Transaction risk monitoring method and device for financial transaction and medium

Through automated transaction feature model matching and technical indicator evaluation, the problem of inefficient anti-money laundering monitoring in the existing technology is solved, and more accurate and efficient risk identification and monitoring is achieved, adapting to the business needs and regulatory requirements of financial institutions, and reducing the number of people who are in the industry. Operating costs.

CN118967132APending Publication Date: 2024-11-15INSPUR GENERSOFT CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410983735.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-22
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

The existing anti-money laundering monitoring technology relies on manual audits and traditional tools. It is inefficient in processing massive transaction data, which is prone to errors and omissions due to human factors, and cannot meet the timely and accurate monitoring needs, which affects the compliance and operating costs of financial institutions.

Method used

By obtaining the current transaction information of financial transactions, matching with pre-configured transaction feature models, combining transaction feature information and technical indicators for evaluation, and automatically identifying anti-money laundering risks, including matching and evaluation of transaction business information, account information and amount information. Generate risk matching results.

Benefits of technology

Improve the accuracy and efficiency of anti-money laundering monitoring, reduce manual intervention, enable more comprehensive and in-depth identification of potential risks, adapt to changing risk scenarios, enhance financial institutions' compliance and risk management capabilities, and reduce operating costs. .

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118967132A_ABST
    Figure CN118967132A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses a transaction risk monitoring method and device for a financial transaction and a medium, and relates to the technical field of risk monitoring, and the method comprises the steps: obtaining the current transaction information of a to-be-monitored financial transaction, and obtaining the current transaction information of the to-be-monitored financial transaction through the transaction business information and the transaction account information in the current transaction information; performing matching in a plurality of pre-configured transaction feature models, determining a current transaction feature model corresponding to the to-be-monitored financial transaction, performing transaction feature matching according to the current transaction information and transaction feature information in the current transaction feature model, and determining a transaction feature matching result, performing technical index evaluation on the transaction account information and the transaction amount information through a plurality of pieces of configuration transaction characteristic index information in the current transaction characteristic model and a logic combination relationship among the plurality of pieces of configuration transaction characteristic index information, and determining a technical index matching result; and based on the transaction feature matching result and the technical index matching result, determining anti-money laundering transaction risk information of the to-be-monitored financial transaction.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of risk monitoring technology, and in particular to a transaction risk monitoring method, device and medium for financial transactions. Background Art

[0002] With the rapid development of science and technology, financial institutions have made significant progress in data processing, risk analysis and customer service. These technologies have brought unprecedented efficiency and accuracy to the financial industry and improved the overall operation level. In contrast, the research and development of anti-money laundering monitoring technology is relatively lagging. Although financial institutions are actively adopting advanced technologies in other fields, they still rely mainly on manual review and traditional monitoring tools for anti-money laundering monitoring. These tools are inefficient when processing massive transaction data and are prone to errors and omissions due to human factors.

[0003] The insufficient supply of products for automatic anti-money laundering monitoring technology makes it difficult for financial institutions to meet the requirements of regulators. In the supervision process, it is usually required to include timely and accurate monitoring and reporting of suspicious transactions and large transactions, and the traditional manual review method obviously cannot meet this demand. The lack of automatic monitoring technology not only affects the compliance of financial institutions, but also increases their operating costs and risks. Therefore, the current anti-money laundering monitoring is usually in the form of manual review and traditional monitoring tools, which are inefficient when processing massive transaction data, and are prone to errors and omissions due to human factors, and cannot meet the needs of timely and accurate monitoring. Summary of the invention

[0004] One or more embodiments of the present specification provide a transaction risk monitoring method, device and medium for financial transactions, which are used to solve the following technical problems: Current anti-money laundering monitoring is usually in the form of manual review and traditional monitoring tools, which are inefficient when processing massive transaction data and are prone to errors and omissions due to human factors, and cannot meet timely and accurate monitoring needs.

[0005] One or more embodiments of this specification adopt the following technical solutions:

[0006] One or more embodiments of the present specification provide a transaction risk monitoring method for financial transactions, the method comprising: obtaining current transaction information of a financial transaction to be monitored, wherein the transaction information comprises transaction business information, transaction account information and transaction amount information; matching the transaction business information in the current transaction information and the transaction account information in a plurality of pre-configured transaction feature models to determine a current transaction feature model corresponding to the financial transaction to be monitored, wherein the current transaction feature model comprises a plurality of transaction feature information, a plurality of configured transaction feature indicator information and a logical combination relationship between the plurality of configured transaction feature indicator information; performing transaction feature matching according to the current transaction information and the transaction feature information in the current transaction feature model to determine a transaction feature matching result, wherein the transaction feature information comprises a business scope feature, a customer group feature and a blacklist and whitelist feature; performing technical indicator evaluation on the transaction account information and the transaction amount information through the plurality of configured transaction feature indicator information in the current transaction feature model and a logical combination relationship between the plurality of configured transaction feature indicator information to determine a technical indicator matching result; and determining anti-money laundering transaction risk information of the financial transaction to be monitored based on the transaction feature matching result and the technical indicator matching result.

[0007] Furthermore, the transaction business information and the transaction account information in the current transaction information are matched in a plurality of pre-configured transaction feature models to determine the current transaction feature model corresponding to the financial transaction to be monitored, specifically including: obtaining the transaction account information and the transaction business information, wherein the transaction account information includes own account information and external account information, and the transaction business information includes any one of payment business, collection business and collection and payment business; obtaining model monitoring attribute information corresponding to a plurality of pre-configured transaction feature models, wherein the model monitoring attribute information includes model monitoring account information and model monitoring business information; performing account matching through the own account information in the transaction account information and the model monitoring account information corresponding to each of the transaction feature models, and performing business matching based on the transaction business information and the model monitoring business information corresponding to each of the transaction feature models to determine the current transaction feature model corresponding to the financial transaction to be monitored.

[0008] Furthermore, before matching the transaction business information and the transaction account information in the current transaction information in a plurality of pre-configured transaction feature models to determine the current transaction feature model corresponding to the financial transaction to be monitored, the method also includes: obtaining a preset transaction feature indicator library, the transaction feature indicator library including a plurality of preset transaction feature indicators; setting basic information corresponding to a plurality of transaction features according to risk monitoring demand information of a financial institution obtained in advance, wherein the basic information of the transaction features includes business scope feature basic information, monitoring type feature basic information, customer group feature basic information and black and white list feature basic information; constructing a plurality of transaction feature models based on the basic information corresponding to each transaction feature and at least one transaction feature indicator in the transaction feature indicator library; setting model monitoring attributes for each of the transaction feature models according to the risk monitoring demand information corresponding to each of the transaction feature models, wherein the model monitoring attributes include model monitoring account attributes and model monitoring business attributes.

[0009] Furthermore, transaction feature matching is performed based on the current transaction information and the transaction feature information in the current transaction feature model to determine a transaction feature matching result, specifically including: extracting the current business scope characteristics, current customer group characteristics and current transaction user characteristics of the financial transaction to be monitored based on the current transaction information; matching the current business scope characteristics and the current customer group characteristics with the business scope characteristics and the customer group characteristics in the transaction feature information, respectively, to determine a first matching result; matching and analyzing the current transaction user characteristics based on the black and white list characteristics in the transaction feature information to determine a second matching result; determining the transaction feature matching result through the first matching result and the second matching result according to a pre-set logical relationship combination.

[0010] Furthermore, through the multiple configured transaction feature indicator information in the current transaction feature model and the logical combination relationship between the multiple configured transaction feature indicator information, the transaction account information and the transaction amount information are evaluated for technical indicators to determine the technical indicator matching result, specifically including: according to each of the configured transaction feature indicator information, the transaction account information and the transaction amount information are evaluated for technical indicators to determine the indicator result corresponding to each of the configured transaction feature indicator information; according to the logical combination relationship between the multiple configured transaction feature indicator information, the multiple indicator results are logically combined to determine the technical indicator matching result, wherein the logical combination includes any one of an or relationship and an and relationship.

[0011] Furthermore, based on the black and white list features in the transaction feature information, the current transaction user features are matched and analyzed to determine a second matching result, specifically including: determining the black and white list features, wherein the black and white list features include an external account blacklist, an external account whitelist, and an account area blacklist; setting black and white list matching priorities corresponding to multiple black and white lists, matching the current transaction user features in turn according to the black and white list matching priorities, and determining the feature matching results corresponding to each of the black and white lists; and performing a logical relationship combination on multiple feature matching results according to a preset black and white list matching logical relationship to determine a second matching result.

[0012] Furthermore, the method also includes: generating a derivative list based on the external account blacklist and the external account whitelist; when the feature matching results corresponding to each of the blacklist and whitelist are matched, performing feature matching on the current transaction user features through the derivative list to determine a risk matching result; based on the risk matching result, correcting the second matching result to determine a corrected matching result.

[0013] Furthermore, a derivative list is generated based on the external account blacklist and the external account whitelist, specifically including: obtaining the current cumulative attempted transaction frequency of each external blacklist account in the external account blacklist, and determining the designated external blacklist account whose current cumulative attempted transaction frequency meets the preset requirements; under the trigger of obtaining the designated authorization, obtaining multiple transaction accounts and transaction frequencies of the designated external blacklist account, so as to construct a risk account knowledge graph with the designated external blacklist account as the starting point based on the multiple transaction accounts and the transaction frequencies; through the risk account knowledge graph, screening multiple risk transaction accounts within a specified range, and setting the current derivative list through the multiple risk transaction accounts and the external account whitelist.

[0014] One or more embodiments of this specification provide a transaction risk monitoring device for financial transactions, including:

[0015] at least one processor; and,

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the above method.

[0018] One or more embodiments of the present specification provide a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured to execute the above method.

[0019] At least one of the above technical solutions adopted in the embodiments of this specification can achieve the following beneficial effects: through the above technical solution, by matching among multiple pre-configured transaction feature models, determining the current transaction feature model corresponding to the financial transaction to be monitored, and combining transaction feature information and technical indicators for comprehensive evaluation, financial institutions can more accurately identify potential anti-money laundering risk transactions and improve the accuracy and pertinence of monitoring; not only transaction amount information is considered, but also transaction business information and transaction account information are comprehensively considered, and in-depth analysis is performed at two levels through transaction feature matching and technical indicator evaluation, so as to monitor financial transactions more comprehensively and deeply and effectively discover hidden anti-money laundering risks; by automatically matching transaction feature models Through the evaluation of model and application technical indicators, financial institutions can quickly and efficiently monitor a large number of financial transactions for anti-money laundering, reduce manual intervention, and improve monitoring efficiency and automation level; the solution allows financial institutions to flexibly configure transaction feature models and technical indicators according to business needs and regulatory requirements, and can dynamically adjust according to real-time transaction data and risk trends, so that the anti-money laundering monitoring system is more adaptable to changing risk scenarios; through accurate anti-money laundering risk identification and effective transaction monitoring, financial institutions can better meet regulatory requirements, reduce the occurrence of violations, and enhance compliance and risk management capabilities; accurate risk identification and timely response measures help reduce the mislabeling of legitimate transactions and improve customer experience. At the same time, through effective monitoring and management of anti-money laundering risk transactions, business continuity and stability are guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art description. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. In the drawings:

[0021] Figure 1 A flowchart of a transaction risk monitoring method for financial transactions provided in an embodiment of this specification;

[0022] Figure 2 A schematic diagram of the structure of a transaction risk monitoring device for financial transactions provided in an embodiment of this specification. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0024] With the rapid development of science and technology, financial institutions have made significant progress in data processing, risk analysis and customer service. These technologies have brought unprecedented efficiency and accuracy to the financial industry and improved the overall operation level. In contrast, the research and development of anti-money laundering monitoring technology is relatively lagging. Although financial institutions are actively adopting advanced technologies in other fields, they still rely mainly on manual review and traditional monitoring tools for anti-money laundering monitoring. These tools are inefficient when processing massive transaction data and are prone to errors and omissions due to human factors.

[0025] The insufficient supply of products for automatic anti-money laundering monitoring technology makes it difficult for financial institutions to meet the requirements of regulators. In the supervision process, it is usually required to include timely and accurate monitoring and reporting of suspicious transactions and large transactions, and the traditional manual review method obviously cannot meet this demand. The lack of automatic monitoring technology not only affects the compliance of financial institutions, but also increases their operating costs and risks. Therefore, the current anti-money laundering monitoring is usually in the form of manual review and traditional monitoring tools, which are inefficient when processing massive transaction data, and are prone to errors and omissions due to human factors, and cannot meet the needs of timely and accurate monitoring.

[0026] The embodiments of this specification provide a method for monitoring transaction risks of financial transactions. It should be noted that the execution subject in the embodiments of this specification may be a server or any device with data processing capabilities. Figure 1 A flowchart of a transaction risk monitoring method for financial transactions provided in an embodiment of this specification is shown as follows: Figure 1 As shown, it mainly includes the following steps:

[0027] Step S101, obtaining current transaction information of a financial transaction to be monitored.

[0028] In one embodiment of the present specification, the initiated financial transaction is monitored by a transaction monitoring system, the financial transaction to be monitored is determined, and the current transaction information of the financial transaction to be monitored is obtained. The transaction information here includes transaction business information, transaction account information and transaction amount information. The transaction business information refers to whether the current transaction is a collection transaction, a payment transaction, or a collection and payment transaction.

[0029] Step S102, matching the transaction business information and transaction account information in the current transaction information with a plurality of pre-configured transaction feature models to determine the current transaction feature model corresponding to the financial transaction to be monitored.

[0030] The current transaction feature model includes a plurality of transaction feature information, a plurality of configuration transaction feature indicator information and a logical combination relationship between the plurality of configuration transaction feature indicator information.

[0031] Before determining the current transaction feature model corresponding to the financial transaction to be monitored by matching the transaction business information and the transaction account information in the current transaction information in a plurality of pre-configured transaction feature models, the method further includes: obtaining a pre-set transaction feature indicator library, the transaction feature indicator library including a plurality of preset transaction feature indicators; setting basic information corresponding to a plurality of transaction features according to the risk monitoring demand information of the financial institution obtained in advance, wherein the basic information of the transaction features includes business scope feature basic information, monitoring type feature basic information, customer group feature basic information and black and white list feature basic information; constructing a plurality of transaction feature models based on the basic information corresponding to each transaction feature and at least one transaction feature indicator in the transaction feature indicator library; setting a model monitoring attribute for each of the transaction feature models according to the risk monitoring demand information corresponding to each of the transaction feature models, wherein the model monitoring attribute includes a model monitoring account attribute and a model monitoring business attribute.

[0032] In one embodiment of the present specification, a transaction characteristic index library is pre-set. The transaction characteristic index library here can be set according to the actual monitoring needs of the financial institution. The transaction characteristic index library includes multiple pre-set preset transaction characteristic indicators, such as frequent fund collection and payment between the same payer and payee in a short period of time, long-term idle accounts are suddenly activated for unknown reasons, accounts with small capital flow usually have abnormal capital inflows and a large amount of fund collection and payment in a short period of time, the same account (sponsor) transfers funds in multiple scattered transfers in a short period of time, the same account (sponsor) transfers funds out multiple scattered transfers in a short period of time, and activities increase significantly in a short period of time. It should be noted that in the embodiment of the present specification, it is mainly used for anti-money laundering transaction monitoring of financial institutions. There are multiple financial departments, subsidiaries, etc. in financial institutions to monitor the account risks within the financial institutions. Therefore, when setting the transaction characteristic index library, it can be set according to the actual transaction situation of the financial institution.

[0033] Obtain account information of multiple accounts within a financial institution, analyze multiple monitoring accounts that the financial institution needs to monitor based on the risk monitoring needs of the financial institution, set the account transaction features that need to be monitored, and determine the basic information corresponding to multiple transaction features. The basic information of transaction features includes basic information on business scope features (collection, payment, or collection and payment), basic information on monitoring type features (real-time monitoring or periodic monitoring), basic information on customer group features (personal transfers or public transfers), and basic information on blacklist and whitelist features (organization personnel blacklist, organization personnel whitelist, and regional blacklist). In addition to the above basic information, it also includes monitoring type information (suspicious monitoring unrelated to the amount or large-amount monitoring related to the amount), whether it is cross-border, and other information.

[0034] According to the actual needs of financial institutions, SQL statements for monitoring technical indicators of the minimum dimension are preset, that is, each technical indicator corresponds to an SQL statement. By combining technical indicators and their logical relationships, transaction features are configured to meet the needs of personalized monitoring of different accounts. According to the basic information corresponding to each transaction feature and the monitoring needs under this basic information, at least one corresponding transaction feature indicator is determined in the transaction feature indicator library according to the monitoring needs to build multiple transaction feature models. The obtained multiple transaction feature models are used to meet the personalized monitoring needs of different accounts and different sub-departments of financial institutions. Through the risk monitoring demand information corresponding to each transaction feature model, model monitoring attributes are set for each transaction feature model. The model monitoring attributes include model monitoring account attributes and model monitoring business attributes. The model monitoring account attributes here include account information, account belonging department information, and other related information used to identify account attributes.

[0035] The transaction business information and the transaction account information in the current transaction information are matched in a plurality of pre-configured transaction feature models to determine the current transaction feature model corresponding to the financial transaction to be monitored, specifically including: obtaining the transaction account information and the transaction business information, wherein the transaction account information includes own account information and external account information, and the transaction business information includes any one of payment business, collection business and collection and payment business; obtaining model monitoring attribute information corresponding to a plurality of pre-configured transaction feature models, wherein the model monitoring attribute information includes model monitoring account information and model monitoring business information; performing account matching through the own account information in the transaction account information and the model monitoring account information corresponding to each of the transaction feature models, and performing business matching based on the transaction business information and the model monitoring business information corresponding to each of the transaction feature models to determine the current transaction feature model corresponding to the financial transaction to be monitored.

[0036] In one embodiment of the present specification, in a financial transaction monitoring system, in order to determine the current transaction feature model corresponding to a certain financial transaction to be monitored, a series of matching processes are usually required. This process involves comparing the transaction account information and transaction business information with the model monitoring attribute information corresponding to multiple pre-configured transaction feature models. Transaction account information and transaction business information are obtained, and the transaction account information includes own account information and external account information. Own account information refers to the information of the internal account of the financial institution, while external account information refers to the account information of the external entity (such as other banks, companies or individuals) that conducts transactions with the financial institution. Transaction business information includes any one of payment business, collection business and collection and payment business, describing the specific type of transaction. Model monitoring attribute information corresponding to multiple pre-configured transaction feature models is obtained, and the model monitoring attribute information includes model monitoring account information and model monitoring business information. Use the own account information in the transaction account information to match the model monitoring account information corresponding to each transaction feature model. If the transaction account information meets the account monitoring requirements of a certain model, the account matching is successful. In the case of successful account matching, there may be a situation where the same account is monitored for collection without payment monitoring. The transaction business information is matched with the model monitoring business information corresponding to each transaction feature model. If the transaction business type meets the business monitoring requirements of a certain model, the business matching is successful. If a transaction feature model meets both the account matching and business matching conditions, then the model is determined as the current transaction feature model corresponding to the financial transaction to be monitored.

[0037] Through the above technical solution, through detailed account matching and business matching, the system can accurately associate each transaction with the most applicable transaction feature model, thereby more accurately identifying potential risk behaviors; compared with simple rule matching or manual review, this method can significantly reduce false positives and missed positives, and improve the accuracy of monitoring; the entire process is highly automated, reducing the need for manual intervention and improving processing speed and efficiency; the system can complete the matching and monitoring process in a short time, respond quickly to suspicious transactions, and prevent the spread of risks; transaction feature models and model monitoring attribute information can be configured and adjusted according to the specific needs of financial institutions, making the system highly flexible and adaptable; with the emergence of new risk types and changes in monitoring needs, the system can easily add new transaction feature models and monitoring attributes to maintain the cutting-edge nature of its monitoring capabilities. By determining the current transaction feature model, the system can allocate resources more specifically, invest more monitoring resources in high-risk areas, and improve resource utilization efficiency; reduce unnecessary monitoring work and false positive processing costs, thereby reducing overall operating costs.

[0038] Step S103, performing transaction feature matching according to the current transaction information and the transaction feature information in the current transaction feature model, and determining a transaction feature matching result.

[0039] Among them, the transaction characteristic information includes business scope characteristics, customer group characteristics and black and white list characteristics.

[0040] According to the current transaction information and the transaction feature information in the current transaction feature model, transaction feature matching is performed to determine the transaction feature matching result, specifically including: extracting the current business scope feature, the current customer group feature and the current transaction user feature of the financial transaction to be monitored according to the current transaction information; matching the current business scope feature and the current customer group feature with the business scope feature and the customer group feature in the transaction feature information, respectively, to determine a first matching result; based on the blacklist and whitelist features in the transaction feature information, matching analysis is performed on the current transaction user feature to determine a second matching result; and the transaction feature matching result is determined through the first matching result and the second matching result according to a preset logical relationship combination.

[0041] In one embodiment of the present specification, first, based on the current transaction information of the financial transaction to be monitored, the following three key features are extracted: current business scope features, which describe the business category to which the transaction belongs, such as collection, payment, collection and payment, etc.; current customer group features, which describe the type of customer group participating in the transaction, such as individuals and corporate, etc.; current transaction user features, which describe the characteristics of the specific user or account conducting the transaction.

[0042] Match the extracted current transaction features with the corresponding features in the transaction feature information library, and match the current business scope features and the current customer group features with the business scope features and customer group features in the transaction feature information library, respectively. If both are matched successfully, the first matching result is "matched"; otherwise, it is "unmatched". Based on the blacklist and whitelist features in the transaction feature information library, match and analyze the current transaction user features. If the current transaction user belongs to a specific user group in the blacklist or whitelist, determine the second matching result according to the preset rules. Finally, the final transaction feature matching result is determined by logically combining the pre-set first matching result and the second matching result:

[0043] If the first matching result is "match", and the second matching result also meets the preset conditions (such as not belonging to the blacklist or belonging to the whitelist), the transaction feature matching result is "match". If the first matching result is "no match", or the second matching result does not meet the preset conditions (such as belonging to the blacklist), the transaction feature matching result is "no match". If the transaction feature matching result is "pass", continue to perform subsequent monitoring steps. If the transaction feature matching result is "fail", the transaction is rejected and determined to be an anti-money laundering risk transaction.

[0044] Through the above technical solutions, through detailed feature matching and blacklist and whitelist analysis, the system can more accurately identify potential risky transactions, reduce false positives and missed reports, and improve the accuracy of overall risk monitoring; the automated feature extraction and matching process reduces manual intervention and improves processing speed, allowing financial institutions to respond to suspicious transactions more quickly and take timely measures to prevent the spread of risks; clear feature matching and blacklist and whitelist analysis processes improve the transparency of transaction monitoring activities, help financial institutions meet regulatory requirements, and enhance the trust of regulators and the general public; accurate risk identification and timely response measures help reduce the erroneous rejection of legitimate transactions, improve customer experience, and ensure business continuity and stability.

[0045] Based on the black and white list features in the transaction feature information, a matching analysis is performed on the current transaction user features to determine a second matching result, specifically including: determining the black and white list features, wherein the black and white list features include an external account blacklist, an external account whitelist, and an account area blacklist; setting black and white list matching priorities corresponding to multiple black and white lists, matching the current transaction user features in turn according to the black and white list matching priorities, and determining a feature matching result corresponding to each of the black and white lists; and performing a logical relationship combination on multiple feature matching results according to a preset black and white list matching logical relationship to determine a second matching result.

[0046] In one embodiment of the present specification, the blacklist and whitelist features include an external account blacklist, an external account whitelist, and an account area blacklist. The external account blacklist contains external account information that is considered to have high risk or bad records. The external account whitelist contains external account information that is considered to have low risk or trustworthy. Account area blacklist: contains accounts in a specific region or country, which are considered to be high risk for some reason. Set the blacklist and whitelist matching priority. Generally, the external account blacklist (highest priority), external account whitelist (medium priority), and account area blacklist (lowest priority) are in descending order. According to the set priority order, the current transaction user features are matched in turn. Check whether the current transaction involves an external account in the blacklist. If so, the feature matching result is recorded as "blacklist match"; Check whether the current transaction involves an external account in the whitelist. If so, the feature matching result is recorded as "whitelist match"; Account area blacklist matching: Check whether the region or country where the current transaction account is located is in the blacklist. If so, the feature matching result is recorded as "regional blacklist match". According to the preset blacklist and white list matching logical relationship, multiple feature matching results are combined to determine the second matching result. Generally, if there is a blacklist match or a regional blacklist match, it is considered that there is an anti-money laundering transaction risk; if there is no blacklist match and the whitelist matches, it is determined that there is no anti-money laundering transaction risk; if there is no blacklist match, the whitelist does not match, and there is a regional blacklist match, it is considered that there is an anti-money laundering transaction risk. It should be noted that the second matching result corresponding to the existence of anti-money laundering transaction risk is a match failure, and the second matching result corresponding to the absence of anti-money laundering transaction risk is a match pass.

[0047] The method also includes: generating a derivative list based on the external account blacklist and the external account whitelist; when each feature matching result corresponding to the blacklist and whitelist is a match passed, performing feature matching on the current transaction user feature through the derivative list to determine the risk matching result; based on the risk matching result, correcting the second matching result to determine the corrected matching result.

[0048] In one embodiment of the present specification, in order to improve the comprehensiveness of risk monitoring, a derivative list is generated based on the external account blacklist and the external account whitelist, and the derivative list here refers to the risk whitelist in the whitelist that has an association relationship with the blacklist account. When the feature matching results corresponding to each of the blacklist and the whitelist are matched, the feature matching of the current transaction user features is performed through the derivative list to determine the risk matching result; at this time, the second matching result is matched, and if the risk matching result is matched unsuccessfully, the revised matching result is determined to be matched unsuccessfully.

[0049] A derivative list is generated according to the external account blacklist and the external account whitelist, specifically including: obtaining the current cumulative attempted transaction frequency of each external blacklist account in the external account blacklist, and determining the designated external blacklist account whose current cumulative attempted transaction frequency meets the preset requirements; under the trigger of obtaining the designated authorization, obtaining multiple transaction accounts and transaction frequencies of the designated external blacklist account, so as to construct a risk account knowledge graph with the designated external blacklist account as the starting point based on the multiple transaction accounts and the transaction frequencies; through the risk account knowledge graph, screening multiple risk transaction accounts within a specified range, and setting the current derivative list through the multiple risk transaction accounts and the external account whitelist.

[0050] In one embodiment of the present specification, an external account blacklist is extracted from a transaction monitoring system, and the current cumulative attempted transaction frequency of each blacklist account is queried to obtain the cumulative attempted transaction frequency data of each blacklist account. According to business rules or preset conditions (such as cumulative attempted transaction frequency threshold), the designated external blacklist accounts whose cumulative attempted transaction frequency exceeds the preset cumulative attempted transaction frequency threshold are screened out from the blacklist accounts, and one or more designated external blacklist accounts are determined. Under the trigger of obtaining the designated authorization, multiple transaction accounts and their transaction frequencies associated with the designated external blacklist account are queried. It should be noted that, due to the limitation of permissions, the external accounts obtained here are those existing in the system, that is, the authorized external accounts are obtained. Such external accounts can be accounts in the whitelist, and the transaction account list of the designated external blacklist account and its corresponding transaction frequency are obtained. Using a graph database or graph computing technology, a risk account knowledge graph is constructed with the designated external blacklist account as the starting point. The nodes in the graph represent transaction accounts, the edges represent the transaction relationships between accounts, and the weights of the edges can represent the transaction frequencies, generating a risk account knowledge graph. In the risk account knowledge graph, graph algorithms (such as PageRank, community detection, etc.) or custom rules are applied to screen multiple risky trading accounts within a specified range to obtain a list of risky trading accounts. Combine the screened risky trading accounts with the external account whitelist, and set the overlapping accounts to obtain the current derivative list. In other words, the derivative list includes accounts in the whitelist that trade with blacklist accounts. It is considered that this account also has risks, and the current derivative list is generated. The derivative list is applied to the transaction monitoring system, and additional risk assessment and monitoring are performed on transactions involving the derivative list to improve the accuracy and efficiency of the transaction monitoring system, and timely discover and respond to potential risky transactions. By constructing a risk account knowledge graph, financial institutions can have a more comprehensive understanding of the transaction behavior and risk characteristics of blacklist accounts and their associated accounts, thereby more accurately identifying potential risky trading accounts.

[0051] Step S104, performing technical indicator evaluation on the transaction account information and the transaction amount information through the multiple configuration transaction feature indicator information in the current transaction feature model and the logical combination relationship between the multiple configuration transaction feature indicator information to determine the technical indicator matching result.

[0052] Through multiple configuration transaction feature indicator information in the current transaction feature model and the logical combination relationship between the multiple configuration transaction feature indicator information, a technical indicator evaluation is performed on the transaction account information and the transaction amount information to determine a technical indicator matching result, specifically including: according to each configuration transaction feature indicator information, a technical indicator evaluation is performed on the transaction account information and the transaction amount information to determine an indicator result corresponding to each configuration transaction feature indicator information; according to the logical combination relationship between the multiple configuration transaction feature indicator information, a plurality of the indicator results are logically combined to determine a technical indicator matching result, wherein the logical combination includes any one of an or relationship and an and relationship.

[0053] In one embodiment of the present specification, for each configured transaction feature indicator information, the corresponding technical analysis method is used to evaluate the transaction account information and transaction amount information. The indicator results corresponding to each configured transaction feature indicator information are obtained, and these results can be Boolean values, such as match / mismatch or other forms. The logical combination relationship between multiple configured transaction feature indicator information is clarified. The relationship can be an "or" (OR) relationship, indicating that only one of the conditions needs to be met; it can also be an "and" (AND) relationship, indicating that all conditions need to be met at the same time. According to the defined logical combination relationship, multiple indicator results are logically combined. A technical indicator matching result is obtained, which indicates whether the transaction meets all or some specific technical indicator conditions. Since the configured transaction feature indicator information is an anti-money laundering risk indicator, if it is met, it is determined that the match fails and there is an anti-money laundering transaction risk. If it is not met, it is determined that the match passes and there is no anti-money laundering transaction risk.

[0054] Through the above technical solution, by conducting technical indicator evaluation on each configured transaction characteristic indicator information and making a comprehensive judgment based on the logical combination relationship, financial institutions can more accurately identify potential risky transactions and reduce misjudgments and missed judgments; financial institutions are allowed to flexibly configure transaction characteristic indicator information and logical combination relationships according to business needs and regulatory requirements, so that the transaction monitoring system can adapt to different risk scenarios and monitoring needs; through technical indicator evaluation and logical combination, financial institutions can quickly screen and classify a large number of transactions, focus on high-risk transactions, and improve the efficiency and response speed of transaction monitoring; support dynamic adjustment of transaction characteristic indicator information and logical combination relationships based on real-time transaction data and risk trends, so that financial institutions can respond to new risk challenges and business changes in a timely manner.

[0055] Step S105, based on the transaction feature matching results and the technical indicator matching results, determine the anti-money laundering transaction risk information of the financial transaction to be monitored.

[0056] In one embodiment of the present specification, the anti-money laundering transaction risk information of the financial transaction to be monitored is determined by comprehensively combining the transaction feature matching results and the technical indicator matching results. As long as there is a matching result indicating that there is an anti-money laundering transaction risk, the financial transaction to be monitored is determined to be an anti-money laundering transaction.

[0057] Through the above technical solution, by matching in multiple pre-configured transaction feature models, determining the current transaction feature model corresponding to the financial transaction to be monitored, and combining transaction feature information and technical indicators for comprehensive evaluation, financial institutions can more accurately identify potential anti-money laundering risk transactions and improve the accuracy and pertinence of monitoring; not only transaction amount information, but also transaction business information and transaction account information are considered comprehensively, and in-depth analysis is conducted through transaction feature matching and technical indicator evaluation, so as to monitor financial transactions more comprehensively and deeply and effectively discover hidden anti-money laundering risks; through automatic matching of transaction feature models and application of technical indicator evaluation, financial institutions can quickly and efficiently conduct anti-money laundering monitoring of a large number of financial transactions, reduce manual intervention, and improve monitoring efficiency and automation level; the solution allows financial institutions to flexibly configure transaction feature models and technical indicators according to business needs and regulatory requirements, and can dynamically adjust according to real-time transaction data and risk trends, so that the anti-money laundering monitoring system is more adaptable to changing risk scenarios; through accurate anti-money laundering risk identification and effective transaction monitoring, financial institutions can better meet regulatory requirements, reduce the occurrence of violations, and enhance compliance and risk management capabilities; accurate risk identification and timely response measures help reduce the situation of erroneous labeling of legitimate transactions and improve customer experience. At the same time, business continuity and stability are ensured through effective monitoring and management of anti-money laundering risk transactions.

[0058] The embodiment of this specification also provides a transaction risk monitoring device for financial transactions, such as Figure 2 As shown, the device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above method.

[0059] The embodiments of the present specification also provide a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured to execute the above method.

[0060] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0061] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0062] The devices and media provided in the embodiments of this specification correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0063] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0064] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0065] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0066] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0067] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0068] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0069] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0070] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0071] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A method for monitoring transaction risk of financial transactions, characterized in that: The method comprises: Acquiring current transaction information of the financial transaction to be monitored, wherein the transaction information includes transaction business information, transaction account information and transaction amount information; By matching the transaction business information and the transaction account information in the current transaction information in a plurality of pre-configured transaction feature models, a current transaction feature model corresponding to the financial transaction to be monitored is determined, wherein the current transaction feature model includes a plurality of transaction feature information, a plurality of configured transaction feature indicator information, and a logical combination relationship between the plurality of configured transaction feature indicator information; According to the current transaction information and the transaction feature information in the current transaction feature model, transaction feature matching is performed to determine a transaction feature matching result, wherein the transaction feature information includes business scope features, customer group features, and blacklist and whitelist features; Performing a technical indicator evaluation on the transaction account information and the transaction amount information through the multiple configuration transaction feature indicator information in the current transaction feature model and the logical combination relationship between the multiple configuration transaction feature indicator information to determine a technical indicator matching result; Based on the transaction feature matching result and the technical indicator matching result, anti-money laundering transaction risk information of the financial transaction to be monitored is determined.

2. A method for monitoring transaction risk of financial transactions according to claim 1, characterized in that: By matching the transaction business information and the transaction account information in the current transaction information with a plurality of pre-configured transaction feature models, the current transaction feature model corresponding to the financial transaction to be monitored is determined, specifically including: Acquire the transaction account information and the transaction service information, wherein the transaction account information includes own account information and external account information, and the transaction service information includes any one of payment service, collection service and collection and payment service; Acquire model monitoring attribute information corresponding to a plurality of pre-configured transaction feature models, wherein the model monitoring attribute information includes model monitoring account information and model monitoring business information; Account matching is performed through the own account information in the transaction account information and the model monitoring account information corresponding to each of the transaction feature models, and business matching is performed based on the transaction business information and the model monitoring business information corresponding to each of the transaction feature models to determine the current transaction feature model corresponding to the financial transaction to be monitored.

3. A method for monitoring transaction risk of financial transactions according to claim 1, characterized in that: Before matching the transaction business information and the transaction account information in the current transaction information with a plurality of pre-configured transaction feature models to determine the current transaction feature model corresponding to the financial transaction to be monitored, the method further includes: Acquire a preset transaction characteristic indicator library, wherein the transaction characteristic indicator library includes a plurality of preset transaction characteristic indicators; According to the risk monitoring demand information of the financial institution obtained in advance, basic information corresponding to multiple transaction characteristics is set, wherein the basic information of the transaction characteristics includes basic information of business scope characteristics, basic information of monitoring type characteristics, basic information of customer group characteristics and basic information of blacklist and whitelist characteristics; constructing a plurality of transaction feature models based on basic information corresponding to each transaction feature and at least one transaction feature indicator in the transaction feature indicator library; Model monitoring attributes are set for each of the transaction feature models through the risk monitoring requirement information corresponding to each of the transaction feature models, wherein the model monitoring attributes include model monitoring account attributes and model monitoring business attributes.

4. A method for monitoring transaction risk of financial transactions according to claim 1, characterized in that: Performing transaction feature matching according to the current transaction information and the transaction feature information in the current transaction feature model to determine a transaction feature matching result specifically includes: Extracting the current business scope characteristics, current customer group characteristics and current transaction user characteristics of the financial transaction to be monitored according to the current transaction information; Matching the current business scope characteristics and the current customer group characteristics with the business scope characteristics and the customer group characteristics in the transaction characteristic information, respectively, to determine a first matching result; Based on the blacklist and whitelist features in the transaction feature information, matching analysis is performed on the current transaction user features to determine a second matching result; The transaction feature matching result is determined by combining the first matching result and the second matching result according to a preset logical relationship.

5. The transaction risk monitoring method for financial transactions according to claim 1, characterized in that: By using the multiple configuration transaction feature indicator information in the current transaction feature model and the logical combination relationship between the multiple configuration transaction feature indicator information, the transaction account information and the transaction amount information are evaluated for technical indicators to determine the technical indicator matching result, specifically including: According to each of the configuration transaction characteristic indicator information, a technical indicator evaluation is performed on the transaction account information and the transaction amount information to determine an indicator result corresponding to each of the configuration transaction characteristic indicator information; According to the logical combination relationship between the multiple configuration transaction characteristic indicator information, the multiple indicator results are logically combined to determine the technical indicator matching result, wherein the logical combination includes any one of an or relationship and an and relationship.

6. A method for monitoring transaction risk of financial transactions according to claim 4, characterized in that: Based on the blacklist and whitelist features in the transaction feature information, matching analysis is performed on the current transaction user features to determine a second matching result, specifically including: Determining the blacklist and whitelist features, wherein the blacklist and whitelist features include an external account blacklist, an external account whitelist, and an account region blacklist; Setting blacklist and whitelist matching priorities corresponding to a plurality of blacklists and whitelists, matching the current transaction user features in turn according to the blacklist and whitelist matching priorities, and determining the feature matching results corresponding to each of the blacklist and whitelists; According to the preset blacklist and whitelist matching logical relationship, a plurality of the feature matching results are logically combined to determine a second matching result.

7. A method for monitoring transaction risk of financial transactions according to claim 6, characterized in that: The method further comprises: Generate a derivative list according to the external account blacklist and the external account whitelist; When the feature matching results corresponding to each of the blacklist and whitelist are matched, the feature matching of the current transaction user is performed through the derived list to determine the risk matching result; Based on the risk matching result, the second matching result is corrected to determine a corrected matching result.

8. A method for monitoring transaction risk of financial transactions according to claim 7, characterized in that: Generate a derivative list based on the external account blacklist and the external account whitelist, specifically including: Obtaining the current cumulative attempted transaction frequency of each external blacklist account in the external account blacklist, and determining a designated external blacklist account whose current cumulative attempted transaction frequency meets a preset requirement; Under the trigger of obtaining the designated authorization, multiple transaction accounts and transaction frequencies of the designated external blacklist account are obtained, so as to construct a risk account knowledge graph with the designated external blacklist account as the starting point based on the multiple transaction accounts and the transaction frequencies; A plurality of risky transaction accounts within a specified range are screened through the risky account knowledge graph, and a current derivative list is set through the plurality of risky transaction accounts and the external account whitelist.

9. A transaction risk monitoring device for financial transactions, characterized in that: The device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the method according to any one of claims 1 to 8.

10. A non-volatile computer storage medium storing computer executable instructions, characterized in that: The computer executable instructions are configured to execute the method according to any one of claims 1 to 8.

Citation Information

Cited By

  • Transaction sink matching method and device based on natural language processing, and electronic equipment

    CN119741107A