CN110659989A - Active exploration type compliance anti-money laundering method, device, system and storage medium - Google Patents
Active exploration type compliance anti-money laundering method, device, system and storage medium Download PDFInfo
- Publication number
- CN110659989A CN110659989A CN201910854632.7A CN201910854632A CN110659989A CN 110659989 A CN110659989 A CN 110659989A CN 201910854632 A CN201910854632 A CN 201910854632A CN 110659989 A CN110659989 A CN 110659989A
- Authority
- CN
- China
- Prior art keywords
- transaction
- data
- effective
- transaction data
- monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004900 laundering Methods 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 238000012544 monitoring process Methods 0.000 claims abstract description 91
- 230000002159 abnormal effect Effects 0.000 claims abstract description 23
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims description 9
- 238000012163 sequencing technique Methods 0.000 claims description 7
- 230000007704 transition Effects 0.000 claims description 7
- 238000009826 distribution Methods 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 9
- 230000007547 defect Effects 0.000 abstract description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000012546 transfer Methods 0.000 description 4
- 238000012216 screening Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012502 risk assessment Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000002547 anomalous effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The embodiment of the invention discloses an active probing type compliance anti-money laundering method, a device, a system and a storage medium, wherein the method comprises the following steps: preprocessing the monitoring data to obtain effective monitoring data; carrying out classified statistics on the effective transaction data; associating each type of effective transaction data after classified statistics with a preset transaction index respectively; sorting according to the association result and a preset sorting rule, and displaying to a worker; and receiving abnormal transaction data input by the staff, associating the abnormal transaction data with the effective fund network, and displaying an association result to the staff. By the method, the defect that a part of suspicious cases cannot be monitored because a single transaction index cannot directly generate the cases is avoided, and the problem of poor monitoring effect caused by data quality problems can also be avoided. The monitoring comprehensiveness and accuracy are greatly improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of transaction security, in particular to an active exploration type compliance anti-money laundering method, device, system and storage medium.
Background
The existing anti-money laundering monitoring system is mainly used for monitoring suspicious data of illegal molecular money laundering and forwarding the suspicious data to related staff for processing. The existing suspicious monitoring indexes are divided into two types, wherein one type is a direct trigger generation case; the other is that the case is not generated directly but is generated together with other indexes.
On one hand, the index effect is poor due to the data quality problem of the financial institution, and then a part of suspicious cases can not be monitored.
For the monitorable indexes which do not directly generate cases, since when suspicious data which accord with the monitoring indexes are monitored, only early warning is generated, and cases are not directly generated. Such suspect data would not be analyzed by the staff and therefore it is likely that an illegal molecular money laundering case would be undetected as well.
In addition to the mentioned data processing procedure being less rigorous, there is also a certain drawback for the existing monitoring model of the anti-money laundering monitoring system, for example, the monitoring rules in the monitoring model are only simple combinations. For example, by manually setting key features or score settings as conditions for generating a case. Such a mechanical monitoring model is not suitable for all application scenarios. Finally, the monitoring is unreasonable, and the monitoring effect cannot reach a good effect.
Disclosure of Invention
Therefore, the embodiment of the invention provides an active probing type compliance anti-money laundering method, device, system and storage medium, which aim to solve the technical problem that the anti-money laundering monitoring system is not comprehensive and accurate in case monitoring of illegal molecular money laundering due to the fact that suspicious monitoring indexes and monitoring models in the existing anti-money laundering monitoring system are not reasonable enough.
In order to achieve the above object, the embodiments of the present invention provide the following technical solutions:
according to a first aspect of embodiments of the present invention, there is provided an actively-solicited compliance anti-money laundering method, comprising:
preprocessing the monitoring data to obtain effective monitoring data, wherein the monitoring data comprises effective transaction data and an effective fund network;
carrying out classified statistics on the effective transaction data;
associating each type of effective transaction data after classified statistics with a preset transaction index respectively;
sequencing according to the association result and a preset sequencing rule, and displaying to a worker so that the worker can determine whether each type of effective transaction data is abnormal according to the association result and the sequencing sequence;
and receiving abnormal transaction data input by the staff, associating the abnormal transaction data with the effective fund network, and displaying an association result to the staff.
Further, the valid transaction data is sub-counted according to one or more of the following classification types:
the proportion of the fund source channel, the proportion of the fund going channel, the number of fund source opponents, the number of fund going opponents, the area of the transaction opponent account and the time distribution of the transaction flow.
Further, the preset transaction indicators include: pre-set pre-warning information and/or pre-set transaction transition characteristics.
Further, the preset warning information includes one or more of the following: public inspection legal department surveys and has published data information, anti-money laundering administrative department surveys and has published data information, risk prompt information sent by supervision department, negative news information of media reports.
Further, the monitoring data is preprocessed to obtain effective monitoring data, and the effective monitoring data specifically comprises one or more of the following:
counting the incomplete data in the monitoring data so that the workers can complete the incomplete data;
cleaning redundant data in the monitoring data;
counting the type and the quantity of the transaction data to be additionally recorded and the content of the transaction data to be additionally recorded so as to facilitate timely correction by a worker;
extracting transaction data exceeding a preset limit and suspicious transaction data not conforming to transaction rules;
duplicate data in the funds network is removed, as well as transaction data having a common transaction relationship.
According to a second aspect of embodiments of the present invention, there is provided an actively probed compliance anti-money laundering device comprising:
further, the processing unit is used for preprocessing the monitoring data to obtain effective monitoring data, and the monitoring data comprises effective transaction data and an effective fund network;
the classified statistic unit is used for performing classified statistic on the effective transaction data;
the association unit is used for associating each type of effective transaction data after classified statistics with preset transaction indexes respectively;
the sorting unit is used for sorting according to the association result and a preset sorting rule and displaying the sorting to the staff so that the staff can determine whether each type of effective transaction data is abnormal or not according to the association result and the sorting sequence;
the receiving unit is used for receiving abnormal transaction data input by a worker;
the association unit is also used for associating the abnormal transaction data with the effective fund network and displaying the association result to the staff.
Further, the classification statistical unit is specifically configured to:
the valid transaction data is sub-statistically collected according to one or more of the following classification types:
the proportion of the fund source channel, the proportion of the fund going channel, the number of fund source opponents, the number of fund going opponents, the area of the transaction opponent account and the time distribution of the transaction flow.
Further, the preset transaction indicators include: pre-set pre-warning information and/or pre-set transaction transition characteristics.
According to a third aspect of embodiments of the present invention, there is provided an actively-solicited compliance anti-money laundering system, comprising: a processor and a memory;
the memory is used for storing one or more program instructions;
a processor for executing one or more program instructions to perform any of the method steps of an unsolicited compliant anti-laundering method as above.
According to a fourth aspect of embodiments of the present invention, there is provided a computer storage medium having one or more program instructions embodied therein for execution by an unsolicited compliant unwasher system by any method step of an unsolicited compliant unwasher method as above.
The embodiment of the invention has the following advantages: and preprocessing the monitoring data to obtain effective monitoring data. And the subsequent monitoring process is ensured to be more accurate. The effective transaction data are classified and counted, then each type of effective transaction data are respectively associated with preset transaction indexes, and then the effective transaction data are sorted according to a preset sorting rule according to the association result, so that a worker can conveniently determine whether each type of effective transaction data is abnormal. If the abnormity exists, the abnormity is associated with the effective fund network, and the whole industry chain of illegal molecular money laundering cases can be screened out in a point-to-surface mode. By the method, the defect that a part of suspicious cases cannot be monitored because a single transaction index cannot directly generate the cases is avoided, and the problem of poor monitoring effect caused by data quality problems can also be avoided. Meanwhile, the monitoring rules are not simply superposed any more, and key features or scores are not set manually to serve as conditions for generating cases, so that unreasonable monitoring is avoided naturally. Through this kind of mode, promoted comprehensive, the accuracy of monitoring greatly.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.
The structures, ratios, sizes, and the like shown in the present specification are only used for matching with the contents disclosed in the specification, so as to be understood and read by those skilled in the art, and are not used to limit the conditions that the present invention can be implemented, so that the present invention has no technical significance, and any structural modifications, changes in the ratio relationship, or adjustments of the sizes, without affecting the effects and the achievable by the present invention, should still fall within the range that the technical contents disclosed in the present invention can cover.
Fig. 1 is a schematic flow chart of an actively-solicited compliance anti-money laundering method according to embodiment 1 of the present invention;
fig. 2 is a schematic structural diagram of an actively probing compliance money laundering device according to embodiment 2 of the present invention;
fig. 3 is a schematic structural diagram of an actively-solicited compliance anti-money laundering system according to embodiment 3 of the present invention.
Detailed Description
The present invention is described in terms of particular embodiments, other advantages and features of the invention will become apparent to those skilled in the art from the following disclosure, and it is to be understood that the described embodiments are merely exemplary of the invention and that it is not intended to limit the invention to the particular embodiments disclosed. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Embodiment 1 of the present invention provides an active probing compliance anti-money laundering method, as specifically shown in fig. 1, the method includes the following steps:
and step 110, preprocessing the monitoring data to obtain effective monitoring data.
In particular, preprocessing the monitoring data may include, but is not limited to, one or more of the following.
1) Counting the incomplete data in the monitoring data so that the workers can complete the incomplete data;
imperfect data, such as the modern payline name and line number table, the system may screen out all fields in the table that are empty of information and then present them to the staff in a particular form. And the information of the financial institution network points can be used for calling an API (application program interface) of a Baidu or Gaode map and calling a real administrative division code so as to be applied to accurate association of regions, so that the working personnel can be perfected according to actual conditions.
2) And cleaning redundant data in the monitoring data.
After redundant data in the monitoring data are cleaned, the data can be classified. For example, cross-deal information by a trading opponent is also inserted into the opponent information sheet. When the cross-bank transaction information of the opponent is collated, screening and searching can be carried out according to the following sequence:
and searching the types of the transaction data according to the sequence of the large payment system, the city business clearing system, the small payment system and the super online banking system, then sorting the data corresponding to a certain type, and inserting the data into a preset position of the adversary information table. The processing procedure of the step is mainly to acquire a trading area where a trading opponent is located when the trading opponent carries out cross-bank trading.
3) And counting the type and the quantity of the transaction data to be subjected to additional recording and the content of the transaction data to be subjected to additional recording so as to facilitate timely correction of workers.
Specifically, after the type and the quantity of the transaction data to be additionally recorded and the content of the transaction data to be additionally recorded are counted, the analysis by a worker can be facilitated, and the reason for the occurrence of the additional recording can be determined. For example, the phenomena of internal accounts of financial institutions, different account names of the same account, different areas of the same equipment and the like existing in transaction data are checked and corrected. Then, after the staff takes the corrective action, the problem does not appear subsequently, and the data quality is also improved.
4) And extracting transaction data exceeding a preset limit and suspicious transaction data not conforming to transaction rules.
Specifically, the large transaction data and the suspicious transaction data need to be extracted and then displayed to the staff. The quality analysis method is used for analyzing the quality of the large-amount transaction data and the suspicious transaction data by the staff.
If the problem exists, the data with the problem is directly associated with the effective fund network, and the final problem relation network is obtained. If the problem exists, the worker needs to take positive measures to ensure that the problem is solved in time and improve the quality of monitoring data.
If the data of the monitoring rule CPKY-1110 with the largest triggering amount in month 8 is analyzed in an integrated mode, 3418 cases are involved, and 77648 pens are involved in the transaction.
Transaction condition filtering
1. The counted transaction codes are 37 items, self-service transaction codes judged by individuals are set to be reserved according to the definition of monitoring rules, other transaction codes are set to be filtered, and the number of the filtered data reaches 5989. 9624 the single stream of transactions occurs most frequently in the case.
2. The account transfer transaction between the accounts of the clients in the local bank is filtered, and the transaction 584 can be filtered;
3. the rules that the old people or the minors frequently carry out self-service transaction are divided into active transaction and passive transaction, the passive transaction is filtered, and the filtered data reaches 24383 strokes.
4. After transaction filtering, the number of cases is reduced from 3418 to 2861 pens, and 557 pens are reduced, accounting for 16.30%.
(II) rule recalculation
The rule triggering condition is that the number of the cases is 5 and the amount of money is 20 ten thousand yuan, the case data is recalculated, and after the cases which do not meet the condition are set to be invalid, 908 cases are reserved, 48 cases are generated every day, and the number of the cases accounts for 26.57% of the number of the original cases.
5) Duplicate data in the funds network is removed, as well as transaction data having a common transaction relationship.
Specifically, the fund network may record repeated data, and also may have some transaction data having a public transaction relationship, for example, the transaction institution related to the counterparty is a pay treasure, a WeChat, etc., and there is no fund association relationship between the monitoring object and the counterparty before, and only this time of public transaction. It is likely that the monitoring object purchases something and needs to pay a certain transaction amount to the other party. Or pay electricity fee, water fee, etc. These large amounts of transaction data then take up a lot of space in the money network and do not help anything to find cases of illegal molecular money laundering. Therefore, duplicate data in the fund network and transaction data with a common transaction relationship are also removed. For example, data on payment and the like may be classified as public information and filtered out. The specific classification may include one or more of the following: including, for example, a funding network, the same IP or MAC address, the same contact, such as a corporate representative, a financial staff, a reconciliation staff or agent, or other networking conditions.
And step 120, carrying out classified statistics on the effective transaction data.
Specifically, when performing the classification statistics, the classification may be performed according to the following types, and it should be noted that the classification includes, but is not limited to, one or more of the following types:
the proportion of the fund source channel, the proportion of the fund going channel, the number of fund source opponents, the number of fund going opponents, the area of the transaction opponent account and the time distribution of the transaction flow.
The specific classification types can be added or removed according to actual situations, and are not limited too much here. The classification can be performed by using a cluster analysis algorithm, and the specific classification process is the prior art and is not described in detail herein.
And step 130, associating each type of effective transaction data after classified statistics with a preset transaction index respectively.
Specifically, the preset transaction monitoring index is actually a transaction index obtained by optimizing the existing transaction index by the staff. In optimizing the trading index, the following principles may be followed, but are not limited to:
1. the transaction monitoring indexes are explored and researched, and parameters are adjusted, so that case triggering tends to be in a reasonable range;
2. further researching and analyzing cases which do not generate case information in index early warning and generate large early warning amount, and using the cases as a direction for improving and optimizing transaction indexes;
3. for the transaction indexes of directly generated cases, the threshold value can be researched and adjusted in an active exploration mode, and the threshold value can be changed until the transaction indexes are more reasonable.
4. And continuously perfecting the suspicious characteristic label and associating the suspicious characteristic label with the transaction index.
5. The trade index is improved and adjusted continuously according to the actual situation.
Optionally, before performing step 130, the method may further include:
optionally, the preset transaction indicators include: pre-set pre-warning information and/or pre-set transaction transition characteristics.
Further optionally, the preset warning information includes one or more of the following: public inspection legal department surveys and has published data information, anti-money laundering administrative department surveys and has published data information, risk prompt information sent by supervision department, negative news information of media reports.
Optionally, when associating each type of valid transaction data after the classification statistics with a preset transaction index, the following rules may be followed:
for example, the subject where several preset transaction indexes coexist is screened out, or the subject where several preset transaction indexes occur sequentially is screened out.
For example, personal information such as account information, name, and identification card of some person is extracted from the early warning information, and then matched with the transaction information of the transaction object in the implementation, and once an intersection exists, the object to be monitored currently is determined, or some transaction data may be abnormal, and this way is to screen out a main body where several preset transaction indexes coexist. After this step is performed, step 140 may be performed again.
The transaction transition characteristic is that the transaction funds are transferred from one account to other accounts and then transferred from other accounts to the account for some funds, and the amount is not limited.
For example, in one case, the customer transfers across the bank under the same name, and within 10 minutes, transfers out, the amount is less than 100 dollars. This may be the case if the user is probing if his current account can be used further. In another case, after a small amount test is carried out on a certain account, ten thousand yuan of money of the account is transferred in a few minutes, the situation is suspicious, and it is very likely that illegal molecules confirm whether the current account is frozen or not in a small amount test mode, if the current account is not frozen, some funds can be transferred into the account and then transferred out through the account; in another case, the same-name opponents are transferred in and out across the lines, the time interval is 10 minutes, and the sum is less than 100 yuan. Frequent roll-outs may also be used as an exploration of trade overtime characteristics.
For example, small transactions within 100 yuan are screened, then cross-bank transfer-in opponents and clients are screened to be of the same name, then the transactions are screened to be transferred in a transfer-out time interval of 10 minutes, or transfer-out opponents are transferred to be of the same name. After the screening is completed, the data are determined to be suspicious data, which is to screen out several subjects whose preset transaction indicators occur in sequence, and then execute step 140.
And 140, sorting according to the association result and a preset sorting rule, and displaying to a worker.
Specifically, the correlation results may be sorted from high to low. Moreover, it is necessary to display the occupation, industry, region, etc. corresponding to the monitoring object and/or the counterparty while sequencing, for example, financial practitioners in the financial industry, which is a high-risk industry itself, are an occupation to deal with money at any time. The risk level for which there is a money laundering transaction will be higher. The system needs more workers to analyze the financial cases and is also beneficial to monitoring the financial cases.
When the staff determines that some kind of valid transaction data is abnormal, the data is input into the active probing type compliance anti-money laundering system. The anomalous transaction data is associated with the active funds network by the proactive probing compliant anti-money laundering system, i.e., step 150 is performed.
And 150, receiving abnormal transaction data input by the staff, associating the abnormal transaction data with the effective fund network, and displaying the association result to the staff.
Specifically, the correlation result may be presented to the staff in the form of a report of the suspicious transaction.
It should be noted that, because the types of crimes are different, the adopted preset transaction indexes or statistical data and the like have a certain difference according to the different crimes, but the analysis ideas are basically consistent.
In a specific application scenario, the method can be used in an overseas money laundering case. Screening the main bodies of the overseas cash-taking transactions from the transaction data, carrying out classification statistical association with the transaction data, associating more than 50% of the main bodies of the overseas cash-taking transactions from the cross-bank with a fund network, and carrying out visual analysis on the main bodies of the overseas cash-taking transactions from the same opponent of the cross-bank.
Such an approach may also assess the risk of money laundering for the product/service, as the overseas cash-taking business is also a financial service. While actively exploring suspicious transactions, respectively counting the number of clients involved in the business and the suspicious number, and finally forming a money laundering risk assessment result, or applying the information to money laundering risk assessment of an organization, and taking a corresponding risk score after the ratio of the suspicious transactions in a financial product/service reaches a certain proportion.
The embodiment of the invention provides an active exploration type compliance anti-money laundering method, which is used for preprocessing monitoring data and acquiring effective monitoring data. And the subsequent monitoring process is ensured to be more accurate. The effective transaction data are classified and counted, then each type of effective transaction data are respectively associated with preset transaction indexes, and then the effective transaction data are sorted according to a preset sorting rule according to the association result, so that a worker can conveniently determine whether each type of effective transaction data is abnormal. If the abnormity exists, the abnormity is associated with the effective fund network, and the whole industry chain of illegal molecular money laundering cases can be screened out in a point-to-surface mode. By the method, the defect that a part of suspicious cases cannot be monitored because a single transaction index cannot directly generate the cases is avoided, and the problem of poor monitoring effect caused by data quality problems can also be avoided. Meanwhile, the monitoring rules are not simply superposed any more, and key features or scores are not set manually to serve as conditions for generating cases, so that unreasonable monitoring is avoided naturally. Through this kind of mode, promoted comprehensive, the accuracy of monitoring greatly.
Corresponding to the above embodiment 1, embodiment 2 of the present invention further provides an active probing type compliance money laundering device, as shown in fig. 2, specifically, the device includes: a processing unit 201, a classification statistical unit 202, an association unit 203, a sorting unit 204 and a receiving unit 205.
The processing unit 201 is configured to pre-process the monitoring data to obtain effective monitoring data, where the monitoring data includes effective transaction data and an effective fund network;
a classification statistical unit 202, configured to perform classification statistics on valid transaction data;
the association unit 203 is configured to associate each type of valid transaction data after classified statistics with a preset transaction index;
the sorting unit 204 is configured to sort according to a preset sorting rule according to the association result and display the sorted result to a worker, so that the worker determines whether each type of valid transaction data is abnormal according to the association result and the sorting order;
a receiving unit 205, configured to receive transaction data input by a worker and having an abnormality;
the association unit 203 is further configured to associate the transaction data with the valid fund network, and display the association result to the staff.
Optionally, the classification statistical unit 202 is specifically configured to:
the valid transaction data is sub-statistically collected according to one or more of the following classification types:
the proportion of the fund source channel, the proportion of the fund going channel, the number of fund source opponents, the number of fund going opponents, the area of the transaction opponent account and the time distribution of the transaction flow.
Optionally, the preset transaction indicators include: pre-set pre-warning information and/or pre-set transaction transition characteristics.
Optionally, the preset warning information includes one or more of the following: public inspection legal department surveys and has published data information, anti-money laundering administrative department surveys and has published data information, risk prompt information sent by supervision department, negative news information of media reports.
Optionally, the processing unit 201 performs preprocessing on the monitoring data to obtain effective monitoring data, which specifically includes one or more of the following:
counting the incomplete data in the monitoring data so that the workers can complete the incomplete data;
cleaning redundant data in the monitoring data;
counting the type and the quantity of the transaction data to be additionally recorded and the content of the transaction data to be additionally recorded so as to facilitate timely correction by a worker;
extracting transaction data exceeding a preset limit and suspicious transaction data not conforming to transaction rules;
duplicate data in the funds network is removed, as well as transaction data having a public relationship.
The functions performed by each component of the active probing type compliance money laundering device provided by the embodiment of the present invention have been described in detail in the above embodiment 1, and therefore, redundant description is not repeated here.
The embodiment of the invention provides an active detection type compliance anti-money laundering device, which is used for preprocessing monitoring data and acquiring effective monitoring data. And the subsequent monitoring process is ensured to be more accurate. The effective transaction data are classified and counted, then each type of effective transaction data are respectively associated with preset transaction indexes, and then the effective transaction data are sorted according to a preset sorting rule according to the association result, so that a worker can conveniently determine whether each type of effective transaction data is abnormal. If the abnormity exists, the abnormity is associated with the effective fund network, and the whole industry chain of illegal molecular money laundering cases can be screened out in a point-to-surface mode. By the method, the defect that a part of suspicious cases cannot be monitored because a single transaction index cannot directly generate the cases is avoided, and the problem of poor monitoring effect caused by data quality problems can also be avoided. Meanwhile, the monitoring rules are not simply superposed any more, and key features or scores are not set manually to serve as conditions for generating cases, so that unreasonable monitoring is avoided naturally. Through this kind of mode, promoted comprehensive, the accuracy of monitoring greatly.
In accordance with the above-mentioned embodiments, embodiment 3 of the present invention further provides an active probing compliance anti-money laundering system, specifically as shown in fig. 3, the system includes: a processor 301 and a memory 302;
the memory 302 is used to store one or more program instructions;
processor 301 for executing one or more program instructions for performing any method steps of an unsolicited compliant anti-money laundering method as described in the above embodiments.
The embodiment of the invention provides an active exploration type compliance anti-money laundering system, which preprocesses monitoring data and obtains effective monitoring data. And the subsequent monitoring process is ensured to be more accurate. The effective transaction data are classified and counted, then each type of effective transaction data are respectively associated with preset transaction indexes, and then the effective transaction data are sorted according to a preset sorting rule according to the association result, so that a worker can conveniently determine whether each type of effective transaction data is abnormal. If the abnormity exists, the abnormity is associated with the effective fund network, and the whole industry chain of illegal molecular money laundering cases can be screened out in a point-to-surface mode. By the method, the defect that a part of suspicious cases cannot be monitored because a single transaction index cannot directly generate the cases is avoided, and the problem of poor monitoring effect caused by data quality problems can also be avoided. Meanwhile, the monitoring rules are not simply superposed any more, and key features or scores are not set manually to serve as conditions for generating cases, so that unreasonable monitoring is avoided naturally. Through this kind of mode, promoted comprehensive, the accuracy of monitoring greatly.
In correspondence with the above embodiments, embodiments of the present invention also provide a computer storage medium containing one or more program instructions therein. Wherein the one or more program instructions are for executing an unsolicited compliant anti-money laundering method as described above by an unsolicited compliant anti-money laundering system.
In an embodiment of the invention, the processor may be an integrated circuit chip having signal processing capability. The Processor may be a general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete Gate or transistor logic device, discrete hardware component.
The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The processor reads the information in the storage medium and completes the steps of the method in combination with the hardware.
The storage medium may be a memory, for example, which may be volatile memory or nonvolatile memory, or which may include both volatile and nonvolatile memory.
The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory.
The volatile Memory may be a Random Access Memory (RAM) which serves as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), SLDRAM (SLDRAM), and Direct Rambus RAM (DRRAM).
The storage media described in connection with the embodiments of the invention are intended to comprise, without being limited to, these and any other suitable types of memory.
Those skilled in the art will appreciate that the functionality described in the present invention may be implemented in a combination of hardware and software in one or more of the examples described above. When software is applied, the corresponding functionality may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
The above embodiments are only for illustrating the embodiments of the present invention and are not to be construed as limiting the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made on the basis of the embodiments of the present invention shall be included in the scope of the present invention.
Claims (10)
1. An active heuristic compliance anti-money laundering method, comprising:
preprocessing monitoring data to obtain effective monitoring data, wherein the monitoring data comprises effective transaction data and an effective fund network;
carrying out classified statistics on the effective transaction data;
associating each type of effective transaction data after classified statistics with a preset transaction index respectively;
sequencing according to the association result and a preset sequencing rule, and displaying to a worker so that the worker can determine whether each type of effective transaction data is abnormal according to the association result and the sequencing sequence;
and receiving abnormal transaction data input by a worker, associating the abnormal transaction data with the effective fund network, and displaying an association result to the worker.
2. The method of claim 1, wherein the valid transaction data is sub-counted according to one or more of the following classification types:
the proportion of the fund source channel, the proportion of the fund going channel, the number of fund source opponents, the number of fund going opponents, the area of the transaction opponent account and the time distribution of the transaction flow.
3. The method according to claim 1 or 2, wherein the pre-set transaction metrics comprise: pre-set pre-warning information and/or pre-set transaction transition characteristics.
4. The method of claim 3, wherein the pre-set pre-warning information comprises one or more of: public inspection legal department surveys and has published data information, anti-money laundering administrative department surveys and has published data information, risk prompt information sent by supervision department, negative news information of media reports.
5. The method according to claim 1, wherein the preprocessing of the monitoring data to obtain valid monitoring data specifically includes one or more of the following:
counting the incomplete data in the monitoring data so that the worker can complete the incomplete data;
cleaning redundant data in the monitoring data;
counting the type and the quantity of the transaction data to be additionally recorded and the content of the transaction data to be additionally recorded so as to facilitate timely correction of the staff;
extracting transaction data exceeding a preset limit and suspicious transaction data not conforming to transaction rules;
duplicate data in the funds network is removed, as well as transaction data having a common transaction relationship.
6. An active probing compliant anti-money laundering device, comprising:
the processing unit is used for preprocessing the monitoring data to obtain effective monitoring data, and the monitoring data comprises effective transaction data and an effective fund network;
the classified statistic unit is used for performing classified statistic on the effective transaction data;
the association unit is used for associating each type of effective transaction data after classified statistics with preset transaction indexes respectively;
the sorting unit is used for sorting according to the association result and a preset sorting rule and displaying the sorting to a worker so that the worker can determine whether each type of effective transaction data is abnormal or not according to the association result and the sorting sequence;
the receiving unit is used for receiving abnormal transaction data input by a worker;
the association unit is also used for associating the abnormal transaction data with the effective fund network and displaying the association result to the staff.
7. The apparatus according to claim 6, wherein the classification statistic unit is specifically configured to:
performing statistics on the valid transaction data according to one or more of the following classification types:
the proportion of the fund source channel, the proportion of the fund going channel, the number of fund source opponents, the number of fund going opponents, the area of the transaction opponent account and the time distribution of the transaction flow.
8. The apparatus of claim 6, wherein the pre-set transaction metrics comprise: pre-set pre-warning information and/or pre-set transaction transition characteristics.
9. An active probing compliance anti-money laundering system, comprising: a processor and a memory;
the memory is to store one or more program instructions;
the processor, configured to execute one or more program instructions to perform the method of any of claims 1-6.
10. A computer storage medium comprising one or more program instructions for performing the method of any one of claims 1-6 by an unsolicited compliant anti-money laundering system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910854632.7A CN110659989A (en) | 2019-09-10 | 2019-09-10 | Active exploration type compliance anti-money laundering method, device, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910854632.7A CN110659989A (en) | 2019-09-10 | 2019-09-10 | Active exploration type compliance anti-money laundering method, device, system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110659989A true CN110659989A (en) | 2020-01-07 |
Family
ID=69036914
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910854632.7A Pending CN110659989A (en) | 2019-09-10 | 2019-09-10 | Active exploration type compliance anti-money laundering method, device, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110659989A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111445255A (en) * | 2020-03-11 | 2020-07-24 | 中国光大银行股份有限公司 | Method and device for determining abnormal fund transfer relationship |
| CN111915316A (en) * | 2020-08-18 | 2020-11-10 | 南方电网数字电网研究院有限公司 | Suspicious transaction monitoring method and device, computer equipment and storage medium |
| CN113191072A (en) * | 2021-03-30 | 2021-07-30 | 中国建设银行股份有限公司 | Suspicious transaction monitoring method and device based on longitudinal federal logistic regression |
| CN113807853A (en) * | 2020-11-12 | 2021-12-17 | 中科金审(北京)科技有限公司 | Economic crime identification method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101706930A (en) * | 2009-10-22 | 2010-05-12 | 杭州信雅达科技有限公司 | Ontology-based anti-money laundering early-warning method |
| CN106547838A (en) * | 2016-10-14 | 2017-03-29 | 北京银丰新融科技开发有限公司 | Method based on the suspicious funds transaction of fund network monitor |
| CN107358360A (en) * | 2017-07-14 | 2017-11-17 | 成都农村商业银行股份有限公司 | The abnormal traffic data screening method of anti money washing system |
| CN109461078A (en) * | 2018-10-22 | 2019-03-12 | 中信网络科技股份有限公司 | A kind of abnormal transaction identification method and system based on funds transaction network |
| CN110046993A (en) * | 2018-12-15 | 2019-07-23 | 深圳壹账通智能科技有限公司 | Illicit gain legalizes behavior monitoring method, system, computer installation and medium |
-
2019
- 2019-09-10 CN CN201910854632.7A patent/CN110659989A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101706930A (en) * | 2009-10-22 | 2010-05-12 | 杭州信雅达科技有限公司 | Ontology-based anti-money laundering early-warning method |
| CN106547838A (en) * | 2016-10-14 | 2017-03-29 | 北京银丰新融科技开发有限公司 | Method based on the suspicious funds transaction of fund network monitor |
| CN107358360A (en) * | 2017-07-14 | 2017-11-17 | 成都农村商业银行股份有限公司 | The abnormal traffic data screening method of anti money washing system |
| CN109461078A (en) * | 2018-10-22 | 2019-03-12 | 中信网络科技股份有限公司 | A kind of abnormal transaction identification method and system based on funds transaction network |
| CN110046993A (en) * | 2018-12-15 | 2019-07-23 | 深圳壹账通智能科技有限公司 | Illicit gain legalizes behavior monitoring method, system, computer installation and medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111445255A (en) * | 2020-03-11 | 2020-07-24 | 中国光大银行股份有限公司 | Method and device for determining abnormal fund transfer relationship |
| CN111915316A (en) * | 2020-08-18 | 2020-11-10 | 南方电网数字电网研究院有限公司 | Suspicious transaction monitoring method and device, computer equipment and storage medium |
| CN113807853A (en) * | 2020-11-12 | 2021-12-17 | 中科金审(北京)科技有限公司 | Economic crime identification method |
| CN113191072A (en) * | 2021-03-30 | 2021-07-30 | 中国建设银行股份有限公司 | Suspicious transaction monitoring method and device based on longitudinal federal logistic regression |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110659989A (en) | Active exploration type compliance anti-money laundering method, device, system and storage medium | |
| US20090182653A1 (en) | System and method for case management | |
| US8732084B2 (en) | Identification and risk evaluation | |
| US7693767B2 (en) | Method for generating predictive models for a business problem via supervised learning | |
| US20080021801A1 (en) | Dynamic multidimensional risk-weighted suspicious activities detector | |
| US7720751B2 (en) | System and method of continuous assurance for internal control | |
| US20030233319A1 (en) | Electronic fund transfer participant risk management clearing | |
| US8386381B1 (en) | Method and system for detecting, monitoring and addressing data compromises | |
| US20020120559A1 (en) | Tiered processing method and system for identifying and mitigating merchant risk | |
| Riccioni et al. | Regular paths in financial markets: Investigating the Benford's law | |
| US8321314B2 (en) | Negotiable instrument electronic clearance monitoring systems and methods | |
| CN115082225A (en) | Enterprise financing risk assessment method and device | |
| CN115063228A (en) | Anti-money laundering management platform and anti-money laundering method | |
| CN115564449A (en) | Risk control method and device for transaction account and electronic equipment | |
| US20170206596A1 (en) | Value at Risk Models for AML Compliance and Due Diligence | |
| CN110991650A (en) | Method and device for training card maintenance identification model and identifying card maintenance behavior | |
| US8682684B2 (en) | Method, apparatus and computer program product for monitoring compliance in reporting unclaimed property | |
| CN111861733A (en) | Fraud prevention and control system and method based on address fuzzy matching | |
| US20040215579A1 (en) | Supplemental address verification | |
| TWI618013B (en) | Automatic deposit cheque system and method of perfomring the same | |
| CN114493864A (en) | Capital big data based anomaly detection system and method | |
| CN111861734B (en) | Test evaluation system and method for three-party data source | |
| CN115062079A (en) | Transaction flow processing method, device, equipment and storage medium | |
| CN110956445B (en) | Method and device for generating risk file | |
| CN113051257A (en) | Service data cleaning method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200107 |
|
| RJ01 | Rejection of invention patent application after publication |