Anti-money laundering transaction identification method and device, equipment and storage medium

Abstract

The invention discloses an anti-money laundering transaction identification method, an anti-money laundering transaction identification device, computer equipment and a computer readable storage medium. The method comprises the following steps: acquiring historical transaction data and current transaction data of a plurality of target objects; according to a preset transaction data detection model, executing data logic analysis on the historical transaction data and the current transaction data, and determining a detection result for the money laundering behavior characteristics; and according to a detection result, determining compliance degree rating information of each target object so as to determine the governance and system compliance degree of the target object in the aspect of anti-money laundering. According to the method and the device, the historical data and the current data are subjected to data analysis, particularly logic analysis, by utilizing the detection model, so that the data detection result determined according to the transaction data provided by each legal person is obtained, and furthermore, the transaction compliance degree of each legal person can be evaluated according to the data detection result, so that the transaction compliance degree of each legal person is evaluated. Therefore, anti-money laundering identification and control are carried out on two levels of transaction and legal persons.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to an anti-money laundering transaction identification method, an anti-money laundering transaction identification device, a computer device, and a computer-readable storage medium. Background Art

[0002] Anti-money laundering customer identification is the process by which financial institutions identify, analyze and judge abnormal situations such as customer identity, customer rating, source of funds, transaction behavior, etc. in accordance with laws, regulations and regulatory requirements, and take effective control measures to prevent illegal and criminal activities such as money laundering and terrorist financing.

[0003] At present, the relevant technologies for anti-money laundering customer identification generally start from the data level and conduct anti-money laundering analysis on the customers to be identified according to the pre-configured rules. Compared with the analysis at the data level, the above analysis process has defects in the analysis at the logical rule level, which may lead to simple conclusions and confusing logic, which may further lead to identification errors and cause major risks of money laundering. Summary of the invention

[0004] The present application provides an anti-money laundering transaction identification method, an anti-money laundering transaction identification device, a computer device and a computer-readable storage medium.

[0005] The anti-money laundering transaction identification method involved in the implementation mode of the present application comprises the following steps:

[0006] Obtain historical transaction data and current transaction data of multiple target objects;

[0007] According to a preset transaction data detection model, a data logic analysis is performed on the historical transaction data and the current transaction data to determine a detection result for the characteristics of money laundering behavior, wherein the transaction data detection model is trained based on a machine learning algorithm according to a preset detection data indicator library;

[0008] Based on the detection results, compliance rating information of each target object is determined to determine the governance and system compliance of the target object in anti-money laundering.

[0009] In this way, the present application can use the historical transaction data and current transaction data of multiple legal persons as the analysis data basis, and use the detection model to perform data analysis on the historical data and current data respectively, especially to perform logical analysis on the historical transaction data and the current transaction data, so as to obtain data detection results determined based on the transaction data provided by each legal person, and further, it can also evaluate the transaction compliance level of each legal person based on the above data detection results, thereby performing anti-money laundering identification and control at both the transaction itself and the legal person levels.

[0010] In some implementations, the acquiring of historical transaction data and current transaction data of multiple target objects includes:

[0011] Based on the preset data port, according to the transaction data stored in each of the target objects, current transaction data corresponding to the transaction currently being executed and historical transaction data corresponding to the completed transaction are obtained;

[0012] According to the target object, the historical transaction data and the current transaction data are marked and distinguished based on the unique identification information corresponding to the target object.

[0013] In this way, the present application also provides a method for obtaining historical transaction records and current transaction records, and can also distinguish the acquired transaction data using the unique identification information of the legal person, so as to facilitate the subsequent compliance rating of different legal persons.

[0014] In some embodiments, performing data logic analysis on the historical transaction data and the current transaction data according to a preset transaction data detection model to determine the detection result for the characteristics of money laundering behavior includes:

[0015] The detection result of the historical transaction data for the money laundering behavior characteristics is determined based on the historical transaction data and the preset verification detection indicators in the detection data indicator library.

[0016] Thus, the present application provides a method for performing data analysis based on historical transaction data.

[0017] In some embodiments, the performing of data logic analysis on the historical transaction data and the current transaction data according to a preset transaction data detection model to determine the detection result for the characteristics of money laundering behavior also includes:

[0018] According to the current transaction data and preset transaction logic, the current transaction data is detected to determine the detection result of the current transaction data for the money laundering behavior characteristics.

[0019] Thus, the present application provides a method for performing data analysis and logic analysis based on current transaction data.

[0020] In certain embodiments, the method further comprises:

[0021] Determining feedback information based on the detection result of the current transaction data for the characteristics of money laundering behavior;

[0022] The feedback information is sent to the user according to a preset prompting method, so that the user can confirm the feedback information in time.

[0023] In this way, the present application can also feed back the detection results of the current transaction data to the user in the form of prompt information, so that the user can promptly confirm the above prompt information, thereby promptly identifying the transaction data that is determined by the model to be likely to involve money laundering behavior.

[0024] In certain embodiments, determining compliance rating information of each target object based on the detection result to determine the governance and system compliance of the target object in anti-money laundering includes:

[0025] According to the detection results and the detection element level of each indicator in the detection data indicator library, based on a preset weighted average algorithm, the compliance rating information of the target object is determined.

[0026] In this way, the present application can also evaluate the compliance level of each corresponding legal person based on the above-mentioned detection results of historical transaction records and current transaction records.

[0027] In certain embodiments, the method further comprises:

[0028] According to the detection results and the compliance rating information of the target object, corresponding data governance and institutional compliance data processing countermeasures are determined.

[0029] In this way, this application can further provide countermeasures and references for data governance and institutional compliance measures based on the transaction data detection results and compliance level evaluation of each legal person.

[0030] The anti-money laundering transaction identification device in the implementation mode of the present application includes:

[0031] A data acquisition module is used to acquire historical transaction data and current transaction data of multiple target objects;

[0032] A data analysis module, configured to perform data logic analysis on the historical transaction data and the current transaction data according to a preset transaction data detection model, and determine a detection result for the characteristics of money laundering behavior, wherein the transaction data detection model is trained based on a machine learning algorithm according to a preset detection data indicator library;

[0033] The data rating module is used to determine the compliance rating information of each target object based on the detection results, so as to determine the governance and system compliance of the target object in anti-money laundering.

[0034] The computer device in the implementation mode of the present application includes a memory and a processor. The memory stores a computer program. When the computer program is executed by the processor, the above method is implemented.

[0035] The computer-readable storage medium in the embodiments of the present application stores a computer program, and when the computer program is executed by one or more processors, the above method is implemented.

[0036] Additional aspects and advantages of the embodiments of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the embodiments of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0038] Figure 1 A flowchart of an anti-money laundering transaction identification method in an embodiment of the present application;

[0039] Figure 2 A flowchart of an anti-money laundering transaction identification method in an embodiment of the present application;

[0040] Figure 3 A flowchart of an anti-money laundering transaction identification method in an embodiment of the present application;

[0041] Figure 4 A flowchart of an anti-money laundering transaction identification method in an embodiment of the present application;

[0042] Figure 5 A flowchart of an anti-money laundering transaction identification method in an embodiment of the present application;

[0043] Figure 6 It is a flowchart of the anti-money laundering transaction identification method in the implementation mode of this application. DETAILED DESCRIPTION

[0044] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals represent the same or similar elements or elements having the same or similar functions from beginning to end. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the embodiments of the present application, and cannot be understood as limiting the embodiments of the present application.

[0045] See also Figure 1 The anti-money laundering transaction identification method in the implementation mode of the present application comprises the following steps:

[0046] 01: Get historical transaction data and current transaction data of multiple target objects;

[0047] 02: According to the preset transaction data detection model, perform data logic analysis on historical transaction data and current transaction data to determine the detection results for the characteristics of money laundering behavior.

[0048] The transaction data detection model is trained based on a machine learning algorithm according to a preset detection data indicator library;

[0049] 03: Based on the test results, determine the compliance rating information of each target object to determine the target object’s governance and system compliance with anti-money laundering.

[0050] The anti-money laundering transaction identification device in the embodiment of the present application can implement the above-mentioned anti-money laundering transaction identification method. Specifically, the device includes a data acquisition module, a data analysis module and a data rating module, wherein the data acquisition module is used to acquire historical transaction data and current transaction data of multiple target objects, the data analysis module is used to perform data logic analysis on the historical transaction data and the current transaction data according to a preset transaction data detection model, and determine the detection results for the characteristics of money laundering behavior, and the data rating module is used to determine the compliance rating information of each target object according to the detection results, so as to determine the governance and system compliance of the target object in anti-money laundering.

[0051] The computer device in the embodiment of the present application can implement the above-mentioned anti-money laundering transaction identification method. Specifically, the computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor is used to obtain historical transaction data and current transaction data of multiple target objects, and is used to perform data logic analysis on the historical transaction data and the current transaction data according to a preset transaction data detection model, determine the detection results for the characteristics of money laundering behavior, and determine the compliance rating information of each target object according to the detection results, so as to determine the governance and system compliance of the target object in anti-money laundering.

[0052] Specifically, in order to target the risks of money laundering transactions that may exist in legal entities such as banks and stock exchanges (corresponding to the target objects), this application proposes an anti-money laundering transaction identification method, which is generally implemented by configuring an anti-money laundering transaction identification system on one or more specific devices in a server device or a data processing network. There is a data connection relationship between the above-mentioned identification system and the devices of multiple legal entities, so as to obtain transaction information from the devices of each legal entity. When anti-money laundering data analysis is required, the anti-money laundering transaction identification system obtains transaction data from each legal entity through the above-mentioned data interface. The above-mentioned transaction information includes both the historical transaction data previously saved and the current transaction data that is currently occurring or has just been completed within a preset time period. The above-mentioned preset time period is generally a shorter time period, such as a time period range of 10 minutes from the current time.

[0053] On this basis, illustratively, in order to be able to quickly and conveniently call the above-mentioned transaction data, the acquired historical transaction data and current transaction data can be saved on a server device or a storage device in a data processing network to form a transaction database, wherein the transaction database can be divided into two parts: a historical transaction database and a current transaction database. The above-mentioned historical transaction data is saved in the historical transaction database, and the above-mentioned current transaction data is saved in the current transaction database.

[0054] Next, when the transaction data of each legal entity is obtained, the historical transaction database and the current transaction database are used as data sources, and the required transaction data is extracted from the historical transaction database and the current transaction database. The transaction data is used as the data basis and the pre-trained transaction data detection model is used to perform data logic detection processing, so that the anti-money laundering identification detection results of the transaction data of each legal entity can be obtained. Among them, since the timeliness of the current transaction data is different from that of the historical transaction data, the above-mentioned timeliness difference can also be used alone as part of the detection basis for anti-money laundering identification. Therefore, illustratively, the above-mentioned transaction data detection model performs the detection of historical transaction data and the detection of current transaction data separately, that is, the detection of historical transaction data adopts the analysis logic corresponding to the historical transaction data, and the detection of current transaction data adopts the analysis logic corresponding to the current transaction data.

[0055] In addition, the training process of the above-mentioned transaction data detection model is generally based on a preset standardized detection index library. The above-mentioned detection index library generally stores a large amount of transaction data related to the characteristics of suspected money laundering transactions and the corresponding detection index data. On the basis of the above-mentioned historical transaction database, combined with the above-mentioned detection index library, the data in the two sets of databases are used as training sets and verification sets, and the above-mentioned detection index data are added or adjusted based on machine learning, so as to obtain a transaction data detection model that can be used for anti-money laundering identification and analysis for multiple legal entities. For example, based on the historical transaction database, the index call is continuously performed, and the index data is verified based on the above-mentioned transaction data detection model, so as to improve the logical calculation process of the index library and the transaction data detection model, maximize the output of statistical elements of non-compliant items, and strive to achieve detailed information drilling for each element in the transaction data.

[0056] Finally, after determining the above-mentioned test results, the above-mentioned anti-money laundering identification system can also evaluate the anti-money laundering compliance rating of the legal entity behind the transaction data corresponding to the test results based on the test results, so as to describe whether the above-mentioned legal entity can effectively curb money laundering transactions in terms of anti-money laundering governance, institutional compliance, etc., thereby providing a reference for anti-money laundering work in the next period of time.

[0057] In this way, the present application can use the historical transaction data and current transaction data of multiple legal persons as the analysis data basis, and use the detection model to perform data analysis on the historical data and current data respectively, especially to perform logical analysis on the historical transaction data and the current transaction data, so as to obtain data detection results determined based on the transaction data provided by each legal person, and further, it can also evaluate the transaction compliance level of each legal person based on the above data detection results, thereby performing anti-money laundering identification and control at both the transaction itself and the legal person levels.

[0058] See also Figure 2 In some embodiments, step 01 includes:

[0059] 011: Based on the preset data port and the transaction data stored in each target object, obtain the current transaction data corresponding to the currently executed transaction and the historical transaction data corresponding to the completed transaction;

[0060] 012: According to the target object, historical transaction data and current transaction data are marked and distinguished based on the unique identification information corresponding to the target object.

[0061] In some embodiments, the data acquisition module is also used to obtain current transaction data corresponding to a currently executing transaction and historical transaction data corresponding to completed transactions based on the transaction data stored in each target object itself based on a preset data port, and is used to mark and distinguish the historical transaction data and current transaction data based on the unique identification information corresponding to the target object.

[0062] In some embodiments, the processor is also used to obtain, based on a preset data port and according to the transaction data stored in each target object itself, current transaction data corresponding to a currently executing transaction and historical transaction data corresponding to completed transactions, and to mark and distinguish the historical transaction data and current transaction data based on the unique identification information corresponding to the target object.

[0063] Specifically, on the basis of the above-mentioned implementation mode, illustratively, in order to improve the efficiency of data acquisition and facilitate the unification of data formats, the data interface set between the above-mentioned anti-money laundering transaction identification system and the equipment of each legal entity is the same data interface, and the data format that can be transmitted through the above-mentioned data interface needs to be set to the data format required by the above-mentioned data interface. The specific data format setting can be set according to the actual situation, and this application does not make specific restrictions. For example, for legal entity A, its internal transaction data format is format A, for legal entity B, its internal transaction data format is format B, and the transaction data format required by the data interface set between the above-mentioned anti-money laundering transaction identification system and each legal entity is format C. Before sending transaction data to the above-mentioned identification system, legal entity A needs to rewrite the transaction data to be sent from the transaction data under format A to the transaction data under format C according to the requirements of format C. Similarly, legal entity B needs to rewrite the transaction data to be sent from the transaction data under format B to the transaction data under format C according to the requirements of format C before sending transaction data to the above-mentioned identification system.

[0064] Further, when the anti-money laundering transaction identification system receives transaction data sent by each legal entity through the above-mentioned data interface, the identification system first parses the received data according to the format requirements, and restores the above-mentioned data into two parts: historical transaction data and current transaction data, so as to facilitate the subsequent use of the above-mentioned detection model for data logic analysis. In order to be able to determine the compliance rating information for different legal entities, it is necessary to correspond the parsed transaction data to the legal entity, so that the detection results corresponding to the legal entity can be obtained. Therefore, illustratively, when each legal entity sends transaction data to the above-mentioned identification system, it will also synchronously send its corresponding unique identification information to the above-mentioned identification system. After receiving the unique identification information, the above-mentioned identification system directly uses the above-mentioned unique identification information to mark the parsed historical transaction data and current transaction data when parsing the historical transaction data and the current transaction data according to the acquired transaction data, so as to distinguish the transaction data sent by each legal entity according to the legal entity.

[0065] The above-mentioned unique identification information generally includes the legal person code, legal person name, etc. In order to simplify the identification process of the legal person, the legal person code is exemplarily used as the above-mentioned unique identification information. For example, the legal person institution is a bank, and its unique identification information is a bank code string consisting of 11 characters. For another example, the legal person institution is a financial institution, and its unique identification information is the unified social credit code of the legal person and other organizations. The specific type of the legal person code depends on the type of legal person and industry standards, and this application does not make specific limitations.

[0066] In this way, the present application also provides a method for obtaining historical transaction records and current transaction records, and can also distinguish the acquired transaction data using the unique identification information of the legal person, so as to facilitate the subsequent compliance rating of different legal persons.

[0067] See also Figure 3 In some embodiments, step 02 includes:

[0068] 021: Based on the historical transaction data and preset verification detection indicators in the detection data indicator library, determine the detection results of the historical transaction data for the characteristics of money laundering behavior.

[0069] In certain embodiments, the data analysis module is further used to determine the detection results of the historical transaction data for the characteristics of money laundering behavior based on the historical transaction data and preset verification detection indicators in the detection data indicator library.

[0070] In certain embodiments, the processor is further configured to determine a detection result of the historical transaction data for money laundering behavior characteristics based on the historical transaction data and preset verification detection indicators in the detection data indicator library.

[0071] Specifically, on the basis of the above implementation, when the transaction data sent by a legal person is obtained and the historical transaction data and the current transaction data are parsed from it, or when the identification system calls the historical transaction data that needs to be analyzed from the historical transaction database, the parsed or called historical transaction data is used as the input data of the transaction data detection model, and the transaction data detection model is used to perform data level analysis and logic level analysis on the above input data with one or more rule logic indicators in the detection data indicator library for each link in the transaction process as the reference standard. Among them, the above rule logic indicators are set based on the requirements of the superior competent department of the legal person for anti-money laundering identification, and the above detection data indicator library is generally composed of calculation indicators, detection indicators and indicator models, wherein the indicator model is the first node, which is obtained by freely combining multiple detection indicators, and each detection indicator includes multiple specific rule logic indicators. The above data level analysis mainly lies in parsing the customer identification data according to the historical transaction information, and the above customer identification data includes customer information, executed transaction action information, etc. The above-mentioned logic level analysis is mainly to perform logical verification based on the above-mentioned executed transaction action information and the rule logic indicators set according to the requirements of the superior administrative department of the legal person institution for anti-money laundering identification, so as to detect characteristic information that may be suspected of money laundering in the transaction actions.

[0072] Through the data analysis and logical analysis process of the historical transaction data by the above-mentioned transaction data detection model, the logical non-compliant items in the historical transaction data can be classified, output and fed back to the above-mentioned anti-money laundering transaction identification system, thereby completing the data analysis and logical analysis of the historical transaction data and obtaining the detection results for the money laundering behavior characteristics in the historical transaction data.

[0073] Thus, the present application provides a method for performing data analysis based on historical transaction data.

[0074] See also Figure 4 In some embodiments, step 02 further includes:

[0075] 022: According to the current transaction data and the preset transaction logic, the current transaction data is detected to determine the detection result of the current transaction data for the characteristics of money laundering behavior.

[0076] In certain embodiments, the data analysis module is further configured to detect the current transaction data based on the current transaction data and a preset transaction logic, and determine a detection result of the current transaction data for characteristics of money laundering behavior.

[0077] In some embodiments, the processor is further configured to detect the current transaction data based on the current transaction data and a preset transaction logic, and determine a detection result of the current transaction data for characteristics of money laundering behavior.

[0078] Specifically, on the basis of the above implementation, when the transaction data sent by a legal person is obtained and the historical transaction data and the current transaction data are parsed from it, or when the identification system calls the historical transaction data that needs to be analyzed from the current transaction database, the parsed or called current transaction data is used as the input data of the transaction data detection model, and the transaction data detection model is used to analyze the current transaction at the data level and the logic level based on the transaction action logic standard (corresponding to the preset transaction logic) stipulated by the legal person or its superior competent department, combined with the transaction action that the customer is currently conducting or has just completed, so as to implement compliance constraints on it. The above data level analysis mainly involves parsing the customer identification data from the historical transaction information, and the above customer identification data includes customer information, executed transaction action information, etc. The above logic level analysis mainly involves performing logic verification based on the above executed transaction action information and the rule logic indicators set based on the requirements of the superior competent department of the legal person for anti-money laundering identification, and detecting the characteristic information that may be suspected of money laundering in the transaction action. For the logical level analysis of the current transaction data, for example, if the current transaction data corresponds to a transaction that is being executed, the anti-money laundering transaction identification system will include the transaction actions that the customer is executing in the screening scope and generate a screening opinion based on the above transaction actions. In addition, legal entities can also conduct money laundering transaction screening and fill in screening opinions based on the above transaction actions through manual input.

[0079] Through the data analysis and logical analysis process of the current transaction data by the above-mentioned transaction data detection model, the logical non-compliant items in the current transaction data can be classified, output and fed back to the above-mentioned anti-money laundering transaction identification system, thereby completing the data analysis and logical analysis of the current transaction data and obtaining the detection results for the money laundering behavior characteristics in the current transaction data.

[0080] Thus, the present application provides a method for performing data analysis and logic analysis based on current transaction data.

[0081] See also Figure 5 In some embodiments, the anti-money laundering transaction identification method further includes:

[0082] 0231: Determine feedback information based on the detection results of the money laundering behavior characteristics of the current transaction data;

[0083] 0232: Send feedback information to users according to the preset prompt method so that users can confirm the feedback information in time.

[0084] In some embodiments, the data analysis module is further used to determine feedback information based on the detection results of the money laundering behavior characteristics of the current transaction data, and to send feedback information to the user according to a preset prompt method so that the user can confirm the feedback information in time.

[0085] In some embodiments, the processor is further used to determine feedback information based on the detection results of the money laundering behavior characteristics of the current transaction data, and to send the feedback information to the user according to a preset prompt method so that the user can confirm the feedback information in time.

[0086] Specifically, on the basis of the above-mentioned implementation mode, after completing the above-mentioned data level analysis and logic level analysis process for the current transaction data, if non-compliant items suspected of money laundering are found in the transaction data during the logic level analysis, or the detection results show that the current transaction data is suspected of money laundering, then exemplarily, the anti-money laundering transaction identification system triggers the generation of an abnormal prompt (corresponding to feedback information) for providing feedback to the user. The above-mentioned abnormal prompt is generally provided to the user via the server-side device where the system is located or a specific terminal device in the data processing network. The prompt method may be a pop-up prompt, a voice prompt or other prompt method that can attract the user's attention.

[0087] In addition, in some examples, when generating the above-mentioned exception prompts, corresponding exception prompts of different types or different contents can be generated according to different above-mentioned non-compliance items, so that users can directly judge the non-compliance items existing in the current transaction record according to the type or content of the exception prompts.

[0088] In this way, the present application can also feed back the detection results of the current transaction data to the user in the form of prompt information, so that the user can promptly confirm the above prompt information, thereby promptly identifying the transaction data that is determined by the model to be likely to involve money laundering behavior.

[0089] It should be noted that the above-mentioned transaction data detection model can be deployed on a separate server device in the above-mentioned data processing network. Considering the performance requirements, it can also be dispersedly deployed on multiple server devices in the data processing network. When performing the detection, the device resources for performing the detection can be allocated according to the actual needs and the performance of the device. On the one hand, the above-mentioned transaction data detection model can automatically trigger the detection when the transaction data is received from each legal entity, or the user can log in to the anti-money laundering transaction identification system on the device and call the above-mentioned transaction data detection model for manual detection. The above-mentioned login generally refers to the user logging in to the anti-money laundering transaction identification system based on the login data corresponding to the legal entity identification and the affiliated institution, so that the anti-money laundering transaction identification system assigns permissions to the logged-in user according to the above-mentioned legal entity identification and the affiliated institution.

[0090] See also Figure 6 In some embodiments, step 03 includes:

[0091] 031: According to the test results and the test element level of each indicator in the test data indicator library, based on the preset weighted average algorithm, determine the compliance rating information of the target object.

[0092] In certain embodiments, the data rating module is further used to determine the compliance rating information of the target object based on a preset weighted average algorithm according to the detection results and the detection element level of each indicator in the detection data indicator library.

[0093] In certain embodiments, the processor is further configured to determine compliance rating information of the target object based on a preset weighted average algorithm according to the detection results and the detection element level of each indicator in the detection data indicator library.

[0094] Specifically, on the basis of the above implementation, when the detection results of historical transaction data and current transaction data are determined, it is equivalent to determining the detection results of suspected money laundering transactions in the transactions executed by the legal entity corresponding to the above historical transaction data and current transaction data within a period of time. In order to more conveniently use the above detection results to provide guidance for anti-money laundering transaction identification in the next period of time, in some examples, when the detection results of historical transaction data and current transaction data of a legal entity are determined according to the transaction data detection model of the user, according to the detection factor level of the rule logic indicator used in the detection process of obtaining the above detection results in the detection logic indicator library, the detection values ​​corresponding to each rule logic indicator in the detection result are weighted averaged to obtain an average score, and further based on the numerical range of the average score, the compliance rating information of the corresponding legal entity in anti-money laundering transaction identification is determined. Since the above-mentioned anti-money laundering transaction identification system can be connected to the data of multiple legal entities based on a unified data interface, the compliance rating information of each legal entity connected to the above-mentioned anti-money laundering transaction identification system in anti-money laundering transaction identification can be obtained according to the above-mentioned method, thereby intuitively presenting the compliance level and control effect of the industry as a whole and each legal entity in the anti-money laundering transaction.

[0095] In this way, the present application can also evaluate the compliance level of each corresponding legal person based on the above-mentioned detection results of historical transaction records and current transaction records.

[0096] In some embodiments, the anti-money laundering transaction identification method further includes:

[0097] Based on the test results and the compliance rating information of the target object, determine the corresponding data governance and institutional compliance data processing countermeasures.

[0098] In certain embodiments, the data rating module is also used to determine corresponding data governance and institutional compliance data processing strategies based on the detection results and the compliance rating information of the target object.

[0099] In certain embodiments, the processor is further used to determine corresponding data governance and institutional compliance data processing strategies based on the detection results and compliance rating information of the target object.

[0100] Specifically, on the basis of the above-mentioned implementation mode, exemplarily, in order to more intuitively provide a reference for the anti-money laundering transaction identification of each legal entity in the next period of time, after determining the above-mentioned test results and the compliance rating of the corresponding legal entity, according to the pre-stored comparison information of the processing countermeasures and the test results, or the processing countermeasures and the above-mentioned compliance rating, the anti-money laundering transaction identification system can provide a reference for the data governance measures required for the legal entity in the next period of time for data suspected of money laundering transactions, and the institutional compliance design for suspected money laundering transactions based on the test results and compliance rating of each legal entity, so that the staff of the legal entity can use the above-mentioned processing countermeasures as a reference to identify and control all transactions of their own legal entity in the next period of time for anti-money laundering transactions, so as to reduce the incidence of money laundering transactions as much as possible, thereby enhancing the effectiveness of anti-money laundering transactions.

[0101] In this way, this application can further provide countermeasures and references for data governance and institutional compliance measures based on the transaction data detection results and compliance level evaluation of each legal person.

[0102] The computer-readable storage medium in the embodiments of the present application stores a computer program, and when the computer program is executed by one or more processors, the above method is implemented.

[0103] In the description of this specification, the descriptions with reference to the terms "certain embodiments", "in an example", "exemplarily", etc., mean that the specific features, structures, materials or characteristics described in conjunction with the embodiments or examples are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0104] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0105] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for identifying anti-money laundering transactions, characterized in that: The method comprises: Obtain historical transaction data and current transaction data of multiple target objects; According to a preset transaction data detection model, a data logic analysis is performed on the historical transaction data and the current transaction data to determine a detection result for the characteristics of money laundering behavior, wherein the transaction data detection model is trained based on a machine learning algorithm according to a preset detection data indicator library; Based on the detection results, compliance rating information of each target object is determined to determine the governance and system compliance of the target object in anti-money laundering.

2. The method according to claim 1, characterized in that The obtaining of historical transaction data and current transaction data of multiple target objects includes: Based on the preset data port, according to the transaction data stored in each of the target objects, current transaction data corresponding to the transaction currently being executed and historical transaction data corresponding to the completed transaction are obtained; According to the target object, the historical transaction data and the current transaction data are marked and distinguished based on the unique identification information corresponding to the target object.

3. The method according to claim 1, characterized in that The performing of data logic analysis on the historical transaction data and the current transaction data according to the preset transaction data detection model to determine the detection result for the characteristics of money laundering behavior includes: The detection result of the historical transaction data for the money laundering behavior characteristics is determined based on the historical transaction data and the preset verification detection indicators in the detection data indicator library.

4. The method according to claim 1, characterized in that: The method further comprises: performing data logic analysis on the historical transaction data and the current transaction data according to a preset transaction data detection model to determine a detection result for the characteristics of money laundering behavior; According to the current transaction data and preset transaction logic, the current transaction data is detected to determine the detection result of the current transaction data for the money laundering behavior characteristics.

5. The method according to claim 4, characterized in that The method further comprises: Determining feedback information based on the detection result of the current transaction data for the characteristics of money laundering behavior; The feedback information is sent to the user according to a preset prompting method, so that the user can confirm the feedback information in time.

6. The method according to claim 1, characterized in that Determining compliance rating information of each target object based on the detection results to determine the governance and system compliance of the target object in anti-money laundering, including: According to the detection results and the detection element level of each indicator in the detection data indicator library, based on a preset weighted average algorithm, the compliance rating information of the target object is determined.

7. The method according to claim 1, characterized in that The method further comprises: According to the detection results and the compliance rating information of the target object, corresponding data governance and institutional compliance data processing countermeasures are determined. 8.An anti-money laundering transaction identification device, characterized in that: The device comprises: A data acquisition module is used to acquire historical transaction data and current transaction data of multiple target objects; A data analysis module, configured to perform data logic analysis on the historical transaction data and the current transaction data according to a preset transaction data detection model, and determine a detection result for the characteristics of money laundering behavior, wherein the transaction data detection model is trained based on a machine learning algorithm according to a preset detection data indicator library; The data rating module is used to determine the compliance rating information of each target object based on the detection results, so as to determine the governance and system compliance of the target object in anti-money laundering.

9. A computer device, characterized in that: The computer device comprises a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by one or more processors, the method according to any one of claims 1 to 7 is implemented.

Images