Data processing method, strategy generation method and data processing system

Abstract

The embodiment of the invention provides a data processing method, a strategy generation method and a data processing system, the data processing method is applied to a data processing unit in the data processing system, the data processing system comprises a strategy generation unit, and the strategy generation unit comprises the steps of determining item types of a plurality of items, and generating a strategy according to the item types, dividing a plurality of risk control strategies into a plurality of risk control strategy sets, the risk control strategies being generated by the strategy generation unit by using strategy generation parameters; a target risk control strategy set corresponding to a target item is determined from the multiple risk control strategy sets, and the target item is any one of the multiple items; performing risk control detection on to-be-detected data corresponding to the target item by using the target risk control strategy set to obtain a risk control detection result of the to-be-detected data, the to-be-detected data being data generated in an execution process of the target item; and the accuracy and efficiency of data risk control detection are improved.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of risk control technology, and in particular to a data processing method. One or more embodiments of this specification also relate to a data processing system, a strategy generation method, a computing device, a computer-readable storage medium, and a computer program product. Background Art

[0002] With the continuous development of insurance services, the control of data risks has become a key issue in the process of implementing insurance services. By conducting data risk control, the risks of insurance services can be effectively reduced and the stable implementation of insurance services can be ensured.

[0003] The current data risk control detection is achieved by manually checking data. However, the manual verification risk control detection method will lead to low efficiency and poor accuracy. Therefore, how to improve the accuracy and efficiency of data risk control detection has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] In view of this, an embodiment of this specification provides a data processing method. One or more embodiments of this specification also relate to a data processing system, a policy generation method, a data processing device, a policy generation 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 data processing method is provided, which is applied to a data processing unit in a data processing system, wherein the data processing system includes a policy generating unit, including: Determining project types of multiple projects, and dividing multiple risk control strategies into multiple risk control strategy sets according to the project types, wherein the risk control strategies are generated by the strategy generation unit using strategy generation parameters; Determining a target risk control strategy set corresponding to a target project from a plurality of risk control strategy sets, wherein the target project is any one of the plurality of projects; The target risk control strategy set is used to perform risk control detection on the data to be detected corresponding to the target project to obtain the risk control detection result of the data to be detected, wherein the data to be detected is the data generated during the execution of the target project.

[0006] According to a second aspect of an embodiment of this specification, a data processing device is provided, which is applied to a data processing unit in a data processing system, wherein the data processing system includes a policy generating unit, including: a risk control strategy set determination module, configured to determine project types of a plurality of projects, and divide a plurality of risk control strategies into a plurality of risk control strategy sets according to the project types, wherein the risk control strategies are generated by the strategy generation unit using strategy generation parameters; a target risk control strategy set determination module, configured to determine a target risk control strategy set corresponding to a target project from a plurality of risk control strategy sets, wherein the target project is any one of the plurality of projects; The risk control detection module is configured to use the target risk control strategy set to perform risk control detection on the data to be detected corresponding to the target project, and obtain the risk control detection result of the data to be detected, wherein the data to be detected is the data generated during the execution of the target project.

[0007] According to a third aspect of an embodiment of this specification, a policy generation method is provided, which is applied to a policy generation unit in a data processing system, wherein the data processing system includes a data processing unit, including: Determine strategy generation parameters, and use the strategy generation parameters to generate multiple risk control strategies to be tested; Using the risk control detection data, a strategy detection is performed on each risk control strategy to be detected, and multiple risk control strategies that pass the strategy detection are obtained, so that the data processing unit can perform risk control detection on the data to be detected generated during the execution of the target project based on the multiple risk control strategies.

[0008] According to a fourth aspect of an embodiment of this specification, a policy generation device is provided, which is applied to a policy generation unit in a data processing system, wherein the data processing system includes a data processing unit, including: A strategy generation module is configured to determine strategy generation parameters and generate a plurality of risk control strategies to be tested using the strategy generation parameters; The strategy detection module is configured to use the risk control detection data to perform strategy detection on each risk control strategy to be detected, and obtain multiple risk control strategies that pass the strategy detection, so that the data processing unit can perform risk control detection on the data to be detected generated during the execution of the target project based on the multiple risk control strategies.

[0009] According to a fifth aspect of an embodiment of this specification, there is provided a data processing system, including a policy generating unit and a data processing unit; The strategy generation unit is used to determine strategy generation parameters, and use the strategy generation parameters to generate multiple risk control strategies to be detected, and use the risk control detection data to perform strategy detection on each risk control strategy to be detected, so as to obtain multiple risk control strategies that pass the strategy detection; The data processing unit is used to determine the project types of multiple projects, and divide multiple risk control strategies into multiple risk control strategy sets according to the project types, and determine a target risk control strategy set corresponding to a target project from the multiple risk control strategy sets, wherein the target project is any one of the multiple projects, and the target risk control strategy set is used to perform risk control detection on the data to be detected corresponding to the target project to obtain the risk control detection result of the data to be detected, wherein the data to be detected is the data generated during the execution of the target project.

[0010] According to a sixth aspect of an embodiment of this specification, a computing device is provided, including: Memory and processor; The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions. When the computer programs / instructions are executed by the processor, the steps of any one of the above methods are implemented.

[0011] According to a seventh aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores a computer program / instruction, and the computer program / instruction implements the steps of any one of the above methods when executed by a processor.

[0012] According to an eighth aspect of the embodiments of this specification, a computer program product is provided, including a computer program / instruction, which implements the steps of any one of the above methods when executed by a processor.

[0013] The data processing method applied to the data processing unit provided in one or more embodiments of the present specification can utilize multiple risk control strategies generated by the policy generation unit in the data processing system, and divide the multiple risk control strategies into multiple risk control strategy sets according to the project type, so as to facilitate the subsequent efficient determination of the corresponding target risk control strategy set for the target project; then, for the data to be tested generated during the execution of the target project, the target risk control strategy set can be used to automatically perform risk control testing on the data to be tested, so as to quickly obtain accurate risk control testing results, avoiding the problem of low efficiency and poor accuracy caused by manually checked risk control testing methods, and improving the accuracy and efficiency of data risk control testing. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is an application schematic diagram of a data processing method provided by an embodiment of this specification; Figure 2 is a flow chart of a data processing method provided by an embodiment of this specification; Figure 3 is a flow chart of a strategy generation method provided by an embodiment of this specification; Figure 4It is a processing flow chart of a data processing method and a strategy generation method provided by an embodiment of this specification; Figure 5 is a structural diagram of a data processing system provided by an embodiment of this specification; Figure 6 is a structural schematic diagram of a data processing device provided by an embodiment of this specification; Figure 7 It is a structural diagram of a strategy generation device provided by an embodiment of this specification; Figure 8 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0015] 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.

[0016] 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", "said" 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.

[0017] 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".

[0018] 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.

[0019] In one or more embodiments of this specification, a large model refers to a deep learning model with large-scale model parameters, which usually contains hundreds of millions, tens of billions, hundreds of billions, trillions, or even more than 10 trillion model parameters. A large model can also be called a foundation model / foundation model. The large model is pre-trained with large-scale unlabeled corpus to produce a pre-trained model with more than 100 million parameters. This model can adapt to a wide range of downstream tasks, and the model has good generalization ability, such as a large-scale language model (LLM), a multi-modal pre-training model, etc.

[0020] When the big model is used in practice, only a small number of samples are needed to fine-tune the pre-trained model and it can be applied to different tasks. The big model can be widely used in natural language processing (NLP), computer vision and other fields. Specifically, it can be applied to computer vision tasks such as visual question answering (VQA), image caption (IC), image generation, as well as natural language processing tasks such as text-based sentiment classification, text summary generation, and machine translation. The main application scenarios of the big model include digital assistants, intelligent robots, search, online education, office software, e-commerce, intelligent design, etc.

[0021] First, the terms involved in one or more embodiments of this specification are explained.

[0022] BMI (Body Mass Index): refers to body mass index.

[0023] With the continuous development of insurance services, the control of data risks has become a key issue in the process of implementing insurance services. By conducting data risk control, the risks of insurance services can be effectively reduced and the stable implementation of insurance services can be ensured.

[0024] In the insurance industry, risk control strategies are an important means to ensure the company's risk management and stable business operations. Currently, insurance companies usually face the following problems when deploying risk control strategies: The manual process is complex and time-consuming: The deployment process of risk control strategies usually requires the actuarial risk control team to submit a form to the development and testing team for offline configuration, testing, and deployment. This process requires multiple communications and coordination, which consumes a lot of time and human resources.

[0025] Dependence on development and testing resources: Since the deployment of risk control strategies requires the participation of development and testing teams, this leads to a high degree of reliance on development and testing resources. If development and testing resources are tight, the launch cycle of the strategy will be greatly extended, affecting the response speed and flexibility of the company's business.

[0026] Low strategy reusability: Although 80% of risk control strategies can be reused between different products, the efficiency of strategy reuse is not high in the current process. Every time a new product is launched, the strategy needs to be rewritten and tested, which results in serious duplication of work.

[0027] Online and offline consistency issues: Since the testing and deployment of policies are separated, it is easy to cause inconsistencies between online and offline policies, which increases risks and management difficulties.

[0028] Long launch cycle for new products: In the existing process, the launch of new products requires resubmission and testing of risk control strategies. The process is complicated and cumbersome, which affects the speed of new products to market.

[0029] Based on this, in this specification, a data processing method is provided. One or more embodiments of this specification also relate to a data processing system, a policy generation method, a data processing device, a policy generation 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.

[0030] See also Figure 1 , Figure 1 A schematic diagram of an application of a data processing method provided according to an embodiment of the present specification is shown. Figure 1 It can be seen that the data processing method provided in the embodiment of the present application can be applied to Figure 1 The application scenarios shown are not limited to these. Figure 1In the application scenario shown, the method is applied to a server 10, and the server 10 can be connected to one or more client devices 20 through a local area network connection, a wide area network connection, an Internet connection, or other types of data networks. The client devices 20 here may include but are not limited to: smart phones, tablet computers, laptops, PDAs, personal computers, smart home devices, vehicle-mounted devices, etc. The client device 20 can interact with the user through a graphical user interface to implement the method provided in the embodiments of this specification.

[0031] In the embodiments of the present specification, the system composed of the client device 20 and the server 10 can execute the following steps: the client device 20 executes sending the insurance information uploaded by the user through the graphical user interface to the server 10; the server 10 executes operations such as building a policy set, self-service selection of policies / policy sets, and new product launches; wherein, building a policy set means: according to business needs, multiple risk control policies are constructed into a risk control policy set; self-service selection of policies / policy sets means: on the CeMo operation platform, the corresponding policy set is selected for the new project; new product launch means: on the CeMo operation platform, the configured risk control policy is automatically called, the customer's insurance information is risk assessed and the results are fed back to the client; thereby improving the overall efficiency and accuracy of risk control detection.

[0032] See also Figure 2 , Figure 2 A flow chart of a data processing method provided according to an embodiment of the present specification is shown. The data processing method is applied to a data processing unit in a data processing system, and the data processing system includes a strategy generation unit; specifically, the following steps are included.

[0033] Step 202: determine project types of multiple projects, and divide multiple risk control strategies into multiple risk control strategy sets according to the project types, wherein the risk control strategies are generated by the strategy generation unit using strategy generation parameters.

[0034] Among them, the data processing system can be understood as a system used to process the data to be tested. The data processing system is a data processing system for insurance risk control. Risk control detection is performed on the data to be tested through risk control strategies to detect whether there is a risk control risk in the data to be tested.

[0035] The data processing unit can be understood as a unit in the data processing system that is used to perform risk control detection on the data to be detected, and the policy generation unit can be understood as a unit in the data processing system that is used to generate risk control policies; the data processing unit or the policy generation unit can be a service-end, server, platform and other units. For example, the data processing unit can be a modeling operation platform, which is used to perform risk control detection through risk control classification; the policy generation unit can be a rule engine, which is used to generate risk control policies and provide risk control policies to the data processing unit during the process of the data processing unit performing risk control detection.

[0036] Among them, the project can be understood as a service that needs to be tested for risk control, for example, the project can be insurance services, financial services, etc. The project type can be understood as the type corresponding to the project, and different projects can be of the same project type or different project types; taking the project as an insurance service as an example, multiple projects can be accident insurance services, health insurance services, travel insurance services, and car insurance services, etc., and the accident insurance service corresponds to the accident type, the health insurance service corresponds to the health type, and the travel insurance service and car insurance service correspond to the travel insurance type.

[0037] The risk control strategy can be understood as a strategy for performing risk control detection on the data to be detected, so as to determine whether the data to be detected has risks; the risk control strategy can be stored in the strategy generation unit, or the risk control strategy can be a data storage unit obtained from the strategy generation unit and stored locally by the data storage unit. The risk control strategy can be a code statement, a script, an application, etc., and is not specifically limited here. For example, in the case where the project is an insurance service, the risk control strategy can be: age risk assessment strategy, disease history risk assessment strategy, BMI risk assessment strategy.

[0038] The risk control strategy set can be understood as a set consisting of one or at least two risk control strategies. For example, in the case where the project is an insurance service, the risk control strategy set may include: age risk assessment strategy, disease history risk assessment strategy, and BMI risk assessment strategy.

[0039] The strategy generation parameter can be understood as a parameter for generating a risk control strategy, and the strategy generation parameter can be a code statement or a strategy generation text. It should be noted that the risk control strategy is a strategy generated by the strategy generation unit using the strategy generation parameter and tested by the risk control detection data.

[0040] In one or more embodiments provided in this specification, since 80% of the strategies (risk control strategies) between different projects (insurance products) are reusable, repeated writing and testing of strategies in the existing process wastes resources. Based on this, this method maximizes the reusability of strategies, reduces duplication of work, and improves the reusability of strategies by establishing a strategy set and a reuse mechanism; the specific implementation method is as follows.

[0041] The project types are multiple; The multiple risk control strategies are divided into multiple risk control strategy sets according to the project type, including: Receiving a policy division request sent by a client, wherein the policy division request carries an association relationship between each project type and each risk control strategy, and the policy division request is sent by the client when a user performs a policy division operation on a policy division interface; Based on the association relationship, determining the associated risk control strategy corresponding to each project type from the multiple risk control strategies; Based on the associated risk control strategies corresponding to the project types, a risk control strategy set corresponding to the project types is constructed.

[0042] Among them, the policy division request can be a request to divide multiple risk control strategies into a risk control strategy set; the association relationship can be information that characterizes the relationship between each project type and each risk control strategy; the policy division interface can be understood as a human-computer interaction interface for dividing multiple risk control strategies into risk control strategy sets, and the policy division interface can be an application interface or a web page; the policy division operation can be understood as an operation of constructing a policy set.

[0043] The associated risk control strategy can be understood as a strategy associated with the project type. For example, the age risk assessment strategy, the disease history risk assessment strategy, and the BMI risk assessment strategy can be associated with the children's medical insurance service (project). The risk control strategy set consisting of the age risk assessment strategy, the disease history risk assessment strategy, and the BMI risk assessment strategy corresponds to the children's medical insurance service.

[0044] Taking the application of the data processing method provided in this specification in an insurance scenario as an example, the data processing method is explained, wherein the project is children's medical insurance; the risk control strategies are age risk assessment strategy, medical history risk assessment strategy, and BMI risk assessment strategy; and the data processing unit is a modeling operation platform.

[0045] Based on this, this method can build a policy set on the CeMo operation platform. Specifically, on the CeMo operation platform, operators can build a policy set (i.e., a risk control policy set) based on insurance service needs. The policy set is composed of multiple stock policies selected on demand to meet different business scenarios. For the "children's medical insurance" product, operators may choose to combine existing health insurance (product line) related policies. For example, the policy set of children's medical insurance products may include stock policies such as age risk assessment strategy, disease history risk assessment strategy, and BMI risk assessment strategy.

[0046] It should be noted that before building a policy set, this method also needs to establish an association between policies and rules on the CeMo operation platform; on the CeMo operation platform, the risk control team will establish an association between the generated stock policies and specific rules, and declare the applicable product line (such as health insurance), policy primary key, and information about the feedback business after hitting. For example, policy 1 (age risk assessment strategy) is associated with age rules; policy 2 (disease history risk assessment strategy) is associated with disease history rules; policy 3 (BMI risk assessment strategy) is associated with BMI rules; and policies 1, 2, and 3 can also declare that the applicable product line is health insurance. That is, policies 1, 2, and 3 are marked as applicable to health insurance.

[0047] Step 204: Determine a target risk control policy set corresponding to a target project from a plurality of risk control policy sets, wherein the target project is any one of the plurality of projects.

[0048] In one or more embodiments provided in this specification, since the launch of a new project (insurance product) requires resubmission and testing of the risk control strategy, the process is cumbersome. Therefore, this method simplifies the risk control strategy configuration and launch process of new products through self-service selection of risk control strategy and approval mechanism, simplifies the new product launch process, and accelerates the listing process of new products. The specific implementation method is as follows.

[0049] Determining a target risk control strategy set corresponding to a target project from a plurality of risk control strategy sets includes: receiving a policy set determination request for the target project sent by a client, wherein the policy set determination request carries a policy set identifier corresponding to the target project, and the policy set determination request is sent by the client when a user performs a policy set processing operation on a policy set processing interface; Based on the policy set identifier, a target risk control policy set corresponding to the target project is determined from the multiple risk control policy sets.

[0050] Among them, the policy set determination request can be understood as a request for selecting a corresponding risk control policy set for a target project; the policy set identifier can be understood as information used to uniquely identify a risk control policy set, for example, the policy set identifier can be a risk control policy set name or a risk control policy set identifier.

[0051] The policy set processing interface can be understood as a human-computer interaction interface for selecting a corresponding risk control policy set for a target project, and the policy set processing interface can be an application interface or a web page. The policy set processing operation can be understood as an operation performed by a user on the policy set processing interface to select a corresponding risk control policy set for a target project.

[0052] Continuing with the above example, in this method, during the self-service selection of the policy set, the operator self-selects the policy set required for the "Children's Medical Insurance Service" product to be launched on the human-computer interaction interface provided by the CeMo operation platform, so that the CeMo operation platform can determine the policy set corresponding to the children's medical insurance service based on the user's selection. After the selection is completed, submit the approval process. For example, the example operation is: the team selected the policy set required for the "Children's Medical Insurance Service" product on the CeMo operation platform, including age risk assessment strategy, disease history risk assessment strategy and BMI risk assessment strategy. Then, the team submitted the policy set for approval.

[0053] In one or more embodiments provided in this specification, in the process of self-service selection of risk control strategies, this method can also select a target risk control strategy from multiple risk control strategies, and build a target risk control strategy set based on the target risk control strategy, so as to flexibly select a suitable risk control strategy according to actual needs and avoid the problem that the pre-built risk control strategy set is incompatible with the target project; the specific implementation method is: Determining a target risk control strategy set corresponding to a target project from a plurality of risk control strategy sets includes: receiving a policy set determination request for the target project sent by a client, wherein the policy set determination request carries a policy identifier corresponding to the target project, and the policy set determination request is sent by the client when a user performs a policy set processing operation on a policy set processing interface; Based on the strategy identifier, a target risk control strategy corresponding to the target project is determined from the multiple risk control strategies, and based on the target risk control strategy, a target risk control strategy set corresponding to the target project is constructed.

[0054] The strategy identifier may be understood as information used to uniquely identify a risk control strategy. For example, the strategy identifier may be a risk control strategy name or a risk control strategy identifier.

[0055] Following the above example, in the process of self-service strategy selection, the operator selects the strategy required for the "Children's Medical Insurance Service" product to be launched on the human-computer interaction interface provided by the CeMo operation platform, so that the CeMo operation platform can determine the risk control strategy (i.e., target risk control strategy) corresponding to the children's medical insurance service according to the user's choice, and form a risk control strategy set (i.e., target risk control strategy set) based on the risk control strategy. After the selection is completed, submit the approval process. For example, the example operation is: the team selects the strategy required for the "Children's Medical Insurance Service" product on the CeMo operation platform, including age risk assessment strategy, disease history risk assessment strategy, and BMI risk assessment strategy. Then, the strategy is constructed into a strategy set, and the team submits the strategy set for approval.

[0056] It should be noted that in this method, during the approval and release process, the approval team reviews the policies or policy sets submitted by the business team to ensure that they meet the company's risk control requirements. After the review is passed, the policy or policy set is released online. For example, the approval personnel receive the policy or policy set application submitted by the business team; the approval personnel review the rules and test results of each policy to confirm that it meets the company's risk control standards; the approval personnel approve the policy set and release it online.

[0057] In one or more embodiments provided in this specification, the step of performing risk control detection on the data to be detected corresponding to the target project by using the target risk control strategy set and obtaining the risk control detection result of the data to be detected further includes: Receiving the data to be detected sent by the client, wherein the data to be detected is sent by the client when the user performs a data processing operation on a data processing interface; Among them, the data to be tested can be understood as data that needs to be tested for risks (i.e., risk control testing) to determine whether there are risks; when this method is applied to an insurance scenario, the target project is the insurance service; after the insurance service is put into operation, the insured person can participate in the insurance service; in the process of participating in the insurance service, the user needs to submit the corresponding insurance information (i.e., the data to be tested), including but not limited to: age, physical health information, disease information, etc.

[0058] The data processing interface can be understood as a human-computer interaction interface through which a user submits data to be detected. The data processing interface can be an application program interface or a web page.

[0059] Continuing with the above example, when users participate in insurance services, they need to fill in the insurance information in the insurance interface (data processing interface) of the client; after the user completes filling in the insurance information, the client can send the insurance information to the server (Cemulation Operation Platform) for risk control detection.

[0060] Step 206: Using the target risk control strategy set, perform risk control detection on the data to be detected corresponding to the target project to obtain the risk control detection result of the data to be detected, wherein the data to be detected is the data generated during the execution of the target project.

[0061] Among them, risk control detection can be understood as a risk assessment operation; the risk control detection result can be understood as the result obtained from the risk control detection of the data to be detected; for example, the risk control detection result can be a risk level or a risk score.

[0062] In one or more embodiments provided in this specification, the step of performing risk control detection on the data to be detected corresponding to the target project by using the target risk control strategy set to obtain the risk control detection result of the data to be detected includes: Obtaining a target risk control strategy included in the target risk control strategy set from a data storage unit, and performing risk control detection on the data to be detected using the target risk control strategy to determine a risk control detection result of the data to be detected; or The target risk control strategy included in the target risk control strategy set is called from the strategy generation unit, and the target risk control strategy is used to perform risk control detection on the data to be detected to determine the risk control detection result of the data to be detected.

[0063] Among them, the data storage unit can be a unit for storing risk control strategies, and the data storage unit is associated with the data processing unit; for example, the data storage unit can be a database, a local disk of the data storage unit, a server, etc., and no specific restrictions are made here.

[0064] Using the above example, after the new insurance product (target project) is launched, the data processing system will automatically call the configured risk control strategy, make automated decisions on the insurance information provided by the user, and provide timely feedback on the results. The risk control strategy can be stored in the strategy generation unit, or the risk control strategy can be obtained from the strategy generation unit by the data storage unit and stored locally.

[0065] Based on this, in the process of risk detection, the modeling operation platform can obtain the risk control strategy from the local disk, and use the risk control strategy to conduct risk assessment on the insurance information to obtain the corresponding risk score; or, the modeling operation platform can call the risk control strategy stored in the rule engine, and use the risk control strategy to conduct risk assessment on the insurance information to obtain the corresponding risk score. For example, the age risk assessment strategy is: between 18 and 60 years old, the risk score is 1. The disease history risk assessment strategy is: customers with a history of major diseases, the risk score is 3. The BMI risk assessment strategy is: customers with a body mass index (BMI) of more than 30, the risk score is 2. The user's insurance information is evaluated through this risk assessment strategy (risk control strategy) to obtain the user's risk score.

[0066] In the above embodiments, the method can obtain risk control strategies from a data storage unit or a strategy generation platform for risk detection, thereby realizing flexible storage of risk control strategies according to actual conditions, improving the applicability of the method, and realizing rapid deployment and effective operation of risk control strategies in actual product applications.

[0067] In one or more embodiments provided in this specification, after performing risk control detection on the data to be detected corresponding to the target project using the target risk control strategy set and obtaining the risk control detection result of the data to be detected, the method further includes: The risk control detection result is sent to the client.

[0068] Continuing with the above example, after obtaining the risk score (i.e., the risk control detection result), the result can be fed back to the client in a timely manner so as to be displayed to the user.

[0069] The data processing method applied to the data processing unit provided in one or more embodiments of the present specification can utilize multiple risk control strategies generated by the policy generation unit in the data processing system, and divide the multiple risk control strategies into multiple risk control strategy sets according to the project type, so as to facilitate the subsequent efficient determination of the corresponding target risk control strategy set for the target project; then, for the data to be tested generated during the execution of the target project, the target risk control strategy set can be used to automatically perform risk control testing on the data to be tested, so as to quickly obtain accurate risk control testing results, avoiding the problem of low efficiency and poor accuracy caused by manually checked risk control testing methods, and improving the accuracy and efficiency of data risk control testing.

[0070] See also Figure 3 , Figure 3 A flow chart of a policy generation method provided according to an embodiment of the present specification is shown. The policy generation method is applied to a policy generation unit in a data processing system, wherein the data processing system includes a data processing unit; the method specifically includes the following steps.

[0071] Step 302: Determine strategy generation parameters, and use the strategy generation parameters to generate multiple risk control strategies to be tested.

[0072] Among them, the policy generation parameter can be understood as a parameter for generating the risk control policy, and the policy generation parameter can be a code statement or a policy generation text; the risk control policy to be tested is a policy that requires policy testing.

[0073] In one or more embodiments provided in this specification, the current development process of risk control strategies relies on development and testing resources for offline testing and deployment, resulting in a long online cycle and affecting business response speed. This method aims to achieve rapid deployment and release of risk control strategies through the online operation system, thereby improving the efficiency of risk control strategy deployment and overall efficiency. In addition, due to the separation of testing and deployment of current risk control strategies, it is easy to cause inconsistencies in online and offline strategies. This method achieves consistency and controllability of strategies through online management of rule engines and policy sets, thereby achieving consistency of risk control strategies online and offline. Based on this, this method utilizes the policy generation unit in the data processing system to generate risk control strategies; and then utilizes the data processing unit in the data processing system to perform risk detection based on the risk control strategies; and the way in which the policy generation unit generates risk control strategies is as follows.

[0074] The policy generation parameter is a code statement or a policy generation text; The determining strategy generation parameters includes: Receiving the code statement or policy generation text sent by the client, wherein the code statement is sent by the client when the user performs a code statement writing operation on the policy generation interface, and the policy generation text is sent by the client when the user performs a policy generation operation on the policy generation interface; The method of using the strategy generation parameters to generate multiple risk control strategies to be tested includes: In a case where the policy generation parameter is the policy generation text, inputting the policy generation text into a policy generation model to obtain the multiple risk control policies to be detected; or When the policy generation parameter is the code statement, the code statement is used as the multiple risk control policies to be detected.

[0075] The policy generation text can be understood as the text used to generate the risk control policy to be tested. For example, the policy generation text can be "generate a code to test the risk scores of customers of different age groups". The policy generation model can be understood as a large language model, which is used to perform language reasoning based on the policy generation text to obtain a model of code statements corresponding to the policy generation text.

[0076] The strategy generation interface can be understood as a human-computer interaction interface for generating risk control strategies. The strategy generation interface can be an application interface or a web page. The strategy generation operation can be understood as an operation in which a user inputs a strategy generation text, thereby realizing the generation of a risk control strategy.

[0077] Taking the application of the strategy generation method provided in this specification in an insurance scenario as an example, the strategy generation method is explained, wherein the project is children's medical insurance; the risk control strategies are age risk assessment strategy, medical history risk assessment strategy, and BMI risk assessment strategy; and the strategy generation unit is a rule engine.

[0078] Based on this, in the process of writing risk control rules, the actuarial risk control team can write relevant risk control rules (i.e., code statements) according to the needs of the "Children's Medical Insurance" product through the human-computer interaction interface provided by the rule engine. For example, a series of rules are written to assess risks based on factors such as the insured's age, health status, and previous medical history. The sample rule (i.e., the risk control strategy to be tested) is: For those aged between 18 and 60, the risk score is 1. For customers with a history of major diseases, the risk score is 3. For customers with a body mass index (BMI) of more than 30, the risk score is 2.

[0079] Alternatively, in the process of writing risk control rules, the actuarial risk control team can input a rule generation text "generate a code to test the risk scores of customers of different age groups" through the human-computer interaction interface provided by the rule engine according to the needs of the "children's medical insurance" product, and input the rule generation text (i.e., the strategy generation text) into the code generation model (i.e., the strategy generation model) for language reasoning to obtain the rule "age between 18 and 60 years old, risk score is 1" (i.e., the risk control strategy to be tested).

[0080] Step 304: Using the risk control detection data, perform a strategy detection on each risk control strategy to be detected, and obtain multiple risk control strategies that pass the strategy detection, so that the data processing unit can perform risk control detection on the data to be detected generated during the execution of the target project based on the multiple risk control strategies.

[0081] Among them, the risk control detection data can be understood as data used to perform strategy detection on the risk control strategy to be detected. For example, the risk control detection data can be insurance information used to perform strategy detection on the risk control strategy to be detected.

[0082] In one or more embodiments provided in this specification, the use of risk control detection data to perform strategy detection on each risk control strategy to be detected, and obtaining multiple risk control strategies that pass the strategy detection, includes: Performing risk control detection on the risk control detection data using the risk control strategies to be detected, and obtaining risk control detection results corresponding to the risk control strategies to be detected; The risk control strategies to be tested corresponding to the multiple risk control detection results that meet the preset detection pass conditions are determined as the multiple risk control strategies.

[0083] The risk control detection result may be understood as the detection result of the risk control strategy to be detected, for example, the risk control detection result performs risk detection on the risk control detection data and gives a risk score or risk level.

[0084] Among them, satisfying the preset detection pass condition can be understood as multiple risk control detection results being consistent with the actual risk control detection results, thereby determining that the risk control strategy to be tested can accurately identify risks.

[0085] Continuing with the above example, in the process of testing and verifying the rules, this method requires rigorous testing and verification of the written risk control rules to ensure their accuracy and effectiveness. Specifically, the team first determines the sample data (such as insurance information) for testing the rules, and uses the rule engine to simulate and test these rules to verify their performance in various scenarios. That is, to verify the risk detection capabilities of these rules for sample data. Example tests are: testing the risk scores of customers of different age groups. Testing the risk scores of customers with or without a history of major diseases. Testing the risk scores of customers with different BMIs.

[0086] After completing the test verification of the rules, the stock strategy is generated based on the rules that have passed the test verification; specifically, the rules that have passed the test verification will be used by the rule engine to generate the stock strategy. These strategies are stored in the risk control strategy library for subsequent use. Example stock strategies are: Strategy 1: Age risk assessment strategy. Strategy 2: Disease history risk assessment strategy. Strategy 3: BMI risk assessment strategy.

[0087] The policy generation method applied to the policy generation unit provided in one or more embodiments of this specification can generate multiple risk control policies to be detected by using policy generation parameters, and perform policy detection on each risk control policy to be detected by using risk control detection data, thereby obtaining multiple risk control policies, and subsequently accurately performing risk control detection on the multiple risk control policies after detection; The following combination Figure 4 , taking the application of the data processing method and policy generation method provided in this specification in the insurance scenario as an example, the data processing method and policy generation method are further explained. Among them, Figure 4 A processing flow chart of a data processing method and a strategy generation method provided by an embodiment of the present specification is shown, which specifically includes the following steps.

[0088] The processing of the strategy generation method includes steps 402 to 406.

[0089] Step 402: Write risk control rules: The actuarial risk control team writes risk control rules for insurance products.

[0090] Specifically, in the process of writing risk control rules, the actuarial risk control team can write relevant risk control rules (i.e., code statements) according to the needs of the "children's medical insurance" product through the human-computer interaction interface provided by the rule engine.

[0091] For example, a series of rules are written to assess the risk based on factors such as the insured's age, health status, and medical history. Example rules are: For customers between 18 and 60 years old, the risk score is 1. For customers with a history of major diseases, the risk score is 3. For customers with a body mass index (BMI) over 30, the risk score is 2.

[0092] Alternatively, in the process of writing risk control rules, the actuarial risk control team can input a rule generation text "generate a code to test the risk scores of customers of different age groups" through the human-computer interaction interface provided by the rule engine according to the needs of the "children's medical insurance" product; The rule-generated text is input into the code generation model for language reasoning to obtain the rule "Age between 18 and 60, risk score is 1".

[0093] Step 404: Test and verify the rules: perform simulation testing and verification on the written rules.

[0094] Specifically, in the process of testing and verifying the rules, the written risk control rules need to be strictly tested and verified to ensure their accuracy and effectiveness.

[0095] The team first determined the sample data (such as insurance information) for rule testing, and used the rule engine to simulate and test these rules to verify their performance in various scenarios. In other words, the risk detection capabilities of these rules for sample data were verified. Example tests include: testing the risk scores of customers of different age groups; testing the risk scores of customers with or without a history of major diseases; and testing the risk scores of customers with different BMIs.

[0096] Step 406: Generate stock strategy: The rule engine generates a verified stock strategy.

[0097] Specifically, after completing the test verification of the rules, a stock strategy is generated based on the rules that have passed the test verification; the rules that have passed the test verification will be generated into a stock strategy by the rule engine.

[0098] These strategies are stored in the risk control strategy library for subsequent use. Example stock strategies are: Strategy 1: Age risk assessment strategy. Strategy 2: Disease history risk assessment strategy. Strategy 3: BMI risk assessment strategy.

[0099] The processing process of the data processing method includes steps 408 to 416.

[0100] Step 408: Establish association between strategies and rules: Establish association between stock strategies and specific rules on the modeling operation platform.

[0101] Specifically, before building a policy set, this method needs to establish an association between policies and rules on the policy modeling operation platform; on the policy modeling operation platform, the risk control team will establish an association between the generated stock policies and specific rules, and declare the applicable product line (such as health insurance), policy primary key, and feedback business information after hitting the target.

[0102] For example, strategy 1 (age risk assessment strategy) is associated with the age rule; strategy 2 (disease history risk assessment strategy) is associated with the disease history rule; strategy 3 (BMI risk assessment strategy) is associated with the BMI rule; and strategies 1, 2, and 3 can also declare that the applicable product line is health insurance. In other words, strategies 1, 2, and 3 are marked as applicable to health insurance.

[0103] Step 410: Build a policy set: Build a policy set according to business requirements.

[0104] Specifically, the method can construct a policy set on the CeMo operation platform; on the CeMo operation platform, operators can construct a policy set according to insurance service needs. The policy set is composed of a combination of multiple stock policies selected on demand to meet different business scenarios.

[0105] For the "children's medical insurance" product, operators may choose to combine existing health insurance (product line) related strategies. For example, the strategy set of children's medical insurance products may include: age risk assessment strategy, disease history risk assessment strategy, BMI risk assessment strategy and other existing strategies.

[0106] Step 412: Self-service selection of policies / policy sets: The business team self-service selects policy sets on the CeMo operation platform and submits them for approval.

[0107] Specifically, in the process of self-selecting strategies or strategy sets, the operator selects the strategies or strategy sets required for the "children's medical insurance service" product to be launched on the human-computer interaction interface provided by the CeMo operation platform, so that the CeMo operation platform can determine the strategy set corresponding to the children's medical insurance service according to the user's selection. After the selection is completed, the approval process is submitted.

[0108] For example, the team selects the policy set required for the "Children's Medical Insurance Service" product on the Cemo Operation Platform, including age risk assessment policy, disease history risk assessment policy, and BMI risk assessment policy. Then, the team submits the policy set for approval.

[0109] Step 414: Approval and release: The approval team reviews and approves the policy set to go online.

[0110] Specifically, in the process of approving and releasing the product, the approval team reviews the policy or policy set submitted by the business team to ensure that it meets the company's risk control requirements.

[0111] After the review is passed, the policy or policy set is released online. For example, the reviewer receives the policy or policy set application submitted by the business team; the reviewer reviews the rules and test results of each policy to confirm that it meets the company's risk control standards; the reviewer approves the policy set and releases it online.

[0112] Step 416: New product launch: The business system automatically calls the configured risk control strategy, conducts risk assessment on the customer and provides feedback on the results.

[0113] Specifically, when participating in insurance services, users need to fill in the insurance information in the insurance interface of the client; after the user completes filling in the insurance information, the client can send the insurance information to the Cemo operation platform for risk control testing.

[0114] After the new insurance product (target project) is launched, the data processing system will automatically call the configured risk control strategy, make automated decisions on the insurance information provided by the user, and provide timely feedback on the results. The risk control strategy can be stored in the strategy generation unit, or the risk control strategy can be obtained from the strategy generation unit by the data storage unit and stored locally.

[0115] Based on this, in the process of risk detection, the modeling operation platform can obtain the risk control strategy from the local disk, and use the risk control strategy to conduct risk assessment on the insurance information to obtain the corresponding risk score; Alternatively, the CeMo operation platform can call the risk control strategy stored in the rule engine, and use the risk control strategy to conduct a risk assessment on the insurance information to obtain the corresponding risk score.

[0116] For example, the age risk assessment strategy is: those aged between 18 and 60 have a risk score of 1. The disease history risk assessment strategy is: for customers with a history of major diseases, the risk score is 3. The BMI risk assessment strategy is: for customers with a body mass index (BMI) of more than 30, the risk score is 2. The user's insurance information is evaluated through this risk assessment strategy (risk control strategy) to obtain the user's risk score.

[0117] Based on the above steps, it can be seen that the data processing method and strategy generation method in the embodiments of this specification provide a method for insurance companies to quickly launch existing risk control strategies, allowing insurance companies to quickly and accurately deploy risk control strategies for insurance products and ensure the efficiency and consistency of new product launches.

[0118] This method is a method for insurance companies to quickly apply existing risk control strategies to insurance products. It aims to solve the problems of complex processes, reliance on development and testing resources, low policy reusability, poor online and offline consistency, and long new product launch cycles in the deployment of existing risk control strategies. By introducing a rule engine and a modeling operation platform, the rapid deployment and release of risk control strategies can be achieved, the reusability and consistency of strategies can be improved, and the new product launch process can be simplified, thereby improving overall efficiency and accuracy.

[0119] This specification also provides a data processing system embodiment. Figure 5 FIG. 1 shows a schematic diagram of a data processing system provided by an embodiment of the present specification. Figure 5 As shown, the system includes: a strategy generating unit 502 and a data processing unit 504; The strategy generation unit 502 is used to determine strategy generation parameters, and use the strategy generation parameters to generate multiple risk control strategies to be detected, and use the risk control detection data to perform strategy detection on each risk control strategy to be detected, and obtain multiple risk control strategies that pass the strategy detection; The data processing unit 504 is used to determine the project types of multiple projects, and divide multiple risk control strategies into multiple risk control strategy sets according to the project types, and determine a target risk control strategy set corresponding to a target project from the multiple risk control strategy sets, wherein the target project is any one of the multiple projects, and the target risk control strategy set is used to perform risk control detection on the data to be detected corresponding to the target project to obtain the risk control detection result of the data to be detected, wherein the data to be detected is the data generated during the execution of the target project.

[0120] The data processing system provided in one or more embodiments of the present specification includes: a policy generation unit and a data processing unit; through the policy generation unit, multiple risk control policies to be detected are generated using policy generation parameters, and each risk control policy to be detected is tested using risk control detection data, thereby obtaining multiple risk control policies, and subsequently, the multiple risk control policies after the test can accurately perform risk control detection; Moreover, through the data processing unit, multiple risk control strategies are divided into multiple risk control strategy sets according to the project type, so as to facilitate the subsequent efficient determination of the corresponding target risk control strategy set for the target project; then, for the data to be tested generated during the execution of the target project, the target risk control strategy set can be used to automatically perform risk control testing on the data to be tested, so as to quickly obtain accurate risk control testing results, avoiding the problem of low efficiency and poor accuracy caused by manual verification of risk control testing methods, and improving the accuracy and efficiency of data risk control testing.

[0121] The above is a schematic scheme of a data processing system of this embodiment. It should be noted that the technical scheme of the data processing system and the technical scheme of the data processing method and the strategy generation method described above are of the same concept, and the details not described in detail in the technical scheme of the data processing system can be referred to the description of the technical scheme of the data processing method and the strategy generation method described above.

[0122] Corresponding to the above method embodiment, this specification also provides a data processing device embodiment, Figure 6 FIG. 1 is a schematic diagram showing the structure of a data processing device provided by an embodiment of the present specification. Figure 6 As shown, the device is applied to a data processing unit in a data processing system, wherein the data processing system includes a strategy generating unit, and the device includes: The risk control strategy set determination module 602 is configured to determine the project types of the multiple projects, and divide the multiple risk control strategies into multiple risk control strategy sets according to the project types, wherein the risk control strategies are generated by the strategy generation unit using strategy generation parameters; The target risk control strategy set determination module 604 is configured to determine a target risk control strategy set corresponding to a target project from multiple risk control strategy sets, wherein the target project is any one of the multiple projects; The risk control detection module 606 is configured to use the target risk control strategy set to perform risk control detection on the data to be detected corresponding to the target project, and obtain the risk control detection result of the data to be detected, wherein the data to be detected is the data generated during the execution of the target project.

[0123] Optionally, there are multiple project types; The risk control strategy set determination module 602 is further configured to: Receiving a policy division request sent by a client, wherein the policy division request carries an association relationship between each project type and each risk control strategy, and the policy division request is sent by the client when a user performs a policy division operation on a policy division interface; Based on the association relationship, determining the associated risk control strategy corresponding to each project type from the multiple risk control strategies; Based on the associated risk control strategies corresponding to the project types, a risk control strategy set corresponding to the project types is constructed.

[0124] Optionally, the risk control detection module 606 is further configured to: Obtaining a target risk control strategy included in the target risk control strategy set from a data storage unit, and performing risk control detection on the data to be detected using the target risk control strategy to determine a risk control detection result of the data to be detected; or The target risk control strategy included in the target risk control strategy set is called from the strategy generation unit, and the target risk control strategy is used to perform risk control detection on the data to be detected to determine the risk control detection result of the data to be detected.

[0125] Optionally, the data processing device further includes a data receiving module configured to: Receiving the data to be detected sent by the client, wherein the data to be detected is sent by the client when the user performs a data processing operation on a data processing interface; The data processing device further includes a result sending module, which is configured to: The risk control detection result is sent to the client.

[0126] Optionally, the target risk control strategy set determination module 604 is further configured to: receiving a policy set determination request for the target project sent by a client, wherein the policy set determination request carries a policy set identifier corresponding to the target project, and the policy set determination request is sent by the client when a user performs a policy set processing operation on a policy set processing interface; Based on the policy set identifier, a target risk control policy set corresponding to the target project is determined from the multiple risk control policy sets.

[0127] The data processing device applied to the data processing unit provided in one or more embodiments of the present specification can utilize multiple risk control strategies generated by the policy generation unit in the data processing system, and divide the multiple risk control strategies into multiple risk control strategy sets according to the project type, so as to facilitate the subsequent efficient determination of the corresponding target risk control strategy set for the target project; then, for the data to be tested generated during the execution of the target project, the target risk control strategy set can be used to automatically perform risk control testing on the data to be tested, so as to quickly obtain accurate risk control testing results, avoiding the problem of low efficiency and poor accuracy caused by manually checked risk control testing methods, and improving the accuracy and efficiency of data risk control testing.

[0128] The above is a schematic scheme of a data processing device of this embodiment. It should be noted that the technical scheme of the data processing device and the technical scheme of the above data processing method belong to the same concept, and the details of the technical scheme of the data processing device that are not described in detail can be referred to the description of the technical scheme of the above data processing method.

[0129] Corresponding to the above method embodiment, this specification also provides a strategy generation device embodiment, Figure 7 FIG. 1 shows a schematic diagram of a strategy generation device provided by an embodiment of the present specification. Figure 7 As shown, the policy generation device is applied to a policy generation unit in a data processing system, wherein the data processing system includes a data processing unit, and the device includes: The strategy generation module 702 is configured to determine strategy generation parameters and generate a plurality of risk control strategies to be detected using the strategy generation parameters; The strategy detection module 704 is configured to use the risk control detection data to perform strategy detection on each risk control strategy to be detected, and obtain multiple risk control strategies that pass the strategy detection, so that the data processing unit can perform risk control detection on the data to be detected generated during the execution of the target project based on the multiple risk control strategies.

[0130] Optionally, the policy generation parameter is a code statement or a policy generation text; The strategy generation module 702 is further configured to: Receiving the code statement or policy generation text sent by the client, wherein the code statement is sent by the client when the user performs a code statement writing operation on the policy generation interface, and the policy generation text is sent by the client when the user performs a policy generation operation on the policy generation interface; The strategy generation module 702 is further configured to: In a case where the policy generation parameter is the policy generation text, inputting the policy generation text into a policy generation model to obtain the multiple risk control policies to be detected; or When the policy generation parameter is the code statement, the code statement is used as the multiple risk control policies to be detected.

[0131] Optionally, the policy detection module 704 is configured to: Performing risk control detection on the risk control detection data using the risk control strategies to be detected, and obtaining risk control detection results corresponding to the risk control strategies to be detected; The risk control strategies to be tested corresponding to the multiple risk control detection results that meet the preset detection pass conditions are determined as the multiple risk control strategies.

[0132] The policy generation device applied to the policy generation unit provided in one or more embodiments of this specification can generate multiple risk control policies to be detected by using policy generation parameters, and perform policy detection on each risk control policy to be detected by using risk control detection data, thereby obtaining multiple risk control policies, and subsequently accurately performing risk control detection through the multiple risk control policies after detection; The above is a schematic scheme of a strategy generation device of this embodiment. It should be noted that the technical scheme of the strategy generation device and the technical scheme of the above strategy generation method belong to the same concept, and the details not described in detail in the technical scheme of the strategy generation device can be referred to the description of the technical scheme of the above strategy generation method.

[0133] Figure 8 The block diagram of a computing device 800 according to an embodiment of the present specification is shown. The components of the computing device 800 include but are not limited to a memory 810 and a processor 820. The processor 820 is connected to the memory 810 via a bus 830, and a database 850 is used to store data.

[0134] The computing device 800 also includes an access device 840 that enables the computing device 800 to communicate via one or more networks 860. 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 840 may include one or more of any type of network interface (e.g., a network interface card (NIC)) of 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).

[0135] In one embodiment of the present specification, the above components of the computing device 800 and Figure 8 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 8 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.

[0136] The computing device 800 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 800 may also be a mobile or stationary server.

[0137] The processor 820 is used to execute the following computer executable instructions, which, when executed by the processor, implement the steps of the above-mentioned data processing method and strategy generation method.

[0138] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the computing device embodiment, since it is basically similar to the data processing method and policy generation method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the data processing method and policy generation method embodiments.

[0139] An embodiment of the present specification further provides a computer-readable storage medium storing a computer program / instruction, which implements the steps of the above-mentioned data processing method and strategy generation method when executed by a processor.

[0140] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the computer-readable storage medium embodiment, since it is basically similar to the data processing method and policy generation method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the data processing method and policy generation method embodiments.

[0141] An embodiment of the present specification also provides a computer program product, including a computer program / instruction, which implements the steps of the above-mentioned data processing method and strategy generation method when executed by a processor.

[0142] The above is a schematic scheme of a computer program product of this embodiment. It should be noted that the technical scheme of the computer program product and the technical scheme of the above-mentioned data processing method and strategy generation method belong to the same concept, and the details not described in detail in the technical scheme of the computer program product can be referred to the description of the technical scheme of the above-mentioned data processing method and strategy generation method.

[0143] 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.

[0144] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium 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.

[0145] 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.

[0146] 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.

[0147] 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 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 understand and use this specification well. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. A data processing method, characterized in that: A data processing unit applied to a data processing system, wherein the data processing system comprises a policy generating unit, including: Determining project types of multiple projects, and dividing multiple risk control strategies into multiple risk control strategy sets according to the project types, wherein the risk control strategies are generated by the strategy generation unit using strategy generation parameters; Determining a target risk control strategy set corresponding to a target project from a plurality of risk control strategy sets, wherein the target project is any one of the plurality of projects; The target risk control strategy set is used to perform risk control detection on the data to be detected corresponding to the target project to obtain the risk control detection result of the data to be detected, wherein the data to be detected is the data generated during the execution of the target project.

2. The method according to claim 1, characterized in that: The project type is multiple; The multiple risk control strategies are divided into multiple risk control strategy sets according to the project type, including: Receiving a policy division request sent by a client, wherein the policy division request carries an association relationship between each project type and each risk control strategy, and the policy division request is sent by the client when a user performs a policy division operation on a policy division interface; Based on the association relationship, determining the associated risk control strategy corresponding to each project type from the multiple risk control strategies; Based on the associated risk control strategies corresponding to the project types, a risk control strategy set corresponding to the project types is constructed.

3. The method according to claim 1, characterized in that The step of using the target risk control strategy set to perform risk control detection on the data to be detected corresponding to the target project to obtain the risk control detection result of the data to be detected includes: Obtaining a target risk control strategy included in the target risk control strategy set from a data storage unit, and performing risk control detection on the data to be detected using the target risk control strategy to determine a risk control detection result of the data to be detected; or The target risk control strategy included in the target risk control strategy set is called from the strategy generation unit, and the target risk control strategy is used to perform risk control detection on the data to be detected to determine the risk control detection result of the data to be detected.

4. The method according to any one of claims 1 to 3, characterized in that: Before performing risk control detection on the data to be detected corresponding to the target project by using the target risk control strategy set and obtaining the risk control detection result of the data to be detected, the method further includes: Receiving the data to be detected sent by the client, wherein the data to be detected is sent by the client when the user performs a data processing operation on a data processing interface; After performing risk control detection on the data to be detected corresponding to the target project by using the target risk control strategy set and obtaining the risk control detection result of the data to be detected, the method further includes: The risk control detection result is sent to the client.

5. The method according to any one of claims 1 to 3, characterized in that: Determining a target risk control strategy set corresponding to a target project from a plurality of risk control strategy sets includes: receiving a policy set determination request for the target project sent by a client, wherein the policy set determination request carries a policy set identifier corresponding to the target project, and the policy set determination request is sent by the client when a user performs a policy set processing operation on a policy set processing interface; Based on the policy set identifier, a target risk control policy set corresponding to the target project is determined from the multiple risk control policy sets.

6. A strategy generation method, characterized in that: A policy generating unit applied to a data processing system, wherein the data processing system comprises a data processing unit, including: Determine strategy generation parameters, and use the strategy generation parameters to generate multiple risk control strategies to be tested; Using the risk control detection data, a strategy detection is performed on each risk control strategy to be detected, and multiple risk control strategies that pass the strategy detection are obtained, so that the data processing unit can perform risk control detection on the data to be detected generated during the execution of the target project based on the multiple risk control strategies.

7. The method according to claim 6, characterized in that The policy generation parameter is a code statement or a policy generation text; The determining strategy generation parameters includes: Receiving the code statement or policy generation text sent by the client, wherein the code statement is sent by the client when the user performs a code statement writing operation on the policy generation interface, and the policy generation text is sent by the client when the user performs a policy generation operation on the policy generation interface; The method of using the strategy generation parameters to generate multiple risk control strategies to be tested includes: In a case where the policy generation parameter is the policy generation text, inputting the policy generation text into a policy generation model to obtain the multiple risk control policies to be detected; or When the policy generation parameter is the code statement, the code statement is used as the multiple risk control policies to be detected.

8. The method according to claim 6, characterized in that The method of using the risk control detection data to perform a strategy detection on each risk control strategy to be detected, and obtaining multiple risk control strategies that pass the strategy detection, includes: Performing risk control detection on the risk control detection data using the risk control strategies to be detected, and obtaining risk control detection results corresponding to the risk control strategies to be detected; The risk control strategies to be tested corresponding to the multiple risk control detection results that meet the preset detection pass conditions are determined as the multiple risk control strategies.

9. A data processing system, characterized in that: including a strategy generation unit and a data processing unit; The strategy generation unit is used to determine strategy generation parameters, and use the strategy generation parameters to generate multiple risk control strategies to be detected, and use the risk control detection data to perform strategy detection on each risk control strategy to be detected, so as to obtain multiple risk control strategies that pass the strategy detection; The data processing unit is used to determine the project types of multiple projects, and divide multiple risk control strategies into multiple risk control strategy sets according to the project types, and determine a target risk control strategy set corresponding to a target project from the multiple risk control strategy sets, wherein the target project is any one of the multiple projects, and the target risk control strategy set is used to perform risk control detection on the data to be detected corresponding to the target project to obtain the risk control detection result of the data to be detected, wherein the data to be detected is the data generated during the execution of the target project.

10. A computing device, characterized in that include: Memory and processor; The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions. When the computer program / instructions are executed by the processor, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium, characterized in that: It stores a computer program / instruction, which implements the steps of the method described in any one of claims 1 to 8 when executed by a processor.

12. A computer program product, characterized in that The method comprises a computer program / instruction which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 8.

Images