CN109461078A - A kind of abnormal transaction identification method and system based on funds transaction network - Google Patents
A kind of abnormal transaction identification method and system based on funds transaction network Download PDFInfo
- Publication number
- CN109461078A CN109461078A CN201811227516.4A CN201811227516A CN109461078A CN 109461078 A CN109461078 A CN 109461078A CN 201811227516 A CN201811227516 A CN 201811227516A CN 109461078 A CN109461078 A CN 109461078A
- Authority
- CN
- China
- Prior art keywords
- data
- transaction
- risk
- feature
- network
- 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.)
- Granted
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000004900 laundering Methods 0.000 claims abstract description 85
- 230000000694 effects Effects 0.000 claims description 40
- 230000001186 cumulative effect Effects 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 8
- 206010000117 Abnormal behaviour Diseases 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 238000007418 data mining Methods 0.000 claims description 6
- 238000005406 washing Methods 0.000 claims description 6
- 238000013139 quantization Methods 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims description 2
- 238000011835 investigation Methods 0.000 abstract description 10
- 230000008901 benefit Effects 0.000 abstract description 8
- 238000009412 basement excavation Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 230000003542 behavioural effect Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000011002 quantification Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000029305 taxis Effects 0.000 description 2
- 208000001613 Gambling Diseases 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The abnormal transaction identification method and system based on funds transaction network that the invention discloses a kind of, the exception transaction identification method include the following steps: the step of constructing Data Mart by multiclass subject data, determine the step of base values data, generate the step of the step of the first feature of risk data, multiple funds transaction networks that establishment is formed based on transaction data, generate the step of abnormal transaction suspected cases and generate the step of suspicious examination is reported；The exception transaction identification system includes: Data Mart building module, base values excavation module, feature of risk generation module, trade network establishment module, suspected cases generation module and screens report generation module.Funds transaction network and transaction risk model based on foundation, the present invention can thoroughly restore money laundering process and money laundering scene, provide strong support and help for the work of money laundering behavior investigation；The present invention also has outstanding advantages of precision is high, comprehensive good, objectivity is strong.
Description
Technical field
The present invention relates to transaction data processing technology fields, and more specifically, the present invention is a kind of based on funds transaction net
The abnormal transaction identification method and system of network.
Background technique
Anti money washing often refers to prevent to cover up, conceal the tissue criminal of Drug-related crimes, underworld property by various modes
Crime gained and its receipts such as crime, terrorist activity crime, smuggling offences, crime of embezzlement and bribery and destruction Financial Management order crime
The source of benefit and the money-laundering of property, the main activities of money laundering are substantially by financial transaction realization, so can lead to
Investigation financial transaction discovery money laundering phenomenon is crossed, but if only relying on the data of financial transaction of manpower manual investigation magnanimity, discovery is washed
Money behavior is impossible；In consideration of it, the prior art uses database, index calculates or storing process coding calculates
Etc. modes identify that abnormal transaction, try to find out money laundering behavior, it is a large amount of practice have shown that: aforesaid way still can not be accurately and comprehensively
Identify abnormal transaction, effect or undesirable, the later period still has extreme difficulty to the investigation of money laundering behavior.
Therefore, how it is accurate and comprehensively identify abnormal transaction, provided for the work of money laundering behavior investigation it is strong
Data support, the emphasis for becoming those skilled in the art's technical problem urgently to be resolved and studying always.
Summary of the invention
For the solution transaction of the existing technology that can not accurately and comprehensively note abnormalities, to money laundering behavior investigation working pit edge
It helping the problems such as smaller, the present invention innovatively provides a kind of abnormal transaction identification method and system based on funds transaction network,
From the characteristics of abnormal trading activity itself, using the feature of risk that abnormal trading activity has as foundation, it is fixed against fund
The building of trade network, the present invention can thoroughly restore money laundering process and money laundering scene, provide for the work of money laundering behavior investigation
Strong support and help.
To realize above-mentioned technical purpose, the invention discloses a kind of abnormal transaction identification sides based on funds transaction network
Method, the exception transaction identification method include the following steps；
The transactional related data obtained is standardized, to convert multiclass for the transactional related data
Subject data constructs Data Mart by the multiclass subject data；
Fairground based on the data is handled the multiclass subject data in Data Mart by data mining mode,
To obtain for the base values data as abnormal behaviour standard of comparison；
Using the base values data as foundation, feature calculation is carried out to the data in Data Mart, to generate the
One feature of risk data；
It enables with the All Activity data of the first feature of risk data correlation as data basis, according to being transferred to for fund
It produces relationship and sets up the multiple funds transaction networks formed based on the transaction data；
Each funds transaction network is subjected to feature of risk matching with the transaction risk model pre-established respectively, to calculate
Matching degree is reached the funds transaction network of risk thresholding by the matching degree of each funds transaction network and transaction risk model
As abnormal suspected cases of trading.
Based on above-mentioned technical solution, the present invention can note abnormalities trading situation from a large amount of transactional related data,
It precisely and comprehensively determines abnormal transaction, thoroughly restores money laundering process and money laundering scene, provide line for the work of money laundering behavior investigation
Rope and evidence, it is of the existing technology effectively to solve the problems, such as.
Further, during setting up funds transaction network, include the following steps；
All Activity data associated with the first feature of risk data are extracted, the All Activity data structure is utilized
Build interim risk data fairground；
The relationship of producing is transferred to as foundation using fund, and the All Activity data in interim risk data fairground are divided
Group processing；Wherein, enable between the transaction data in group exist be transferred to or produce relationship；
Whole transaction data in same group are set up at having the fund for being transferred to or producing relationship between network node
Trade network, the network node are at least one of user, account, equipment.
Based on above-mentioned improved technical solution, the present invention can clearly give expression to the pass of the treasury trade between suspicious transaction
The money laundering risks feature for including in system, each network and related personnel provide greatly for abnormal transaction identification, Anti-Money Laundering
Help.
Further, transaction risk model is established in the following way；
To money laundering number of packages according to carrying out displaying definition, by money laundering number of packages that displaying defines according to classifying, thus
Make the money laundering number of packages for belonging to Same Scene according under the same scene type；
Under any one scene type, the second feature of risk data in the scene in money laundering case data are extracted, are based on
Second feature of risk data establish transaction risk model；Wherein, a kind of scene type corresponds to a kind of transaction risk model.
Based on above-mentioned improved technical solution, the present invention is by way of money laundering case displaying by money laundering Activity recognition field
To establish accurate, comprehensive transaction risk model, and then artificial parameter configuration work amount is effectively reduced in Jing Hua, to realize
Abnormal trading activity, money laundering behavior are more accurately identified.
It further, will be with the fund when funds transaction network and transaction risk model carry out feature of risk matching
The corresponding first feature of risk data of trade network, the second feature of risk data corresponding with the transaction risk model carry out wind
Dangerous characteristic matching.
Further, the first feature of risk data are matched into knot with the feature of risk of the second feature of risk data
Fruit is quantified, and enabling quantized result is cumulative total score or logical expression；
If quantized result is cumulative total score, by cumulative total score pre-determined threshold score value corresponding with risk thresholding into
Row compares, suspicious as abnormal transaction above or equal to the corresponding funds transaction network of cumulative total score of pre-determined threshold score value
Case；
If quantized result is logical expression, the logical expression default expression formula corresponding with risk thresholding is carried out
Matching regard funds transaction network corresponding with the matched logical expression of default expression formula as abnormal transaction suspected cases.
Further, the transaction risk model is anti money washing model.
Further, when carrying out feature calculation to the data in Data Mart, include the following steps；
Risk case feature is defined by referring to the mode of base values data, according to the risk case feature to data
Data in fairground are screened and are parsed, using parsing result as the first feature of risk data.
Further, for the risk case feature for describing risk case, the risk case includes: different enterprises
Legal representative or senior executive are identical, different enterprises possess the same corporate accounting, connected transaction occurs for many enterprises, belonging to enterprise
Industry be specific industry, trading frequency and transaction size and registered enterprise fund scale be not obviously inconsistent, evade supervision be intended to obviously,
To public account frequently to personal account is transferred to substantial contribution, funds transaction private to the revolution of public account is all handed over by Web bank
Easily.
Further, which further includes following steps；
After determining the abnormal transaction suspected cases, will data relevant to the abnormal transaction suspected cases fill to
In specified template file, to generate suspicious examination report.
Further, the multiclass subject data includes client's subject data, account subject data and subject of transaction data.
Further, the base values data include bank's various dimensions Information Statistics data；Bank's various dimensions letter
Breath statistical data include: to the legal person of public law, self-employed worker, its hetero-organization, to the distribution situation data of private natural person, savings account, loan
Money account distribution situation data, transaction channel accounting, transaction stroke count, transaction amount distribution situation data, wholesale client trading
Ranking data, industry trading activity distribution situation data, age bracket trading activity data, transaction whereabouts ground distribution situation number
According to.
To realize the above-mentioned technical purpose, the invention also discloses a kind of abnormal transaction identification system based on funds transaction network
System, the exception transaction identification system includes Data Mart building module, base values excavates module, feature of risk generates mould
Block, trade network set up module and suspected cases generation module；
The Data Mart constructs module, for being standardized to the transactional related data obtained, thus will
The transactional related data is converted into multiclass subject data, and for constructing Data Mart by the multiclass subject data；
The base values excavates module, for fairground based on the data, by data mining mode to Data Mart
In multiclass subject data handled, to obtain for the base values data as abnormal behaviour standard of comparison；
The feature of risk generation module is used for using the base values data as foundation, to the number in Data Mart
According to feature calculation is carried out, to generate the first feature of risk data；
The trade network sets up module, makees for enabling with the All Activity data of the first feature of risk data correlation
For data basis, for setting up the multiple funds transaction nets formed based on the transaction data according to the relationship that produces that is transferred to of fund
Network；
The suspected cases generation module, for by each funds transaction network respectively with the transaction risk mould that pre-establishes
Type carries out feature of risk matching, to calculate the matching degree of each funds transaction network and transaction risk model, for that will match
Degree reaches the funds transaction network of risk thresholding as abnormal transaction suspected cases.
Based on above-mentioned technical solution, the present invention can note abnormalities trading situation from a large amount of transactional related data,
It precisely and comprehensively determines abnormal transaction, thoroughly restores money laundering process and money laundering scene, provide line for the work of money laundering behavior investigation
Rope and evidence, it is of the existing technology effectively to solve the problems, such as.
Further, the trade network set up module include interim fairground construction unit, transaction data processing unit and
Trade network sets up unit；
The interim fairground construction unit, for extracting All Activity number associated with the first feature of risk data
Construct interim risk data fairground accordingly and using the All Activity data；
The transaction data processing unit, for being transferred to the relationship of producing as according to interim risk data collection using fund
All Activity data in city are grouped processing, for enable between the transaction data in group exist be transferred to or produce relationship；
The trade network sets up unit, and whole transaction data for that will be in same group are set up between network node
With the funds transaction network for being transferred to or producing relationship, the network node is at least one of user, account, equipment.
Based on above-mentioned improved technical solution, the present invention can clearly give expression to the pass of the treasury trade between suspicious transaction
The money laundering risks feature for including in system, each network and related personnel provide greatly for abnormal transaction identification, Anti-Money Laundering
Help.
Further, the abnormal transaction identification system further includes that risk model establishes module；
The risk model establishes module, is used for money laundering number of packages according to displaying definition is carried out, for determining displaying
The money laundering number of packages of justice is according to classifying, to make the money laundering number of packages for belonging to Same Scene according under the same scene type；
Under any one scene type, the risk model establishes module for extracting the second wind in the scene in money laundering case data
Dangerous characteristic and transaction risk model is established based on the second feature of risk data；Wherein, a kind of scene type corresponds to a kind of friendship
Easy risk model.
Further, the suspected cases generation module is also used to carry out in funds transaction network and transaction risk model
Feature of risk will the first feature of risk data corresponding with the funds transaction network and the transaction risk model pair when matching
The the second feature of risk data answered carry out feature of risk matching.
Further, the suspected cases generation module is also used to the first feature of risk data and described second
The feature of risk matching result of feature of risk data is quantified, quantized result is enabled to be cumulative total score or logical expression, with
And for determining abnormal transaction suspected cases according to quantized result.
Further, which further includes screening report generation module；
The examination report generation module, for filling data relevant to the exception transaction suspected cases to specified
In template file, to generate suspicious examination report.
The invention has the benefit that funds transaction network and transaction risk model based on foundation, the present invention can be thorough
Money laundering process and money laundering scene are restored, provides strong support and help for the work of money laundering behavior investigation；The present invention also has
Outstanding advantages of precision is high, comprehensive good, objectivity is strong.
The present invention can be effectively reduced the objectivity of artificial parameter configuration work amount and parameter setting: be based on base by system
Plinth index calculates completion automatically, and numerical value is more objective and accurate, can sufficiently meet different geographical, and the characteristic quantification of different clients group needs
It wants.
The present invention can effectively promote the recognition capability and accuracy of suspected cases: money laundering Activity recognition displaying is led to
Cross group relation, funds transaction network is started with, not merely only focus on certain transaction or some client, can thoroughly restore money laundering
Process overall picture.
Present invention innovation provides model quantization scheme, keeps the present invention simpler and easy-to-use, quantitative criteria is objective and accurate: will
Money laundering Activity recognition procedure decomposition are as follows: index-feature-model different levels recycles big data computing capability, sufficiently identifies
Behavioural habits, money laundering feature and the Model Matching situation of a main body, each level can constantly extend according to actual needs, so
The present invention has many advantages, such as applied widely, easy to promote and utilize.Above-mentioned model quantizing process is simple, effective, can be more straight
It sees reaction money laundering scene: according to the money laundering risks model Quantitative System of the money laundering risks identification Theoretical Design of itself, passing through formula
Model quantizing process can be transferred to business personnel to complete by method and percentile method, and business thinking can be easily embodied in system.
The present invention by suspected cases it is objective reduce money laundering behavior generation process and funds flow, resources flow with
And fund flow condition, it is objective to have reacted the client's group information for participating in money laundering behavior, it is financial institution and regulatory agency into one
Clear up a criminal case is walked, advantageous clue and evidence are provided.
After the present invention is cured as software systems, the money laundering case examination process of automation, continuous and effective may be implemented, have
Effect reduces manual working pressure, has outstanding advantages of highly reliable, at low cost.
Detailed description of the invention
Fig. 1 is the flow diagram of the abnormal transaction identification method based on funds transaction network.
Fig. 2 is the constructional flow schematic diagram of funds transaction network of the present invention.
Fig. 3 is the schematic diagram for the funds transaction network that network node is user.
Fig. 4 is the Establishing process schematic diagram of transaction risk model of the present invention.
Fig. 5 is the composition block diagram of the abnormal transaction identification system based on funds transaction network.
Specific embodiment
With reference to the accompanying drawings of the specification to a kind of abnormal transaction identification method based on funds transaction network of the invention and
System carries out detailed explanation and illustration.
Embodiment one
The abnormal transaction identification method based on funds transaction network that present embodiment discloses a kind of, the present invention is to abnormal transaction
The basis of characterization of (including money laundering risks) is the data, such as Fig. 1 such as the customer data, account data and all kinds of transaction journals of bank
Shown, which includes the following steps.
Step S1 obtains the transactional related data of bank, is standardized to the transactional related data obtained, from
And multiclass subject data is converted by transactional related data, for example the data of credit system, state's clone system, core system are converted
For identical theme standard, Data Mart is constructed by multiclass subject data, which is used for the basis of abnormal transaction identification；
In the present embodiment, multiclass subject data includes client's subject data, account subject data and subject of transaction data etc..The present embodiment
ETL mode also can be used: i.e. extraction (extract), interaction conversion (transform), load (load), to incomplete client
Information, account information and counterparty information are improved according to supervision standard and amended record, guarantees the consistency and completely of data
Property.
Step S2, the Data Mart based on above-mentioned standard, by data mining mode to the multiclass theme in Data Mart
Data are handled, and the present embodiment calculates multiclass subject data (i.e. basis using the data digging methods such as cluster, recurrence, iteration
Data target), cover the Information Statistics data of each dimension of bank, to obtain for as abnormal behaviour standard of comparison
Base values data have the distinctive standard value database of every financial institution to be formed；Base values data may include bank
Various dimensions Information Statistics data；Bank's various dimensions Information Statistics data include: to the legal person of public law, self-employed worker, its hetero-organization, to privately
The distribution situation data of right people, savings account, loan account distribution situation data, transaction channel accounting, transaction stroke count, trade gold
Volume distribution situation data, the ranking data of wholesale client trading, industry trading activity distribution situation data, age bracket transaction
Behavioral data, transaction whereabouts ground nearly 100 indexs such as distribution situation data.These indexs embody different industries, all ages and classes
The financial feature of equal groups, trade preference, behavioural habits etc., can also embody business preference, the regional feature, locality of financial institution
Client's group characteristics etc., the present embodiment establish the distinctive criterion of bank, to establish the distinctive abnormal behaviour of bank
Standard of comparison.
Step S3, the present embodiment are based on base values data and Data Mart, using base values data as foundation, logarithm
Feature calculation is carried out according to the data in fairground, to generate the first feature of risk data, and then anti money washing standard can be constructed
Risk case library；In the present embodiment, in Data Mart data carry out feature calculation when, include the following steps: by referring to
The mode of base values data defines risk case feature, and is capable of forming persistence configuration, the risk case feature and normal
The relevant affair character of trading activity is aobvious there are include in certain specific money laundering scenes in significant difference, reflection process of exchange
Feature is write, the data in Data Mart are screened and parsed according to risk case feature, using parsing result as the first wind
Dangerous characteristic.Wherein, risk case feature is for describing risk case, for example, risk case includes: the legal of different enterprises
Representative or senior executive are identical, different enterprises possess the same corporate accounting, connected transaction, the affiliated industry of enterprise occur for many enterprises
Obviously be not inconsistent for specific industry, trading frequency and transaction size and registered enterprise fund scale, evade supervision be intended to it is obvious, to public affairs
Account is frequently to personal account is transferred to substantial contribution, funds transaction private to the revolution of public account all passes through internet bank trade etc.
Deng.Although not can determine that the money laundering behavior that certainly exists by some above-mentioned risk case, money laundering behavior centainly with it is above-mentioned at least
One risk case is related, thus based on risk case and the first feature of risk data of determination constitute money laundering case basis want
Element.By largely testing and attempting, quantified nearly 500 risk cases of the present embodiment have at least generated 500 kinds
First feature of risk data, features described above calculating process can realize that multi-thread concurrent executes, and have computational efficiency height, can per diem give birth to
The advantages that at the first feature of risk data.
Step S4 is enabled with the All Activity data of the first feature of risk data correlation as data basis, according to fund
It is transferred to the relationship that produces and sets up the multiple funds transaction networks formed based on transaction data；The funds transaction network can reflect comprehensively
Funds flow, the transaction feature of client group etc. of money laundering risks are provided, and can be changed according to real time data and be set up automatically,
Abatement in real time, as shown in Fig. 2, including the following steps during setting up funds transaction network.
Step S40 is extracted and the first feature of risk for the All Activity data of all the first feature of risk data correlations
The associated All Activity data of data recycle All Activity data to construct interim risk data fairground.
Step S41 is transferred to the relationship of producing as foundation, to the All Activity number in interim risk data fairground using fund
It is handled according to being grouped；Wherein, enable between the transaction data in group exist be transferred to or produce relationship.
Whole transaction data in same group are set up and are transferred to or produce pass at having between network node by step S42
The funds transaction network of system, funds transaction network provided in this embodiment are the transaction journal data shapes that will have certain relevance
It is grouped at a set of independent funds transaction flowing water, the first above-mentioned feature of risk data of this relevance major embodiment (or wind
Dangerous event), for example, " its legal representative of different enterprises or senior executive is identical, different enterprises possess the same corporate accounting or more
Connected transaction occurs for enterprise, family " etc., the customer information etc. for contact of participating in business in the grouping is more embodied, this is based on, it can be fast
What speed identified that the network has can be with feature and composition of personnel etc.；Wherein, network node be user, account, in equipment extremely
Few one kind, present embodiment discloses the funds transaction networks that a kind of network node is user, as shown in figure 3, for example, (1) is transferred to
The amount of money is accumulative: 1,000,000；It is accumulative to produce the amount of money: 800,000, cash transaction: 200,000；Accumulative transaction stroke count: 15；(2) Li Chengjian to
Lee's small yarn is accumulative to be transferred to 200,000, trades stroke count 3；(3) Tommy is transferred to 50,000 to Lee's small yarn is accumulative, trades stroke count 1；(4) Cai
Lee's Wen Qingxiang small yarn is accumulative to be transferred to 250,000, trades stroke count 1；(5) Hou Xiao east orientation Lee small yarn is accumulative is transferred to 100,000, stroke count 1 of trading
Pen；(6) all shirts are transferred to 400,000 to Lee's small yarn is accumulative, trade stroke count 6；(7) Chen Sicheng is transferred to 200,000 to Li Chengjian is accumulative, transaction
Stroke count 1；(8) Lee's small yarn is transferred to 750,000 to Hou Xiaodong is accumulative, trades stroke count 1；(9) Lee's small yarn is transferred to 50,000 to all shirts are accumulative,
Transaction stroke count 1.
The present embodiment constructs funds transaction network through the above way, includes a fixed number in each funds transaction network
Amount the first feature of risk data, but the suspicious degree of each funds transaction network, with the presence or absence of money laundering behavior, specifically exist which
Situations such as money laundering behavior, is still indefinite, so, the present embodiment, which is used, constructs money laundering risks model based on the displaying of money laundering case
Etc. technological means, explication is carried out to every a kind of money laundering part, so that it is determined that the suspicious degree of each funds transaction network, whether
There are money laundering behavior, specifically there is situations such as which money laundering behavior.
Each funds transaction network is carried out feature of risk with the transaction risk model pre-established respectively by step S5
Match, to calculate the matching degree of each funds transaction network and transaction risk model, matching degree is reached to the money of risk thresholding
Golden trade network can give alarm to the funds transaction network for reaching risk thresholding as abnormal transaction suspected cases.The case
Include: a) participating in whole customer informations of money laundering process；B) Transaction Information of money laundering behavior is reacted；C) react money laundering behavior can
Doubt identification point；D) and reaction matching criteria group characteristics standard value etc..
In the present embodiment, transaction risk model can be the anti money washing model dedicated for anti money washing, in funds transaction net
When network and transaction risk model carry out feature of risk matching, can will the first feature of risk data corresponding with funds transaction network,
The second feature of risk data corresponding with transaction risk model carry out feature of risk matching.For the matched accuracy of raising and reliably
Property, the present embodiment quantify the feature of risk matching result of the first feature of risk data and the second feature of risk data, can
Enabling quantized result is that cumulative total score or logical expression, the present embodiment can be according to patrolling between each feature of risk matching result
The tightness degree for the relationship of collecting determines quantification manner: if logical relation is stronger between feature of risk matching result, public affairs can be used
Formula method, i.e. logical expression；If if between feature of risk matching result logical relation compared with, percentile method can be used, i.e., it is cumulative
Total score.
If quantized result is cumulative total score, cumulative total score pre-determined threshold score value corresponding with risk thresholding is compared
Compared with the corresponding abnormal transaction of funds transaction network conduct of cumulative total score above or equal to pre-determined threshold score value can doubtful case
Example.Such as: " the money laundering scene that scene 1- gains refund by cheating " of " doubtful crime money laundering model of paying taxes " includes 6 suspicious characteristics:
(1) the affiliated industry of enterprise is that specific industry (score value=1), (2) trading frequency and transaction size and registered enterprise fund scale are bright
Aobvious not to be inconsistent (score value=10), (3) evade supervision and are intended to more apparent (score value=8), and (4) are frequently transferred to public account to personal account
A large amount of amount of money (score value=7), (5) revolve private (score value=7) to public account, and (6) funds transaction is substantially all to pass through Web bank
(score value=12)；This equal onrelevant relationship of six features, the present embodiment are tired by counting according to suspicious degree established standards score value
Addition realizes that total score calculates, then compared with case pre-determined threshold score value, if it is greater than pre-determined threshold score value, can determine whether this
The corresponding funds transaction network of quantized result is abnormal transaction suspected cases.
If quantized result is logical expression, by logical expression default expression formula progress corresponding with risk thresholding
Match, regard funds transaction network corresponding with the matched logical expression of default expression formula as abnormal transaction suspected cases.Such as:
" the money laundering scene that scene 2- passes through affiliated enterprise's transfer income " in " doubtful crime money laundering model of paying taxes ", includes 3 risks
Feature: (1) different its legal representative of enterprise or senior executive is identical, (2) different enterprises possess the same corporate accounting, (3) more families
Connected transaction occurs for enterprise；Default expression formula: (1 ∪ 2) ∩ 3 can be obtained after three characteristic quantifications；If logical expression form
Quantized result meet above-mentioned default expression formula, then can determine whether that the corresponding funds transaction network of the quantized result can for abnormal transaction
Doubtful case example.
Step S6, after determining abnormal transaction suspected cases, will data relevant to abnormal transaction suspected cases fill to
In specified template file, to generate suspicious examination report, system-computed process can be covered in suspicious examination report, analyze the case
The whole flow process and relevant evidence information of example, can intuitively be showed by diagrammatic form, which reports can also be through
Bank supervisor department and higher level supervision department etc. are reported to after crossing artificial identification.
The present embodiment can establish transaction risk model in advance as a preferred technical solution, so that abnormal transaction identification makes
With as shown in figure 4, establishing transaction risk model in the following way.
Step 100, to money laundering number of packages according to carry out displaying definition, the present embodiment according to actual needs to money laundering case into
Row explication, by money laundering number of packages that displaying defines according to classifying, to make the money laundering number of packages for belonging to Same Scene
According under the same scene type, in the present embodiment, scene type may include illegal private bank, tax evasion, gambling, telecommunications swindleness
It deceives, more than 20 kinds of illegal fund collection etc., each money laundering case can be carried out comprehensively, accurately to describe.
Step 200, under any one scene type, the second feature of risk number in the scene in money laundering case data is extracted
According to establishing transaction risk model based on the second feature of risk data；Wherein, a kind of scene type corresponds to a kind of transaction risk mould
Type all includes several feature of risk data in every kind of transaction risk model.
Embodiment two
As shown in figure 5, being based on identical inventive concept with embodiment one, one kind is present embodiments provided for realizing implementation
The abnormal transaction identification system based on funds transaction network of the abnormal transaction identification method of example one, the exception transaction identification system
It include: that Data Mart constructs module, base values excavates module, feature of risk generation module, trade network set up module, suspicious
Case generation module, examination report generation module and risk model establish module, and the present embodiment is described as follows.
Data Mart constructs module, for being standardized to the transactional related data obtained, thus will transaction
Related data is converted into multiclass subject data, and for constructing Data Mart by multiclass subject data.
Base values excavate module, for based on Data Mart, by data mining mode to the multiclass in Data Mart
Subject data is handled, to obtain for the base values data as abnormal behaviour standard of comparison.
Feature of risk generation module, for being carried out to the data in Data Mart special using base values data as foundation
Sign calculates, to generate the first feature of risk data.
Trade network sets up module, for enabling with the All Activity data of the first feature of risk data correlation as data base
Plinth, for setting up the multiple funds transaction networks formed based on transaction data according to the relationship that produces that is transferred to of fund.
In the present embodiment, trade network set up module may include interim fairground construction unit, transaction data processing unit and
Trade network sets up unit.
Interim fairground construction unit, for extracting All Activity data associated with the first feature of risk data and benefit
Interim risk data fairground is constructed with All Activity data.
Transaction data processing unit, for being transferred to the relationship of producing as according to in interim risk data fairground using fund
All Activity data be grouped processing, for enable between the transaction data in group exist be transferred to or produce relationship.
Trade network sets up unit, and whole transaction data establishment for that will be in same group has between network node
It is transferred to or produces the funds transaction network of relationship, network node is at least one of user, account, equipment.
Suspected cases generation module, for by each funds transaction network respectively with the transaction risk model that pre-establishes into
The matching of row feature of risk is used for calculating the matching degree of each funds transaction network and transaction risk model by matching degree
Reach the funds transaction network of risk thresholding as abnormal transaction suspected cases.More specifically, suspected cases generation module is also
For will corresponding with funds transaction network first when funds transaction network and transaction risk model carry out feature of risk matching
Feature of risk data, the second feature of risk data corresponding with transaction risk model carry out feature of risk matching.In embodiment 1
Disclosed working method is corresponding, and in the present embodiment, suspected cases generation module is also used to the first feature of risk data and the
The feature of risk matching result of two feature of risk data is quantified, quantized result is enabled to be cumulative total score or logical expression,
Suspected cases generation module is also used to according to the determining abnormal transaction suspected cases of quantized result, and detailed description are as follows.
If quantized result is cumulative total score, cumulative total score pre-determined threshold score value corresponding with risk thresholding is compared
Compared with the corresponding abnormal transaction of funds transaction network conduct of cumulative total score above or equal to pre-determined threshold score value can doubtful case
Example.
If quantized result is logical expression, by logical expression default expression formula progress corresponding with risk thresholding
Match, regard funds transaction network corresponding with the matched logical expression of default expression formula as abnormal transaction suspected cases.
As an improved technical scheme, the abnormal transaction identification system that the present embodiment is related to further includes individually designed risk
Model building module.
Risk model establishes module, is used for money laundering number of packages according to displaying definition is carried out, for define displaying
Money laundering number of packages is according to classifying, to make the money laundering number of packages for belonging to Same Scene according under the same scene type；It is in office
Under one scene type, risk model establishes module for extracting the second feature of risk number in the scene in money laundering case data
Transaction risk model is established according to and based on the second feature of risk data；Wherein, a kind of scene type corresponds to a kind of transaction risk mould
Type.
Report generation module is screened, for filling data relevant to abnormal transaction suspected cases to specified template file
In, to generate suspicious examination report.
In the description of this specification, reference term " the present embodiment ", " one embodiment ", " some embodiments ", " show
The description of example ", " specific example " or " some examples " etc. mean specific features described in conjunction with this embodiment or example, structure,
Material or feature are included at least one embodiment or example of the invention.In the present specification, above-mentioned term is shown
The statement of meaning property is necessarily directed to identical embodiment or example.Moreover, specific features, structure, material or the spy of description
Point may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other,
Those skilled in the art can be by different embodiments or examples described in this specification and different embodiments or examples
Feature is combined.In addition, term " first ", " second " are used for description purposes only, and it should not be understood as instruction or dark
Show relative importance or implicitly indicates the quantity of indicated technical characteristic.The feature of " first ", " second " is defined as a result,
It can explicitly or implicitly include at least one of the features.In the description of the present invention, the meaning of " plurality " is at least two,
Such as two, three etc., unless otherwise specifically defined.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modification, equivalent replacement and simple modifications etc., should all be included in the protection scope of the present invention in content.
Claims (17)
1. a kind of abnormal transaction identification method based on funds transaction network, it is characterised in that: the exception transaction identification method
Include the following steps；
The transactional related data obtained is standardized, to convert multiclass theme for the transactional related data
Data construct Data Mart by the multiclass subject data；
Fairground based on the data is handled the multiclass subject data in Data Mart by data mining mode, with
To for the base values data as abnormal behaviour standard of comparison；
Using the base values data as foundation, feature calculation is carried out to the data in Data Mart, to generate the first wind
Dangerous characteristic；
It enables with the All Activity data of the first feature of risk data correlation as data basis, is produced according to being transferred to for fund
Relationship sets up the multiple funds transaction networks formed based on the transaction data；
Each funds transaction network is subjected to feature of risk matching with the transaction risk model pre-established respectively, it is each to calculate
The matching degree of funds transaction network and transaction risk model, using matching degree reach the funds transaction network of risk thresholding as
Abnormal transaction suspected cases.
2. the abnormal transaction identification method according to claim 1 based on funds transaction network, it is characterised in that: setting up
During funds transaction network, include the following steps；
All Activity data associated with the first feature of risk data are extracted, are faced using All Activity data building
When risk data fairground；
The relationship of producing is transferred to as foundation using fund, and place is grouped to the All Activity data in interim risk data fairground
Reason；Wherein, enable between the transaction data in group exist be transferred to or produce relationship；
Whole transaction data in same group are set up at having the funds transaction for being transferred to or producing relationship between network node
Network, the network node are at least one of user, account, equipment.
3. the abnormal transaction identification method according to claim 1 or 2 based on funds transaction network, it is characterised in that: logical
It crosses under type such as and establishes transaction risk model；
To money laundering number of packages according to displaying definition is carried out, by money laundering number of packages that displaying defines according to classifying, to make to belong to
In Same Scene money laundering number of packages according under the same scene type；
Under any one scene type, the second feature of risk data in the scene in money laundering case data are extracted, are based on second
Feature of risk data establish transaction risk model；Wherein, a kind of scene type corresponds to a kind of transaction risk model.
4. the abnormal transaction identification method according to claim 3 based on funds transaction network, it is characterised in that:
It, will be corresponding with the funds transaction network when funds transaction network and transaction risk model carry out feature of risk matching
First feature of risk data, the second feature of risk data corresponding with the transaction risk model carry out feature of risk matching.
5. the abnormal transaction identification method according to claim 4 based on funds transaction network, it is characterised in that:
The feature of risk matching result of the first feature of risk data and the second feature of risk data is quantified, is enabled
Quantized result is cumulative total score or logical expression；
If quantized result is cumulative total score, cumulative total score pre-determined threshold score value corresponding with risk thresholding is compared
Compared with the corresponding abnormal transaction of funds transaction network conduct of cumulative total score above or equal to pre-determined threshold score value can doubtful case
Example；
If quantized result is logical expression, by the logical expression default expression formula progress corresponding with risk thresholding
Match, regard funds transaction network corresponding with the matched logical expression of default expression formula as abnormal transaction suspected cases.
6. the abnormal transaction identification method according to claim 5 based on funds transaction network, it is characterised in that: the friendship
Easy risk model is anti money washing model.
7. according to claim 1 into 2,4 to 6 described in any claim based on the abnormal transaction identification of funds transaction network
Method, it is characterised in that: when carrying out feature calculation to the data in Data Mart, include the following steps；
Risk case feature is defined by referring to the mode of base values data, according to the risk case feature to Data Mart
In data screened and parsed, using parsing result as the first feature of risk data.
8. the abnormal transaction identification method according to claim 7 based on funds transaction network, it is characterised in that: the wind
Dangerous affair character for describing risk case, the risk case include: different enterprises legal representative or senior executive it is identical, no
Possess the same corporate accounting with enterprise, connected transaction occurs for many enterprises, the affiliated industry of enterprise is specific industry, trading frequency
Obviously it is not inconsistent with transaction size and registered enterprise fund scale, evades supervision intention obviously, to public account frequently to personal account
It is transferred to substantial contribution, funds transaction private to the revolution of public account all passes through internet bank trade.
9. knowing according to claim 1 to the abnormal transaction described in any claim in 2,4 to 6,8 based on funds transaction network
Other method, it is characterised in that: the exception transaction identification method further includes following steps；
After determining the abnormal transaction suspected cases, data relevant to the exception transaction suspected cases are filled to specified
In template file, to generate suspicious examination report.
10. the abnormal transaction identification method according to claim 1 based on funds transaction network, it is characterised in that: described
Multiclass subject data includes client's subject data, account subject data and subject of transaction data.
11. the abnormal transaction identification method according to claim 1 based on funds transaction network, it is characterised in that: described
Base values data include bank's various dimensions Information Statistics data；Bank's various dimensions Information Statistics data include: to public law
People, self-employed worker, its hetero-organization, the distribution situation data to private natural person, savings account, loan account distribution situation data are handed over
Easy channel accounting, transaction stroke count, transaction amount distribution situation data, the ranking data of wholesale client trading, industry transaction
Behavior distribution situation data, age bracket trading activity data, transaction whereabouts ground distribution situation data.
12. a kind of abnormal transaction identification system based on funds transaction network, it is characterised in that: the exception transaction identification system
Module is constructed including Data Mart, base values excavates module, feature of risk generation module, trade network set up module and suspicious
Case generation module；
The Data Mart constructs module, for being standardized to the transactional related data obtained, thus will be described
Transactional related data is converted into multiclass subject data, and for constructing Data Mart by the multiclass subject data；
The base values excavates module, for fairground based on the data, by data mining mode in Data Mart
Multiclass subject data is handled, to obtain for the base values data as abnormal behaviour standard of comparison；
The feature of risk generation module, for using the base values data as foundation, to the data in Data Mart into
Row feature calculation, to generate the first feature of risk data；
The trade network sets up module, for enabling with the All Activity data of the first feature of risk data correlation as number
According to basis, for setting up the multiple funds transaction networks formed based on the transaction data according to the relationship that produces that is transferred to of fund；
The suspected cases generation module, for by each funds transaction network respectively with the transaction risk model that pre-establishes into
The matching of row feature of risk is used for calculating the matching degree of each funds transaction network and transaction risk model by matching degree
Reach the funds transaction network of risk thresholding as abnormal transaction suspected cases.
13. the abnormal transaction identification system according to claim 12 based on funds transaction network, it is characterised in that: described
It includes that interim fairground construction unit, transaction data processing unit and trade network set up unit that trade network, which sets up module,；
The interim fairground construction unit, for extract associated with the first feature of risk data All Activity data with
And interim risk data fairground is constructed using the All Activity data；
The transaction data processing unit, for being transferred to the relationship of producing as according to in interim risk data fairground using fund
All Activity data be grouped processing, for enable between the transaction data in group exist be transferred to or produce relationship；
The trade network sets up unit, and whole transaction data establishment for that will be in same group has between network node
It is transferred to or produces the funds transaction network of relationship, the network node is at least one of user, account, equipment.
14. the abnormal transaction identification system according to claim 12 or 13 based on funds transaction network, it is characterised in that:
The exception transaction identification system further includes that risk model establishes module；
The risk model establishes module, is used for money laundering number of packages according to displaying definition is carried out, for define displaying
Money laundering number of packages is according to classifying, to make the money laundering number of packages for belonging to Same Scene according under the same scene type；It is in office
Under one scene type, the risk model establishes module for extracting the second risk spy in the scene in money laundering case data
It levies data and establishes transaction risk model based on the second feature of risk data；Wherein, a kind of scene type corresponds to a kind of transaction wind
Dangerous model.
15. the abnormal transaction identification system according to claim 14 based on funds transaction network, it is characterised in that:
The suspected cases generation module is also used to when funds transaction network and transaction risk model carry out feature of risk matching
Will and the corresponding first feature of risk data of the funds transaction network, the second risk corresponding with the transaction risk model it is special
It levies data and carries out feature of risk matching.
16. the abnormal transaction identification system according to claim 15 based on funds transaction network, it is characterised in that:
The suspected cases generation module is also used to the first feature of risk data and the second feature of risk data
Feature of risk matching result is quantified, enables quantized result to be cumulative total score or logical expression, and for according to quantization
As a result abnormal transaction suspected cases are determined.
17. the abnormal transaction in 2,13,15,16 described in any claim based on funds transaction network according to claim 1
Identifying system, it is characterised in that: the exception transaction identification system further includes screening report generation module；
The examination report generation module, for filling data relevant to the exception transaction suspected cases to specified template
In file, to generate suspicious examination 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 true CN109461078A (en) | 2019-03-12 |
| CN109461078B 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) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110175916A (en) * | 2019-04-26 | 2019-08-27 | 阿里巴巴集团控股有限公司 | Cash flow checking method and device |
| CN110659989A (en) * | 2019-09-10 | 2020-01-07 | 马洪富 | Active exploration type compliance anti-money laundering method, device, system and storage medium |
| CN110795807A (en) * | 2019-10-28 | 2020-02-14 | 天津大学 | Complex network-based element abnormal structure detection model construction method |
| 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 |
| CN110956445A (en) * | 2019-11-18 | 2020-04-03 | 支付宝(杭州)信息技术有限公司 | Method and device for generating risk file |
| CN111160919A (en) * | 2019-12-31 | 2020-05-15 | 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 |
| CN111667368A (en) * | 2020-05-29 | 2020-09-15 | 中国工商银行股份有限公司 | Anti-money laundering monitoring system and method |
| CN111737287A (en) * | 2020-05-29 | 2020-10-02 | 深圳追一科技有限公司 | Suspicious case determination method and device, computer equipment and storage medium |
| CN111833182A (en) * | 2020-07-27 | 2020-10-27 | 中国工商银行股份有限公司 | Method and device for identifying risk object |
| CN112215616A (en) * | 2020-11-30 | 2021-01-12 | 四川新网银行股份有限公司 | Method and system for automatically identifying abnormal fund transaction based on network |
| CN112221155A (en) * | 2020-10-10 | 2021-01-15 | 陈夏焱 | 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 |
| 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 |
| CN112561703A (en) * | 2020-12-23 | 2021-03-26 | 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 |
| CN113379540A (en) * | 2020-11-09 | 2021-09-10 | 中科金审(北京)科技有限公司 | Capital data analysis system |
Citations (11)
| 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 |
| US20090040934A1 (en) * | 2007-08-06 | 2009-02-12 | Hitachi, Ltd. | Distributed System |
| CN104813355A (en) * | 2012-08-27 | 2015-07-29 | Y-S·宋 | Transactional monitoring system |
| 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 |
| CN106294521A (en) * | 2015-06-12 | 2017-01-04 | 交通银行股份有限公司 | Date storage method and data warehouse |
| 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 |
| 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 |
| 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 |
| 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 (11)
| 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 |
| US20090040934A1 (en) * | 2007-08-06 | 2009-02-12 | Hitachi, Ltd. | Distributed System |
| CN104813355A (en) * | 2012-08-27 | 2015-07-29 | Y-S·宋 | Transactional monitoring system |
| 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 |
| CN106294521A (en) * | 2015-06-12 | 2017-01-04 | 交通银行股份有限公司 | Date storage method and data warehouse |
| 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 |
| 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 |
| 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 |
| 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 |
Cited By (23)
| 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 |
| CN110175916A (en) * | 2019-04-26 | 2019-08-27 | 阿里巴巴集团控股有限公司 | Cash flow checking method and device |
| 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 |
| CN110795807A (en) * | 2019-10-28 | 2020-02-14 | 天津大学 | Complex network-based element abnormal structure detection model construction method |
| CN110795807B (en) * | 2019-10-28 | 2023-07-18 | 天津大学 | Construction method of element abnormal structure detection model based on complex network |
| CN110956445A (en) * | 2019-11-18 | 2020-04-03 | 支付宝(杭州)信息技术有限公司 | Method and device for generating risk file |
| 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 |
| CN111160919A (en) * | 2019-12-31 | 2020-05-15 | 众安信息技术服务有限公司 | Block chain address risk assessment 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 |
| CN111737287A (en) * | 2020-05-29 | 2020-10-02 | 深圳追一科技有限公司 | Suspicious case determination method and device, computer equipment and storage medium |
| 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 |
| CN111667368A (en) * | 2020-05-29 | 2020-09-15 | 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 |
| CN111833182A (en) * | 2020-07-27 | 2020-10-27 | 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 |
| CN112221155A (en) * | 2020-10-10 | 2021-01-15 | 陈夏焱 | 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 |
| CN112215616A (en) * | 2020-11-30 | 2021-01-12 | 四川新网银行股份有限公司 | Method and system for automatically identifying abnormal fund transaction based on network |
| CN112561703A (en) * | 2020-12-23 | 2021-03-26 | 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109461078B (en) | 2020-09-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109461078A (en) | A kind of abnormal transaction identification method and system based on funds transaction network | |
| CN109492945A (en) | Business risk identifies monitoring method, device, equipment and storage medium | |
| CN110866820A (en) | Real-time monitoring system, method, equipment and storage medium for banking business | |
| US8706587B1 (en) | Statistical prioritization and detection of potential financial crime events | |
| CN109377339B (en) | Auxiliary screening method and system for suspicious transaction cases | |
| CN110781308A (en) | Anti-fraud system for building knowledge graph based on big data | |
| CN111553563A (en) | Method and device for determining enterprise fraud risk | |
| CN116128627A (en) | Risk prediction method, risk prediction device, electronic equipment and storage medium | |
| CN113962703A (en) | Anti-money laundering monitoring method, device and system | |
| CN111127201A (en) | Financial anti-money laundering cloud computing resource optimal allocation system and method based on SMDP | |
| WO2022143431A1 (en) | Method and apparatus for training anti-money laundering model | |
| CN110399818A (en) | A kind of method and apparatus of risk profile | |
| Moudani et al. | Fraud detection in mobile telecommunication | |
| Zhang et al. | Pattern recognition of construction bidding system based on image processing | |
| CN114493864A (en) | Capital big data based anomaly detection system and method | |
| CN114819494A (en) | Enterprise risk early warning method, device, equipment and medium | |
| CN110570301B (en) | Risk identification method, device, equipment and medium | |
| CN113822751A (en) | Online loan risk prediction method | |
| Sengodan | Customer Segmentation Using Mobile Phone Usage Data to Reveal Finance Application User’s Behavior | |
| CN117291615B (en) | Visual contrast analysis method and device for overcoming anti-fraud based on network payment | |
| Knyazeva et al. | A graph-based data mining approach to preventing financial fraud: a case study | |
| CN116644372B (en) | Account type determining method and device, electronic equipment and storage medium | |
| Pastor Sanz | A New Approach to Detecting Irregular Behavior in the Network Structure of Public Contracts | |
| US20230377038A1 (en) | Early network growth warning system and method | |
| Pastor | A new approach to detecting irregular behavior in the network structure of public contracts |
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 | ||
| 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. |
|
| 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 | ||
| 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 |
|
| 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 |
|
| 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 |