Business processing method, device and equipment, medium and product

Through the multi-layer evaluation index system, the problem of difficult to guarantee the quality of suspicious transaction reports in the existing technology is solved, and the quantitative evaluation and quality improvement of suspicious transaction reports are achieved.

CN118982356APending Publication Date: 2024-11-19TENCENT TECHNOLOGY (SHENZHEN) CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410999359.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

The lack of effective quantitative evaluation methods in the prior art makes it difficult to guarantee the quality of suspicious transaction reports and cannot form high-quality suspicious transaction reports documents.

Method used

Using a multi-layer evaluation index system, the suspicious transaction report documents are evaluated and processed. By obtaining a business evaluation model that is suitable for the business scenario, a multi-layer evaluation index system is constructed, and the evaluation results are generated based on the relative and absolute weights of the evaluation index, and the evaluation results are characterized. The effectiveness of screening and analysis of suspicious transaction report documents.

Benefits of technology

The quantitative evaluation of suspicious transaction report documents has been achieved, the quality and accuracy of the report have been improved, and the identification and analysis of suspicious transactions has been optimized and improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118982356A_ABST
    Figure CN118982356A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a service processing method, device and equipment, a medium and a product. The method comprises the following steps: acquiring a suspicious transaction report file aiming at a business scene, wherein the suspicious transaction report file is a file obtained by discriminating and analyzing suspicious transactions in the business scene; obtaining a service evaluation model matched with the service scene, wherein a multi-layer evaluation index system matched with the service scene is arranged in the service evaluation model; and adopting a multi-layer evaluation index system in the business evaluation model to perform evaluation processing on the suspicious transaction report file to obtain an evaluation result of the suspicious transaction report file, the evaluation result being used for representing validity of discrimination analysis of the suspicious transaction report file on the suspicious transaction in the business scene. According to the embodiment of the invention, the effectiveness of the suspicious transaction report work can be quantified, and a high-quality suspicious transaction report file can be formed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a business processing method, a business processing apparatus, a computer device, a computer-readable storage medium, and a computer program product. Background Art

[0002] The suspicious transaction reporting system refers to a system whereby financial institutions, when they determine that there are suspicious transactions in a business scenario, will form a suspicious transaction report file by screening and analyzing the suspicious transactions in the business scenario, and then submit the suspicious transaction report file to the relevant regulatory authorities. At present, there is a lack of a comprehensive and in-depth quantitative evaluation method for the effectiveness of suspicious transaction reporting, which is not conducive to forming a high-quality suspicious transaction report file. Summary of the invention

[0003] The embodiments of the present application provide a business processing method, apparatus and equipment, medium, and product, which can quantify the effectiveness of suspicious transaction reporting work and facilitate the formation of a high-quality suspicious transaction report file.

[0004] On the one hand, an embodiment of the present application provides a service processing method, the method comprising:

[0005] Obtain suspicious transaction report files for business scenarios. Suspicious transaction report files are files obtained by screening and analyzing suspicious transactions in business scenarios.

[0006] Obtain a business evaluation model adapted to the business scenario, wherein a multi-layer evaluation indicator system adapted to the business scenario is provided in the business evaluation model, wherein the multi-layer evaluation indicator system includes N levels, each level includes at least one group of evaluation indicators, and each group of evaluation indicators includes at least one evaluation indicator; any evaluation indicator in the nth level of the multi-layer evaluation indicator system supports being disassembled into a group of evaluation indicators in the n+1th level, where N and n are both positive integers, and n is less than or equal to N;

[0007] The multi-layer evaluation index system in the business evaluation model is used to evaluate the suspicious transaction report file and obtain the evaluation results of the suspicious transaction report file. The evaluation results are used to characterize the effectiveness of the suspicious transaction report file in identifying and analyzing suspicious transactions in business scenarios.

[0008] On the other hand, an embodiment of the present application provides a service processing device, the device comprising:

[0009] An acquisition unit, used to acquire a suspicious transaction report file for a business scenario, where the suspicious transaction report file is a file obtained by screening and analyzing suspicious transactions in the business scenario;

[0010] The acquisition unit is further used to acquire a business evaluation model adapted to the business scenario, wherein a multi-layer evaluation index system adapted to the business scenario is provided in the business evaluation model, wherein the multi-layer evaluation index system includes N levels, each level includes at least one group of evaluation indicators, and each group of evaluation indicators includes at least one evaluation indicator; any evaluation indicator in the nth level of the multi-layer evaluation index system supports being disassembled into a group of evaluation indicators in the n+1th level, wherein N and n are both positive integers, and n is less than or equal to N;

[0011] The processing unit is used to evaluate and process the suspicious transaction report file using the multi-layer evaluation index system in the business evaluation model to obtain an evaluation result of the suspicious transaction report file, and the evaluation result is used to characterize the effectiveness of the suspicious transaction report file in identifying and analyzing suspicious transactions in business scenarios.

[0012] In one embodiment, when the acquisition unit is used to acquire a business evaluation model adapted to a business scenario, the following steps are specifically performed:

[0013] Based on the scenario characteristics of business scenarios, build a multi-layer evaluation indicator system that is compatible with business scenarios;

[0014] Obtain the relative weight of each evaluation indicator in the multi-layer evaluation indicator system. The relative weight is used to indicate the importance of the evaluation indicator in the group to which it belongs.

[0015] Based on the relative weight of each evaluation indicator in the multi-layer evaluation indicator system, an absolute weight is set for each evaluation indicator in the multi-layer evaluation indicator system; the absolute weight is used to indicate the importance of the evaluation indicator in the corresponding level;

[0016] A multi-layer evaluation index system containing absolute weights is determined as a business evaluation model that is compatible with business scenarios.

[0017] In one embodiment, when the acquisition unit is used to acquire the relative weight of each evaluation index in the multi-layer evaluation index system, the following steps are specifically performed:

[0018] Obtain the relative importance of each evaluation index in the same group at each level of the multi-level evaluation index system;

[0019] According to the relative importance of each evaluation index in the same group, hierarchical analysis is performed on each evaluation index in the multi-layer evaluation index system to obtain the relative weight of each evaluation index in the multi-layer evaluation index system.

[0020] In one embodiment, any level in the multi-layer evaluation index system is represented as the nth level, and any group of evaluation indicators in the nth level is represented as the nth level. q Group, nth q The group evaluation index contains M evaluation indicators, n qand M are positive integers;

[0021] The processing unit is used to perform hierarchical analysis on each evaluation indicator in the multi-layer evaluation indicator system according to the relative importance between each evaluation indicator in the same group, and when obtaining the relative weight of each evaluation indicator in the multi-layer evaluation indicator system, specifically execute the following steps:

[0022] Based on the nth q The relative importance of the M evaluation indicators included in the group evaluation indicators is used to construct a first judgment matrix. The matrix size of the first judgment matrix is ​​M×M. The element at position (i, j) in the first judgment matrix represents the relative importance of the i-th evaluation indicator compared to the j-th evaluation indicator among the M evaluation indicators. Both i and j are positive integers less than or equal to M.

[0023] Obtaining the maximum eigenvalue of the first judgment matrix, and obtaining the eigenvector corresponding to the maximum eigenvalue;

[0024] The relative weights of the M evaluation indicators are determined based on the feature vector, wherein the kth element in the feature vector is the relative weight of the kth evaluation indicator among the M evaluation indicators, and k is a positive integer less than or equal to M.

[0025] In one embodiment, before the obtaining unit is used to obtain the eigenvector corresponding to the maximum eigenvalue, the processing unit is further used to perform the following steps:

[0026] Based on the number M and the maximum eigenvalue, the first judgment matrix is ​​checked for consistency;

[0027] If the first judgment matrix passes the consistency check, it triggers the acquisition of the eigenvector corresponding to the maximum eigenvalue.

[0028] In one embodiment, the processing unit is used to perform the following steps when performing consistency check on the first judgment matrix based on the number M and the maximum eigenvalue:

[0029] Determining a consistency index parameter based on the number M and the maximum eigenvalue, and determining a random consistency ratio parameter based on the matrix size of the first judgment matrix;

[0030] The ratio between the consistency index parameter and the random consistency ratio parameter is determined as the target consistency ratio parameter;

[0031] If the target consistency ratio parameter meets the preset ratio threshold condition, it is determined that the first judgment matrix passes the consistency test.

[0032] In one embodiment, any level in the multi-layer evaluation index system is represented as the nth level, and any group of evaluation indicators in the nth level is represented as the nth level. q Group, nth qThe group evaluation index contains M evaluation indicators, n q and M are positive integers;

[0033] When the acquisition unit is used to acquire the relative importance between the evaluation indicators in the same group at each level of the multi-layer evaluation indicator system, the following steps are specifically performed:

[0034] Obtain multiple preset importances of the i-th evaluation indicator compared to the j-th evaluation indicator among the M evaluation indicators, where the i-th evaluation indicator and the j-th evaluation indicator are any two of the M evaluation indicators under the first evaluation dimension, and i and j are both positive integers less than or equal to M;

[0035] Performing mean processing on multiple preset importances of the i-th evaluation indicator compared to the j-th evaluation indicator to obtain the relative importance of the i-th evaluation indicator compared to the j-th evaluation indicator;

[0036] The inverse of the relative importance of the i-th evaluation indicator to the j-th evaluation indicator is determined as the relative importance of the j-th evaluation indicator to the i-th evaluation indicator.

[0037] In one embodiment, any level in the multi-layer evaluation index system is represented as the nth level, and any evaluation index in the nth level is represented as the evaluation index P;

[0038] If n is 1, the processing unit is used to set the absolute weight for each evaluation indicator in the multi-layer evaluation indicator system based on the relative weight of each evaluation indicator in the multi-layer evaluation indicator system, and specifically performs the following steps: setting the relative weight of the evaluation indicator P of the first level to the absolute weight of the evaluation indicator P;

[0039] If n is greater than 1, the processing unit is used to set absolute weights for each evaluation indicator in the multi-layer evaluation indicator system based on the relative weights of each evaluation indicator in the multi-layer evaluation indicator system, and specifically performs the following steps: obtain the disassembly path of the evaluation indicator P of the n-th level, and perform weight recursive processing according to the relative weights of each evaluation indicator in the disassembly path to obtain the absolute weight of the evaluation indicator P; wherein, the evaluation indicator P of the n-th level is obtained by disassembling the evaluation indicator Q of the first level level level by level, and the disassembly path is used to record the corresponding evaluation indicators of each level obtained through the disassembly process from the evaluation indicator Q of the first level to the evaluation indicator P of the n-th level, and P and Q are both positive integers.

[0040] In one embodiment, the multi-layer evaluation index system further includes an absolute weight of each evaluation index in the multi-layer evaluation index system; the processing unit is used to use the multi-layer evaluation index system in the business evaluation model to evaluate the suspicious transaction report file, and when obtaining the evaluation result of the suspicious transaction report file, specifically perform the following steps:

[0041] Obtain the quantitative value of each evaluation indicator in the multi-layer evaluation indicator system for the suspicious transaction report file;

[0042] Generate an evaluation score for the suspicious transaction report file based on the quantitative value of the indicator under each evaluation indicator in the multi-layer evaluation indicator system and the absolute weight of each evaluation indicator in the multi-layer evaluation indicator system;

[0043] Generate the effectiveness score of the suspicious transaction report based on the evaluation score of the suspicious transaction report file and the preset total effectiveness score;

[0044] The effectiveness score of the suspicious transaction report is determined as the evaluation result of the suspicious transaction report file.

[0045] In one embodiment, any level in the multi-layer evaluation index system is represented as the nth level, any evaluation index in the nth level is represented as evaluation index P, P is a positive integer, and the processing unit is further used to perform the following steps:

[0046] The index quantified value of the suspicious transaction report file under the evaluation index P at the nth level is weighted with the absolute weight of the evaluation index P to obtain the evaluation score of the suspicious transaction report file under the evaluation index P;

[0047] If the evaluation score of the suspicious transaction report file under the evaluation index P does not meet the preset score threshold condition, a report supplement prompt information is generated, and the report supplement prompt information is used to prompt the suspicious transaction report file to add report content for screening and analyzing suspicious transactions in the business scenario under the evaluation index P;

[0048] The supplementary prompt information of the report shall be determined as the evaluation result of the suspicious transaction report file.

[0049] In one embodiment, the processing unit is used to generate the evaluation score of the suspicious transaction report file based on the indicator quantification value of each evaluation indicator in the multi-layer evaluation indicator system and the absolute weight of each evaluation indicator in the multi-layer evaluation indicator system, and specifically perform the following steps:

[0050] The absolute weight of the target evaluation index in the multi-layer evaluation index system and the index quantification value of the suspicious transaction report file under the target evaluation index are weighted and summed to obtain the evaluation score of the suspicious transaction report file; the target evaluation index is the evaluation index that has not been disassembled in the multi-layer evaluation index system.

[0051] In one embodiment, the multi-layer evaluation index system includes a first level, a second level, and a third level; the first level includes overall indicators of suspicious transaction reports, transaction object analysis depth indicators, and transaction behavior analysis depth indicators;

[0052] The overall indicator of suspicious transaction reports is broken down into the word count indicator of suspicious transaction reports and the conclusion indicator of suspicious transaction reports at the second level; the depth indicator of transaction object analysis is broken down into the information integrity indicator of transaction object, the information validity indicator of transaction object, and the completeness indicator of transaction object investigation at the second level; the depth indicator of transaction behavior analysis is broken down into the behavior anomaly analysis indicator, transaction anomaly analysis indicator, risk event analysis indicator, related information analysis indicator, and early warning model analysis indicator at the second level;

[0053] Among them, the transaction object information integrity index is broken down into the name missing index, certificate number missing index, address missing index, business scope missing index, operator information missing index, beneficiary information missing index, and risk rating missing index at the third level; the transaction object information validity index is broken down into the suspicious transaction report and object investigation report consistency analysis missing index, business license anomaly analysis missing index, legal person anomaly analysis missing index, beneficial owner anomaly analysis missing index, and transaction object information authenticity analysis missing index at the third level; the transaction object investigation integrity index is broken down into the object investigation report missing index at the third level;

[0054] Among them, the behavior anomaly analysis indicators are broken down into the registration behavior anomaly analysis indicators, account opening and closing behavior anomaly analysis indicators, object investigation report feedback anomaly analysis indicators, and operation address anomaly analysis indicators at the third level; the transaction anomaly analysis indicators are broken down into the business model anomaly analysis missing indicators, transaction scenario anomaly analysis missing indicators, transaction time anomaly analysis missing indicators, transaction location anomaly analysis missing indicators, transaction resource anomaly analysis missing indicators, transaction note information anomaly analysis missing indicators, transaction model anomaly analysis missing indicators, and counterparty anomaly analysis missing indicators at the third level; the risk event analysis indicators are broken down into the negative feedback analysis missing indicators and the hit list analysis missing indicators at the third level; the related information analysis indicators are broken down into the related object analysis missing indicators, the basic information related analysis missing indicators, and the counterparty related analysis missing indicators at the third level; the early warning model analysis indicators are broken down into the early warning model analysis missing indicators at the third level.

[0055] On the other hand, an embodiment of the present application provides a computer device, the computer device comprising:

[0056] A processor for loading and executing computer programs;

[0057] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the business processing method is implemented.

[0058] On the other hand, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program, and the computer program is suitable for being loaded by a processor and executing the above-mentioned business processing method.

[0059] On the other hand, an embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the above-mentioned business processing method is implemented.

[0060] In an embodiment of the present application, a suspicious transaction report file for a business scenario can be obtained, and the suspicious transaction report file is a file obtained by identifying and analyzing suspicious transactions in the business scenario; a business evaluation model adapted to the business scenario is obtained, and a multi-layer evaluation indicator system adapted to the business scenario is provided in the business evaluation model, and the multi-layer evaluation indicator system includes N levels, each level includes at least one group of evaluation indicators, and each group of evaluation indicators includes at least one evaluation indicator; any evaluation indicator in the nth level of the multi-layer evaluation indicator system supports being disassembled into a group of evaluation indicators in the n+1th level, N and n are both positive integers, and n is less than or equal to N; the multi-layer evaluation indicator system in the business evaluation model is used to evaluate and process the suspicious transaction report file to obtain an evaluation result of the suspicious transaction report file, and the evaluation result is used to characterize the effectiveness of the suspicious transaction report file in identifying and analyzing suspicious transactions in the business scenario. It can be seen that the embodiments of the present application can use a business evaluation model that is adapted to the business scenario to quantitatively evaluate the effectiveness of suspicious transaction reporting work (i.e., the work of identifying and analyzing suspicious transactions in business scenarios). This objective evaluation based on data support facilitates a better understanding and improvement of suspicious transaction report files, and is conducive to the formation of a high-quality suspicious transaction report file. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0062] Figure 1 It is a schematic diagram of the architecture of a business processing system provided in an embodiment of the present application;

[0063] Figure 2 It is a flowchart of a business processing solution provided by an embodiment of the present application;

[0064] Figure 3 It is a flowchart of a business processing method provided by an embodiment of the present application;

[0065] Figure 4 It is a business processing flow chart provided by an embodiment of the present application;

[0066] Figure 5 It is a schematic diagram of the architecture of a business processing solution provided in an embodiment of the present application;

[0067] Figure 6 This is a schematic diagram of effectiveness score distribution provided in an embodiment of the present application;

[0068] Figure 7 This is a schematic diagram of a single indicator analysis provided in an embodiment of the present application;

[0069] Figure 8 It is a structural diagram of a service processing device provided in an embodiment of the present application;

[0070] Fig. 9 It is a structural diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0071] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0072] See also Figure 1 , Figure 1 Schematic diagram of a business system provided by an embodiment of the present application. Figure 1 As shown, the business system may include a business server 100 and a terminal cluster. The terminal cluster may include multiple terminal devices. The embodiment of the present application does not limit the number of terminal devices included in the terminal cluster. Figure 1As shown, the terminal cluster may specifically include: terminal device 200a, terminal device 200b, terminal device 200c, ..., terminal device 200n, wherein there may be a communication connection between the terminal clusters, for example, there is a communication connection between terminal device 200a and terminal device 200b, and there is a communication connection between terminal device 200a and terminal device 200c. At the same time, any terminal device in the terminal cluster may have a communication connection with the business server 100, for example, there is a communication connection between terminal device 200a and business server 100, so that each terminal device in the terminal cluster may exchange data with the business server 100 through the communication connection. Among them, the above-mentioned communication connection does not limit the connection method, and may be directly or indirectly connected through a wired communication method, or directly or indirectly connected through a wireless communication method, or through other methods, and this application does not make any restrictions here.

[0073] The business server 100 may be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud database, cloud service, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN, and big data and artificial intelligence platform. The terminal device may be a smart phone, tablet computer, laptop computer, desktop computer, PDA, mobile internet device (MID), wearable device (such as smart watch, smart bracelet, etc.), smart computer, smart car and other smart terminals.

[0074] like Figure 1 Each terminal device in the terminal cluster shown in the figure may be installed with a service client (a computer program for completing one or more specific tasks). When the service client runs in each terminal device, it can communicate with the above-mentioned Figure 1 Data is exchanged between the business servers 100 shown. The business client may be a payment client, a game client, an instant messaging client, a live broadcast client, a short video client, a video client, a music client, a shopping client, a novel client, a browser, or other business clients with data information functions such as displaying text, images, audio, and video. The business client may be an independent client or an embedded sub-client integrated in a client (such as a payment client, etc.), which is not limited here.

[0075] In the embodiment of the present application, the payment client is a client that can provide payment services (or resource transfer services) for business objects. The payment client is not limited to a client that only includes payment services. For example, the payment client can also provide a variety of services such as chat services, recording services, and playback services for business objects. For example, the payment client can be an instant messaging client that includes payment services, or a shopping client that includes payment services, or a live broadcast client that includes payment services, etc. The so-called business object refers to the object of the business client service (including but not limited to: individual users, enterprises, individual businesses, etc.).

[0076] In a feasible implementation, the business system may be a system used by a financial institution, where a financial institution refers to an entity or organization engaged in financial business, such as a financial institution that may include but is not limited to: a bank, a securities company, an insurance company, a fund company, an encrypted resource exchange, a financial technology company (such as a payment institution, a third-party payment platform, etc.). At this time, the business system can achieve a reasonable allocation of resources (such as electronic funds, stocks, bonds, and futures) by dispatching social funds to promote economic development. Exemplarily, the business client may be a payment client, and the business server 100 may be a backend server of the payment client. Each terminal device may perform a resource transfer service with the business server 100 through an installed payment client. For example, when a business object (such as business object a) performs a transfer operation to another business object (such as business object b), the business client used by business object a may generate a resource transfer request, send the resource transfer request to the business server 100, and the business server 100 responds to the resource transfer request and transfers the resources of business object a to business object b.

[0077] Although conducting transactions (i.e., resource transfer) through business systems is more convenient, it also makes transaction supervision difficult. For example, some criminals may use the Internet to carry out illegal financial activities. Illegal financial activities usually refer to transactions or activities that are unauthorized or violate laws and regulations, such as resource laundering. The so-called resource laundering refers to the use of a series of complex transactions to make resources obtained through illegal activities look like legal sources.

[0078] Suspicious transactions refer to transactions involving such illegal financial activities. When a financial institution suspects or determines that a suspicious transaction has occurred, it is necessary to report such suspicious transactions to the relevant regulatory authorities in the form of a file to help the regulatory authorities identify illegal financial activities. For example, a database may be deployed in the business server 100, and after each transaction is executed, the corresponding transaction data will be stored in the database. The business server 100 can obtain transaction data from the database, and then identify whether there is a suspicious transaction through the transaction data in the database. When a suspicious transaction is identified, the operator of the suspicious transaction report can be informed, and the operator can identify and analyze the suspicious transaction to generate a suspicious transaction report file. The operator can send the suspicious transaction report file to the relevant regulatory authorities through the business server 100. It is understandable that in some financial institutions, the suspicious transaction report file can also be automatically generated by a machine according to some preset rules, and the present application does not limit the generation method of the suspicious transaction report file.

[0079] Understandably, the focus of suspicious transaction reporting is to conduct screening and analysis of suspicious transactions. The so-called screening and analysis refers to the in-depth analysis and identification of suspicious transactions, so as to draw correct conclusions or judgments. This process usually involves the collection, organization and induction of information, as well as the interpretation and reasoning of data and facts. For example, operators need to investigate the customers involved in suspicious transactions, and conduct manual screening and analysis based on the customer's identity characteristics, transaction characteristics, behavioral characteristics, etc., and write the analysis process and conclusions of suspicious transactions. Suspicious transaction report documents can help regulators more accurately and intuitively understand the characteristics, judgment conclusions, judgment basis and other information of reported suspicious transactions.

[0080] The quality of suspicious transaction reporting (i.e., screening and analyzing suspicious transactions) determines the value of a suspicious transaction report file. In practice, the quality of suspicious transaction reporting is determined by many factors, including the work process, financial data, and human experience. Therefore, it is necessary to establish a comprehensive quantitative evaluation method and comprehensively evaluate the quality of suspicious transaction reporting in combination with the business scenarios involved in the business system. In this way, the quantitative evaluation method can be used to screen out suspicious transaction report files of lower quality and conduct screening and analysis again, and the quality of suspicious transaction report files can be continuously improved.

[0081] See also Figure 2 , Figure 2 1 is a flow chart of a service processing solution provided in an embodiment of the present application. The service processing solution can be executed by the service server 100. The service processing solution generally includes:

[0082] 1. Build a business evaluation model that matches the business scenario:

[0083] In the specific implementation, a multi-level progressive evaluation index is designed in combination with the business scenario, and a multi-level evaluation index system adapted to the business scenario is constructed. The multi-level evaluation index system includes N levels, each level contains at least one group of evaluation indicators, and each group of evaluation indicators contains at least one evaluation indicator; any evaluation indicator in the nth level of the multi-level evaluation index system supports being disassembled into a group of evaluation indicators in the n+1th level, N and n are both positive integers, and n is less than or equal to N. The importance of each evaluation indicator in the multi-level evaluation index system in the layer is compared and scored, and the absolute weight of each evaluation indicator in the multi-level evaluation index system is obtained. The multi-level evaluation index system containing absolute weights is determined as a business evaluation model adapted to the business scenario.

[0084] 2. Use a business evaluation model that is compatible with the business scenario to evaluate suspicious transaction report files.

[0085] In specific implementation, a suspicious transaction report file for a business scenario can be obtained. The suspicious transaction report file is a file obtained by screening and analyzing suspicious transactions in the business scenario. Then, a business evaluation model adapted to the business scenario can be obtained. In this way, the multi-layer evaluation index system in the business evaluation model can be used to determine the quantitative value of the index of the suspicious transaction report file under each evaluation index in the multi-layer evaluation index system. Then, the quantitative value of the index of the suspicious transaction report file under each evaluation index in the multi-layer evaluation index system and the absolute weight of each evaluation index in the multi-layer evaluation index system are used to evaluate the suspicious transaction report file and obtain a comprehensive score (i.e., the evaluation result of the suspicious transaction report file). The evaluation result of the suspicious transaction report file can be used to know the effectiveness of the suspicious transaction report file in screening and analyzing suspicious transactions in the business scenario.

[0086] It can be seen that the embodiments of the present application can construct a scientific and comprehensive multi-layer evaluation index system to conduct qualitative and quantitative analysis of suspicious transaction report files to evaluate the quality and accuracy of suspicious transaction report files, and quantify the effectiveness of suspicious transaction report files in identifying and analyzing suspicious transactions, which is conducive to continuously optimizing and improving the identification and analysis of suspicious transactions, thereby improving the quality of suspicious transaction report files.

[0087] Understandably, Figure 1 The possible system structures of the technical solution of the present application are merely exemplified, and the system structures of the technical solution of the present application are not limited. That is, the technical solution of the present application can also provide other forms of system structures.

[0088] The following describes the specific embodiments of the business processing solution in conjunction with the accompanying drawings. Figure 3 , Figure 3is a flow chart of a business processing method provided by an embodiment of the present application. The business processing method can be Figure 1 The service server 100 in the embodiment is executed, wherein the service processing method mainly includes but is not limited to the following steps S301 to S303:

[0089] S301. Obtain a suspicious transaction report file for a business scenario. The suspicious transaction report file is a file obtained by screening and analyzing suspicious transactions in the business scenario.

[0090] For financial institutions, business scenarios refer to scenarios in which a series of transactions or operational events occur in a specific business context. Financial institutions need to ensure that transactions occurring in business scenarios comply with relevant laws, regulations and regulatory requirements. Therefore, when transactions occur in business scenarios, they can collect transaction data related to the transaction (such as information on both parties to the transaction, the time when the transaction occurred, the amount of resource transfer in the transaction, etc.), and use machine learning, data analysis and other technologies to analyze and mine the collected transaction data to identify potential suspicious transactions. For example, by comparing the amount of resource transfer of the transaction with that of similar transactions in the same period, if the amount of resource transfer is significantly deviated, it may be a suspicious transaction. If the same customer conducts frequent transactions and the transaction frequency is significantly higher than the average level, it may be a suspicious transaction. If the transaction object is a high-risk area or is associated with an organization involved in resource laundering or other illegal financial activities, it may be a suspicious transaction. If the transaction type suddenly changes or involves high-risk business compared with the customer's historical transaction pattern, it may be a suspicious transaction. Furthermore, financial institutions can generate suspicious transaction report files for business scenarios by screening and analyzing suspicious transactions, such as describing in detail the characteristics, background, risk level and other information of suspicious transactions, and proposing corresponding risk assessments and recommended measures. The generated suspicious transaction report files need to be reviewed internally to ensure that the report content is accurate and complete. In the embodiment of the present application, a suspicious transaction report file can be obtained during the internal review stage.

[0091] S302. Acquire a business evaluation model that is compatible with the business scenario. The business evaluation model is provided with a multi-layer evaluation indicator system that is compatible with the business scenario. The multi-layer evaluation indicator system includes N levels, each level includes at least one group of evaluation indicators, and each group of evaluation indicators includes at least one evaluation indicator. Any evaluation indicator in the nth level of the multi-layer evaluation indicator system supports being decomposed into a group of evaluation indicators in the n+1th level. N and n are both positive integers, and n is less than or equal to N.

[0092] The embodiment of the present application supports the step-by-step decomposition of evaluation indicators when constructing a multi-layer evaluation indicator system, that is, any evaluation indicator in the nth layer can be decomposed into a group of evaluation indicators in the n+1th layer, so that each layer of the multi-layer evaluation indicator system can contain at least one group of evaluation indicators, and each group of evaluation indicators can contain at least one evaluation indicator. Evaluation indicators are quantitative or qualitative standards used to measure, evaluate or describe a specific situation, process or entity.

[0093] See also Figure 4 The business process flow chart shown in Figure 4 As shown, obtaining a business evaluation model adapted to the business scenario includes the following steps S31-S34:

[0094] S31. Based on the scenario characteristics of business scenarios, build a multi-layer evaluation indicator system that is compatible with the business scenarios.

[0095] In the design process of the multi-layer evaluation index system, it is necessary to consider the scenario characteristics of the business scenario. The scenario characteristics may include but are not limited to: business characteristics of the business scenario (for example, banks focus on personal customer service, insurance companies focus on risk management, etc.), customer characteristics of the business scenario (for example, some business scenarios are mainly for corporate customers, and some business scenarios are mainly for individual customers), scenario types of business scenarios, types and methods of illegal financial activities involved in business scenarios, and the risk level of the financial institution to which the business scenario belongs. For example, when facing corporate customers, the evaluation indicators may include: whether to analyze business license anomalies, and when facing individual customers, the evaluation indicators may not include: whether to analyze business license anomalies. For another example, the higher the risk level of a financial institution, the more detailed the evaluation indicators will be.

[0096] The embodiment of the present application designs a universal multi-layer evaluation index system, which is applicable to the business scenarios of most financial institutions. Specifically, as shown in Table 1 below, the multi-layer evaluation index system includes a first level, a second level, and a third level; the first level includes the overall index of suspicious transaction reports, the depth index of transaction object analysis, and the depth index of transaction behavior analysis, that is, the first group of evaluation indicators; the overall index of suspicious transaction reports is broken down into the word count index of suspicious transaction reports and the conclusion index of suspicious transaction reports under the second level, that is, the second group of evaluation indicators; the depth index of transaction object analysis is broken down into the information integrity index of transaction objects, the validity index of transaction object information, and the completeness index of transaction object investigation under the second level, that is, the third group of evaluation indicators; the depth index of transaction behavior analysis is broken down into the information integrity index of transaction objects, the validity index of transaction objects, and the completeness index of transaction object investigation under the second level, that is, the third group of evaluation indicators; the depth index of transaction behavior analysis is broken down into the information integrity index of transaction objects, the validity index of transaction objects, and the completeness index of transaction object information under the third level, that is, the third group of evaluation indicators. The indicators are decomposed into the behavior anomaly analysis indicators, transaction anomaly analysis indicators, risk event analysis indicators, related information analysis indicators, and early warning model analysis indicators at the second level, which are the fourth group of evaluation indicators; among them, the transaction object information integrity indicators are decomposed into the name missing indicator, certificate number missing indicator, address missing indicator, business scope missing indicator, operator information missing indicator, beneficiary information missing indicator, and risk rating missing indicator at the third level, which are the fifth group of evaluation indicators; the transaction object information validity indicators are decomposed into the suspicious transaction report and object investigation report consistency analysis missing indicator, business license anomaly analysis missing indicator, legal person missing indicator, etc. at the third level. Abnormal analysis missing indicators, beneficial owner abnormal analysis missing indicators, transaction object information authenticity analysis missing indicators, namely the sixth group of evaluation indicators; transaction object investigation integrity indicators are broken down into object investigation report missing indicators under the third level; behavioral abnormal analysis indicators are broken down into registration behavior abnormal analysis indicators, account opening and closing behavior abnormal analysis indicators, object investigation report feedback abnormal analysis indicators, and operation address abnormal analysis indicators under the third level, namely the seventh group of evaluation indicators; transaction abnormal analysis indicators are broken down into business model abnormal analysis missing indicators, transaction scenario abnormal analysis missing indicators, transaction time abnormal analysis missing indicators, and transaction abnormal analysis missing indicators under the third level. The eighth group of evaluation indicators include the missing indicators of location anomaly analysis, the missing indicators of transaction resource anomaly analysis, the missing indicators of transaction note information anomaly analysis, the missing indicators of transaction mode anomaly analysis, and the missing indicators of counterparty anomaly analysis. The risk event analysis indicators are broken down into the missing indicators of negative feedback analysis and hit list analysis at the third level, which are the ninth group of evaluation indicators. The related information analysis indicators are broken down into the missing indicators of related object analysis, basic information related analysis, and counterparty related analysis at the third level, which are the tenth group of evaluation indicators. The early warning model analysis indicators are broken down into the missing indicators of early warning model analysis at the third level:

[0097] Table 1. Multi-layer evaluation index system:

[0098]

[0099]

[0100]

[0101] For the first level, the overall indicator of suspicious transaction reports is a qualitative indicator for evaluating the overall situation of suspicious transaction report files. The depth indicator of transaction object analysis is a qualitative indicator for evaluating the identity analysis of transaction objects. The depth indicator of transaction behavior analysis is a qualitative indicator for evaluating the behavior analysis of transaction objects.

[0102] For the second level, the word count indicator of suspicious transaction report is a quantitative indicator describing the word count of the suspicious transaction report file. The conclusion indicator of suspicious transaction report is a quantitative indicator describing the conclusion of the suspicious transaction in the suspicious transaction report file. The transaction object information integrity indicator is a qualitative indicator for evaluating the integrity of the identity information of the transaction object. The transaction object information validity indicator is a qualitative indicator for evaluating the validity of the identity information of the transaction object. The transaction object investigation integrity indicator is a qualitative indicator for evaluating the completeness of the due diligence measures of the transaction object. The behavior anomaly analysis indicator is a qualitative indicator for evaluating the analysis of the abnormal behavior of the transaction object. The transaction anomaly analysis indicator is a qualitative indicator for evaluating the analysis of suspicious transactions. The risk event analysis indicator is a qualitative indicator for measuring the risk analysis of the transaction object. The correlation information analysis indicator is a qualitative indicator for measuring the analysis of the correlation information of the transaction object. The early warning model analysis indicator is a qualitative indicator for measuring the analysis of the early warning model. The early warning model is a machine learning model used to identify suspicious transactions, which can analyze the characteristics of suspicious transactions hitting the early warning model.

[0103] For the third level, the name missing indicator is a quantitative indicator for assessing whether the name of the transaction object is included. The certificate number missing indicator is a quantitative indicator for assessing whether the business certificate number is included. The address missing indicator is a quantitative indicator for assessing whether the registered address is included. The business scope missing indicator is a quantitative indicator for assessing whether the business scope is included. The operator information missing indicator is a quantitative indicator for assessing whether the legal person information / operator information is included. The so-called legal person information / operator information refers to the information of the legal representative or person in charge of a company or organization. The beneficiary information missing indicator is a quantitative indicator for assessing whether the beneficiary information is included. The beneficiary information refers to the personal information of a natural person or organization that benefits from a transaction or investment. The risk rating missing indicator is a quantitative indicator for assessing whether the risk rating is included. The so-called risk rating is used to reflect the probability of illegal financial activities of the transaction object (such as the potential degree of resource laundering activities, that is, the level of resource laundering risk). The suspicious transaction report and object investigation report consistency analysis missing indicator is a quantitative indicator for assessing whether the suspicious transaction report file and the transaction object's investigation report are analyzed for consistency. The business license abnormality analysis missing indicator is a quantitative indicator for assessing whether the business license of the transaction object is analyzed for abnormalities. The legal person abnormal analysis missing index is a quantitative index for evaluating whether the legal person conducts abnormal analysis. The legal person may refer to a financial institution. The beneficial owner abnormal analysis missing index is a quantitative index for evaluating whether the beneficial owner conducts abnormal analysis. The transaction object information authenticity analysis missing index is a quantitative index for evaluating whether the transaction object's identity information conducts authenticity analysis. The object investigation report missing index is a quantitative index describing whether the transaction object conducts due diligence. Due diligence refers to the process of conducting a comprehensive review of the transaction object. Through due diligence, an investigation report on the transaction object can be generated. The registration behavior abnormal analysis index is a quantitative index for evaluating whether the analysis of centralized registration behavior abnormality is missing. Centralized registration behavior abnormality refers to the abnormal behavior of business objects registering in large quantities at the same time or at the same place. The account opening and closing behavior abnormal analysis index may include the account opening and closing abnormal analysis index and the account opening abnormal analysis index. The account opening and closing abnormal analysis index is a quantitative index for evaluating whether the analysis of account opening and closing behavior abnormality is missing. The account opening and closing abnormal analysis index is a quantitative index for evaluating whether the analysis of account opening and closing behavior abnormality is missing. The account opening and closing abnormal behavior refers to frequent account opening and closing behaviors, and the account opening abnormal behavior refers to a large number of account opening behaviors. The abnormal analysis index of the feedback of the object investigation report is a quantitative index for evaluating whether the business proof of secondary transaction due diligence is included. The business proof of secondary transaction due diligence refers to the material obtained by further in-depth research and review of the existing preliminary due diligence materials (such as the object investigation report). The abnormal analysis index of the operation address is a quantitative index for evaluating whether the suspicious analysis of the IP address of the transaction object is missing. The abnormal analysis missing index of the business model is a quantitative index for evaluating whether the business model of the transaction object is analyzed abnormally. The abnormal analysis missing index of the transaction scenario is a quantitative index for evaluating whether the transaction scenario of the transaction object is analyzed abnormally.The indicator of missing abnormal analysis of transaction time is a quantitative indicator for evaluating whether abnormal analysis is conducted on the transaction time of the transaction object. The indicator of missing abnormal analysis of transaction location is a quantitative indicator for evaluating whether abnormal analysis is conducted on the transaction location of the transaction object. The indicator of missing abnormal analysis of transaction resources may include the indicator of missing abnormal analysis of resource flow direction and the indicator of missing abnormal analysis of resource quantity. The indicator of missing abnormal analysis of resource flow direction is a quantitative indicator for evaluating whether abnormal analysis is conducted on the resource flow direction (including resource source and resource destination) of the transaction object, and the indicator of missing abnormal analysis of resource quantity is a quantitative indicator for evaluating whether abnormal analysis is conducted on the resource transfer quantity of the transaction. The indicator of missing abnormal analysis of transaction note information is a quantitative indicator for evaluating whether abnormal analysis is conducted on the transaction note information. The indicator of missing abnormal analysis of transaction mode is a quantitative indicator for evaluating whether abnormal analysis is conducted on the transaction mode of the transaction object. The indicator of missing abnormal analysis of counterparty is a quantitative indicator for evaluating whether abnormal analysis is conducted on the counterparty. The missing indicators of negative feedback analysis may include the missing indicators of complaint analysis, public opinion analysis and judicial investigation and freezing analysis. The missing indicators of complaint analysis are quantitative indicators for evaluating whether the complaints of the transaction object are analyzed. The missing indicators of public opinion analysis are quantitative indicators for evaluating whether the negative public opinion of the transaction object is analyzed. The missing indicators of judicial investigation and freezing analysis are quantitative indicators for evaluating whether the transaction object is involved in the analysis of judicial investigation and freezing status. The missing indicators of hit list analysis include the missing indicators of blacklist hit analysis and the missing indicators of business directory hit analysis. The missing indicators of blacklist hit analysis are quantitative indicators for evaluating whether the transaction object is analyzed for hitting the blacklist. The missing indicators of business directory hit analysis are quantitative indicators for evaluating whether the transaction object is analyzed for hitting the industrial and commercial abnormal business directory. The missing indicators of associated object analysis are quantitative indicators for evaluating whether to analyze the historical suspicious situations of associated objects. The so-called associated objects refer to objects that are associated with the transaction object, such as the legal person or beneficial owner of the transaction object. The missing indicators of basic information association analysis are indicators for evaluating whether to analyze the basic information association between different transaction objects, such as the overlap of the legal persons or beneficial owners of different transaction objects. The missing indicator of counterparty association analysis is a quantitative indicator for evaluating whether to analyze whether the counterparty of the transaction object has suspicious transactions with other suspicious objects. The missing indicator of early warning model analysis is a quantitative indicator for evaluating whether to combine early warning models to analyze suspicious transactions.

[0104] Transaction objects refer to business objects involved in transactions. Qualitative indicators are indicators that describe properties, characteristics or attributes, and are usually used to evaluate and express non-digital information. Quantitative indicators are indicators that can be measured and expressed in numbers, which can provide more accurate information and allow for quantitative analysis and comparison. In general, qualitative indicators provide a subjective description of the characteristics of things, while quantitative indicators provide a more objective and accurate way of measurement and analysis.

[0105] Understandably, financial institutions can add, delete, or modify evaluation indicators under this multi-layer evaluation indicator system based on specific business scenarios, the latest methods of illegal financial activities, the risk level of financial institutions, etc., to obtain a suitable multi-layer evaluation indicator system.

[0106] S32. Obtain the relative weight of each evaluation indicator in the multi-layer evaluation indicator system, where the relative weight is used to indicate the importance of the evaluation indicator in the group to which it belongs.

[0107] In one embodiment, the relative importance of each evaluation indicator in the same group in each level of the multi-layer evaluation indicator system can be obtained. Assume that in the embodiment of the present application, any level in the multi-layer evaluation indicator system is represented as the nth level, and any group of evaluation indicators in the nth level is represented as the nth level. q Group, nth q The group evaluation index contains M evaluation indicators, n q and M are positive integers. Any two evaluation indicators among the M evaluation indicators are expressed as: the i-th evaluation indicator and the j-th evaluation indicator, i and j are both positive integers less than or equal to M, and i can be equal to j. Take the relative importance of the i-th evaluation indicator compared to the j-th evaluation indicator as an example for explanation. Specifically, multiple preset importances of the i-th evaluation indicator compared to the j-th evaluation indicator among the M evaluation indicators are obtained, and the multiple preset importances of the i-th evaluation indicator compared to the j-th evaluation indicator are averaged to obtain the relative importance of the i-th evaluation indicator compared to the j-th evaluation indicator. Among them, the preset importance is obtained based on expert experience, and the expert experience is the valuable experience and insights accumulated by experienced and knowledgeable professionals in a professional field in long-term practice and work. In the embodiment of the present application, multiple preset importances are set using the experience of multiple experts, and multiple preset importances are averaged, so that a more comprehensive and comprehensive conclusion can be obtained, which reduces subjective bias and is conducive to improving the accuracy of relative importance. Optionally, the reciprocal of the relative importance of the i-th evaluation indicator compared to the j-th evaluation indicator may be determined as the relative importance of the j-th evaluation indicator compared to the i-th evaluation indicator.

[0108] In specific implementation, each expert may determine the preset importance of the i-th evaluation indicator compared to the j-th evaluation indicator according to the importance comparison scale table shown in Table 2 below:

[0109] Table 2. Importance comparison scale table:

[0110] Scale meaning 1 Indicates that the two evaluation indicators are equally important 3 Indicates that one evaluation metric is slightly more important than another evaluation metric 5 Indicates that one evaluation indicator is significantly more important than another evaluation indicator 7 Indicates that one evaluation metric is more important than another evaluation metric 9 Indicates that one evaluation indicator is extremely important than another evaluation indicator 2,4,6,8 The median of the above adjacent judgments

[0111] Then, according to the relative importance of each evaluation index in the same group, each evaluation index in the multi-layer evaluation index system is subjected to hierarchical analysis to obtain the relative weight of each evaluation index in the multi-layer evaluation index system. q Specifically, based on the nth q The relative importance of the M evaluation indicators included in the group evaluation indicators is used to construct a first judgment matrix. The matrix size of the first judgment matrix is ​​M×M. The element at position (i, j) in the first judgment matrix represents the relative importance of the i-th evaluation indicator compared to the j-th evaluation indicator among the M evaluation indicators. Both i and j are positive integers less than or equal to M. The maximum eigenvalue of the first judgment matrix can be obtained, and the eigenvector corresponding to the maximum eigenvalue can be obtained. The relative weights of the M evaluation indicators are determined based on the eigenvector, where the k-th element in the eigenvector is the relative weight of the k-th evaluation indicator among the M evaluation indicators, and k is a positive integer less than or equal to M.

[0112] In one implementation, the maximum eigenvalue Where A represents the first judgment matrix, W represents the column vector obtained by normalizing the first judgment matrix A by column, and W k represents the kth element of the column vector W, (AW) k represents the dot product of the kth row of the first judgment matrix A and the column vector W. Then, according to the formula: (λ max EA) x = 0 to find the maximum eigenvalue λ max The corresponding eigenvector x, where E represents the identity matrix.

[0113] It can be understood that if the kth evaluation indicator in the nth layer is only decomposed into one evaluation indicator in the n+1th layer, then the relative weight of the evaluation indicator obtained by decomposing the kth evaluation indicator is 1 (ie, 100%).

[0114] In one embodiment, before obtaining the eigenvector corresponding to the maximum eigenvalue, the following steps may be performed: based on the quantity M and the maximum eigenvalue, a consistency check is performed on the first judgment matrix; wherein the consistency check is performed on the first judgment matrix to ensure that the logic between the comparisons in the first judgment matrix is ​​consistent and reasonable. If the first judgment matrix passes the consistency check, the eigenvector corresponding to the maximum eigenvalue is obtained.

[0115] Specifically, the consistency index parameter can be determined based on the number M and the maximum eigenvalue; for example, the number M and the maximum eigenvalue are substituted into the formula: CI = (λ max-M) / (M-1) to obtain the consistency index parameter CI. In addition, the random consistency ratio parameter can be determined based on the matrix size of the first judgment matrix. Specifically, the random consistency ratio parameter RI can be determined according to the matrix size of the first judgment matrix and the RI value table. For example, when the matrix size of the first judgment matrix is ​​2×2, the random consistency ratio parameter RI=0; when the matrix size of the first judgment matrix is ​​3×3, the random consistency ratio parameter RI=0; when the matrix size of the first judgment matrix is ​​4×4, the random consistency ratio parameter RI=0.58; when the matrix size of the first judgment matrix is ​​5×5, the random consistency ratio parameter RI=0.90; when the matrix size of the first judgment matrix is ​​6×6, the random consistency ratio parameter RI=1.12; when the matrix size of the first judgment matrix is ​​7×7, the random consistency ratio parameter RI=1.24; when the matrix size of the first judgment matrix is ​​8×8, the random consistency ratio parameter RI=1.32; when the matrix size of the first judgment matrix is ​​9×9, the random consistency ratio parameter RI=1.41; when the matrix size of the first judgment matrix is ​​10×10, the random consistency ratio parameter RI=1.45. Then, the ratio between the consistency index parameter and the random consistency ratio parameter (i.e., CI / RI) is determined as the target consistency ratio parameter CR. If the target consistency ratio parameter CR satisfies the preset ratio threshold condition, it is determined that the first judgment matrix passes the consistency test. Optionally, the preset ratio threshold condition includes a preset ratio threshold, which can be 0.1. When the target consistency ratio parameter CR is less than the preset ratio threshold, it is determined that the first judgment matrix passes the consistency test. When the target consistency ratio parameter CR is greater than or equal to the preset ratio threshold, it is determined that the first judgment matrix fails the consistency test. In addition, when the random consistency ratio parameter RI=0, it can be determined that the first judgment matrix passes the consistency test.

[0116] For example, the following Tables 3 to 12 are judgment matrices determined for each group in the multi-layer evaluation index system shown in Table 1 above in the embodiment of the present application:

[0117] Table 3. Judgment matrix of the first group of evaluation indicators:

[0118]

[0119]

[0120] Table 4. Judgment matrix of the second group of evaluation indicators:

[0121] Overall indicators of suspicious transaction reports Word count indicator for suspicious transaction reports Suspicious transaction report conclusion indicators Word count indicator for suspicious transaction reports 1 0.49 Suspicious transaction report conclusion indicators 2.05 1

[0122] Table 5. Judgment matrix of the third group of evaluation indicators:

[0123]

[0124] Table 6. Judgment matrix of the fourth group of evaluation indicators:

[0125]

[0126] Table 7. Judgment matrix of the fifth group of evaluation indicators:

[0127]

[0128]

[0129] Table 8. Judgment matrix of the sixth group of evaluation indicators:

[0130]

[0131]

[0132] Table 9. Judgment matrix of the seventh group of evaluation indicators:

[0133]

[0134] Table 10. Judgment matrix of the eighth group of evaluation indicators:

[0135]

[0136]

[0137] Table 11. Judgment matrix of the ninth group of evaluation indicators:

[0138]

[0139]

[0140] Table 12. Judgment matrix of the tenth group of evaluation indicators:

[0141]

[0142] Table 13 below shows the results of consistency testing for the first level of the multi-layer evaluation index system shown in Table 1:

[0143] Table 13. Consistency test results corresponding to the first level:

[0144]

[0145] Table 14 below shows the results of consistency testing for the second level of the multi-layer evaluation index system shown in Table 1:

[0146] Table 14. Consistency test results corresponding to the second level:

[0147]

[0148]

[0149] S33. Based on the relative weight of each evaluation indicator in the multi-layer evaluation indicator system, an absolute weight is set for each evaluation indicator in the multi-layer evaluation indicator system; the absolute weight is used to indicate the importance of the evaluation indicator in the corresponding level.

[0150] Specifically, after obtaining the relative weights of each evaluation indicator in the multi-layer evaluation indicator system, the recursive calculation method can be used to calculate the absolute weights of indicators at different levels in the current level. Assume that any level in the multi-layer evaluation indicator system is represented as the nth level, and any evaluation indicator in the nth level is represented as evaluation indicator P. ① If n is 1, then based on the relative weights of each evaluation indicator in the multi-layer evaluation indicator system, an absolute weight is set for each evaluation indicator in the multi-layer evaluation indicator system, including: setting the relative weight of the evaluation indicator P of the first level to the absolute weight of the evaluation indicator P. ② If n is greater than 1, then based on the relative weight of each evaluation indicator in the multi-layer evaluation indicator system, an absolute weight is set for each evaluation indicator in the multi-layer evaluation indicator system, including: obtaining the disassembly path of the evaluation indicator P of the nth layer, performing weight recursion processing according to the relative weight of each evaluation indicator in the disassembly path, and obtaining the absolute weight of the evaluation indicator P; wherein the evaluation indicator P of the nth layer is obtained by disassembling the evaluation indicator Q of the first layer layer by layer, and the disassembly path is used to record the corresponding evaluation indicators of each layer obtained by disassembling in the process of disassembling from the evaluation indicator Q of the first layer to the evaluation indicator P of the nth layer layer by layer, and P and Q are both positive integers. Among them, the weight recursion processing refers to multiplying the relative weights of each evaluation indicator in the disassembly path, for example, the absolute weight of the name missing indicator = the relative weight of the transaction object analysis depth indicator × the relative weight of the transaction object information integrity indicator × the relative weight of the name missing indicator.

[0151] Exemplarily, the relative weight table corresponding to the multi-layer evaluation index system shown in Table 1 is the following Table 15:

[0152] Table 15. Relative weights corresponding to the multi-layer evaluation index system:

[0153]

[0154]

[0155]

[0156]

[0157] Then the absolute weight table corresponding to the multi-layer evaluation index system shown in Table 1 is the following Table 16:

[0158] Table 16. Absolute weight table corresponding to the multi-layer evaluation index system:

[0159]

[0160]

[0161]

[0162]

[0163] S34. Determine a multi-layer evaluation index system including absolute weights as a business evaluation model that is compatible with the business scenario.

[0164] S303. Use the multi-layer evaluation index system in the business evaluation model to evaluate the suspicious transaction report file to obtain an evaluation result of the suspicious transaction report file, which is used to characterize the effectiveness of the suspicious transaction report file in identifying and analyzing suspicious transactions in business scenarios.

[0165] The business evaluation model includes the absolute weight of each evaluation indicator in the multi-layer evaluation indicator system. In one implementation, the multi-layer evaluation indicator system in the business evaluation model is used to evaluate the suspicious transaction report file to obtain the evaluation result of the suspicious transaction report file, including: obtaining the indicator quantification value of the suspicious transaction report file under each evaluation indicator in the multi-layer evaluation indicator system. Among them, the indicator quantification value is a numerical representation obtained by quantitatively analyzing the suspicious transaction report file under the evaluation indicator. For example, if the suspicious transaction report file contains the name of the transaction object, then the indicator quantification value of the suspicious transaction report file under the name missing indicator can be 0. If the suspicious transaction report file does not contain the name of the transaction object, then the indicator quantification value of the suspicious transaction report file under the name missing indicator can be 1.

[0166] Furthermore, the evaluation score of the suspicious transaction report file can be generated based on the index quantification value of the suspicious transaction report file under each evaluation index in the multi-layer evaluation index system and the absolute weight of each evaluation index in the multi-layer evaluation index system. In one implementation, the index quantification value of the suspicious transaction report file under each evaluation index in the first level of the multi-layer evaluation index system and each evaluation index in the first level of the multi-layer evaluation index system can be weighted and summed to obtain the evaluation score of the suspicious transaction report file. In another implementation, the index quantification value of the suspicious transaction report file under each evaluation index in the second level of the multi-layer evaluation index system and each evaluation index in the second level of the multi-layer evaluation index system can be weighted and summed to obtain the evaluation score of the suspicious transaction report file. The index quantification values ​​of these two methods are all quantification values ​​under qualitative indicators, so the evaluation scores obtained have a certain degree of subjectivity. In the embodiment of the present application, the absolute weight of the target evaluation index in the multi-layer evaluation index system and the index quantification value of the suspicious transaction report file under the target evaluation index can be weighted and summed to obtain the evaluation score of the suspicious transaction report file; the target evaluation index can be one or more, and the target evaluation index is the evaluation index that has not been disassembled in the multi-layer evaluation index system, that is, the target evaluation index is the quantitative index in the multi-layer evaluation index system. In the process of weighted summation, each index quantification value is multiplied by the absolute weight of the evaluation index to which it belongs, and all the obtained results are added.

[0167] Finally, based on the evaluation score of the suspicious transaction report file and the preset total effectiveness score, the effectiveness score of the suspicious transaction report can be generated. For example, the effectiveness score of the suspicious transaction report is the difference between the preset total effectiveness score and the evaluation score of the suspicious transaction report file. The effectiveness score of the suspicious transaction report is determined as the evaluation result of the suspicious transaction report file.

[0168] In addition, assuming that any level in the multi-layer evaluation indicator system is represented as the nth level, and any evaluation indicator in the nth level is represented as evaluation indicator P, where P is a positive integer. Then, the multi-layer evaluation indicator system in the business evaluation model is used to evaluate the suspicious transaction report file to obtain the evaluation result of the suspicious transaction report file, which may include: weighting the indicator quantification value of the suspicious transaction report file under the evaluation indicator P of the nth level with the absolute weight of the evaluation indicator P to obtain the evaluation score of the suspicious transaction report file under the evaluation indicator P; if the evaluation score of the suspicious transaction report file under the evaluation indicator P does not meet the preset score threshold condition, then generating report supplementary prompt information, the report supplementary prompt information is used to prompt the addition of report content for the identification and analysis of suspicious transactions in the business scenario under the evaluation indicator P in the suspicious transaction report file; and determining the report supplementary prompt information as the evaluation result of the suspicious transaction report file. The preset score threshold condition is to measure whether the quantitative value of the indicator under the evaluation indicator P at the nth level of the suspicious transaction report file reaches the preset score threshold. If the quantitative value of this indicator is larger, the effectiveness of the suspicious transaction report file in identifying and analyzing suspicious transactions tends to be larger. If the quantitative value of the indicator under the evaluation indicator P at the nth level of the suspicious transaction report file is less than the preset score threshold, it is determined that it does not meet the preset score threshold condition. Conversely, if the quantitative value of this indicator is larger, the effectiveness of the suspicious transaction report file in identifying and analyzing suspicious transactions tends to be smaller. If the quantitative value of the indicator under the evaluation indicator P at the nth level of the suspicious transaction report file is greater than the preset score threshold, it is determined that it does not meet the preset score threshold condition; for example, when the quantitative value of the indicator under the name missing indicator of the suspicious transaction report file is 1, it can be determined that the quantitative value of the indicator under the name missing indicator of the suspicious transaction report file does not meet the preset score threshold condition.

[0169] For example, see Figure 5 The architecture diagram of the business processing solution shown in FIG. Figure 5 As shown in the figure, after the business evaluation model is established based on the general multi-layer evaluation index system, 100 suspicious transaction report files of third-party payment institutions are obtained as sample data to input into the business evaluation model. For each suspicious transaction report file, the business evaluation model obtains the evaluation scores of the overall situation, the identity analysis of the transaction object, and the behavior analysis of the transaction object. By summing the evaluation scores of the three dimensions and calculating the difference between the preset effectiveness total score (such as 100), the effectiveness score of the suspicious transaction report file is obtained, and the evaluation score of the suspicious transaction report file under each evaluation index can be generated. Figure 6The effectiveness score distribution diagram shown in the figure shows that the effectiveness of the suspicious transaction reporting work of third-party payment institutions is generally good. The effectiveness scores of all suspicious transaction report files are distributed above 93 points, and the effectiveness scores of more than 70% of the suspicious transaction report files are above 98 points. See also Figure 7 From the single indicator analysis diagram shown, it can be seen that (1) in terms of the overall suspicious transaction report, the word count of 3 suspicious transaction report files did not meet the word count requirement (within 200-300 words), indicating that the overall analysis content of these three suspicious transaction report files was insufficient. (2) In terms of the identity analysis of the transaction object, 2 suspicious transaction report files lacked analysis of the beneficiary's identity information. (3) In terms of the behavior analysis of the transaction object, the main problem was insufficient analysis depth. For example, 6 suspicious transaction report files had abnormal centralized registration behavior that was not analyzed, 1 suspicious transaction report file had abnormal account opening behavior that was not analyzed, and 3 suspicious transaction report files did not conduct due diligence on the transaction object. In addition, 7 suspicious transaction report files did not analyze the transaction counterparty, 11 suspicious transaction report files involved judicial investigation and freezing that were not analyzed, and 3 suspicious transaction report files involved abnormal industrial and commercial business lists that were not analyzed, indicating that external risk information was not collected in a timely and effective manner during the screening and analysis process. In the analysis of related information, 1 suspicious transaction report file did not analyze the suspicious circumstances reported by the related object in the past.

[0170] Based on the above evaluation results, third-party payment institutions can clarify the focus and direction of improvement in suspicious transaction reporting work, and take the following measures: First, establish an irregular suspicious transaction training mechanism, use the effectiveness of suspicious transaction reporting work as the content of suspicious transaction analysis training, focus on analyzing evaluation indicators with low evaluation scores, and continuously improve the ability of operators to identify and analyze; second, strengthen research on illegal financial activities, and continuously adjust the evaluation indicators in the multi-layer evaluation indicator system to ensure the quality of the multi-layer evaluation indicator system; third, strengthen the systematic construction of business evaluation models, such as combining business evaluation models with quality inspection links in suspicious operation processes, and embedding business evaluation models in the suspicious transaction reporting process of suspicious operation processes, which can not only improve the coverage of quality inspection, but also ensure the consistency of quality inspection caliber and avoid operational risks of manual sampling.

[0171] Suspicious transaction reporting is an important part of risk management for financial institutions, and the core of suspicious transaction reporting is the identification of suspicious transactions. Through the quantitative evaluation method proposed in this application, the effectiveness of the identification and analysis of suspicious transactions can be quantified, which improves the efficiency and compliance of the effectiveness evaluation, and can guide financial institutions to optimize the suspicious transaction reporting work, so that the suspicious transaction report files can be more comprehensive and effective; in addition, the embodiment of the present application establishes a scientific and complete multi-layer evaluation indicator system for the effectiveness of suspicious transaction reporting, and as a universal system, it is applicable to various suspicious transaction report files.

[0172] The collection and processing of relevant data in the embodiments of this application should be strictly in accordance with the requirements of relevant laws and regulations. The acquisition of personal information requires the knowledge or consent of the individual subject (or the legal basis for obtaining the information), and the subsequent use and processing of data shall be carried out within the scope of authorization of laws and regulations and the subject of personal information. For example, when the embodiments of this application are applied to specific products or technologies, such as when collecting the identity information of a business object, it is necessary to obtain the permission or consent of the first business object, and the collection, use and processing of relevant data shall comply with the relevant laws, regulations and standards of the relevant region.

[0173] The method of the embodiment of the present application is described in detail above. In order to facilitate better implementation of the above scheme of the embodiment of the present application, the device of the embodiment of the present application is provided below accordingly.

[0174] Figure 8 is a schematic diagram of a business processing device provided in an embodiment of the present application; the business processing device 800 can be used to execute Figure 3 Some or all of the steps in the method embodiment shown. Figure 8 The business processing device 800 includes the following units: an acquisition unit 801 and a processing unit 802.

[0175] An acquisition unit 801 is used to acquire a suspicious transaction report file for a business scenario, where the suspicious transaction report file is a file obtained by screening and analyzing suspicious transactions in the business scenario;

[0176] The acquisition unit 801 is further used to acquire a business evaluation model adapted to the business scenario, wherein a multi-layer evaluation indicator system adapted to the business scenario is provided in the business evaluation model, wherein the multi-layer evaluation indicator system includes N levels, each level includes at least one group of evaluation indicators, and each group of evaluation indicators includes at least one evaluation indicator; any evaluation indicator in the nth level of the multi-layer evaluation indicator system supports being disassembled into a group of evaluation indicators in the n+1th level, wherein N and n are both positive integers, and n is less than or equal to N;

[0177] The processing unit 802 is used to use the multi-layer evaluation index system in the business evaluation model to evaluate the suspicious transaction report file and obtain an evaluation result of the suspicious transaction report file. The evaluation result is used to characterize the effectiveness of the suspicious transaction report file in identifying and analyzing suspicious transactions in business scenarios.

[0178] In one embodiment, when the acquisition unit 801 is used to acquire a business evaluation model adapted to a business scenario, the following steps are specifically performed:

[0179] Based on the scenario characteristics of business scenarios, build a multi-layer evaluation indicator system that is compatible with business scenarios;

[0180] Obtain the relative weight of each evaluation indicator in the multi-layer evaluation indicator system. The relative weight is used to indicate the importance of the evaluation indicator in the group to which it belongs.

[0181] Based on the relative weight of each evaluation indicator in the multi-layer evaluation indicator system, an absolute weight is set for each evaluation indicator in the multi-layer evaluation indicator system; the absolute weight is used to indicate the importance of the evaluation indicator in the corresponding level;

[0182] A multi-layer evaluation index system containing absolute weights is determined as a business evaluation model that is compatible with business scenarios.

[0183] In one embodiment, when the acquisition unit 801 is used to acquire the relative weight of each evaluation index in the multi-layer evaluation index system, the following steps are specifically performed:

[0184] Obtain the relative importance of each evaluation index in the same group at each level of the multi-level evaluation index system;

[0185] According to the relative importance of each evaluation index in the same group, hierarchical analysis is performed on each evaluation index in the multi-layer evaluation index system to obtain the relative weight of each evaluation index in the multi-layer evaluation index system.

[0186] In one embodiment, any level in the multi-layer evaluation index system is represented as the nth level, and any group of evaluation indicators in the nth level is represented as the nth level. q Group, nth q The group evaluation index contains M evaluation indicators, n q and M are positive integers;

[0187] The processing unit 802 is used to perform hierarchical analysis on each evaluation indicator in the multi-layer evaluation indicator system according to the relative importance between each evaluation indicator in the same group, and to obtain the relative weight of each evaluation indicator in the multi-layer evaluation indicator system, and specifically execute the following steps:

[0188] Based on the nth qThe relative importance of the M evaluation indicators included in the group evaluation indicators is used to construct a first judgment matrix. The matrix size of the first judgment matrix is ​​M×M. The element at position (i, j) in the first judgment matrix represents the relative importance of the i-th evaluation indicator compared to the j-th evaluation indicator among the M evaluation indicators. Both i and j are positive integers less than or equal to M.

[0189] Obtaining the maximum eigenvalue of the first judgment matrix, and obtaining the eigenvector corresponding to the maximum eigenvalue;

[0190] The relative weights of the M evaluation indicators are determined based on the feature vector, wherein the kth element in the feature vector is the relative weight of the kth evaluation indicator among the M evaluation indicators, and k is a positive integer less than or equal to M.

[0191] In one embodiment, before the obtaining unit 801 is used to obtain the eigenvector corresponding to the maximum eigenvalue, the processing unit 802 is further used to perform the following steps:

[0192] Based on the number M and the maximum eigenvalue, the first judgment matrix is ​​checked for consistency;

[0193] If the first judgment matrix passes the consistency check, it triggers the acquisition of the eigenvector corresponding to the maximum eigenvalue.

[0194] In one embodiment, the processing unit 802 is used to perform the following steps when performing consistency check on the first judgment matrix based on the number M and the maximum eigenvalue:

[0195] Determining a consistency index parameter based on the number M and the maximum eigenvalue, and determining a random consistency ratio parameter based on the matrix size of the first judgment matrix;

[0196] The ratio between the consistency index parameter and the random consistency ratio parameter is determined as the target consistency ratio parameter;

[0197] If the target consistency ratio parameter meets the preset ratio threshold condition, it is determined that the first judgment matrix passes the consistency test.

[0198] In one embodiment, any level in the multi-layer evaluation index system is represented as the nth level, and any group of evaluation indicators in the nth level is represented as the nth level. q Group, nth q The group evaluation index contains M evaluation indicators, n q and M are positive integers;

[0199] When the acquisition unit 801 is used to acquire the relative importance between the evaluation indicators in the same group in each level of the multi-level evaluation indicator system, the following steps are specifically performed:

[0200] Obtain multiple preset importances of the i-th evaluation indicator compared to the j-th evaluation indicator among the M evaluation indicators, where the i-th evaluation indicator and the j-th evaluation indicator are any two of the M evaluation indicators under the first evaluation dimension, and i and j are both positive integers less than or equal to M;

[0201] Performing mean processing on multiple preset importances of the i-th evaluation indicator compared to the j-th evaluation indicator to obtain the relative importance of the i-th evaluation indicator compared to the j-th evaluation indicator;

[0202] The inverse of the relative importance of the i-th evaluation indicator to the j-th evaluation indicator is determined as the relative importance of the j-th evaluation indicator to the i-th evaluation indicator.

[0203] In one embodiment, any level in the multi-layer evaluation index system is represented as the nth level, and any evaluation index in the nth level is represented as the evaluation index P;

[0204] If n is 1, the processing unit 802 is used to set the absolute weight for each evaluation indicator in the multi-layer evaluation indicator system based on the relative weight of each evaluation indicator in the multi-layer evaluation indicator system, and specifically performs the following steps: setting the relative weight of the evaluation indicator P of the first level to the absolute weight of the evaluation indicator P;

[0205] If n is greater than 1, the processing unit 802 is used to set absolute weights for each evaluation indicator in the multi-layer evaluation indicator system based on the relative weights of each evaluation indicator in the multi-layer evaluation indicator system, and specifically performs the following steps: obtain the decomposition path of the evaluation indicator P of the n-th level, and perform weight recursive processing according to the relative weights of each evaluation indicator in the decomposition path to obtain the absolute weight of the evaluation indicator P; wherein, the evaluation indicator P of the n-th level is obtained by decomposing the evaluation indicator Q of the first level level level by level, and the decomposition path is used to record the corresponding evaluation indicators of each level obtained through the decomposition process from the evaluation indicator Q of the first level to the evaluation indicator P of the n-th level, and P and Q are both positive integers.

[0206] In one embodiment, the multi-layer evaluation index system further includes the absolute weight of each evaluation index in the multi-layer evaluation index system; the processing unit 802 is used to use the multi-layer evaluation index system in the business evaluation model to evaluate the suspicious transaction report file, and when the evaluation result of the suspicious transaction report file is obtained, the following steps are specifically performed:

[0207] Obtain the quantitative value of each evaluation indicator in the multi-layer evaluation indicator system for the suspicious transaction report file;

[0208] Generate an evaluation score for the suspicious transaction report file based on the quantitative value of the indicator under each evaluation indicator in the multi-layer evaluation indicator system and the absolute weight of each evaluation indicator in the multi-layer evaluation indicator system;

[0209] Generate the effectiveness score of the suspicious transaction report based on the evaluation score of the suspicious transaction report file and the preset total effectiveness score;

[0210] The effectiveness score of the suspicious transaction report is determined as the evaluation result of the suspicious transaction report file.

[0211] In one embodiment, any level in the multi-layer evaluation index system is represented as the nth level, and any evaluation index in the nth level is represented as evaluation index P, where P is a positive integer. The processing unit 802 is further configured to perform the following steps:

[0212] The index quantified value of the suspicious transaction report file under the evaluation index P at the nth level is weighted with the absolute weight of the evaluation index P to obtain the evaluation score of the suspicious transaction report file under the evaluation index P;

[0213] If the evaluation score of the suspicious transaction report file under the evaluation index P does not meet the preset score threshold condition, a report supplement prompt information is generated, and the report supplement prompt information is used to prompt the suspicious transaction report file to add report content for screening and analyzing suspicious transactions in the business scenario under the evaluation index P;

[0214] The supplementary prompt information of the report shall be determined as the evaluation result of the suspicious transaction report file.

[0215] In one embodiment, the processing unit 802 is used to generate the evaluation score of the suspicious transaction report file based on the indicator quantification value of each evaluation indicator in the multi-layer evaluation indicator system and the absolute weight of each evaluation indicator in the multi-layer evaluation indicator system, and specifically perform the following steps:

[0216] The absolute weight of the target evaluation index in the multi-layer evaluation index system and the index quantification value of the suspicious transaction report file under the target evaluation index are weighted and summed to obtain the evaluation score of the suspicious transaction report file; the target evaluation index is the evaluation index that has not been disassembled in the multi-layer evaluation index system.

[0217] In one embodiment, the multi-layer evaluation index system includes a first level, a second level, and a third level; the first level includes overall indicators of suspicious transaction reports, transaction object analysis depth indicators, and transaction behavior analysis depth indicators;

[0218] The overall indicator of suspicious transaction reports is broken down into the word count indicator of suspicious transaction reports and the conclusion indicator of suspicious transaction reports at the second level; the depth indicator of transaction object analysis is broken down into the information integrity indicator of transaction object, the information validity indicator of transaction object, and the completeness indicator of transaction object investigation at the second level; the depth indicator of transaction behavior analysis is broken down into the behavior anomaly analysis indicator, transaction anomaly analysis indicator, risk event analysis indicator, related information analysis indicator, and early warning model analysis indicator at the second level;

[0219] Among them, the transaction object information integrity index is broken down into the name missing index, certificate number missing index, address missing index, business scope missing index, operator information missing index, beneficiary information missing index, and risk rating missing index at the third level; the transaction object information validity index is broken down into the suspicious transaction report and object investigation report consistency analysis missing index, business license anomaly analysis missing index, legal person anomaly analysis missing index, beneficial owner anomaly analysis missing index, and transaction object information authenticity analysis missing index at the third level; the transaction object investigation integrity index is broken down into the object investigation report missing index at the third level;

[0220] Among them, the behavior anomaly analysis indicators are broken down into the registration behavior anomaly analysis indicators, account opening and closing behavior anomaly analysis indicators, object investigation report feedback anomaly analysis indicators, and operation address anomaly analysis indicators at the third level; the transaction anomaly analysis indicators are broken down into the business model anomaly analysis missing indicators, transaction scenario anomaly analysis missing indicators, transaction time anomaly analysis missing indicators, transaction location anomaly analysis missing indicators, transaction resource anomaly analysis missing indicators, transaction note information anomaly analysis missing indicators, transaction model anomaly analysis missing indicators, and counterparty anomaly analysis missing indicators at the third level; the risk event analysis indicators are broken down into the negative feedback analysis missing indicators and the hit list analysis missing indicators at the third level; the related information analysis indicators are broken down into the related object analysis missing indicators, the basic information related analysis missing indicators, and the counterparty related analysis missing indicators at the third level; the early warning model analysis indicators are broken down into the early warning model analysis missing indicators at the third level.

[0221] It should be noted that Figure 8The various units in the business processing device shown can be individually or completely combined into one or several other units to form, or one (some) of the units can be further divided into multiple functionally smaller units to form, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present application. The above-mentioned units are divided based on logical functions. In practical applications, the function of one unit can also be implemented by multiple units, or the functions of multiple units can be implemented by one unit. In other embodiments of the present application, the business processing device can also include other units. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented by the collaboration of multiple units. According to another embodiment of the present application, it can be executed by running on a general computing device such as a computer that includes processing elements and storage elements such as a central processing unit (CPU), a random access storage medium (RAM), and a read-only storage medium (ROM). Figure 3 A computer program (including program code) for each step involved in the corresponding method shown in FIG. Figure 8 The business processing device shown in the embodiment of the present application is implemented based on the business processing method. The computer program can be recorded on a computer-readable recording medium, for example, and loaded into the above-mentioned computing device through the computer-readable recording medium and run therein.

[0222] It can be seen that the embodiments of the present application can use a business evaluation model that is adapted to the business scenario to quantitatively evaluate the effectiveness of suspicious transaction reporting work (i.e., the work of identifying and analyzing suspicious transactions in business scenarios). This objective evaluation based on data support facilitates a better understanding and improvement of suspicious transaction report files, and is conducive to the formation of a high-quality suspicious transaction report file.

[0223] Fig. 9 is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. Fig. 9, the computer device 900 includes a processor 901, a communication interface 902 and a computer-readable storage medium 903. The processor 901, the communication interface 902 and the computer-readable storage medium 903 can be connected via a bus or other means. The communication interface 902 is used to receive and send data. The computer-readable storage medium 903 can be stored in the memory of the computer device 900, and the computer-readable storage medium 903 is used to store a computer program, and the computer program includes program instructions. The processor 901 is used to execute the program instructions stored in the computer-readable storage medium 903. The processor 901 (or CPU (Central Processing Unit)) is the computing core and control core of the computer device 900, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding function.

[0224] The embodiment of the present application also provides a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It is understandable that the computer-readable storage medium here can include both built-in storage media in the computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space that stores the processing system of the computer device. In addition, one or more instructions suitable for being loaded and executed by the processor 901 are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory, or a non-volatile memory (non-volatile memory), such as at least one disk storage; optionally, it can also be at least one computer-readable storage medium located away from the aforementioned processor.

[0225] In one embodiment, the computer-readable storage medium stores one or more instructions; the processor 901 loads and executes the one or more instructions stored in the computer-readable storage medium to implement the above Figure 3 Corresponding steps in the corresponding method embodiment; in a specific implementation, one or more instructions in the computer-readable storage medium are loaded by the processor 901 and execute the following steps:

[0226] Obtain suspicious transaction report files for business scenarios. Suspicious transaction report files are files obtained by screening and analyzing suspicious transactions in business scenarios.

[0227] Obtain a business evaluation model adapted to the business scenario, wherein a multi-layer evaluation indicator system adapted to the business scenario is provided in the business evaluation model, wherein the multi-layer evaluation indicator system includes N levels, each level includes at least one group of evaluation indicators, and each group of evaluation indicators includes at least one evaluation indicator; any evaluation indicator in the nth level of the multi-layer evaluation indicator system supports being disassembled into a group of evaluation indicators in the n+1th level, where N and n are both positive integers, and n is less than or equal to N;

[0228] The multi-layer evaluation index system in the business evaluation model is used to evaluate the suspicious transaction report file and obtain the evaluation results of the suspicious transaction report file. The evaluation results are used to characterize the effectiveness of the suspicious transaction report file in identifying and analyzing suspicious transactions in business scenarios.

[0229] In one embodiment, when the processor 901 is used to obtain a business evaluation model adapted to the business scenario, the processor 901 specifically performs the following steps:

[0230] Based on the scenario characteristics of business scenarios, build a multi-layer evaluation indicator system that is compatible with business scenarios;

[0231] Obtain the relative weight of each evaluation indicator in the multi-layer evaluation indicator system. The relative weight is used to indicate the importance of the evaluation indicator in the group to which it belongs.

[0232] Based on the relative weight of each evaluation indicator in the multi-layer evaluation indicator system, an absolute weight is set for each evaluation indicator in the multi-layer evaluation indicator system; the absolute weight is used to indicate the importance of the evaluation indicator in the corresponding level;

[0233] A multi-layer evaluation index system containing absolute weights is determined as a business evaluation model that is compatible with business scenarios.

[0234] In one embodiment, when the processor 901 is used to obtain the relative weight of each evaluation index in the multi-layer evaluation index system, it specifically performs the following steps:

[0235] Obtain the relative importance of each evaluation index in the same group at each level of the multi-level evaluation index system;

[0236] According to the relative importance of each evaluation index in the same group, hierarchical analysis is performed on each evaluation index in the multi-layer evaluation index system to obtain the relative weight of each evaluation index in the multi-layer evaluation index system.

[0237] In one embodiment, any level in the multi-layer evaluation index system is represented as the nth level, and any group of evaluation indicators in the nth level is represented as the nth level. q Group, nth q The group evaluation index contains M evaluation indicators, n q and M are positive integers;

[0238] The processor 901 is used to perform hierarchical analysis on each evaluation indicator in the multi-layer evaluation indicator system according to the relative importance between each evaluation indicator in the same group, and when obtaining the relative weight of each evaluation indicator in the multi-layer evaluation indicator system, specifically execute the following steps:

[0239] Based on the nth q The relative importance of the M evaluation indicators included in the group evaluation indicators is used to construct a first judgment matrix. The matrix size of the first judgment matrix is ​​M×M. The element at position (i, j) in the first judgment matrix represents the relative importance of the i-th evaluation indicator compared to the j-th evaluation indicator among the M evaluation indicators. Both i and j are positive integers less than or equal to M.

[0240] Obtaining the maximum eigenvalue of the first judgment matrix, and obtaining the eigenvector corresponding to the maximum eigenvalue;

[0241] The relative weights of the M evaluation indicators are determined based on the feature vector, wherein the kth element in the feature vector is the relative weight of the kth evaluation indicator among the M evaluation indicators, and k is a positive integer less than or equal to M.

[0242] In one embodiment, before the processor 901 is used to obtain the eigenvector corresponding to the maximum eigenvalue, the processor 901 is further used to perform the following steps:

[0243] Based on the number M and the maximum eigenvalue, the first judgment matrix is ​​checked for consistency;

[0244] If the first judgment matrix passes the consistency check, it triggers the acquisition of the eigenvector corresponding to the maximum eigenvalue.

[0245] In one embodiment, the processor 901 is used to perform the following steps when performing consistency check on the first judgment matrix based on the quantity M and the maximum eigenvalue:

[0246] Determining a consistency index parameter based on the number M and the maximum eigenvalue, and determining a random consistency ratio parameter based on the matrix size of the first judgment matrix;

[0247] The ratio between the consistency index parameter and the random consistency ratio parameter is determined as the target consistency ratio parameter;

[0248] If the target consistency ratio parameter meets the preset ratio threshold condition, it is determined that the first judgment matrix passes the consistency test.

[0249] In one embodiment, any level in the multi-layer evaluation index system is represented as the nth level, and any group of evaluation indicators in the nth level is represented as the nth level. q Group, nth qThe group evaluation index contains M evaluation indicators, n q and M are positive integers;

[0250] When the processor 901 is used to obtain the relative importance between the evaluation indicators in the same group in each level of the multi-level evaluation indicator system, it specifically performs the following steps:

[0251] Obtain multiple preset importances of the i-th evaluation indicator compared to the j-th evaluation indicator among the M evaluation indicators, where the i-th evaluation indicator and the j-th evaluation indicator are any two of the M evaluation indicators under the first evaluation dimension, and i and j are both positive integers less than or equal to M;

[0252] Performing mean processing on multiple preset importances of the i-th evaluation indicator compared to the j-th evaluation indicator to obtain the relative importance of the i-th evaluation indicator compared to the j-th evaluation indicator;

[0253] The inverse of the relative importance of the i-th evaluation indicator to the j-th evaluation indicator is determined as the relative importance of the j-th evaluation indicator to the i-th evaluation indicator.

[0254] In one embodiment, any level in the multi-layer evaluation index system is represented as the nth level, and any evaluation index in the nth level is represented as the evaluation index P;

[0255] If n is 1, the processor 901 is used to set the absolute weight for each evaluation indicator in the multi-layer evaluation indicator system based on the relative weight of each evaluation indicator in the multi-layer evaluation indicator system, and specifically perform the following steps: set the relative weight of the evaluation indicator P of the first level to the absolute weight of the evaluation indicator P;

[0256] If n is greater than 1, the processor 901 is used to set absolute weights for each evaluation indicator in the multi-layer evaluation indicator system based on the relative weights of each evaluation indicator in the multi-layer evaluation indicator system, and specifically executes the following steps: obtain the disassembly path of the evaluation indicator P of the nth level, and perform weight recursive processing according to the relative weights of each evaluation indicator in the disassembly path to obtain the absolute weight of the evaluation indicator P; wherein, the evaluation indicator P of the nth level is obtained by disassembling the evaluation indicator Q of the first level level level by level, and the disassembly path is used to record the corresponding evaluation indicators of each level obtained through the disassembly process from the evaluation indicator Q of the first level to the evaluation indicator P of the nth level, and P and Q are both positive integers.

[0257] In one embodiment, the multi-layer evaluation index system further includes an absolute weight of each evaluation index in the multi-layer evaluation index system; the processor 901 is used to use the multi-layer evaluation index system in the business evaluation model to evaluate the suspicious transaction report file, and when obtaining the evaluation result of the suspicious transaction report file, specifically execute the following steps:

[0258] Obtain the quantitative value of each evaluation indicator in the multi-layer evaluation indicator system for the suspicious transaction report file;

[0259] Generate an evaluation score for the suspicious transaction report file based on the quantitative value of the indicator under each evaluation indicator in the multi-layer evaluation indicator system and the absolute weight of each evaluation indicator in the multi-layer evaluation indicator system;

[0260] Generate the effectiveness score of the suspicious transaction report based on the evaluation score of the suspicious transaction report file and the preset total effectiveness score;

[0261] The effectiveness score of the suspicious transaction report is determined as the evaluation result of the suspicious transaction report file.

[0262] In one embodiment, any level in the multi-layer evaluation index system is represented as the nth level, and any evaluation index in the nth level is represented as evaluation index P, where P is a positive integer. The processor 901 is further configured to perform the following steps:

[0263] The index quantified value of the suspicious transaction report file under the evaluation index P at the nth level is weighted with the absolute weight of the evaluation index P to obtain the evaluation score of the suspicious transaction report file under the evaluation index P;

[0264] If the evaluation score of the suspicious transaction report file under the evaluation index P does not meet the preset score threshold condition, a report supplement prompt information is generated, and the report supplement prompt information is used to prompt the suspicious transaction report file to add report content for screening and analyzing suspicious transactions in the business scenario under the evaluation index P;

[0265] The supplementary prompt information of the report shall be determined as the evaluation result of the suspicious transaction report file.

[0266] In one embodiment, the processor 901 is used to generate an evaluation score for a suspicious transaction report file based on the indicator quantification value of the suspicious transaction report file under each evaluation indicator in the multi-layer evaluation indicator system and the absolute weight of each evaluation indicator in the multi-layer evaluation indicator system, and specifically perform the following steps:

[0267] The absolute weight of the target evaluation index in the multi-layer evaluation index system and the index quantification value of the suspicious transaction report file under the target evaluation index are weighted and summed to obtain the evaluation score of the suspicious transaction report file; the target evaluation index is the evaluation index that has not been disassembled in the multi-layer evaluation index system.

[0268] In one embodiment, the multi-layer evaluation index system includes a first level, a second level, and a third level; the first level includes overall indicators of suspicious transaction reports, transaction object analysis depth indicators, and transaction behavior analysis depth indicators;

[0269] The overall indicator of suspicious transaction reports is broken down into the word count indicator of suspicious transaction reports and the conclusion indicator of suspicious transaction reports at the second level; the depth indicator of transaction object analysis is broken down into the information integrity indicator of transaction object, the information validity indicator of transaction object, and the completeness indicator of transaction object investigation at the second level; the depth indicator of transaction behavior analysis is broken down into the behavior anomaly analysis indicator, transaction anomaly analysis indicator, risk event analysis indicator, related information analysis indicator, and early warning model analysis indicator at the second level;

[0270] Among them, the transaction object information integrity index is broken down into the name missing index, certificate number missing index, address missing index, business scope missing index, operator information missing index, beneficiary information missing index, and risk rating missing index at the third level; the transaction object information validity index is broken down into the suspicious transaction report and object investigation report consistency analysis missing index, business license anomaly analysis missing index, legal person anomaly analysis missing index, beneficial owner anomaly analysis missing index, and transaction object information authenticity analysis missing index at the third level; the transaction object investigation integrity index is broken down into the object investigation report missing index at the third level;

[0271] Among them, the behavior anomaly analysis indicators are broken down into the registration behavior anomaly analysis indicators, account opening and closing behavior anomaly analysis indicators, object investigation report feedback anomaly analysis indicators, and operation address anomaly analysis indicators at the third level; the transaction anomaly analysis indicators are broken down into the business model anomaly analysis missing indicators, transaction scenario anomaly analysis missing indicators, transaction time anomaly analysis missing indicators, transaction location anomaly analysis missing indicators, transaction resource anomaly analysis missing indicators, transaction note information anomaly analysis missing indicators, transaction model anomaly analysis missing indicators, and counterparty anomaly analysis missing indicators at the third level; the risk event analysis indicators are broken down into the negative feedback analysis missing indicators and the hit list analysis missing indicators at the third level; the related information analysis indicators are broken down into the related object analysis missing indicators, the basic information related analysis missing indicators, and the counterparty related analysis missing indicators at the third level; the early warning model analysis indicators are broken down into the early warning model analysis missing indicators at the third level.

[0272] Based on the same inventive concept, the principles and beneficial effects of solving the problems by the computer device 900 provided in the embodiment of the present application are similar to the principles and beneficial effects of solving the problems by the business processing method in the method embodiment of the present application. Please refer to the principles and beneficial effects of the implementation of the method. For the sake of concise description, they will not be repeated here.

[0273] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program with a predetermined function, and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0274] The embodiment of the present application also provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. The processor of the computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the above-mentioned business processing method.

[0275] A person skilled in the art can appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0276] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loading and executing computer program instructions on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instruction can be stored in a computer-readable storage medium or transmitted by a computer-readable storage medium. The computer instruction can be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (for example, coaxial cable, optical fiber, digital line (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data processing device such as a server, a data center, etc. that contains one or more available media integration. Available media can be magnetic media (for example, floppy disk, hard disk, tape), optical media (for example, DVD), or semiconductor media (for example, solid-state drive (Solid State Disk, SSD)) and the like.

[0277] In this application, elements expressed in the singular are intended to mean "one or more" rather than "one and only one", unless otherwise specified. In this application, "at least one" is intended to mean "one or more", and "more than one" is intended to mean "two or more", unless otherwise specified.

[0278] The above description is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technical object familiar with the technical field can easily think of changes or replacements within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A business processing method, It is characterized in that The method comprises: Obtaining a suspicious transaction report file for a business scenario, wherein the suspicious transaction report file is a file obtained by screening and analyzing suspicious transactions in the business scenario; Acquire a business evaluation model adapted to the business scenario, wherein the business evaluation model is provided with a multi-layer evaluation index system adapted to the business scenario, wherein the multi-layer evaluation index system includes N levels, each level includes at least one group of evaluation indicators, and each group of evaluation indicators includes at least one evaluation indicator; any evaluation indicator in the nth level of the multi-layer evaluation index system supports being disassembled into a group of evaluation indicators in the n+1th level, where N and n are both positive integers, and n is less than or equal to N; The multi-layer evaluation index system in the business evaluation model is used to evaluate the suspicious transaction report file to obtain an evaluation result of the suspicious transaction report file, and the evaluation result is used to characterize the effectiveness of the suspicious transaction report file in identifying and analyzing suspicious transactions in the business scenario.

2. The method according to claim 1, It is characterized in that The acquiring of a business evaluation model adapted to the business scenario includes: Based on the scenario characteristics of the business scenario, construct the multi-layer evaluation indicator system adapted to the business scenario; Obtaining the relative weight of each evaluation indicator in the multi-layer evaluation indicator system, wherein the relative weight is used to indicate the importance of the evaluation indicator in the group to which it belongs; Based on the relative weight of each evaluation indicator in the multi-layer evaluation indicator system, an absolute weight is set for each evaluation indicator in the multi-layer evaluation indicator system; the absolute weight is used to indicate the importance of the evaluation indicator in the corresponding level; A multi-layer evaluation index system including absolute weights is determined as a business evaluation model adapted to the business scenario.

3. The method according to claim 2, It is characterized in that The obtaining of the relative weight of each evaluation index in the multi-layer evaluation index system includes: Obtaining the relative importance of each evaluation index in the same group at each level of the multi-level evaluation index system; According to the relative importance of each evaluation indicator in the same group, a hierarchical analysis process is performed on each evaluation indicator in the multi-layer evaluation indicator system to obtain a relative weight of each evaluation indicator in the multi-layer evaluation indicator system.

4. The method according to claim 3, It is characterized in that Any level in the multi-layer evaluation index system is represented as the nth level, and any group of evaluation indicators in the nth level is represented as the nth level. q group, the nth q The group evaluation index contains M evaluation indicators, n q and M are positive integers; According to the relative importance of each evaluation indicator in the same group, each evaluation indicator in the multi-layer evaluation indicator system is subjected to hierarchical analysis processing to obtain the relative weight of each evaluation indicator in the multi-layer evaluation indicator system, including: Based on the nth q The relative importance of the M evaluation indicators included in the group evaluation indicators is used to construct a first judgment matrix, where the matrix size of the first judgment matrix is ​​M×M, and the element at the position (i, j) in the first judgment matrix represents the relative importance of the i-th evaluation indicator compared to the j-th evaluation indicator among the M evaluation indicators, and i and j are both positive integers less than or equal to M; Obtaining the maximum eigenvalue of the first judgment matrix, and obtaining the eigenvector corresponding to the maximum eigenvalue; The relative weights of the M evaluation indicators are determined based on the feature vector, wherein the kth element in the feature vector is the relative weight of the kth evaluation indicator among the M evaluation indicators, and k is a positive integer less than or equal to M.

5. The method according to claim 4, It is characterized in that Before obtaining the eigenvector corresponding to the maximum eigenvalue, the method further includes: Based on the quantity M and the maximum eigenvalue, performing a consistency check on the first judgment matrix; If the first judgment matrix passes the consistency check, it triggers the acquisition of the eigenvector corresponding to the maximum eigenvalue.

6. The method according to claim 5, It is characterized in that The performing consistency check on the first judgment matrix based on the quantity M and the maximum eigenvalue includes: Determining a consistency index parameter based on the number M and the maximum eigenvalue, and determining a random consistency ratio parameter based on the matrix size of the first judgment matrix; Determining a ratio between the consistency index parameter and the random consistency ratio parameter as a target consistency ratio parameter; If the target consistency ratio parameter meets the preset ratio threshold condition, it is determined that the first judgment matrix passes the consistency check.

7. The method according to claim 3, It is characterized in that Any level in the multi-layer evaluation index system is represented as the nth level, and any group of evaluation indicators in the nth level is represented as the nth level. q group, the nth q The group evaluation index contains M evaluation indicators, n q and M are positive integers; The obtaining of the relative importance of the evaluation indicators in the same group at each level of the multi-layer evaluation indicator system includes: Obtain multiple preset importances of an i-th evaluation indicator compared to a j-th evaluation indicator among the M evaluation indicators, where the i-th evaluation indicator and the j-th evaluation indicator are any two of the M evaluation indicators under the first evaluation dimension, and i and j are both positive integers less than or equal to M; Performing mean processing on multiple preset importances of the i-th evaluation indicator compared to the j-th evaluation indicator to obtain a relative importance of the i-th evaluation indicator compared to the j-th evaluation indicator; The inverse of the relative importance of the i-th evaluation indicator compared to the j-th evaluation indicator is determined as the relative importance of the j-th evaluation indicator compared to the i-th evaluation indicator.

8. The method according to claim 2, It is characterized in that Any level in the multi-layer evaluation index system is represented as the nth level, and any evaluation index in the nth level is represented as the evaluation index P; If n is 1, then the absolute weight is set for each evaluation indicator in the multi-layer evaluation indicator system based on the relative weight of each evaluation indicator in the multi-layer evaluation indicator system, including: setting the relative weight of the evaluation indicator P of the first level to the absolute weight of the evaluation indicator P; If n is greater than 1, then based on the relative weight of each evaluation indicator in the multi-layer evaluation indicator system, an absolute weight is set for each evaluation indicator in the multi-layer evaluation indicator system, including: obtaining the decomposition path of the evaluation indicator P of the n-th level, performing weight recursive processing according to the relative weight of each evaluation indicator in the decomposition path, and obtaining the absolute weight of the evaluation indicator P; wherein, the evaluation indicator P of the n-th level is decomposed level by level of the evaluation indicator Q of the first level, and the decomposition path is used to record the corresponding evaluation indicators of each level obtained through the decomposition process from the evaluation indicator Q of the first level to the evaluation indicator P of the n-th level, and P and Q are both positive integers.

9. The method according to any one of claims 1 to 8, It is characterized in that The multi-layer evaluation index system also includes the absolute weight of each evaluation index in the multi-layer evaluation index system; the multi-layer evaluation index system in the business evaluation model is used to evaluate the suspicious transaction report file to obtain the evaluation result of the suspicious transaction report file, including: Obtaining the quantitative value of each evaluation indicator in the multi-layer evaluation indicator system of the suspicious transaction report file; Generate an evaluation score for the suspicious transaction report file based on the indicator quantification value of each evaluation indicator in the multi-layer evaluation indicator system and the absolute weight of each evaluation indicator in the multi-layer evaluation indicator system; Generating a validity score of the suspicious transaction report based on the evaluation score of the suspicious transaction report file and a preset total validity score; The validity score of the suspicious transaction report is determined as the evaluation result of the suspicious transaction report file.

10. The method according to claim 9, It is characterized in that Any level in the multi-layer evaluation index system is represented as the nth level, any evaluation index in the nth level is represented as evaluation index P, P is a positive integer, and the method further includes: Performing weighted processing on the index quantification value of the suspicious transaction report file under the evaluation index P of the nth level and the absolute weight of the evaluation index P to obtain the evaluation score of the suspicious transaction report file under the evaluation index P; If the evaluation score of the suspicious transaction report file under the evaluation index P does not meet the preset score threshold condition, generating report supplementary prompt information, wherein the report supplementary prompt information is used to prompt the suspicious transaction report file to add report content for screening and analyzing the suspicious transactions in the business scenario under the evaluation index P; The report supplementary prompt information is determined as the evaluation result of the suspicious transaction report file.

11. The method according to claim 9, It is characterized in that The step of generating an evaluation score for the suspicious transaction report file based on the indicator quantification value of each evaluation indicator in the multi-layer evaluation indicator system of the suspicious transaction report file and the absolute weight of each evaluation indicator in the multi-layer evaluation indicator system comprises: The absolute weight of the target evaluation index in the multi-layer evaluation index system and the index quantization value of the suspicious transaction report file under the target evaluation index are weighted and summed to obtain the evaluation score of the suspicious transaction report file; the target evaluation index is the undisassembled evaluation index in the multi-layer evaluation index system.

12. The method according to any one of claims 1 to 8, It is characterized in that The multi-layer evaluation index system includes the first level, the second level, and the third level; the first level includes the overall index of suspicious transaction reports, the depth index of transaction object analysis, and the depth index of transaction behavior analysis; The overall indicator of the suspicious transaction report is broken down into the word count indicator of the suspicious transaction report and the conclusion indicator of the suspicious transaction report at the second level; the transaction object analysis depth indicator is broken down into the transaction object information integrity indicator, the transaction object information validity indicator, and the transaction object investigation integrity indicator at the second level; the transaction behavior analysis depth indicator is broken down into the behavior anomaly analysis indicator, the transaction anomaly analysis indicator, the risk event analysis indicator, the related information analysis indicator, and the early warning model analysis indicator at the second level; Among them, the transaction object information integrity index is broken down into the name missing index, certificate number missing index, address missing index, business scope missing index, operator information missing index, beneficiary information missing index, and risk rating missing index under the third level; the transaction object information validity index is broken down into the suspicious transaction report and object investigation report consistency analysis missing index, business license anomaly analysis missing index, legal person anomaly analysis missing index, beneficial owner anomaly analysis missing index, and transaction object information authenticity analysis missing index under the third level; the transaction object investigation integrity index is broken down into the object investigation report missing index under the third level; Among them, the behavior abnormality analysis indicators are disassembled into registration behavior abnormality analysis indicators, account opening and closing behavior abnormality analysis indicators, object investigation report feedback abnormality analysis indicators, and operation address abnormality analysis indicators under the third level; the transaction abnormality analysis indicators are disassembled into business model abnormality analysis missing indicators, transaction scenario abnormality analysis missing indicators, transaction time abnormality analysis missing indicators, transaction location abnormality analysis missing indicators, transaction resource abnormality analysis missing indicators, transaction note information abnormality analysis missing indicators, transaction model abnormality analysis missing indicators, and counterparty abnormality analysis missing indicators under the third level; the risk event analysis indicators are disassembled into negative feedback analysis missing indicators and hit list analysis missing indicators under the third level; the associated information analysis indicators are disassembled into associated object analysis missing indicators, basic information associated analysis missing indicators, and counterparty associated analysis missing indicators under the third level; the early warning model analysis indicators are disassembled into early warning model analysis missing indicators under the third level.

13. A business processing device, It is characterized in that The device comprises: An acquisition unit, used to acquire a suspicious transaction report file for a business scenario, wherein the suspicious transaction report file is a file obtained by screening and analyzing suspicious transactions in the business scenario; The acquisition unit is further used to acquire a business evaluation model adapted to the business scenario, wherein the business evaluation model is provided with a multi-layer evaluation index system adapted to the business scenario, wherein the multi-layer evaluation index system includes N levels, each level includes at least one group of evaluation indicators, and each group of evaluation indicators includes at least one evaluation indicator; any evaluation indicator in the nth level of the multi-layer evaluation index system supports being disassembled into a group of evaluation indicators in the n+1th level, N and n are both positive integers, and n is less than or equal to N; A processing unit is used to use the multi-layer evaluation index system in the business evaluation model to evaluate the suspicious transaction report file to obtain an evaluation result of the suspicious transaction report file, wherein the evaluation result is used to characterize the effectiveness of the suspicious transaction report file in identifying and analyzing suspicious transactions in the business scenario.

14. A computer device, It is characterized in that include: a processor adapted to execute a computer program; A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the business processing method according to any one of claims 1 to 12 is implemented.

15. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor and executing the business processing method according to any one of claims 1 to 12.

16. A computer program product, It is characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the service processing method according to any one of claims 1 to 12 is implemented.

Citation Information

Cited By

  • Big data-based recharging risk assessment method and system

    CN120672350A