Risk control strategy evaluation method and device and computing equipment

Abstract

The embodiment of the invention provides a risk control strategy evaluation method and device and computing equipment, and the method comprises the steps: obtaining a plurality of pieces of risk control flow data recorded in a risk control service platform under a target risk control business, and deploying at least one first risk control strategy in the risk control service platform, the risk control flow data comprises risk control basic data, an executed first risk control strategy and a corresponding first strategy execution result; a second risk control strategy is executed in the test environment based on the risk control basic data to obtain a corresponding second strategy execution result, and the second risk control strategy is a fresher risk control strategy corresponding to at least one first risk control strategy; and evaluating the second risk control strategy according to the first strategy execution result and the second strategy execution result of each risk control basic data to obtain a risk control strategy evaluation result. Risk control flow data are reproduced in the test environment, the comprehensiveness, coverage rate and authenticity of the test are ensured, and the risk control strategy is evaluated more efficiently and accurately.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of computer technology, and in particular to a risk control strategy evaluation method, device and computing equipment. Background Art

[0002] With the rapid development of computer technology and Internet technology, online business processing is becoming more and more common. The risks and losses caused by business processing are also increasing. For this reason, risk control is receiving more and more attention. Risk control strategies are often configured in risk control service platforms. When users initiate risk control requests, they need to be judged and processed based on the corresponding risk control strategies.

[0003] As the business continues to develop, the risk control strategies in the risk control service platform also need to be continuously updated. The updated risk control strategies need to undergo rigorous testing and evaluation to ensure that they are consistent with the existing business logic and do not introduce new risks. The current evaluation method is manual, time-consuming, labor-intensive, difficult and costly, resulting in low efficiency and accuracy in risk control strategy evaluation. Therefore, a more efficient and accurate risk control strategy evaluation solution is urgently needed. Summary of the invention

[0004] In view of this, an embodiment of this specification provides a risk control strategy evaluation method. One or more embodiments of this specification also relate to a risk control strategy evaluation device, a computing device, a computer-readable storage medium and a computer program product to solve the technical defects existing in the prior art.

[0005] According to a first aspect of an embodiment of this specification, a risk control strategy evaluation method is provided, including: Acquire multiple pieces of risk control traffic data recorded in a risk control service platform under a target risk control business, wherein at least one first risk control strategy is deployed in the risk control service platform, and the risk control traffic data includes risk control basic data, an executed first risk control strategy, and a corresponding first strategy execution result; Executing a second risk control strategy in the test environment based on each risk control basic data to obtain a corresponding second strategy execution result, wherein the second risk control strategy is an updated risk control strategy corresponding to the at least one first risk control strategy; According to the first strategy execution result and the second strategy execution result of each risk control basic data, the second risk control strategy is evaluated to obtain a risk control strategy evaluation result.

[0006] According to a second aspect of an embodiment of this specification, a risk control strategy evaluation device is provided, including: an acquisition module, configured to acquire a plurality of risk control flow data recorded in a risk control service platform under a target risk control business, wherein at least one first risk control strategy is deployed in the risk control service platform, and the risk control flow data includes risk control basic data, an executed first risk control strategy, and a corresponding first strategy execution result; an execution module, configured to execute a second risk control strategy in a test environment based on each risk control basic data to obtain a corresponding second strategy execution result, wherein the second risk control strategy is an updated risk control strategy corresponding to the at least one first risk control strategy; The evaluation module is configured to evaluate the second risk control strategy according to the first strategy execution result and the second strategy execution result of each risk control basic data, and obtain a risk control strategy evaluation result.

[0007] According to a third aspect of an embodiment of this specification, a computing device is provided, including: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the above-mentioned risk control strategy evaluation method are implemented.

[0008] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the above-mentioned risk control strategy evaluation method are implemented.

[0009] According to a fifth aspect of the embodiments of this specification, a computer program product is provided, including a computer program / instruction, which implements the steps of the above-mentioned risk control strategy evaluation method when executed by a processor.

[0010] An embodiment of the present specification provides a risk control strategy evaluation method, which obtains multiple risk control traffic data recorded in a risk control service platform under a target risk control business, wherein at least one first risk control strategy is deployed in the risk control service platform, and the risk control traffic data includes risk control basic data, an executed first risk control strategy, and a corresponding first strategy execution result; a second risk control strategy is executed in a test environment based on each risk control basic data to obtain a corresponding second strategy execution result, wherein the second risk control strategy is an updated risk control strategy corresponding to the at least one first risk control strategy; the second risk control strategy is evaluated according to the first strategy execution result and the second strategy execution result of each risk control basic data to obtain a risk control strategy evaluation result.

[0011] An embodiment of the present specification realizes that, based on multiple risk control traffic data recorded in the risk control service platform, the second risk control strategy is executed in the test environment, the corresponding second strategy execution result is generated, and the second risk control strategy is evaluated in combination with the first strategy execution result recorded in the online risk control service platform to obtain the risk control strategy evaluation result. By recording the risk control traffic data in the online risk control service platform, the data in the actual business scenario can be captured and reproduced in the test environment to verify the performance of the second risk control strategy in the test environment under various circumstances, ensuring the comprehensiveness, coverage and authenticity of the test in the test environment, and completing the evaluation of the risk control strategy more efficiently and accurately, and ensuring the consistency and accuracy of the risk control strategy in the online risk control service platform, greatly reducing the preparation time of the test data in the test environment, and reducing the possibility of manual evaluation errors. Without interfering with the online risk control service platform, the second risk control strategy is fully verified before going online, and the potential problems of the second risk control strategy are discovered and repaired in advance, reducing the risk of the second risk control strategy after going online, and ensuring the stability and reliability of the risk control service platform in operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 This is an architecture diagram of a risk control strategy evaluation system provided by an embodiment of this specification; Figure 2 This is a flow chart of a risk control strategy evaluation method provided by an embodiment of this specification; Figure 3 It is a process flow chart of a risk control strategy evaluation method provided by an embodiment of this specification; Figure 4 This is a schematic diagram of a risk control strategy evaluation interface provided by an embodiment of this specification; Figure 5 It is a structural schematic diagram of a risk control strategy evaluation device provided by an embodiment of this specification; Figure 6 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0013] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

[0014] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0015] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0016] In addition, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0017] First, the terms involved in one or more embodiments of this specification are explained.

[0018] Two-core risk control: refers to the risk management of the two key links of underwriting and claims adjudication in the insurance industry. These two links are the core of insurance companies' control and prevention of risks, and are related to the operating safety and profitability of insurance companies.

[0019] Underwriting: Before the insurance contract is established, the insurance company evaluates the risk level of the insured object based on the insured's application and related information, and decides whether to insure and the specific conditions of underwriting (such as insurance premium rate, insurance amount, insurance period, etc.). Factors that need to be considered during the underwriting process include but are not limited to the insured's credit record, health status, past claims record, etc. The purpose of underwriting is to ensure that the insurance company can set reasonable prices and avoid taking excessive risks, thereby maintaining the company's financial stability.

[0020] Claims verification: It is the process by which the insurance company reviews the claim for compensation filed by the insured after an insurance accident occurs. This involves verifying the authenticity, legality and rationality of the claim materials to determine the amount of compensation. Claims verification not only protects the legitimate rights and interests of the insured, but also prevents false claims and insurance fraud, and protects the legitimate rights and interests of the insurance company from infringement.

[0021] It should be noted that, taking the risk control strategy assessment in insurance scenarios as an example, underwriting and claims are two key links. Underwriting determines whether to accept the insurance application and the calculation of the premium, while claims is related to whether the insurance company can make compensation in a timely and accurate manner after an accident. The accuracy and efficiency of these two links directly affect the operating conditions and service quality of the insurance company.

[0022] With the intensification of market competition and the development of technology, insurance companies are facing tremendous pressure to optimize their core business processes. On the one hand, in order to attract more customers, insurance companies need to provide more personalized and fast services; on the other hand, in order to control risks, insurance companies must ensure the accuracy and compliance of underwriting and claims decisions. Therefore, underwriting and claims systems need to be not only highly intelligent, but also have strong risk control capabilities.

[0023] The manual testing method requires manual construction of a large amount of test data, which is not only time-consuming, but also easy to extend the test cycle. In addition, human errors are prone to occur during manual testing, such as missing some scenarios or entering incorrect data, resulting in unreliable test results. In addition, manual testing is difficult to cover all actual business scenarios, especially complex and changeable business logic, and it is easy to miss some edge cases. Manually constructed data is often not real enough and cannot fully reflect the various situations in the actual production environment. Furthermore, the updated risk control strategy needs to be consistent with the existing business logic, but manual testing is difficult to ensure this, which is easy to introduce new risks. Manual testing is difficult to verify the performance of the updated risk control strategy in various complex scenarios, resulting in the consistency and accuracy of the risk control strategy being difficult to ensure. Updating the risk control strategy to introduce new functions or modify the existing risk control logic may bring unknown risks. Manual testing is difficult to discover these problems in advance, resulting in higher risks after the updated risk control strategy is launched. Manual testing cannot fully verify the stability and reliability of the updated risk control strategy, which may cause problems in actual operation.

[0024] Therefore, in order to solve the above problems, the embodiment of this specification provides a risk control strategy evaluation scheme. The updated risk control strategies need to undergo rigorous testing to ensure that they are consistent with the existing business logic and do not introduce new risks. Therefore, the embodiment of this specification can record the risk control traffic data in the online risk control service platform and replay it in the test environment. By reproducing the actual business scenario, the traffic data playback can help verify the performance of the updated risk control strategy in various situations and ensure the consistency and accuracy of the risk control strategy. In addition, the manual testing method is time-consuming and error-prone. The embodiment of this specification automatically generates test data and replays these data in the test environment, which greatly reduces the time for test preparation and reduces the possibility of human error. It can complete the test task more efficiently and ensure the full verification of the updated risk control strategy before it goes online. Furthermore, the risk control traffic data in the actual production environment contains a variety of business scenarios, which are often difficult to fully cover by manual testing. Traffic playback can capture real business scenarios and use them in the test process, thereby ensuring the comprehensiveness and authenticity of the test, and can better discover potential problems and improve the coverage of the test. When risk control strategies change, such as introducing new features or modifying existing logic, unknown risks may arise. Traffic replay can detect and fix potential problems in advance without interfering with the production environment, reduce the risks after the updated risk control strategy goes online, and ensure stability and reliability in actual operation.

[0025] In this specification, a risk control strategy evaluation method is provided. This specification also involves a risk control strategy evaluation device, a computing device, a computer-readable storage medium, and a computer program product, which are described in detail one by one in the following embodiments.

[0026] See also Figure 1 , Figure 1 The structure diagram of a risk control strategy evaluation system provided by an embodiment of the present specification is shown. The risk control strategy evaluation system may include a client 100 and a server 200; The client 100 is used to initiate a policy evaluation request for a target risk control service to the server 200; The server 200 is used to obtain multiple risk control flow data recorded in the risk control service platform under the target risk control business, wherein at least one first risk control strategy is deployed in the risk control service platform, and the risk control flow data includes risk control basic data, the executed first risk control strategy and the corresponding first strategy execution result; based on each risk control basic data, a second risk control strategy is executed in a test environment to obtain a corresponding second strategy execution result, wherein the second risk control strategy is an updated risk control strategy corresponding to at least one first risk control strategy; according to the first strategy execution result and the second strategy execution result of each risk control basic data, the second risk control strategy is evaluated to obtain a risk control strategy evaluation result.

[0027] In an optional embodiment of the present specification, the server 200 is further used to send the risk control strategy evaluation result to the client 100; the client 100 is further used to receive the risk control strategy evaluation result sent by the server 200.

[0028] By applying the solution of the embodiments of the present specification, by recording risk control traffic data in the online risk control service platform, data in actual business scenarios can be captured and reproduced in a test environment to verify the performance of the second risk control strategy in the test environment under various circumstances, ensuring the comprehensiveness, coverage and authenticity of the tests in the test environment. The evaluation of risk control strategies can be completed more efficiently and accurately, and the consistency and accuracy of risk control strategies in the online risk control service platform can be guaranteed, which greatly reduces the preparation time of test data in the test environment and reduces the possibility of manual evaluation errors. Without interfering with the online risk control service platform, the second risk control strategy can be fully verified before it goes online, potential problems of the second risk control strategy can be discovered and fixed in advance, and the risks after the second risk control strategy goes online can be reduced, thereby ensuring the stability and reliability of the risk control service platform during operation.

[0029] In practical applications, the risk control strategy evaluation system may include multiple clients 100 and a server 200. Multiple clients 100 may establish a communication connection through the server 200. In the risk control strategy evaluation scenario, the server 200 is used to provide risk control strategy evaluation services between multiple clients 100. Multiple clients 100 may serve as senders or receivers, respectively, and realize communication through the server 200. The client 100 may interact with the user through a graphical user interface. The user may interact with the server 200 through the client 100 to receive data sent by other clients 100, or send data to other clients 100, etc. In the risk control strategy evaluation scenario, the user may initiate a policy evaluation request to the server 200 through the client 100, and the server 200 may generate a risk control strategy evaluation result according to the policy evaluation request, and push the risk control strategy evaluation result to other clients that establish communication. Among them, the client 100 and the server 200 are connected through a network. The network provides a medium for the communication link between the client 100 and the server 200. The network may include various connection types, such as wired or wireless communication links or optical fiber cables, etc. The data transmitted by the client 100 may need to be encoded, transcoded, compressed, etc. before being published to the server 200 .

[0030] The client 100 can be a browser, an application (APP, Application), or a web application such as HyperText Markup Language Version 5 (H5, HyperText Markup Language5) application, or a light application (also known as a mini-program, a lightweight application) or a cloud application, etc. The client 100 can be based on the software development kit (SDK, Software Development Kit) of the corresponding service provided by the server 200, such as based on the real-time communication (RTC, Real Time Communication) SDK development and acquisition. The client 100 can be deployed in an electronic device and needs to rely on the device to run or some APPs in the device to run. For example, the electronic device can have a display screen and support information browsing, such as a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, etc. Various other types of applications can also be configured in the electronic device, such as human-computer dialogue applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant messaging tools, mailbox clients, social platform software, etc.

[0031] The server 200 may include servers that provide various services, such as servers that provide communication services to multiple clients, servers for background training that support models used on clients, and servers that process data sent by clients. It should be noted that the server 200 can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. The server can also be a server of a distributed system, or a server combined with a blockchain. The server can also be a cloud server for basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks (CDN, Content Delivery Network), and big data and artificial intelligence platforms, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0032] It is worth noting that the risk control strategy evaluation method provided in the embodiments of this specification is generally executed by the server, but in other embodiments of this specification, the client may also have similar functions to the server, thereby executing the risk control strategy evaluation method provided in the embodiments of this specification. In other embodiments, the risk control strategy evaluation method provided in the embodiments of this specification may also be jointly executed by the client and the server.

[0033] See also Figure 2 , Figure 2 A flow chart of a risk control strategy evaluation method provided according to an embodiment of the present specification is shown, which specifically includes the following steps.

[0034] Step 202: Obtain multiple pieces of risk control traffic data recorded in the risk control service platform under the target risk control business, wherein at least one first risk control strategy is deployed in the risk control service platform, and the risk control traffic data includes risk control basic data, the executed first risk control strategy, and the corresponding first strategy execution result.

[0035] Among them, risk control refers to risk control, and the target risk control business is any risk control business under the risk control scenario, such as underwriting and claims settlement in the insurance scenario. Underwriting and claims settlement are two core links in the insurance industry, and they play a key role in the signing stage of the insurance contract and the payment stage after the accident respectively. Underwriting business refers to the process in which the insurance company evaluates the risk level of the insured based on the deployed risk control strategy according to the insured's health status, age, occupation, living habits and other information, and decides whether to insure and under what conditions. The main purpose of the underwriting business is to ensure that risks can be reasonably assessed to avoid losses due to excessive concentration of high-risk customers; claims settlement business refers to when an insurance accident actually occurs, the insurance company reviews the compensation request made by the insured or beneficiary based on the deployed risk control strategy in accordance with the agreement of the insurance contract, and makes claims based on the review results.

[0036] The risk control service platform refers to a platform that provides risk control services. It integrates big data analysis and risk control strategies, and can help identify, evaluate and manage various risk control projects, such as various insurance projects under the underwriting business, various claims application projects under the claims settlement business, etc. Risk management strategy is a key factor in ensuring product risk management and project compliance. Risk control strategy refers to a series of plans and actions formulated by an enterprise or organization to identify, evaluate, prioritize and take measures to reduce the impact of potential risks on project goals. With the continuous launch of insurance products, insurance companies need to configure and verify a large number of risk control strategies to ensure that these strategies can effectively manage risks. For example, the risk control strategy can be whether a return has been applied for in more than 3 channels within a month, or the user's credit score is below the threshold. The risk control service platform is deployed with at least one first risk control strategy, which refers to the risk control strategy currently launched on the risk control service platform.

[0037] Risk control flow data refers to the relevant data for processing actual risk control requests in the risk control service platform, that is, the business data in the actual business scenario. A piece of risk control flow data may include risk control basic data, the first risk control strategy executed, and the corresponding first strategy execution result. Among them, the risk control basic data refers to the data required for strategy judgment, such as the risk control basic data may include risk control request information, dependent feature data collected from the local database or other third-party platforms based on the risk control request information, etc.; the executed first risk control strategy refers to the first risk control strategy corresponding to the risk control basic data in at least one first risk control strategy deployed by the risk control service platform, and the first strategy execution result is the judgment result obtained by executing the corresponding first risk control strategy on the risk control basic data, such as whether the risk control is passed.

[0038] In actual implementation, the requester can initiate a risk control request to the risk control service platform. The risk control service platform can collect corresponding feature data based on the risk control request to obtain basic risk control data, judge the basic risk control data based on the corresponding first risk control strategy, and determine the first strategy execution result of the risk control request. The basic risk control data, the executed first risk control strategy, and the corresponding first strategy execution result are the risk control traffic data for executing the risk control request. The basic risk control data, the executed first risk control strategy, and the corresponding first strategy execution result of each risk control request in the risk control service platform can be recorded and stored. When it is necessary to update the risk control strategy that has been launched on the risk control service platform, multiple recorded risk control traffic data can be read from the storage module and played back in the test environment, so as to verify the updated risk control strategy before it is launched on the risk control service platform.

[0039] In an optional implementation of this embodiment, multiple pieces of risk control flow data recorded in the risk control service platform under the target risk control business are obtained, including: Record the risk control request information of the risk control service platform and the dependent feature data corresponding to the risk control request information, and use the risk control request information and the dependent feature data as the risk control basic data, wherein the risk control request information is the information carried by the risk control request initiated by the requester, and the dependent feature data is the data obtained from the local database or the third-party platform and required for executing the corresponding first risk control strategy for the risk control request information; Record the first strategy execution result of the corresponding first risk control strategy executed based on the risk control basic data.

[0040] Among them, risk control request information refers to the relevant information of the risk control request initiated by the requesting party to the risk control service platform. The requesting party refers to the business party requesting to analyze the user's risks. For example, in the freight insurance scenario, when a user purchases a certain product, the business platform as the requesting party can request the risk control service platform to verify the user's return risk so that the business platform can determine whether to provide return freight insurance services to the user; for example, in the credit purchase scenario, when a user requests the business platform to use credit points to obtain a certain service, the business platform can, as the requesting party, request the risk control service platform to verify the user's credit risk so as to determine whether to provide credit purchase services to the user.

[0041] The risk control request information may be the risk control parameters carried by the risk control request, that is, the detailed information requested by the requester, such as risk control type, business identifier, source channel, product identifier, user identifier, etc. Dependent feature data refers to data related to the risk control request information and required to execute the corresponding first risk control strategy, such as user attributes, user behavior characteristics, transaction characteristics, etc. The first strategy execution result refers to the execution result in the risk control core and rule engine in the risk control service platform, including the strategy judgment result and related scores, tags, etc.

[0042] It should be noted that after the risk control service platform receives the risk control request initiated by the requester, it can collect the dependent feature data required for risk control strategy verification from the local database or other third-party platform based on the risk control request information of the risk control request. The risk control request information and dependent feature data are the risk control basic data of the risk control request. Based on the risk control basic data, the corresponding first risk control strategy can be executed to obtain the corresponding first strategy execution result.

[0043] For example, the requester can initiate a risk control request to the risk control service platform. The risk control request information of the risk control request is the credit purchase business type and the credit verification of user A. The risk control service platform determines that the required dependent feature data is the user's credit score based on the credit purchase business type. Therefore, the risk control service platform can obtain the credit score of user A from other credit platforms based on the risk control request information. Assuming that the credit score of user A is 90 points, the first risk control strategy corresponding to the credit purchase business type is that the risk control verification passes if the credit score is greater than 80 points. Based on the first risk control strategy, the credit score of user A is verified, and it is determined that the corresponding first strategy execution result is that the verification passes. At this time, a piece of risk control traffic data can be obtained: {risk control request information: credit purchase business type, user A credit verification: dependent feature data: user A's credit score is 90; first risk control strategy: risk control verification passes if the credit score is greater than 80 points; first strategy execution result: verification passes}.

[0044] In actual implementation, the risk control request information of the risk control service platform and the dependent feature data corresponding to the risk control request information can be recorded as the risk control basic data, and the first strategy execution result of the first risk control strategy corresponding to the risk control basic data can be recorded. The risk control basic data corresponding to a risk control request, the executed first risk control strategy, and the corresponding first strategy execution result can be used as a piece of risk control traffic data. Specifically, the recording of the risk control request information, the dependent feature data, and the first strategy execution result can be asynchronous recording, and the actual risk control traffic data can be recorded and collected in the production environment (i.e., the risk control service platform) to provide basic data for subsequent data processing and playback.

[0045] In the embodiments of the present specification, by recording the risk control request information, dependent feature data, the executed first risk control strategy and the corresponding first strategy execution results of the risk control service platform, multiple risk control traffic data can be obtained. The multiple risk control traffic data can cover various actual business scenarios in the risk control service platform, capture real business data, avoid manual construction of test data, greatly reduce the time for test preparation, and reduce the possibility of human errors. The risk control traffic data contains a variety of business scenarios, which are often difficult to fully cover by manual testing, thereby improving the coverage of tests in subsequent test environments.

[0046] Of course, in actual implementation, in addition to recording risk control request information and relying on feature data as basic risk control data, other data related to risk control requests can also be recorded and summarized to obtain basic risk control data, such as historical risk control data, request time, etc.

[0047] In an optional implementation of this embodiment, recording the risk control request information of the risk control service platform and the dependent feature data corresponding to the risk control request information includes: A first recording unit is configured at a service entrance of the risk control service platform, and risk control request information of the risk control service platform is recorded by the first recording unit; A second recording unit is configured in the data acquisition module of the risk control service platform, and the dependent feature data acquired by the data acquisition module from the local database or the third-party platform based on the risk control request information is recorded by the second recording unit; or a second recording unit is configured in the feature storage module of the risk control service platform, and the dependent feature data corresponding to the risk control request information stored in the feature storage module is recorded by the second recording unit; Recording the first strategy execution result of the first risk control strategy corresponding to the risk control basic data, including: A third recording unit is configured in the policy execution module of the risk control service platform, and a first policy execution result of the first risk control policy corresponding to the risk control basic data is recorded through the third recording unit; or a third recording unit is configured in the result storage module of the risk control service platform, and a first policy execution result of the first risk control policy corresponding to the risk control basic data is recorded through the third recording unit.

[0048] The first recording unit, the second recording unit and the third recording unit may be components with data recording function. The first recording unit is used to record risk control request information, the second recording unit is used to record dependency feature data, and the third recording unit is used to record the first strategy execution result.

[0049] In actual implementation, the requester needs to initiate a risk control request to the risk control service platform through the service portal of the risk control service platform, and thus a first recording unit may be configured at the service portal to record the risk control request information passing through the service portal.

[0050] In addition, when the risk control service platform receives a risk control request initiated by the requesting party, the data acquisition module of the risk control service platform can obtain dependent feature data from a local database or a third-party platform based on the risk control request information, and thus a second recording unit can be configured in the data acquisition module to record the dependent feature data obtained by the data acquisition module. Alternatively, after obtaining the dependent feature data corresponding to the risk control request information, the risk control service platform will write the dependent feature data into a feature storage module, such as a feature database, and thus a second recording unit can be configured in the feature storage module of the risk control service platform to record the dependent feature data written into the feature storage module.

[0051] Furthermore, after the risk control service platform obtains the risk control request information and dependent feature data, the policy execution module will execute the corresponding first risk control policy based on the obtained data and obtain the corresponding first policy execution result. The policy execution module can be the risk control core and rule engine of the risk control service platform, so a third recording unit can be configured in the policy execution module to record the first policy execution result. Alternatively, after the risk control service platform executes the corresponding first risk control policy based on the obtained data in the policy execution module and obtains the corresponding first policy execution result, the obtained first policy execution result can be written into the result storage module, so a third recording unit can also be configured in the result storage module to record the first policy execution result written into the result storage module.

[0052] In the embodiments of this specification, a recording tool can be added to the service entrance of the risk control service platform to capture and store in real time the risk control request information of each risk control service platform; a data recording function is added to the data acquisition module to record the dependent feature data related to the risk control request information to ensure that each dependent feature data obtained is correctly recorded; a result recording function is added to the policy execution module to record the execution results of each risk control request in the policy execution module. In the actual production environment, the corresponding module adds a data recording function to record and collect the actual traffic data and policy execution results, providing basic data for subsequent data processing and playback, reducing the preparation time of test data.

[0053] Of course, in actual implementation, the risk control service platform can also write the acquired dependency feature data and the corresponding first strategy execution result into the same storage module, and thus a recording unit can be configured in the storage module to record the dependency feature data and the corresponding first strategy execution result written into the database respectively. The embodiments of this specification do not limit this.

[0054] In an optional implementation of this embodiment, after obtaining multiple pieces of risk control flow data recorded in the risk control service platform under the target risk control business, the method further includes: Determine the strategic assessment needs of the target risk control business; Based on the strategy evaluation requirements, filter out the target traffic data from multiple risk control traffic data; Among them, the second risk control strategy is an updated risk control strategy corresponding to at least one first risk control strategy, that is, the first risk control strategy is the risk control strategy launched on the risk control service platform, and the second risk control strategy is a risk control strategy obtained by updating at least one first risk control strategy and not yet launched.

[0055] It should be noted that at least one first risk control strategy can be deployed in the risk control service platform. When updating the risk control strategy, not every online first risk control strategy may be updated, but rather one or some of the at least one first risk control strategy may be modified, and / or a new risk control strategy may be added based on at least one first risk control strategy to obtain a second risk control strategy.

[0056] In actual implementation, the risk control traffic data recorded on the risk control service platform is comprehensive data covering various businesses and various scenarios. The amount of risk control traffic data is often large, and most of the large amount of risk control traffic data obtained is irrelevant to the risk control strategy that needs to be evaluated. Therefore, the strategy evaluation requirements of the target risk control business can be determined, and the target traffic data can be screened out from multiple risk control traffic data based on the strategy evaluation requirements. The strategy evaluation requirements can refer to the demand information of the current strategy that needs to be evaluated, such as the business identifier to which the strategy belongs, the strategy type, the strategy identifier, etc.

[0057] In one implementation, the policy evaluation requirements of the target risk control business can be determined based on the update information of the second risk control policy relative to the first risk control policy, and then the multiple risk control traffic data can be cleaned based on the policy evaluation requirements to filter out the target traffic data. Specifically, the update policy and the related policy of the update policy can be determined from each first risk control policy based on the update information. The related policy is the risk control policy that references the update policy, and the update policy and the related policy are used as the policy evaluation requirements.

[0058] For example, assume that the first risk control strategy launched in the risk control service platform is: strategy 1, strategy 2, strategy 3, strategy 4, and strategy 5. Assume that due to business needs, strategy 2 is updated and strategy 2' is obtained. It is necessary to verify the updated second risk control strategy before going online. The second risk control strategy is: strategy 1, strategy 2', strategy 3, strategy 4, and strategy 5. Assume that strategy 3 references strategy 2 and strategy 4 references strategy 3. At this time, it can be determined that the policy evaluation requirements need to be evaluated for strategy 2, strategy 3, and strategy 4. The risk control traffic data related to strategy 2, strategy 3, and strategy 4 are selected from the multiple recorded risk control traffic data as the target traffic data.

[0059] In another implementation, it is also possible to receive a policy evaluation requirement configured by a client, and directly filter out target traffic data from multiple risk control traffic data based on the policy evaluation requirement configured on the client.

[0060] For example, the policy evaluation requirement configured by the client is to evaluate the risk control policy related to the credit score. At this time, the risk control traffic data related to the credit score can be filtered out from the multiple recorded risk control traffic data as the target traffic data.

[0061] Specifically, data cleaning scripts and tools can be used to batch process multiple recorded risk control traffic data, synchronize multiple risk control traffic data to the data warehouse, and configure filtering logic in the data warehouse. The filtering logic can be configured based on policy evaluation requirements, establish a data processing flow, and utilize the data processing capabilities of the data warehouse to automatically clean and filter the multiple recorded risk control traffic data according to the configured filtering logic.

[0062] In actual applications, the data warehouse can be configured with a screening logic that selects target traffic data from multiple risk control traffic data based on policy assessment requirements. After determining the policy assessment requirements for the target risk control business, the policy assessment requirements and multiple risk control traffic data can be synchronized to the data warehouse, and the data warehouse can be used to select target traffic data related to the policy assessment requirements. In addition, the target traffic data obtained by screening can be regularly pushed to the corresponding staff for verification and auditing to ensure data quality.

[0063] It should be noted that the risk control traffic data includes the risk control basic data, the corresponding first risk control strategy and the execution result of the first strategy. Therefore, when screening the target traffic data, it is necessary to ensure that the risk control basic data, the first risk control strategy and the execution result of the first strategy correspond to each other, avoid including only the risk control basic data, only the execution result of the first strategy, etc., and ensure data accuracy and consistency.

[0064] In the embodiments of the present specification, after obtaining multiple recorded risk control traffic data, it is possible to further screen out effective target traffic data from the multiple risk control traffic data based on actual policy evaluation requirements, thereby greatly reducing the amount of data for subsequent traffic playback in the test environment, reducing the amount of data processing for traffic playback, improving test efficiency, and saving processing resources.

[0065] Step 204: Execute the second risk control strategy in the test environment based on each risk control basic data to obtain a corresponding second strategy execution result, wherein the second risk control strategy is an updated risk control strategy corresponding to at least one first risk control strategy.

[0066] It should be noted that the second risk control strategy is a risk control strategy obtained by updating at least one first risk control strategy and not yet online, and needs to be evaluated before going online to determine whether it will affect the normal execution of other risk control strategies. In actual implementation, after obtaining multiple recorded risk control traffic data, the risk control basic data in each risk control traffic data can be replayed in the test environment, and the corresponding second risk control strategy can be executed to obtain the corresponding second strategy execution result, so that the risk control strategy can be evaluated based on the online recorded first strategy execution result and the second strategy execution result generated by the playback in the test environment.

[0067] In actual implementation, the test environment is deployed with at least one second risk control strategy corresponding to the first risk control strategy, and any recorded risk control traffic data includes risk control basic data, the corresponding first risk control strategy, and the first strategy execution result. In the test environment, the second risk control strategy corresponding to the first risk control strategy in the test environment is determined, and the second risk control strategy is executed for the risk control basic data to obtain the corresponding second strategy execution result.

[0068] Specifically, a test environment can be built on the risk control strategy evaluation platform, and recorded risk control traffic data can be imported into the test environment for playback. In the test environment, a policy engine and risk control core module that are consistent with the online production environment (that is, the risk control service platform) are deployed to ensure the consistency of policy execution. Mock Server is used to simulate the services and interfaces in the production environment, and the risk control core module in the test environment executes the policy and records the execution results to ensure the authenticity of the test environment. Among them, Mock Server is a tool for simulating external systems or services, and is often used in development and testing environments. Through Mock Server, developers can perform front-end development without actual back-end services, or simulate various scenarios in testing, including normal responses, error responses, delayed responses, etc.

[0069] In an optional implementation of this embodiment, executing the second risk control strategy in the test environment based on each risk control basic data to obtain the corresponding second strategy execution result includes: The corresponding second risk control strategy is executed in the test environment based on the risk control basic data in each target traffic data to obtain the corresponding second strategy execution result.

[0070] It should be noted that after obtaining multiple recorded risk control traffic data, if the multiple risk control traffic data are further cleaned based on the actual strategy evaluation requirements and the effective target traffic data are screened, the corresponding second risk control strategy can be executed in the test environment based on the risk control basic data in each target traffic data to obtain the corresponding second strategy execution result.

[0071] For example, assume that the target traffic data obtained by screening includes risk control traffic data 1-3. Risk control traffic data 1 is {risk control basic data 1, risk control strategy 1, first strategy execution result 1}, risk control traffic data 2 is {risk control basic data 2, risk control strategy 2, first strategy execution result 2}, and risk control traffic data 3 is {risk control basic data 3, risk control strategy 3, first strategy execution result 3}.

[0072] Assume that due to business needs, risk control strategy 2 is updated to obtain risk control strategy 2', and other first risk control strategies remain unchanged. It is necessary to verify the updated second risk control strategy before going online. The second risk control strategies are: risk control strategy 1, risk control strategy 2', and risk control strategy 3.

[0073] Deploy risk control strategy 1, risk control strategy 2', and risk control strategy 3 in the test environment. Execute risk control strategy 1 in the test environment based on risk control basic data 1 to obtain second strategy execution result 1. Execute risk control strategy 2' in the test environment based on risk control basic data 2 to obtain second strategy execution result 2. Execute risk control strategy 3 in the test environment based on risk control basic data 3 to obtain second strategy execution result 3.

[0074] It should be noted that playing back the filtered target traffic data in the test environment avoids playing back invalid recorded data, greatly reduces the amount of data for traffic playback in the test environment, reduces the amount of data processing for traffic playback, improves test efficiency, and saves processing resources.

[0075] Step 206: Evaluate the second risk control strategy according to the first strategy execution result and the second strategy execution result of each risk control basic data to obtain a risk control strategy evaluation result.

[0076] It should be noted that, for each risk control basic data, a risk control strategy evaluation can be performed based on the first strategy execution result recorded online and the second strategy execution result generated by playback in the test environment to determine whether there is an abnormality in the corresponding risk control strategy.

[0077] In an optional implementation of this embodiment, the second risk control strategy is evaluated according to the first strategy execution result and the second strategy execution result of each risk control basic data to obtain the risk control strategy evaluation result, including: Determine candidate risk control data for which the first strategy execution result and the second strategy execution result are inconsistent in each risk control basic data; According to the candidate risk control data, the corresponding second risk control strategy to be executed is evaluated to determine the risk control strategy evaluation result.

[0078] Among them, the risk control strategy evaluation result is the result obtained by evaluating the corresponding second risk control strategy being executed. The evaluation result can be a pass or fail in the evaluation, or a specific abnormal reason.

[0079] In actual implementation, if the execution results of the first strategy and the second strategy corresponding to the risk control basic data are inconsistent, it means that the execution result of the first strategy recorded online is different from the execution result of the second strategy generated by the playback in the test environment. It may be due to the inconsistent results caused by updating the corresponding risk control strategy. The inconsistent results are the inconsistency under normal circumstances when updating the risk control strategy, or it may be because the updated risk control strategy affects the normal execution of other risk control strategies. Therefore, the candidate risk control data in which the execution results of the first strategy and the second strategy are inconsistent in each risk control basic data can be determined, and then the corresponding second risk control strategy can be further evaluated based on the candidate risk control data to determine whether it is an inconsistency under normal circumstances or an inconsistency caused by abnormal influences, and determine the risk control strategy evaluation result.

[0080] In the embodiments of the present specification, candidate risk control data whose execution results of the first strategy recorded online and the execution results of the second strategy generated by the playback in the test environment are inconsistent can be determined, and each candidate risk control data with inconsistent results can be screened out, and then the second risk control strategy executed by it can be evaluated to determine the risk control strategy evaluation result. Without interfering with the online risk control service platform, the second risk control strategy can be fully verified before it goes online, potential problems of the second risk control strategy can be discovered and fixed in advance, and the risk of the second risk control strategy after it goes online can be reduced, thereby ensuring the stability and reliability of the risk control service platform during operation.

[0081] In an optional implementation of this embodiment, evaluating the corresponding second risk control strategy to be executed according to the candidate risk control data and determining the risk control strategy evaluation result includes: Grouping the candidate risk control data according to the risk control strategy to obtain at least one candidate risk control data group; The second risk control strategy executed corresponding to each candidate risk control data group is used as the first abnormal risk control strategy; According to the first abnormal risk control strategy, a risk control strategy evaluation result is generated.

[0082] It should be noted that, since the same risk control strategy may correspond to multiple risk control basic data, there may be multiple candidate risk control data corresponding to the same risk control strategy in the selected candidate risk control data. In actual implementation, the candidate risk control data can be grouped according to the risk control strategy, and the candidate risk control data corresponding to the same risk control strategy can be grouped to obtain at least one candidate risk control data group, one candidate risk control data group corresponds to one second risk control strategy, and the second risk control strategy executed by each candidate risk control data group is used as the first abnormal risk control strategy, and the first abnormal risk control strategy can be further evaluated and analyzed later.

[0083] For example, assuming that the candidate risk control data is candidate risk control data 1-50, candidate risk control data 1-20 corresponds to risk control strategy 2', candidate risk control data 21-30 corresponds to risk control strategy 3, and candidate risk control data 31-50 corresponds to risk control strategy 4. At this time, the risk control data 1-50 can be divided into three candidate risk control data groups, candidate risk control data group 1 corresponds to risk control strategy 2', candidate risk control data group 2 corresponds to risk control strategy 3, and candidate risk control data group 3 corresponds to risk control strategy 4, and risk control strategy 2', risk control strategy 3, and risk control strategy 4 are determined as the first abnormal risk control strategy.

[0084] In the embodiments of the present specification, the obtained candidate risk control data can be grouped, and the second risk control strategy executed corresponding to each candidate risk control data group can be used as the first abnormal risk control strategy. The first abnormal risk control strategy is subsequently evaluated to generate a risk control strategy evaluation result, thereby avoiding multiple identical evaluation and analysis for the same abnormal risk control strategy, greatly reducing the computational complexity of the strategy evaluation, improving the strategy evaluation efficiency, and saving processing resources.

[0085] In an optional implementation of this embodiment, generating a risk control strategy evaluation result according to the first abnormal risk control strategy includes: Determine the verification personnel corresponding to the first abnormal risk control strategy, and push the first abnormal risk control strategy to the corresponding verification personnel; Based on the verification results fed back by the verification personnel for the first abnormal risk control strategy, a risk control strategy evaluation result is generated.

[0086] In actual implementation, the risk control strategy evaluation platform can be pre-configured with verification personnel of different types of risk control strategies. After determining the first abnormal risk control strategy, the corresponding verification personnel can be determined based on the policy type of each first abnormal risk control strategy, and each first abnormal risk control strategy can be pushed to the corresponding verification personnel. The verification personnel will evaluate and analyze the received first abnormal risk control strategy to determine whether the anomaly is a normal situation caused by the modification of the risk control strategy, and feedback the verification results. The risk control strategy evaluation platform generates the corresponding risk control strategy evaluation results based on the verification results.

[0087] Continuing with the above example, risk control strategy 2' is pushed to verifier A, and the feedback verification result is verification passed; risk control strategy 3 is pushed to verifier B, and the feedback verification result is verification passed; risk control strategy 4 is pushed to verifier C, and the feedback verification result is verification failed. At this time, the risk control strategy evaluation result can be generated: after the second risk control strategy that has not been launched is launched, it will affect the normal execution of risk control strategy 4, and the risk control strategy evaluation will fail.

[0088] In the embodiments of the present specification, after determining each first abnormal risk control strategy, each first abnormal risk control strategy can be pushed to the corresponding verification personnel for security and stability verification, and a risk control strategy evaluation result is generated based on the verification results fed back by each verification personnel, thereby ensuring the accuracy of the strategy evaluation, discovering and repairing potential problems of the second risk control strategy that has not been launched in advance, reducing the risk of the second risk control strategy after it is launched, and ensuring the stability and reliability of the risk control service platform during operation.

[0089] In an optional implementation of this embodiment, the second risk control strategy is evaluated according to the first strategy execution result and the second strategy execution result of each risk control basic data to obtain the risk control strategy evaluation result, including: Determine candidate risk control data for which the first strategy execution result and the second strategy execution result are inconsistent in each risk control basic data; Determine each candidate second risk control strategy to be executed corresponding to the candidate risk control data; Determine the second abnormal risk control strategy that is the same as the first risk control strategy among the candidate second risk control strategies; According to the second abnormal risk control strategy, a risk control strategy evaluation result is generated.

[0090] It should be noted that, since the second risk control strategy that has not been launched includes strategies that are inconsistent with the first risk control strategy that has been launched on the risk control service platform, it may also include strategies that are consistent with the first risk control strategy that has been launched on the risk control service platform. In actual implementation, if the second risk control strategy is inconsistent with the first risk control strategy that has been launched on the risk control service platform, it means that the second risk control strategy has been updated, and the inconsistency between the first strategy execution result and the second strategy execution result is caused by the policy update, which is likely to be a normal risk control strategy update; while the second risk control strategy is consistent with the first risk control strategy that has been launched on the risk control service platform, it means that the second risk control strategy has not been updated, but the first strategy execution result and the second strategy execution result are inconsistent, which means that the second risk control strategy is likely to be affected by other risk control strategies and may be abnormal, that is, the second risk control strategy that is the same as the first risk control strategy among the candidate second risk control strategies can be determined as the second abnormal risk control strategy, and then the second abnormal risk control strategy is evaluated to generate the risk control strategy evaluation result.

[0091] Continuing with the above example, in the second risk control strategy, risk control strategy 2' has been updated, which is different from the online risk control strategy 2, while risk control strategy 3 and risk control strategy 4 have not been updated, which are the same as the online risk control strategy 3 and risk control strategy 4. At this time, it can be determined that the second abnormal risk control strategy is risk control strategy 3 and risk control strategy 4.

[0092] Specifically, after determining the second abnormal risk control strategy, the second abnormal risk control strategy can be further pushed to the corresponding verification personnel for verification, or it can be evaluated based on other customized evaluation rules to generate the corresponding risk control strategy evaluation result.

[0093] In the embodiments of the present specification, a second abnormal risk control strategy can be screened out, in which the second risk control strategy is consistent with the first risk control strategy that has been launched on the risk control service platform, but the execution result of the first strategy is inconsistent with the execution result of the second strategy. The second abnormal risk control strategy is subsequently evaluated to generate a risk control strategy evaluation result, further reducing the number of abnormal risk control strategies that require manual verification, greatly reducing the computational complexity of strategy evaluation, improving strategy evaluation efficiency, and saving processing resources.

[0094] In an optional implementation of this embodiment, after evaluating the second risk control strategy according to the first strategy execution result and the second strategy execution result of each risk control basic data and obtaining the risk control strategy evaluation result, the following is further included: Based on the risk control strategy evaluation results, a second risk control strategy is deployed in the risk control service platform.

[0095] In actual implementation, the risk control strategy evaluation result can indicate the evaluation status of the second risk control strategy that has not been launched, and determine whether the second risk control strategy may affect the normal execution of the risk control strategy after it is launched. Therefore, the second risk control strategy can be deployed in the risk control service platform according to the risk control strategy evaluation result. That is, the updated risk control strategy is launched based on the risk control strategy evaluation result.

[0096] In an optional implementation method, if the risk control strategy evaluation result is passed, a second risk control strategy is deployed in the risk control service platform to implement iterative updates of the risk control strategies in the risk control service platform; if the risk control strategy evaluation result is failed, the corresponding operation and maintenance personnel are prompted with the risk of updating the risk control strategy, who handle the issue and then perform the above-mentioned risk control strategy evaluation process until the risk control strategy evaluation result is passed and a second risk control strategy is deployed in the risk control service platform.

[0097] It should be noted that without interfering with the online risk control service platform, it is necessary to ensure that the updated risk control strategy is fully verified before it goes online, discover and fix potential problems with the updated risk control strategy in advance, and go online only when the risk control strategy evaluation results indicate that the evaluation has passed, thereby reducing the risk of the updated risk control strategy after it goes online and ensuring the stability and reliability of the risk control service platform during operation.

[0098] The embodiments of this specification provide a risk control strategy evaluation method, which realizes that by recording risk control traffic data in an online risk control service platform, data in actual business scenarios can be captured and reproduced in a test environment to verify the performance of a second risk control strategy in the test environment under various circumstances, ensuring the comprehensiveness, coverage and authenticity of the tests in the test environment. The risk control strategy evaluation can be completed more efficiently and accurately, and the consistency and accuracy of the risk control strategy in the online risk control service platform can be guaranteed, which greatly reduces the preparation time of test data in the test environment and reduces the possibility of manual evaluation errors. Without interfering with the online risk control service platform, the second risk control strategy can be fully verified before it goes online, potential problems of the second risk control strategy can be discovered and fixed in advance, and the risks after the second risk control strategy goes online can be reduced, thereby ensuring the stability and reliability of the risk control service platform during operation.

[0099] The following combination Figure 3 , taking the application of the risk control strategy evaluation method provided in this specification in the two-core risk control strategy evaluation scenario as an example, the risk control strategy evaluation method is further explained. Figure 3 A process flow chart of a risk control strategy evaluation method provided by an embodiment of this specification is shown as follows: Figure 3As shown, taking the claims settlement business in the two-core risk control service as an example, asynchronous traffic recording is performed on the claims settlement service platform of the claims settlement business to obtain a large amount of claims settlement traffic data, which can specifically include recording the claims request information at the service entrance, recording the dependent feature data corresponding to the claims request information in the data acquisition module, and recording the first strategy execution result of executing the corresponding claims strategy based on the claims request information and the dependent feature data in the strategy execution module.

[0100] Data cleaning is performed on a large amount of asynchronously recorded claims flow data to screen out valid target flow data. Specifically, a large amount of asynchronously recorded claims flow data can be synchronized to a data warehouse, and the data processing capabilities of the data warehouse are used to clean the claims request information, dependent feature data, and the first strategy execution results to obtain valid claims request information, dependent feature data, and the first strategy execution results.

[0101] Import the selected target traffic data into the test environment and replay the traffic in the test environment. Specifically, based on the claim request information and dependent feature data in each target traffic data, the risk control core uses the Mock Server and the rule engine to execute the updated claim strategy and obtain the corresponding second strategy execution result.

[0102] Compare the first strategy execution result and the second strategy execution result corresponding to each claim request information and dependent feature data, generate a claim strategy evaluation result based on the claim strategy with inconsistent strategy execution results, and update the claim strategy online based on the claim strategy evaluation result.

[0103] By applying the two-core risk control strategy automated evaluation scheme proposed in the embodiments of this specification, by recording the claims flow data in the online claims service platform, it is possible to capture data in actual business scenarios and reproduce them in a test environment to verify the performance of updated claims strategies in the test environment under various circumstances, thereby ensuring the comprehensiveness, coverage and authenticity of the tests conducted in the test environment. This allows the evaluation of claims strategies to be completed more efficiently and accurately, and the consistency and accuracy of the claims strategies in the online claims service platform to be guaranteed, greatly reducing the preparation time for test data in the test environment while reducing the possibility of manual evaluation errors. Without interfering with the online claims service platform, this ensures that the updated claims strategies are fully verified before they go online, discovers and fixes potential problems with the updated claims strategies in advance, reduces the risks of the updated claims strategies after they go online, and ensures the stability and reliability of the claims service platform during operation.

[0104] See also Figure 4 , Figure 4An interface schematic diagram of a risk control strategy evaluation interface provided by an embodiment of the present specification is shown. The risk control strategy evaluation interface is divided into a strategy evaluation initiation interface and a result display interface. The strategy evaluation initiation interface includes a strategy evaluation requirement configuration box, an "Initiate" control, and a "Cancel" control, wherein the strategy evaluation requirement configuration box can be used to guide users to configure strategy evaluation requirements. You can enter the strategy evaluation requirements and then click the "Initiate" control to initiate a strategy evaluation request, or you can directly click the "Initiate" control without entering the strategy evaluation requirements to initiate a strategy evaluation request. The strategy evaluation platform executes the above-mentioned risk control strategy evaluation method when it receives a strategy evaluation request.

[0105] The result display interface includes a result display box, which is used to display the generated risk control strategy evaluation results.

[0106] In actual applications, users can operate controls by clicking, double-clicking, touching, hovering the mouse, sliding, long pressing, voice control, or shaking, etc. The selection is based on actual conditions, and the embodiments of this specification do not impose any limitations on this.

[0107] Corresponding to the above method embodiment, this specification also provides a risk control strategy evaluation device embodiment, Figure 5 FIG. 1 is a schematic diagram showing the structure of a risk control strategy evaluation device provided by an embodiment of this specification. Figure 5 As shown, the device comprises: The acquisition module 502 is configured to acquire multiple pieces of risk control flow data recorded in the risk control service platform under the target risk control business, wherein at least one first risk control strategy is deployed in the risk control service platform, and the risk control flow data includes risk control basic data, the executed first risk control strategy, and the corresponding first strategy execution result; An execution module 504 is configured to execute a second risk control strategy in the test environment based on each risk control basic data to obtain a corresponding second strategy execution result, wherein the second risk control strategy is an updated risk control strategy corresponding to at least one first risk control strategy; The evaluation module 506 is configured to evaluate the second risk control strategy according to the first strategy execution result and the second strategy execution result of each risk control basic data, and obtain a risk control strategy evaluation result.

[0108] Optionally, the acquisition module 502 is further configured to: Record the risk control request information of the risk control service platform and the dependent feature data corresponding to the risk control request information, and use the risk control request information and the dependent feature data as the risk control basic data, wherein the risk control request information is the information carried by the risk control request initiated by the requester, and the dependent feature data is the data obtained from the local database or the third-party platform and required for executing the corresponding first risk control strategy for the risk control request information; Record the first strategy execution result of the corresponding first risk control strategy executed based on the risk control basic data.

[0109] Optionally, the acquisition module 502 is further configured to: A first recording unit is configured at a service entrance of the risk control service platform, and risk control request information of the risk control service platform is recorded by the first recording unit; A second recording unit is configured in the data acquisition module of the risk control service platform, and the dependent feature data acquired by the data acquisition module from the local database or the third-party platform based on the risk control request information is recorded by the second recording unit; or a second recording unit is configured in the feature storage module of the risk control service platform, and the dependent feature data corresponding to the risk control request information stored in the feature storage module is recorded by the second recording unit; A third recording unit is configured in the policy execution module of the risk control service platform, and a first policy execution result of the first risk control policy corresponding to the risk control basic data is recorded through the third recording unit; or a third recording unit is configured in the result storage module of the risk control service platform, and a first policy execution result of the first risk control policy corresponding to the risk control basic data is recorded through the third recording unit.

[0110] Optionally, the device further comprises a screening module configured to: Determine the strategic assessment needs of the target risk control business; Based on the strategy evaluation requirements, filter out the target traffic data from multiple risk control traffic data; Accordingly, the execution module 504 is further configured to: The corresponding second risk control strategy is executed in the test environment based on the risk control basic data in each target traffic data to obtain the corresponding second strategy execution result.

[0111] Optionally, the evaluation module 506 is further configured to: Determine candidate risk control data for which the first strategy execution result and the second strategy execution result are inconsistent in each risk control basic data; According to the candidate risk control data, the corresponding second risk control strategy to be executed is evaluated to determine the risk control strategy evaluation result.

[0112] Optionally, the evaluation module 506 is further configured to: Grouping the candidate risk control data according to the risk control strategy to obtain at least one candidate risk control data group; The second risk control strategy executed corresponding to each candidate risk control data group is used as the first abnormal risk control strategy; According to the first abnormal risk control strategy, a risk control strategy evaluation result is generated.

[0113] Optionally, the evaluation module 506 is further configured to: Determine the verification personnel corresponding to the first abnormal risk control strategy, and push the first abnormal risk control strategy to the corresponding verification personnel; Based on the verification results fed back by the verification personnel for the first abnormal risk control strategy, a risk control strategy evaluation result is generated.

[0114] Optionally, the evaluation module 506 is further configured to: Determine candidate risk control data for which the first strategy execution result and the second strategy execution result are inconsistent in each risk control basic data; Determine each candidate second risk control strategy to be executed corresponding to the candidate risk control data; Determine the second abnormal risk control strategy that is the same as the first risk control strategy among the candidate second risk control strategies; According to the second abnormal risk control strategy, a risk control strategy evaluation result is generated.

[0115] Optionally, the device further includes an updating module configured to: Based on the risk control strategy evaluation results, a second risk control strategy is deployed in the risk control service platform.

[0116] The embodiment of the present specification provides a risk control strategy evaluation device, including an acquisition module, an execution module, and an evaluation module. Through the interaction and cooperation of each module, it is possible to capture data in actual business scenarios by recording risk control traffic data in an online risk control service platform, and reproduce it in a test environment to verify the performance of a second risk control strategy in the test environment under various circumstances, thereby ensuring the comprehensiveness, coverage, and authenticity of the tests conducted in the test environment. The evaluation of the risk control strategy can be completed more efficiently and accurately, and the consistency and accuracy of the risk control strategy in the online risk control service platform can be guaranteed, thereby greatly reducing the preparation time for test data in the test environment and reducing the possibility of manual evaluation errors. Without interfering with the online risk control service platform, the second risk control strategy can be fully verified before it goes online, potential problems of the second risk control strategy can be discovered and fixed in advance, and the risks after the second risk control strategy goes online can be reduced, thereby ensuring the stability and reliability of the risk control service platform during operation.

[0117] The above is a schematic scheme of a risk control strategy evaluation device of this embodiment. It should be noted that the technical scheme of the risk control strategy evaluation device and the technical scheme of the above-mentioned risk control strategy evaluation method belong to the same concept, and the details not described in detail in the technical scheme of the risk control strategy evaluation device can be found in the description of the technical scheme of the above-mentioned risk control strategy evaluation method.

[0118] Figure 6The block diagram of a computing device according to an embodiment of the present specification is shown. The components of the computing device 600 include but are not limited to a memory 610 and a processor 620. The processor 620 is connected to the memory 610 via a bus 630, and the database 650 is used to store data.

[0119] The computing device 600 also includes an access device 640 that enables the computing device 600 to communicate via one or more networks 660. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 640 may include one or more of any type of network interface (e.g., a network interface card (NIC)) that is wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a world-wide interoperability for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, and a near field communication (NFC).

[0120] In one embodiment of the present specification, the above components of the computing device 600 and Figure 6 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 6 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0121] The computing device 600 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 600 may also be a mobile or stationary server.

[0122] Among them, the processor 620 is used to execute the following computer-executable instructions, which, when executed by the processor, implement the steps of the above-mentioned risk control strategy evaluation method.

[0123] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above-mentioned risk control strategy evaluation method belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be found in the description of the technical scheme of the above-mentioned risk control strategy evaluation method.

[0124] An embodiment of the present specification also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned risk control strategy evaluation method.

[0125] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned risk control strategy evaluation method belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be found in the description of the technical scheme of the above-mentioned risk control strategy evaluation method.

[0126] An embodiment of the present specification also provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned risk control strategy evaluation method.

[0127] The above is a schematic scheme of a computer program of this embodiment. It should be noted that the technical scheme of the computer program and the technical scheme of the above-mentioned risk control strategy evaluation method belong to the same concept, and the details not described in detail in the technical scheme of the computer program can be found in the description of the technical scheme of the above-mentioned risk control strategy evaluation method.

[0128] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0129] Computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. Computer readable media may include: any entity or device capable of carrying computer program codes, recording media, USB flash drives, mobile hard disks, magnetic disks, optical disks, computer memories, read-only memories (ROM), random access memories (RAM), electric carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the contents of computer readable media may be appropriately increased or decreased according to the requirements of patent practice. For example, in some regions, according to patent practice, computer readable media do not include electric carrier signals and telecommunication signals.

[0130] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0131] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0132] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A risk control strategy evaluation method, characterized in that: include: Acquire multiple pieces of risk control traffic data recorded in a risk control service platform under a target risk control business, wherein at least one first risk control strategy is deployed in the risk control service platform, and the risk control traffic data includes risk control basic data, an executed first risk control strategy, and a corresponding first strategy execution result; Executing a second risk control strategy in the test environment based on each risk control basic data to obtain a corresponding second strategy execution result, wherein the second risk control strategy is an updated risk control strategy corresponding to the at least one first risk control strategy; According to the first strategy execution result and the second strategy execution result of each risk control basic data, the second risk control strategy is evaluated to obtain a risk control strategy evaluation result.

2. The risk control strategy evaluation method according to claim 1, characterized in that: The obtaining of multiple pieces of risk control flow data recorded in the risk control service platform under the target risk control business includes: Recording the risk control request information of the risk control service platform and the dependent characteristic data corresponding to the risk control request information, and using the risk control request information and the dependent characteristic data as the risk control basic data, wherein the risk control request information is the information carried by the risk control request initiated by the requester, and the dependent characteristic data is the data obtained from the local database or the third-party platform and required for executing the corresponding first risk control strategy for the risk control request information; Record a first strategy execution result of executing a corresponding first risk control strategy based on the risk control basic data.

3. The risk control strategy evaluation method according to claim 2, characterized in that: The risk control request information of the recorded risk control service platform and the dependent characteristic data corresponding to the risk control request information include: A first recording unit is configured at a service entrance of the risk control service platform, and risk control request information of the risk control service platform is recorded by the first recording unit; A second recording unit is configured in the data acquisition module of the risk control service platform, and the dependency feature data acquired by the data acquisition module from a local database or a third-party platform based on the risk control request information is recorded by the second recording unit; or a second recording unit is configured in the feature storage module of the risk control service platform, and the dependency feature data corresponding to the risk control request information stored in the feature storage module is recorded by the second recording unit; The recording of a first strategy execution result of a first risk control strategy corresponding to the risk control basic data includes: A third recording unit is configured in the policy execution module of the risk control service platform, and the first policy execution result of the first risk control policy corresponding to the risk control basic data is recorded by the third recording unit; or a third recording unit is configured in the result storage module of the risk control service platform, and the first policy execution result of the first risk control policy corresponding to the risk control basic data is recorded by the third recording unit.

4. The risk control strategy evaluation method according to claim 1, characterized in that: After obtaining the plurality of risk control flow data recorded in the risk control service platform under the target risk control business, the method further includes: Determine the strategy assessment requirements for the target risk control business; Based on the strategy evaluation requirements, filter out target traffic data from the multiple risk control traffic data; Correspondingly, executing the second risk control strategy in the test environment based on each risk control basic data to obtain the corresponding second strategy execution result includes: The corresponding second risk control strategy is executed in the test environment based on the risk control basic data in each target traffic data to obtain the corresponding second strategy execution result.

5. The risk control strategy evaluation method according to claim 1, characterized in that: The step of evaluating the second risk control strategy according to the first strategy execution result and the second strategy execution result of each risk control basic data to obtain the risk control strategy evaluation result includes: Determine candidate risk control data for which the first strategy execution result and the second strategy execution result are inconsistent among the risk control basic data; According to the candidate risk control data, the corresponding second risk control strategy to be executed is evaluated to determine a risk control strategy evaluation result.

6. The risk control strategy evaluation method according to claim 5, characterized in that: The step of evaluating the corresponding second risk control strategy to be executed according to the candidate risk control data and determining the risk control strategy evaluation result includes: Grouping the candidate risk control data according to the risk control strategy to obtain at least one candidate risk control data group; The second risk control strategy executed corresponding to each candidate risk control data group is used as the first abnormal risk control strategy; The risk control strategy evaluation result is generated according to the first abnormal risk control strategy.

7. The risk control strategy evaluation method according to claim 6, characterized in that: Generating the risk control strategy evaluation result according to the first abnormal risk control strategy includes: Determine a verification personnel corresponding to the first abnormal risk control strategy, and push the first abnormal risk control strategy to the corresponding verification personnel; Based on the verification result fed back by the verification personnel for the first abnormal risk control strategy, the risk control strategy evaluation result is generated.

8. The risk control strategy evaluation method according to claim 1, characterized in that: The step of evaluating the second risk control strategy according to the first strategy execution result and the second strategy execution result of each risk control basic data to obtain the risk control strategy evaluation result includes: Determine candidate risk control data for which the first strategy execution result and the second strategy execution result are inconsistent among the risk control basic data; Determining each candidate second risk control strategy to be executed corresponding to the candidate risk control data; Determine the second abnormal risk control strategy that is the same as the first risk control strategy among the candidate second risk control strategies; According to the second abnormal risk control strategy, the risk control strategy evaluation result is generated.

9. The risk control strategy evaluation method according to claim 1, characterized in that: After evaluating the second risk control strategy according to the first strategy execution result and the second strategy execution result of each risk control basic data and obtaining the risk control strategy evaluation result, the method further includes: According to the risk control strategy evaluation result, the second risk control strategy is deployed in the risk control service platform.

10. A risk control strategy evaluation device, characterized in that: include: an acquisition module, configured to acquire a plurality of risk control flow data recorded in a risk control service platform under a target risk control business, wherein at least one first risk control strategy is deployed in the risk control service platform, and the risk control flow data includes risk control basic data, an executed first risk control strategy, and a corresponding first strategy execution result; an execution module, configured to execute a second risk control strategy in a test environment based on each risk control basic data to obtain a corresponding second strategy execution result, wherein the second risk control strategy is an updated risk control strategy corresponding to the at least one first risk control strategy; The evaluation module is configured to evaluate the second risk control strategy according to the first strategy execution result and the second strategy execution result of each risk control basic data, and obtain a risk control strategy evaluation result.

11. A computing device, characterized in that: include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the risk control strategy evaluation method described in any one of claims 1 to 9 are implemented.

12. A computer-readable storage medium, characterized in that: It stores computer executable instructions, which, when executed by a processor, implement the steps of the risk control strategy evaluation method described in any one of claims 1 to 9.

13. A computer program product, characterized in that It includes a computer program / instruction, which, when executed by a processor, implements the steps of the risk control strategy evaluation method described in any one of claims 1 to 9.

Images