale are obviously different from the enterprise registered fund scale, the avoidance supervision intention is obvious, a large amount of funds are frequently transferred to a personal account for a public account, the public account is revolved and private, and the fund transactions are all transacted through an online bank.
Further, the abnormal transaction identification method also comprises the following steps;
and after the abnormal transaction suspicious case is determined, filling data related to the abnormal transaction suspicious case into a specified template file so as to generate a suspicious screening report.
Further, the multi-class theme data comprises customer theme data, account theme data and transaction theme data.
Further, the basic index data comprises bank multi-dimensional information statistical data; the bank multidimensional information statistical data comprises: the data of the distribution condition of the corporate, individual household, other organizations and private persons, the data of the distribution condition of deposit accounts and loan accounts, the data of the distribution condition of transaction channels, the number of transaction strokes and the transaction amount, the data of the ranking condition of the transaction of the large-volume client, the data of the distribution condition of industry transaction behaviors, the data of the age group transaction behaviors and the data of the distribution condition of the transaction destination.
In order to realize the technical purpose, the invention also discloses an abnormal transaction identification system based on the fund transaction network, which comprises a data market building module, a basic index mining module, a risk characteristic generating module, a transaction network building module and a suspicious case generating module;
the data mart construction module is used for carrying out standardization processing on the acquired transaction related data so as to convert the transaction related data into multi-class theme data and constructing a data mart through the multi-class theme data;
the basic index mining module is used for processing various types of theme data in the data marts in a data mining mode based on the data marts to obtain basic index data serving as an abnormal behavior comparison standard;
the risk characteristic generation module is used for performing characteristic calculation on data in the data mart by taking the basic index data as a basis so as to generate first risk characteristic data;
the transaction network establishing module is used for enabling all transaction data associated with the first risk characteristic data to serve as a data base and establishing a plurality of fund transaction networks formed on the basis of the transaction data according to a fund transfer-in and transfer-out relationship;
and the suspicious case generation module is used for respectively carrying out risk characteristic matching on each fund transaction network and a transaction risk model established in advance so as to calculate the matching degree of each fund transaction network and the transaction risk model, and is used for taking the fund transaction network with the matching degree reaching a risk threshold as an abnormal transaction suspicious case.
Based on the technical scheme, the method can find abnormal transaction conditions from a large amount of transaction related data, accurately and comprehensively determine abnormal transactions, completely restore the money laundering process and the money laundering scene, provide clues and evidences for money laundering behavior investigation work, and effectively solve the problems in the prior art.
Further, the transaction network building module comprises a temporary market building unit, a transaction data processing unit and a transaction network building unit;
the temporary market building unit is used for extracting all transaction data associated with the first risk characteristic data and building a temporary risk data market by using all transaction data;
the transaction data processing unit is used for grouping all transaction data in the temporary risk data mart according to the transfer-in and transfer-out relationship of funds, and is used for enabling the transfer-in or transfer-out relationship to exist among the transaction data in the same group;
the transaction network establishing unit is used for establishing all transaction data in the same group into a fund transaction network with transfer-in or transfer-out relationship among network nodes, wherein the network nodes are at least one of users, accounts and equipment.
Based on the improved technical scheme, the invention can clearly express the fund exchange relationship among suspicious transactions, money laundering risk characteristics contained in each network and related personnel, and provides great help for abnormal transaction identification and money laundering prevention work.
Further, the abnormal transaction identification system also comprises a risk model establishing module;
the risk model establishing module is used for carrying out scene definition on money laundering case data and classifying the scene-defined money laundering case data so as to enable the money laundering case data belonging to the same scene to be in the same scene category; under any scene type, the risk model establishing module is used for extracting second risk characteristic data in money laundering case data in the scene and establishing a transaction risk model based on the second risk characteristic data; wherein one scene category corresponds to one transaction risk model.
Further, the suspicious case generation module is further configured to perform risk feature matching on the first risk feature data corresponding to the fund transaction network and the second risk feature data corresponding to the transaction risk model when the fund transaction network performs risk feature matching with the transaction risk model.
Further, the suspicious case generation module is further configured to quantify a risk feature matching result of the first risk feature data and the second risk feature data, make the quantified result an accumulated total score or a logical expression, and determine a suspicious case of abnormal transaction according to the quantified result.
Furthermore, the abnormal transaction identification system also comprises a screening report generation module;
and the screening report generation module is used for filling data related to the abnormal transaction suspicious cases into a specified template file so as to generate a suspicious screening report.
The invention has the beneficial effects that: based on the established fund transaction network and transaction risk model, the money laundering process and the money laundering scene can be thoroughly restored, and powerful support and help are provided for money laundering behavior investigation work; the invention also has the outstanding advantages of high precision, good comprehensiveness, strong objectivity and the like.
The invention can effectively reduce the workload of manual parameter configuration and the objectivity of parameter setting: the system is automatically calculated based on basic indexes, so that the numerical value is more objective and accurate, and the characteristic quantification requirements of different regions and different customer groups can be fully met.
The invention can effectively improve the identification capability and accuracy of the suspicious cases: the money laundering behavior is identified in a scene, and the whole appearance of the money laundering process can be completely restored by starting with group relations and fund transaction networks and paying attention to a certain transaction or a certain client.
The invention innovatively provides a model quantization scheme, so that the method is simpler and easier to use, and the quantization standard is objective and accurate: the money laundering behavior recognition process is decomposed into: the behavior habit, money laundering characteristic and model matching condition of each subject are fully recognized by different levels of the index-characteristic-model and by using the calculation capability of big data, and each level can be continuously expanded according to the actual requirement, so that the method has the advantages of wide application range, convenience in popularization and application and the like. The model has simple and effective quantization process, and can more intuitively reflect money laundering scenes: the money laundering risk model quantization system designed according to the money laundering risk recognition theory can transfer the model quantization process to business personnel to complete through a formula method and a value-dividing method, and can conveniently embody business ideas in the system.
The invention objectively restores the occurrence process of the money laundering behavior, the capital flow direction, the capital flow and the capital flow rate through the suspicious case, objectively reflects the customer group information participating in the money laundering behavior, and provides favorable clues and evidences for further detecting cases by financial institutions and supervisory authorities.
After the method is solidified into a software system, the automatic, continuous and effective money washing case discrimination process can be realized, the manual working pressure is effectively reduced, and the method has the outstanding advantages of strong reliability, low cost and the like.
Drawings
Fig. 1 is a flow chart of an abnormal transaction identification method based on a fund transaction network.
Fig. 2 is a schematic diagram of the construction process of the fund transaction network according to the present invention.
FIG. 3 is a schematic diagram of a funds transaction network in which the network nodes are users.
Fig. 4 is a schematic diagram of a process for establishing a transaction risk model according to the present invention.
FIG. 5 is a block diagram of the components of an anomalous transaction identification system based on a funds transaction network.
Detailed Description
The abnormal transaction identification method and system based on fund transaction network according to the present invention will be explained and explained in detail with reference to the drawings.
Example one
The embodiment discloses an abnormal transaction identification method based on a fund transaction network, the identification of abnormal transactions (including money laundering risks) of the invention is based on the data of bank customer data, account data, various transaction pipelines and the like, and as shown in figure 1, the abnormal transaction identification method comprises the following steps.
Step S1, acquiring transaction related data of the bank, and performing standardization processing on the acquired transaction related data, so as to convert the transaction related data into multi-class theme data, for example, converting data of a credit system, a state system and a core system into the same theme standard, and constructing a data mart through the multi-class theme data, wherein the data mart is used as a basis for identifying abnormal transactions; in this embodiment, the multiple types of theme data include customer theme data, account theme data, transaction theme data, and the like. The present embodiment may also adopt an ETL method: namely extraction (extract), interactive conversion (transform) and loading (load), and perfects and supplements imperfect customer information, account information and information of a counterparty according to a supervision standard, so as to ensure the consistency and integrity of data.
Step S2, based on the standard data mart, processing the multiple types of theme data in the data mart in a data mining manner, in this embodiment, computing the multiple types of theme data (i.e., basic data indexes) by using a data mining method such as clustering, regression, iteration, and the like, which covers information statistical data of each dimension of the bank, so as to obtain basic index data used as a comparison standard of abnormal behavior, so as to form a standard value database unique to each financial institution; the basic index data can comprise bank multidimensional information statistical data; the bank multidimensional information statistical data comprises: the data of the distribution situation of the corporate, individual household, other organizations and private persons, the data of the distribution situation of deposit accounts and loan accounts, the data of the distribution situation of transaction channels, the number of transaction strokes and the transaction amount, the data of the ranking situation of the transaction of large-volume customers, the data of the distribution situation of industry transaction behaviors, the data of age group transaction behaviors, the data of the distribution situation of transaction destination places and the like are nearly 100 indexes. The indexes represent financial characteristics, transaction preferences, behavior habits and the like of groups in different industries, different ages and the like, and can also represent business preferences, regional characteristics, local customer group characteristics and the like of financial institutions.
Step S3, in this embodiment, based on the basic index data and the data mart, the data in the data mart is subjected to feature calculation based on the basic index data to generate first risk feature data, so that a risk event library of the anti-money laundering standard can be constructed; in this embodiment, when performing feature calculation on data in the data mart, the method includes the following steps: the risk event characteristics are defined by referring to the basic index data, persistent configuration can be formed, the risk event characteristics are obviously different from the event characteristics related to normal transaction behaviors and reflect the obvious characteristics contained in certain specific money laundering scenes in the transaction process, the data in the data mart are screened and analyzed according to the risk event characteristics, and the analysis result is used as first risk characteristic data. Wherein the risk event characteristics are used to describe the risk event, for example, the risk event includes: legal representatives or high-level management of different enterprises are the same, different enterprises have the same company accounting, related transactions occur among multiple enterprises, the industry to which the enterprises belong is a specific industry, the transaction frequency and the transaction scale are obviously different from the enterprise registered fund scale, the avoidance supervision intention is obvious, a large amount of funds are frequently transferred to a personal account for a public account, the public account is revolved and private, the fund transactions are all transacted through an online bank, and the like. Although it cannot be determined by a certain risk event that money laundering behavior is certain to be present, money laundering behavior is certain to be related to at least one risk event, so the first risk profile determined based on the risk event constitutes the basic element of the money laundering case. After a lot of experiments and trials, the embodiment has quantified nearly 500 risk events, that is, at least 500 kinds of first risk characteristic data have been generated, and the above-mentioned characteristic calculation process can implement multi-thread concurrent execution, and has the advantages of high calculation efficiency, daily generation of first risk characteristic data, and the like.
Step S4, all transaction data related to the first risk characteristic data are used as data bases, and a plurality of fund transaction networks formed based on the transaction data are established according to the transferring-in and transferring-out relations of the fund; the fund transaction network can comprehensively reflect the fund flow direction, transaction characteristics and the like of a customer group with money laundering risk, and can be automatically established and reduced in real time according to real-time data change, as shown in fig. 2, the fund transaction network establishment process comprises the following steps.
And step S40, extracting all transaction data associated with the first risk characteristic data aiming at all transaction data associated with all first risk characteristic data, and constructing a temporary risk data mart by using all transaction data.
Step S41, grouping all transaction data in the temporary risk data mart according to the transferring-in and transferring-out relationship of funds; wherein, the transaction data in the same group has a transfer-in or transfer-out relationship.
Step S42, all transaction data in the same group are organized into a fund transaction network having a transfer-in or transfer-out relationship between network nodes, the fund transaction network provided in this embodiment forms a set of independent fund transaction flow groups from the transaction flow data having a certain correlation, the correlation mainly represents the first risk characteristic data (or risk event), for example, "legal representatives or high-priority representatives of different enterprises are the same, different enterprises have the same company accounting or multiple enterprises have correlated transactions", and the like, and further represents the client information and the like involved in the transaction in the group, and based on this, the possible characteristics and the personnel composition and the like of the network can be quickly identified; the embodiment discloses a fund transaction network with a network node as a user, as shown in fig. 3, for example, (1) transfer amount accumulation: 100 ten thousand; and (4) accumulating the transfer amount: 80 ten thousand, cash transaction: 20 ten thousand; accumulating transaction strokes: 15 pens; (2) the accumulated amount of the small yarns of the plum in the bearing direction of the plum is changed into 20 ten thousand, and the number of transaction strokes is 3; (3) the TOmmy is accumulated to be shifted into 5 thousands of small Li yarns, and the number of transaction strokes is 1; (4) the Chua's clear is added to 25 thousands of small Li yarns in an accumulated way, and the number of transaction strokes is 1; (5) the accumulated amount of the Hou Dong plum yarns is changed into 10 ten thousand, and the number of transaction strokes is 1; (6) the accumulated amount of the plum small yarns in the circumferential direction is changed into 40 ten thousand, and the transaction number is 6; (7) the accumulation of the Chengxinche Li Chenjian is shifted to 20 ten thousand, and the number of transaction strokes is 1; (8) the Li tulle is turned into 75 ten thousand to the Houxiandong in an accumulated way, and the number of transaction strokes is 1; (9) the accumulated amount of the plum small yarns to the whole shirt is changed into 5 ten thousand, and the number of transaction strokes is 1.
In the embodiment, the fund transaction networks are established in the above manner, each fund transaction network contains a certain amount of first risk characteristic data, but the conditions of the suspicious degree, the existence of the money laundering behavior, the specific existence of the money laundering behavior and the like of each fund transaction network are still unclear, so that the embodiment adopts technical means of establishing a money laundering risk model based on the scene of the money laundering case and the like to accurately define each type of money laundering case, and thus the conditions of the suspicious degree, the existence of the money laundering behavior, the specific existence of the money laundering behavior and the like of each fund transaction network are determined.
And step S5, risk feature matching is carried out on each fund transaction network and a transaction risk model which is established in advance respectively, so as to calculate the matching degree of each fund transaction network and the transaction risk model, the fund transaction network of which the matching degree reaches a risk threshold is used as an abnormal transaction suspicious case, and the fund transaction network of which the matching degree reaches the risk threshold can be alarmed. This case includes: a) all customer information participating in the money laundering process; b) transaction information reflecting money laundering behavior; c) suspicious identification points reflecting money laundering behavior; d) and group feature standard values reflecting matching criteria, and the like.
In this embodiment, the transaction risk model may be an anti-money laundering model dedicated to anti-money laundering, and when the fund transaction network is subjected to risk feature matching with the transaction risk model, the first risk feature data corresponding to the fund transaction network and the second risk feature data corresponding to the transaction risk model may be subjected to risk feature matching. In order to improve the accuracy and reliability of matching, the present embodiment quantizes the risk feature matching results of the first risk feature data and the second risk feature data, and may make the quantization result be an accumulated total score or a logical expression, and the present embodiment may determine the quantization mode according to the closeness degree of the logical relationship between the risk feature matching results: if the logic relation between the risk characteristic matching results is strong, a formula method, namely a logic expression, can be adopted; if the logical relationship between the risk feature matching results is relatively good, a score method, i.e., accumulating the total score, may be used.
And if the quantification result is the accumulated total score, comparing the accumulated total score with a preset threshold score corresponding to the risk threshold, and taking the fund transaction network corresponding to the accumulated total score which is greater than or equal to the preset threshold score as the abnormal transaction suspicious case. For example: scene 1 of the suspected tax crime money-washing model-the money-washing scene of deceiving tax refunds contains 6 suspicious characteristics: (1) the business belongs to a specific business (the value is 1), (2) the transaction frequency and the transaction scale are obviously inconsistent with the registered fund scale of the business (the value is 10), (3) the evasive supervision intention is obvious (the value is 8), (4) a large amount of money is frequently transferred to an individual account for a public account (the value is 7), (5) the public account is revolved and private (the value is 7), (6) the fund transaction is basically carried out through the internet bank (the value is 12); the six characteristics have no correlation, the embodiment sets standard scores according to the suspicious degree, realizes total score calculation through an arithmetic cumulative method, and then compares the total score with the case preset threshold score, if the total score is greater than the preset threshold score, the fund transaction network corresponding to the quantitative result can be judged to be an abnormal transaction suspicious case.
And if the quantitative result is a logic expression, matching the logic expression with a preset expression corresponding to the risk threshold, and taking the fund transaction network corresponding to the logic expression matched with the preset expression as the abnormal transaction suspicious case. For example: scenario 2-money laundering scenario for transferring income through associated enterprises in the suspected tax crime money laundering model includes 3 risk features: (1) legal representatives or high-level managers of different enterprises are the same, (2) different enterprises have the same company accounting, and (3) related transactions occur among multiple enterprises; the three characteristics are quantized to obtain a preset expression: (1. U.S. Pat. No. 2) n.3; if the quantitative result in the form of the logic expression meets the preset expression, the fund transaction network corresponding to the quantitative result can be judged to be an abnormal transaction suspicious case.
Step S6, after the abnormal transaction suspicious case is determined, filling the data related to the abnormal transaction suspicious case into the specified template file, thereby generating a suspicious screening report, wherein the suspicious screening report can cover the system computing process, analyze the whole process of the case and the related evidence information, can be visually displayed in a chart form, and can be manually identified and then reported to the bank administration department, the upper supervision department and the like.
As a preferred technical solution, in this embodiment, a transaction risk model may be established in advance for identifying abnormal transactions, and as shown in fig. 4, the transaction risk model is established in the following manner.
200, extracting second risk characteristic data in money washing case data in any scene category, and establishing a transaction risk model based on the second risk characteristic data; the method comprises the steps that a scene type corresponds to a transaction risk model, and each transaction risk model comprises a plurality of risk characteristic data.
Example two
As shown in fig. 5, based on the same inventive concept as the first embodiment, the present embodiment provides an abnormal transaction identification system based on a fund transaction network for implementing the abnormal transaction identification method of the first embodiment, and the abnormal transaction identification system includes: the system comprises a data market building module, a basic index mining module, a risk characteristic generating module, a transaction network building module, a suspicious case generating module, a screening report generating module and a risk model building module, wherein the specific description of the embodiment is as follows.
And the data mart construction module is used for carrying out standardization processing on the acquired transaction related data so as to convert the transaction related data into multi-class theme data and constructing a data mart through the multi-class theme data.
And the basic index mining module is used for processing the various types of subject data in the data marts in a data mining mode based on the data marts to obtain basic index data serving as an abnormal behavior comparison standard.
And the risk characteristic generation module is used for performing characteristic calculation on the data in the data mart by taking the basic index data as a basis so as to generate first risk characteristic data.
And the transaction network establishing module is used for enabling all transaction data associated with the first risk characteristic data to serve as a data base and establishing a plurality of fund transaction networks formed based on the transaction data according to the transferring-in and transferring-out relation of the fund.
In this embodiment, the transaction network building module may include a temporary market building unit, a transaction data processing unit, and a transaction network building unit.
And the temporary bazaar construction unit is used for extracting all transaction data associated with the first risk characteristic data and constructing a temporary risk data bazaar by using all transaction data.
And the transaction data processing unit is used for grouping all transaction data in the temporary risk data mart according to the transfer-in and transfer-out relationship of funds, and is used for enabling the transfer-in or transfer-out relationship to exist between the transaction data in the same group.
And the transaction network establishing unit is used for establishing all transaction data in the same group into a fund transaction network with a transfer-in or transfer-out relationship among network nodes, and the network nodes are at least one of users, accounts and equipment.
And the suspicious case generation module is used for respectively carrying out risk characteristic matching on each fund transaction network and a transaction risk model established in advance so as to calculate the matching degree of each fund transaction network and the transaction risk model, and is used for taking the fund transaction network with the matching degree reaching a risk threshold as an abnormal transaction suspicious case. More specifically, the suspicious case generation module is further configured to perform risk feature matching on first risk feature data corresponding to the fund transaction network and second risk feature data corresponding to the transaction risk model when the fund transaction network performs risk feature matching with the transaction risk model. Corresponding to the working method disclosed in embodiment 1, in this embodiment, the suspicious case generating module is further configured to quantize the risk feature matching result of the first risk feature data and the second risk feature data, and make the quantization result be an accumulated total score or a logical expression, and the suspicious case generating module is further configured to determine the suspicious case of the abnormal transaction according to the quantization result, which is described in detail below.
And if the quantification result is the accumulated total score, comparing the accumulated total score with a preset threshold score corresponding to the risk threshold, and taking the fund transaction network corresponding to the accumulated total score which is greater than or equal to the preset threshold score as the abnormal transaction suspicious case.
And if the quantitative result is a logic expression, matching the logic expression with a preset expression corresponding to the risk threshold, and taking the fund transaction network corresponding to the logic expression matched with the preset expression as the abnormal transaction suspicious case.
As an improved technical solution, the abnormal transaction identification system according to this embodiment further includes a risk model building module designed separately.
The risk model establishing module is used for carrying out scene definition on the money laundering case data and classifying the scene-defined money laundering case data so as to enable the money laundering case data belonging to the same scene to be in the same scene category; under any scene type, the risk model building module is used for extracting second risk characteristic data in money laundering case data in the scene and building a transaction risk model based on the second risk characteristic data; wherein one scene category corresponds to one transaction risk model.
And the screening report generating module is used for filling data related to the abnormal transaction suspicious cases into the specified template file so as to generate a suspicious screening report.
In the description herein, references to the description of the term "the present embodiment," "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction. Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and simplifications made in the spirit of the present invention are intended to be included in the scope of the present invention.
Claims (15)
1. An abnormal transaction identification method based on a fund transaction network is characterized in that: the abnormal transaction identification method comprises the following steps;
carrying out standardization processing on the acquired transaction related data so as to convert the transaction related data into multi-class theme data, and constructing a data mart through the multi-class theme data; and imperfect customer information, account information and information of a transaction opponent are perfected and added in by adopting the modes of extraction, interactive conversion and loading;
processing various types of subject data in the data mart by adopting a clustering, regression and iteration data mining mode based on the data mart to obtain basic index data used as an abnormal behavior comparison standard;
performing characteristic calculation on data in the data mart by taking the basic index data as a basis, so as to generate first risk characteristic data;
all transaction data related to the first risk characteristic data are used as a data base, and a plurality of fund transaction networks formed based on the transaction data are established according to a fund transfer-in and transfer-out relation, and the fund transaction networks are automatically established and reduced in real time according to real-time data change;
risk characteristic matching is carried out on each fund transaction network and a transaction risk model which is established in advance respectively, so that the matching degree of each fund transaction network and the transaction risk model is calculated, and the fund transaction network of which the matching degree reaches a risk threshold is used as an abnormal transaction suspicious case;
establishing a transaction risk model by the following method;
carrying out scene definition on money laundering case data, wherein the scene type of the money laundering case is defined to be various, and classifying the money laundering case data defined in the scene type, so that the money laundering case data belonging to the same scene are in the same scene type;
under any scene category, second risk characteristic data in money washing case data in the scene are extracted, and a transaction risk model is established based on the second risk characteristic data; wherein one scene category corresponds to one transaction risk model.
2. The abnormal transaction identification method based on fund transaction network according to claim 1, wherein: in the process of establishing a fund transaction network, the method comprises the following steps;
extracting all transaction data associated with the first risk characteristic data, and constructing a temporary risk data mart by using all transaction data;
grouping all transaction data in the temporary risk data mart according to the transferring-in and transferring-out relationship of funds; wherein, the transaction data in the same group has a transfer-in or transfer-out relationship;
and all the transaction data in the same group are established into a fund transaction network with a transfer-in or transfer-out relationship among network nodes, wherein the network nodes are at least one of users, accounts and equipment.
3. The abnormal transaction identification method based on fund transaction network according to claim 1, wherein:
and when the risk characteristics of the fund transaction network are matched with the transaction risk model, performing risk characteristic matching on first risk characteristic data corresponding to the fund transaction network and second risk characteristic data corresponding to the transaction risk model.
4. The abnormal transaction identification method based on fund transaction network according to claim 3, wherein:
quantifying the risk characteristic matching result of the first risk characteristic data and the second risk characteristic data, and enabling the quantification result to be an accumulated total score or a logic expression;
if the quantification result is an accumulated total score, comparing the accumulated total score with a preset threshold score corresponding to a risk threshold, and taking a fund transaction network corresponding to the accumulated total score which is greater than or equal to the preset threshold score as an abnormal transaction suspicious case;
and if the quantitative result is a logic expression, matching the logic expression with a preset expression corresponding to the risk threshold, and taking the fund transaction network corresponding to the logic expression matched with the preset expression as the abnormal transaction suspicious case.
5. The abnormal transaction identification method based on fund transaction network according to claim 4, wherein: the transaction risk model is an anti-money laundering model.
6. The abnormal transaction identification method based on fund transaction network according to any claim 1-2, 4-5, wherein: when the feature calculation is carried out on the data in the data mart, the method comprises the following steps;
and defining risk event characteristics by referring to basic index data, screening and analyzing data in the data mart according to the risk event characteristics, and taking an analysis result as first risk characteristic data.
7. The abnormal transaction identification method based on fund transaction network according to claim 6, wherein: the risk event features are used to describe risk events, including: legal representatives or high-level management of different enterprises are the same, the different enterprises have the same company accounting, related transactions occur among multiple enterprises, the industry to which the enterprises belong is a specific industry, the transaction frequency and the transaction scale are obviously different from the enterprise registered fund scale, the avoidance supervision intention is obvious, a large amount of funds are frequently transferred to a personal account for a public account, the public account is revolved and private, and the fund transactions are all transacted through an online bank.
8. The abnormal transaction identification method based on fund transaction network according to any claim 1-2, 3-5, 7, wherein: the abnormal transaction identification method also comprises the following steps;
and after the abnormal transaction suspicious case is determined, filling data related to the abnormal transaction suspicious case into a specified template file so as to generate a suspicious screening report.
9. The abnormal transaction identification method based on fund transaction network according to claim 1, wherein: the multi-class theme data comprises customer theme data, account theme data and transaction theme data.
10. The abnormal transaction identification method based on fund transaction network according to claim 1, wherein: the basic index data comprises bank multi-dimensional information statistical data; the bank multidimensional information statistical data comprises: the data of the distribution condition of the corporate, individual household, other organizations and private persons, the data of the distribution condition of deposit accounts and loan accounts, the data of the distribution condition of transaction channels, the number of transaction strokes and the transaction amount, the data of the ranking condition of the transaction of the large-volume client, the data of the distribution condition of industry transaction behaviors, the data of the age group transaction behaviors and the data of the distribution condition of the transaction destination.
11. An abnormal transaction identification system based on a fund transaction network is characterized in that: the abnormal transaction identification system comprises a data mart construction module, a basic index mining module, a risk characteristic generation module, a transaction network construction module and a suspicious case generation module;
the data mart construction module is used for carrying out standardization processing on the acquired transaction related data so as to convert the transaction related data into multi-class theme data and constructing a data mart through the multi-class theme data; and imperfect customer information, account information and information of a transaction opponent are perfected and added in by adopting the modes of extraction, interactive conversion and loading;
the basic index mining module is used for processing various types of subject data in the data mart by adopting clustering, regression and iteration data mining modes based on the data mart to obtain basic index data used as an abnormal behavior comparison standard;
the risk characteristic generation module is used for performing characteristic calculation on data in the data mart by taking the basic index data as a basis so as to generate first risk characteristic data;
the transaction network establishing module is used for enabling all transaction data related to the first risk characteristic data to serve as a data base and establishing a plurality of fund transaction networks formed based on the transaction data according to a fund transfer-in and transfer-out relation, and the fund transaction networks are automatically established and reduced in real time according to real-time data change;
the suspicious case generation module is used for respectively carrying out risk characteristic matching on each fund transaction network and a transaction risk model established in advance so as to calculate the matching degree of each fund transaction network and the transaction risk model, and is used for taking the fund transaction network with the matching degree reaching a risk threshold as an abnormal transaction suspicious case;
the abnormal transaction identification system also comprises a risk model establishing module;
the risk model establishing module is used for carrying out scene definition on money laundering case data, wherein the scene type of the money laundering case is defined to be various, and the risk model establishing module is used for classifying the money laundering case data which are defined in the scene type, so that the money laundering case data belonging to the same scene are in the same scene type; under any scene type, the risk model establishing module is used for extracting second risk characteristic data in money laundering case data in the scene and establishing a transaction risk model based on the second risk characteristic data; wherein one scene category corresponds to one transaction risk model.
12. The funds transaction network based abnormal transaction identification system of claim 11 wherein: the transaction network building module comprises a temporary market building unit, a transaction data processing unit and a transaction network building unit;
the temporary market building unit is used for extracting all transaction data associated with the first risk characteristic data and building a temporary risk data market by using all transaction data;
the transaction data processing unit is used for grouping all transaction data in the temporary risk data mart according to the transfer-in and transfer-out relationship of funds, and is used for enabling the transfer-in or transfer-out relationship to exist among the transaction data in the same group;
the transaction network establishing unit is used for establishing all transaction data in the same group into a fund transaction network with transfer-in or transfer-out relationship among network nodes, wherein the network nodes are at least one of users, accounts and equipment.
13. The funds transaction network based abnormal transaction identification system of claim 11 wherein:
the suspicious case generation module is further used for performing risk feature matching on first risk feature data corresponding to the fund transaction network and second risk feature data corresponding to the transaction risk model when the fund transaction network is subjected to risk feature matching with the transaction risk model.
14. The funds transaction network based abnormal transaction identification system of claim 13 wherein:
the suspicious case generating module is further configured to quantify a risk feature matching result of the first risk feature data and the second risk feature data, make the quantified result an accumulated total score or a logical expression, and determine a suspicious case of abnormal transaction according to the quantified result.
15. The funds transaction network based abnormal transaction identification system of any of claims 11, 12, 13, 14 wherein: the abnormal transaction identification system also comprises a discrimination report generation module;
and the screening report generation module is used for filling data related to the abnormal transaction suspicious cases into a specified template file so as to generate a suspicious screening report.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811227516.4A CN109461078B (en) | 2018-10-22 | 2018-10-22 | Abnormal transaction identification method and system based on fund transaction network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811227516.4A CN109461078B (en) | 2018-10-22 | 2018-10-22 | Abnormal transaction identification method and system based on fund transaction network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109461078A CN109461078A (en) | 2019-03-12 |
| CN109461078B true CN109461078B (en) | 2020-09-11 |
Family
ID=65608012
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811227516.4A Active CN109461078B (en) | 2018-10-22 | 2018-10-22 | Abnormal transaction identification method and system based on fund transaction network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109461078B (en) |
Families Citing this family (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110175916B (en) * | 2019-04-26 | 2023-07-18 | 创新先进技术有限公司 | Fund flow checking method and device |
| CN110276620B (en) * | 2019-06-28 | 2024-09-17 | 深圳前海微众银行股份有限公司 | Method and device for determining abnormal transaction |
| CN110659989A (en) * | 2019-09-10 | 2020-01-07 | 马洪富 | Active exploration type compliance anti-money laundering method, device, system and storage medium |
| CN112541765A (en) * | 2019-09-20 | 2021-03-23 | 京东数字科技控股有限公司 | Method and apparatus for detecting suspicious transactions |
| CN110795807B (en) * | 2019-10-28 | 2023-07-18 | 天津大学 | A method for building an abnormal structure detection model of elements based on complex networks |
| CN110956445B (en) * | 2019-11-18 | 2023-03-10 | 支付宝(杭州)信息技术有限公司 | Method and device for generating risk file |
| CN110942314A (en) * | 2019-12-02 | 2020-03-31 | 中国建设银行股份有限公司 | Abnormal account supervision method and device |
| CN111160919B (en) * | 2019-12-31 | 2024-01-23 | 众安信息技术服务有限公司 | Block chain address risk assessment method and device |
| CN111507820A (en) * | 2020-04-08 | 2020-08-07 | 上海金仕达软件科技有限公司 | Gridding financial wind control intelligent system |
| CN111737287B (en) * | 2020-05-29 | 2024-11-26 | 深圳追一科技有限公司 | Method, device, computer equipment and storage medium for determining suspicious cases |
| CN111667368B (en) * | 2020-05-29 | 2023-08-18 | 中国工商银行股份有限公司 | Anti-money laundering monitoring system and method |
| CN111833182B (en) * | 2020-07-27 | 2024-03-08 | 中国工商银行股份有限公司 | Method and device for identifying risk object |
| CN112221155B (en) * | 2020-10-10 | 2021-09-07 | 上海逗视网络科技有限公司 | Game data identification method based on artificial intelligence and big data and game cloud center |
| CN112330329A (en) * | 2020-10-12 | 2021-02-05 | 支付宝(杭州)信息技术有限公司 | Risk transaction data processing method, device, equipment and 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 |
| CN113807853A (en) * | 2020-11-12 | 2021-12-17 | 中科金审(北京)科技有限公司 | Economic crime identification method |
| CN112215616B (en) * | 2020-11-30 | 2021-04-30 | 四川新网银行股份有限公司 | Method and system for automatically identifying abnormal fund transaction based on network |
| CN112561703B (en) * | 2020-12-23 | 2022-10-25 | 支付宝(杭州)信息技术有限公司 | Method and system for depicting local relationship network based on asynchronous network depiction and real-time feature extraction |
| CN113919844A (en) * | 2021-09-28 | 2022-01-11 | 陕西师范大学 | Multi-view network transaction risk identification method based on data Petri net |
| CN114331431A (en) * | 2021-12-24 | 2022-04-12 | 中国工商银行股份有限公司 | Method, device, equipment and medium for reporting large-value cash transaction data |
| CN114971142A (en) * | 2022-03-04 | 2022-08-30 | 中国建设银行股份有限公司 | Illegal fund risk assessment method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105005931A (en) * | 2014-04-24 | 2015-10-28 | 中国银联股份有限公司 | Method and device for controlling risk of transfer transaction |
| CN106327340A (en) * | 2016-08-04 | 2017-01-11 | 中国银联股份有限公司 | Method and device for detecting abnormal node set in financial network |
| CN107730262A (en) * | 2017-10-23 | 2018-02-23 | 阿里巴巴集团控股有限公司 | One kind fraud recognition methods and device |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004252517A (en) * | 2003-02-18 | 2004-09-09 | Hitachi Ltd | Reserved dealings inquiry method and financial system |
| JP4512621B2 (en) * | 2007-08-06 | 2010-07-28 | 株式会社日立製作所 | Distributed system |
| US10163158B2 (en) * | 2012-08-27 | 2018-12-25 | Yuh-Shen Song | Transactional monitoring system |
| CN106294521B (en) * | 2015-06-12 | 2019-09-06 | 交通银行股份有限公司 | Date storage method and data warehouse |
| CN107067324A (en) * | 2017-04-18 | 2017-08-18 | 上海翼翎数据信息技术有限公司 | A kind of utilization network packet capturing data realize the method and system of transaction risk control |
| CN107767021A (en) * | 2017-09-12 | 2018-03-06 | 阿里巴巴集团控股有限公司 | A kind of risk control method and equipment |
| 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 |
| CN108564376A (en) * | 2018-04-20 | 2018-09-21 | 阿里巴巴集团控股有限公司 | Risk control method, device, server and readable storage medium storing program for executing |
-
2018
- 2018-10-22 CN CN201811227516.4A patent/CN109461078B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105005931A (en) * | 2014-04-24 | 2015-10-28 | 中国银联股份有限公司 | Method and device for controlling risk of transfer transaction |
| CN106327340A (en) * | 2016-08-04 | 2017-01-11 | 中国银联股份有限公司 | Method and device for detecting abnormal node set in financial network |
| CN107730262A (en) * | 2017-10-23 | 2018-02-23 | 阿里巴巴集团控股有限公司 | One kind fraud recognition methods and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109461078A (en) | 2019-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109461078B (en) | Abnormal transaction identification method and system based on fund transaction network | |
| CN109543096B (en) | Data query method, device, computer equipment and storage medium | |
| Lin et al. | Detecting the financial statement fraud: The analysis of the differences between data mining techniques and experts’ judgments | |
| CN109377339B (en) | Auxiliary screening method and system for suspicious transaction cases | |
| CN112668859A (en) | Big data based customer risk rating method, device, equipment and storage medium | |
| CN109767327A (en) | Customer information acquisition and its application method based on anti money washing | |
| CN109767226B (en) | Method and device for generating suspicious transaction statistical view based on big data | |
| CN112631889B (en) | Portrayal method, device, equipment and readable storage medium for application system | |
| US20200065867A1 (en) | Patent valuation system | |
| CN111833182B (en) | Method and device for identifying risk object | |
| CN112581283B (en) | Method and device for analyzing and warning transaction behavior of commercial bank employees | |
| CN111583033A (en) | Association analysis method and device based on relation between listed company and stockholder | |
| CN111709826A (en) | Target information determination method and device | |
| CN114493619A (en) | A construction method of enterprise credit information label based on power data | |
| CN117391440A (en) | Enterprise information reconnaissance platform and method | |
| CN111708897A (en) | Target information determination method, device and equipment | |
| CN108734021B (en) | Financial loan big data risk assessment method and system based on privacy-removing data | |
| CN115545886A (en) | Overdue risk identification method, overdue risk identification device, overdue risk identification equipment and storage medium | |
| Liu et al. | Credit assessment of contractors: a rough set method | |
| Bender et al. | A General Framework for the Identification and Categorization of Risks-An Application to the Context of Financial Markets | |
| Shi et al. | Bank financial sustainability evaluation: Data envelopment analysis with random forest and Shapley additive explanations | |
| CN117114812A (en) | Financial product recommendation method and device for enterprises | |
| CN115879548A (en) | Knowledge graph construction method and system for customer identity recognition | |
| CN114493864A (en) | Capital big data based anomaly detection system and method | |
| CN114139061A (en) | Target customer screening system and method thereof |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100107 9 / F, Beichen Taiyue building, a 13 Beiyuan Road, Chaoyang District, Beijing Patentee after: Beijing Lingyan Technology Co.,Ltd. Address before: 100107 9 / F, Beichen Taiyue building, a 13 Beiyuan Road, Chaoyang District, Beijing Patentee before: CITIC APPLICATION SERVICE PROVIDER Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20190312 Assignee: CHINA TECHNOLOGY EXCHANGE Co.,Ltd. Assignor: Beijing Lingyan Technology Co.,Ltd. Contract record no.: X2022110000044 Denomination of invention: A Method and System for Identifying Abnormal Transactions Based on Capital Transaction Network Granted publication date: 20200911 License type: Exclusive License Record date: 20220928 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A Method and System for Identifying Abnormal Transactions Based on Capital Transaction Network Effective date of registration: 20220930 Granted publication date: 20200911 Pledgee: CHINA TECHNOLOGY EXCHANGE Co.,Ltd. Pledgor: Beijing Lingyan Technology Co.,Ltd. Registration number: Y2022110000255 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| EC01 | Cancellation of recordation of patent licensing contract |
Assignee: CHINA TECHNOLOGY EXCHANGE Co.,Ltd. Assignor: Beijing Lingyan Technology Co.,Ltd. Contract record no.: X2022110000044 Date of cancellation: 20240322 |
|
| EC01 | Cancellation of recordation of patent licensing contract | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Granted publication date: 20200911 Pledgee: CHINA TECHNOLOGY EXCHANGE Co.,Ltd. Pledgor: Beijing Lingyan Technology Co.,Ltd. Registration number: Y2022110000255 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right |