Business post-governor method, device, equipment, medium and product

Abstract

The invention relates to a business governor method, device and equipment, a medium and a product. The method comprises the following steps: acquiring initial business data; performing tagging processing on the initial service data to obtain tag service data, the tag service data including the initial service data and a feature tag corresponding to the initial service data; and on the basis of the feature tag, a governor task is generated according to the tag business data, and the governor task is used for auditing the initial business data by auditing personnel. By adopting the method, the efficiency of the business governor method can be improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a business post-supervision method, device, equipment, medium and product. Background Art

[0002] In the insurance processing business scenario, it is necessary to conduct post-business supervision on the insurance policies in the contract issuance process, that is, to conduct compliance and normative verification on the business data corresponding to the completed and effective insurance policies.

[0003] In traditional technology, SQL (Structured Query Language) is used to query and obtain business data from the database and to audit the business data. However, with the high-quality development requirements of the insurance industry and the continuous improvement of digital operation capabilities, the number of insurance policies has increased sharply, the amount of business data is large, and the business post-supervision methods in traditional technologies are inefficient. Summary of the invention

[0004] Based on this, it is necessary to provide an efficient business post-supervision method, device, equipment, medium and product to address the above technical issues.

[0005] In a first aspect, the present application provides a business post-supervision method, the method comprising:

[0006] Obtain initial business data;

[0007] The initial business data is labeled to obtain labeled business data, where the labeled business data includes the initial business data and feature labels corresponding to the initial business data;

[0008] Based on feature tags, post-supervision tasks are generated according to the tagged business data and sent to the task platform. The post-supervision tasks are used by auditors to review the initial business data.

[0009] In one embodiment, the feature labels include risk labels and business labels, and the initial business data is labeled to obtain labeled business data, including:

[0010] For each initial business data, determine the risk factor information corresponding to the initial business data;

[0011] According to the preset risk assessment rules, each risk factor information is risk labeled to obtain the risk label corresponding to the risk factor information;

[0012] According to the preset business type rules, the initial business data is processed into business tags to obtain business tags;

[0013] The risk label and the business label are added to the initial business data to obtain the labeled business data.

[0014] In one embodiment, risk labeling is performed on each risk factor information according to a preset risk mapping rule to obtain a risk label corresponding to the risk factor information, including:

[0015] For each risk factor information, the risk factor information is quantified using the preset risk assessment rules to obtain the risk factor corresponding to the risk factor information;

[0016] A risk label is obtained based on the risk factor information and the risk factor corresponding to the risk factor information.

[0017] In one embodiment, risk labeling is performed on each risk factor information according to a preset risk mapping rule to obtain a risk label corresponding to the risk factor information, including:

[0018] Use the pre-trained risk assessment model to perform feature extraction processing on each risk factor information and initial business data to obtain the risk feature information corresponding to each risk factor information;

[0019] The risk characteristic information is classified and processed to obtain risk labels.

[0020] In one embodiment, based on the feature tags, a post-supervision task is generated according to the tag business data, including:

[0021] Selecting a target feature tag from the feature tags; extracting target tag business data from tag business data corresponding to the target feature tag according to the target feature tag and a preset extraction scale;

[0022] Generate post-supervision tasks based on target label business data.

[0023] In one embodiment, the method further comprises:

[0024] Obtain the real-time task progress corresponding to the post-supervision task from the task platform;

[0025] Based on the real-time task progress, the initial business data is updated to obtain updated task data;

[0026] Store the updated task data in the data warehouse.

[0027] In a second aspect, the present application also provides a business post-supervision device, the device comprising:

[0028] A data acquisition module, used to acquire initial business data;

[0029] A label generation module is used to label the initial business data to obtain label business data, where the label business data includes the initial business data and feature labels corresponding to the initial business data;

[0030] The task publishing module is used to generate post-supervision tasks based on feature tags and tagged business data, and send them to the task platform. The post-supervision tasks are used by auditors to review the initial business data.

[0031] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method of the first aspect are implemented.

[0032] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method of the first aspect when the computer program is executed by a processor.

[0033] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which implements the steps of the method of the first aspect when executed by a processor.

[0034] In the above-mentioned business post-supervision method, device, equipment, medium and product, one aspect provides a business post-supervision method, by obtaining initial business data; labeling the initial business data to obtain labeled business data, the labeled business data includes the initial business data and feature tags corresponding to the initial business data; based on the feature tags, a post-supervision task is generated according to the labeled business data, and the post-supervision task is used for auditors to review the initial business data. In this embodiment, by labeling the initial business data and generating the post-supervision task based on the feature tags, the post-supervision task can be accurately generated, the dynamic generation of the post-supervision task can be realized, the rapid changes in business can be adapted, and underreporting and false reporting can be avoided, thereby improving the efficiency of the business post-supervision method. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 An application environment diagram of a business post-supervision method in an embodiment;

[0037] Figure 2 A flowchart of a business post-supervision method in one embodiment;

[0038] Figure 3 A flowchart of the steps of performing a post-supervision task in one embodiment;

[0039] Figure 4 A flowchart of steps for obtaining tag service data in one embodiment;

[0040] Figure 5 A flowchart of a business post-supervision method in another embodiment;

[0041] Figure 6 A schematic diagram of the structure of a business post-supervision system in an embodiment;

[0042] Figure 7 A structural block diagram of a business post-supervision device in an embodiment;

[0043] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0045] The business post-supervision method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the data warehouse 102 communicates with the server 104 through the network. Among them, the server 104 can be implemented with an independent server or a server cluster composed of multiple servers; the data warehouse 102 can store the initial business data that the server 104 needs to call, and the data warehouse 102 can be integrated on the server 104, or it can be placed on the cloud or other network servers. The data warehouse 102 can be a relational database, such as a Gaussian distributed relational database, SQL Server, MySQL, or a non-relational database, such as MongoDB. The server 104 is used to obtain the initial business data; the initial business data is labeled to obtain labeled business data, and the labeled business data includes the initial business data and the feature labels corresponding to the initial business data; based on the feature labels, a post-supervision task is generated according to the labeled business data, and sent to the task platform, and the post-supervision task is used for auditors to review the initial business data.

[0046] In an exemplary embodiment, Figure 2 As shown, a business post-supervision method is provided, which is applied to Figure 1 The server 104 in the example is used for explanation, and the steps include the following steps 202 to 206.

[0047] in:

[0048] Step 202: Acquire initial business data.

[0049] The initial business data is the full brightness data in one inspection cycle. For example, one inspection cycle can be one day or one week.

[0050] The initial business data can be obtained by the server from the data warehouse. For example, the server requests the data from the data warehouse (DW), the data warehouse prepares the initial business data in the data operation layer (Operation Data Store, ODS), and then sends the initial business data to the server through the data details layer (DataWarehouseDetails, DWD).

[0051] The initial business data is based on insurance policies, and one piece of initial business data corresponds to the business data involved in one insurance policy.

[0052] Step 204 , labeling the initial business data to obtain labeled business data, where the labeled business data includes the initial business data and feature labels corresponding to the initial business data.

[0053] Among them, labeling processing refers to dividing the initial business data into different categories according to the characteristics in the initial business data, and generating corresponding labels based on different categories. Labels can be used to indicate the feature category of the initial business data, and can also be used to indicate the degree of feature correspondence.

[0054] Exemplarily, the feature label can be a label generated based on the type of insurance product, such as health insurance, life insurance, and property insurance; or, it can be a label generated based on the type of customer group, such as individual customers, small and micro enterprises, and large enterprises; or, it can be a label generated based on the risk feature type, such as high risk and ordinary risk. Another exemplary feature, in the label generated based on the risk feature type, the feature label can also include the risk level, and the high-risk feature label is the feature label corresponding to the initial business data whose risk level is greater than the preset risk threshold.

[0055] Step 206, based on the feature tags, a post-supervision task is generated according to the tagged business data and sent to the task platform. The post-supervision task is used for auditors to review the initial business data.

[0056] In a possible implementation, Figure 3As shown, the post-supervision tasks generated according to the label business data are distributed to the corresponding institutional task pool through the task platform. In the task pool of each institution, the auditor extracts the post-supervision tasks that have the authority to review, and reviews the post-supervision tasks according to the post-supervision process of preliminary review, rectification, and review. Specifically, the preliminary review reviews the post-supervision tasks. If there are no errors, they are completed. If there are errors, the audit points of the corresponding problems are checked and rectification tasks are generated. Rectification personnel can be assigned or enter the rectification task pool. Entering the rectification node, the rectification personnel who receive the rectification task will make rectifications according to the audit points, or roll back if there are no problems. Entering the review node, the auditor of the preliminary review node verifies the rectification task. If there are no problems, it is completed. If there are still problems with the rectification task verification, the rectification task is updated and rolled back to the rectification node. The post-supervision task execution method provided in this embodiment can monitor the entire process of the post-supervision task to ensure the compliance and transparency of the post-supervision task execution process.

[0057] In a possible implementation, the provided method also includes quality inspection for completed post-supervision tasks, specifically including: generating quality inspection tasks based on completed post-supervision tasks, and distributing them to the corresponding institutional task pool through the task platform. In each institutional task pool, the quality inspector extracts the quality inspection tasks that have the authority to review, and conducts quality inspection on the quality inspection tasks according to the quality inspection process of preliminary review, rectification, and review. Specifically, the preliminary review conducts quality inspection on the quality inspection tasks. If there is no error, it will be completed. If there is an error, the review points of the corresponding problem will be checked, and rectification tasks will be generated. Rectification personnel can be assigned, or they can enter the rectification task pool. Entering the rectification node, the rectification personnel who receive the rectification task will make rectifications according to the review points, or roll back if there is no problem. Entering the review node, the quality inspector of the preliminary review node will check the rectification task. If there is no problem, it will be completed. If there is still a problem with the verification of the rectification task, the rectification task will be updated and rolled back to the rectification node.

[0058] In the above-mentioned business post-supervision method, initial business data is obtained; the initial business data is labeled to obtain labeled business data, which includes the initial business data and feature tags corresponding to the initial business data; based on the feature tags, a post-supervision task is generated according to the labeled business data, and the post-supervision task is used for auditors to review the initial business data. In this embodiment, by labeling the initial business data and generating the post-supervision task based on the feature tags, the post-supervision task can be accurately generated, the dynamic generation of the post-supervision task is realized, the rapid changes in business are adapted, and omissions and false alarms are avoided, thereby improving the efficiency of the business post-supervision method.

[0059] In an exemplary embodiment, based on Figure 2 The embodiment shown, as Figure 4 As shown, the feature labels in the provided method include risk labels and business labels. The process of labeling the initial business data in the provided method to obtain the labeled business data includes:

[0060] Step 402: for each initial business data, determine the risk factor information corresponding to the initial business data.

[0061] Among them, risk factor information refers to information on various factors that may cause risks in the initial business data. Risk factors may include customers, insurance institutions and salesmen.

[0062] Exemplarily, customer information may include age, gender, occupation, health status, past claims record, and credit record. By evaluating the number of institutions where the customer has insured within six months, the difference between the customer's declared income and the average income of his or her industry or region, and the frequency of past claims or premium arrears records, it is possible to determine whether there are customer-related risks.

[0063] As another example, the insured institution information may include the insured institution's corresponding credit rating, operating history, complaint rate, and claims service efficiency. By evaluating the insured institution's financial status through the insured institution information, it can be determined whether there are financial risks such as failure to redeem claims in a timely manner, or based on the institution's record of illegal and irregular activities, it can be determined whether there are compliance risks such as affecting the validity of the insurance policy.

[0064] As another example, salesperson information may include the salesperson's sales record, compliance history, customer evaluations, and agent qualifications. By evaluating the salesperson's information, it can be determined whether there are compliance risks such as false advertising, misleading sales, or improper operation records, or whether there are behavioral ethical risks such as tie-in sales and high commissions.

[0065] Step 404, according to the preset risk assessment rules, risk labeling is performed on each risk factor information to obtain a risk label corresponding to the risk factor information.

[0066] Optionally, the risk label may be generated by collating and analyzing risk factor information based on a BI (Business Intelligence) data analysis tool.

[0067] In a possible implementation, step 404 may further include: for each risk factor information, using a preset risk assessment rule to quantify the risk factor information to obtain a risk factor corresponding to the risk factor information; and obtaining a risk label based on each risk factor information and the risk factor corresponding to the risk factor information.

[0068] Exemplarily, risk factors may include risk customer factors, risk institution factors, and risk sales factors. The risk assessment rules corresponding to the risk customer factors may include weighted summation of the number of insurance institutions, income differences, and credit scores of customers in the customer information within the statistical assessment interval to obtain the risk customer factors. The risk assessment rules corresponding to the risk institution factors may include scoring and assigning values ​​to the assets and liabilities and illegal and irregular records in the insurance institution information to obtain the risk institution factors. The risk assessment rules corresponding to the risk sales factors may include grading the compliance history and customer evaluation in the salesperson information to determine the risk sales factors.

[0069] Among them, the risk label can be generated according to the risk factor information and the risk factor corresponding to the risk factor information in accordance with a preset label format. Exemplarily, the label format can be: "Risk level-risk factor-risk factor". Among them, the risk level is divided according to the value of the risk factor. Exemplarily, when the value range of the risk factor is (0,1), the risk factor value belongs to (0,0.3], then the risk level is determined to be low risk; the risk factor value belongs to (0.3,0.8], then the risk level is determined to be medium risk; the risk factor value belongs to (0.8,1), then the risk level is determined to be high risk. When the risk customer factor value is 0.8, the corresponding risk label can be expressed as "medium risk-customer-0.8". For each initial business data, it can have multiple risk labels, such as including a risk label whose risk factor is an insured institution and a risk label whose risk factor is a salesperson.

[0070] In a possible implementation, step 404 may further include: using a pre-trained risk assessment model to perform feature extraction processing on each risk factor information and initial business data to obtain risk feature information corresponding to each risk factor information; and classifying the risk feature information to obtain a risk label.

[0071] Exemplarily, the risk assessment model may be a feature extraction model based on a neural network, and the risk feature information may be obtained by combining, crossing and reducing the dimension of each risk factor information.

[0072] For example, based on the credit record in the customer information, the regional risk information in the insurance institution information, and the premium amount and payment method in the initial business data, the risk label corresponding to the financial behavior risk can be determined. If there is a mismatch between the customer identity and their economic behavior in the information of various risk factors, such as low-income people buying ultra-high premium policies, the source of premium payment funds is unknown, the flow of funds is abnormal, and customers frequently cancel orders and cancel insurance with large premium amounts, it indicates that there may be financial behavior risks, and a risk label corresponding to the financial behavior risk is generated.

[0073] As another example, based on the clarity and authenticity of the identity verification image in the customer information, there are cases where the submitted image is blurry or unclear and the authenticity cannot be verified, the image has obvious signs of editing or tampering, the information on the identity document does not match the information filled in by the customer, the customer submits non-compliant images multiple times, or the reasons for the modifications are far-fetched, and there are high similarities between images submitted by different customers, indicating that there may be a risk of image abnormality, and a risk label corresponding to the image abnormality is generated.

[0074] For example, DBSCAN (Density-Based Spatial Clustering of Applications with Noise) or Isolation Forest method can be used to classify risk feature information to obtain risk labels corresponding to risk factor information.

[0075] Step 406: Perform service labeling processing on the initial service data according to the preset service type rule to obtain a service label.

[0076] Among them, the business type rule can be a type classification rule generated based on the insurance product type or customer group type, and different types of names or logos can be used as business labels.

[0077] Step 408: Add the risk label and the business label to the initial business data to obtain label business data.

[0078] In this embodiment, based on the initial business data, the feature label corresponding to each initial business data is determined, which provides an effective and accurate index label for generating the post-supervision task, and can effectively improve the efficiency of the business post-supervision method.

[0079] In an exemplary embodiment, the method provided is based on feature tags and the process of generating a post-supervision task according to label business data includes: selecting a target feature tag from the feature tags; extracting target label business data from the label business data corresponding to the target feature tag according to the target feature tag and a preset extraction scale; and generating a post-supervision task according to the target label business data.

[0080] The target feature tag may be a randomly extracted feature tag or a feature tag actively selected by an operator. Extracting the target tag business data may be, for each target feature tag, randomly extracting from all tag business data corresponding to the target feature tag based on the number corresponding to the extraction scale to obtain the target tag business data. Optionally, the extraction scale may be a specific ratio, and the ratios corresponding to each target feature tag may be the same or different.

[0081] Optionally, the target tag business data may be specifically extracted based on specific data in the tag business data, such as extracted based on an insurance policy number or customer identity information.

[0082] Among them, the post-supervision task is obtained by organizing the target label business data according to the preset task form, and the post-supervision task includes the complete target label business data.

[0083] In a possible implementation, the provided method further includes: obtaining real-time task progress corresponding to the post-supervision task from the task platform; updating the initial business data based on the real-time task progress to obtain updated task data; and storing the updated task data in a data warehouse.

[0084] Among them, the post-supervision tasks can be stored based on the OceanBase database and published to the task platform, so that the auditors can extract the tasks on the task platform and review the extracted post-supervision tasks. The OceanBase database is used to query the task progress of the post-supervision tasks in the task platform, and the data is updated in the OceanBase database when the task progress changes, and the data in the data warehouse is updated synchronously.

[0085] In this embodiment, data is extracted from tagged business data based on feature tags to generate post-supervision tasks, which can generate post-supervision tasks for different feature tag tendencies, thereby improving the risk control capability and post-supervision efficiency of the business post-supervision method.

[0086] In an exemplary embodiment, Figure 5 As shown, a business post-supervision method is provided, which is applied to Figure 1 The server 104 in the example is used for explanation, and the steps include the following steps 501 to 510.

[0087] in:

[0088] Step 501, obtaining initial business data.

[0089] Step 502: for each initial business data, determine the risk factor information corresponding to the initial business data.

[0090] Step 503: for each risk factor information, the risk factor information is quantified using a preset risk assessment rule to obtain a risk factor corresponding to the risk factor information.

[0091] Step 504: Obtain a risk label according to each risk factor information and the risk factor corresponding to the risk factor information.

[0092] Step 505: Perform service labeling processing on the initial service data according to the preset service type rule to obtain a service label.

[0093] Step 506: Add the risk label and the business label to the initial business data to obtain label business data.

[0094] Step 507, based on the feature tag, a post-supervision task is generated according to the tagged business data and sent to the task platform. The post-supervision task is used for auditors to review the initial business data.

[0095] Among them, a target feature tag is selected from the feature tags; according to the target feature tag and a preset extraction scale, target tag business data is extracted from the tag business data corresponding to the target feature tag; and a post-supervision task is generated according to the target tag business data.

[0096] Step 508, obtaining the real-time task progress corresponding to the post-supervision task from the task platform.

[0097] Step 509: based on the real-time task progress, the initial business data is updated to obtain updated task data.

[0098] Step 510: Store the update task data in the data warehouse.

[0099] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0100] In an exemplary embodiment, Figure 6 As shown, a business post-supervision system is provided, in which a data processing layer is used to obtain initial business data; the initial business data is labeled to obtain labeled business data, which includes the initial business data and feature labels corresponding to the initial business data; based on the feature labels, a post-supervision task is generated according to the labeled business data and sent to the task platform, and the post-supervision task is used for auditors to review the initial business data.

[0101] Based on the same inventive concept, the embodiment of the present application also provides a business post-supervision device for implementing the business post-supervision method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more business post-supervision device embodiments provided below can refer to the limitations of the business post-supervision method above, and will not be repeated here.

[0102] In an exemplary embodiment, Figure 7 As shown, a business post-supervision device is provided, including: a data acquisition module 702, a label generation module 704 and a task release module 706, wherein:

[0103] Data acquisition module 702, used to acquire initial business data;

[0104] The label generation module 704 is used to label the initial business data to obtain label business data, where the label business data includes the initial business data and feature labels corresponding to the initial business data;

[0105] The task publishing module 706 is used to generate a post-supervision task based on the feature tag and the tagged business data, and send it to the task platform. The post-supervision task is used for the auditor to review the initial business data.

[0106] In one of the embodiments, the label generation module 704 is also used to determine the risk factor information corresponding to the initial business data for each initial business data; perform risk labeling processing on each risk factor information according to a preset risk assessment rule to obtain a risk label corresponding to the risk factor information; perform business labeling processing on the initial business data according to a preset business type rule to obtain a business label; and add the risk label and the business label to the initial business data to obtain labeled business data.

[0107] In one embodiment, the label generation module 704 is also used to quantify the risk factor information for each risk factor information using a preset risk assessment rule to obtain a risk factor corresponding to the risk factor information; and obtain a risk label based on each risk factor information and the risk factor corresponding to the risk factor information.

[0108] In one of the embodiments, the label generation module 704 is also used to use a pre-trained risk assessment model to perform feature extraction processing on each risk factor information and initial business data to obtain risk feature information corresponding to each risk factor information; classify the risk feature information to obtain a risk label.

[0109] In one of the embodiments, the task publishing module 706 is also used to select a target feature tag from the feature tags; extract target tag business data from the tag business data corresponding to the target feature tag according to the target feature tag and a preset extraction scale; and generate a post-supervision task based on the target tag business data.

[0110] In one embodiment, the task publishing module 706 is also used to obtain the real-time task progress corresponding to the post-supervision task from the task platform; based on the real-time task progress, update the initial business data to obtain updated task data; and store the updated task data in the data warehouse.

[0111] Each module in the above-mentioned business post-supervision device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0112] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 8 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store initial business data and label business data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a business post-supervision method is implemented.

[0113] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0114] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0115] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0116] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0117] 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 this application 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 relevant regulations.

[0118] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Relational databases include Gaussian distributed relational databases, and non-relational databases may include distributed databases based on blockchains, etc., without limitation thereto. The processors involved in each embodiment provided in this application may be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, data processing logic devices based on quantum computing, etc., without limitation thereto.

[0119] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0120] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A business post-supervision method, characterized in that: The method comprises: Obtain initial business data; Performing labeling processing on the initial business data to obtain label business data, wherein the label business data includes the initial business data and a feature label corresponding to the initial business data; Based on the feature tag, a post-supervision task is generated according to the tagged business data and sent to the task platform. The post-supervision task is used for auditors to review the initial business data.

2. The method according to claim 1, characterized in that The characteristic labels include risk labels and business labels, and the labeling process of the initial business data to obtain the label business data includes: For each initial business data, determining risk factor information corresponding to the initial business data; According to the preset risk assessment rules, each of the risk factor information is subjected to risk labeling processing to obtain a risk label corresponding to the risk factor information; According to a preset business type rule, the initial business data is subjected to business labeling processing to obtain a business label; The risk label and the service label are added to the initial service data to obtain the label service data.

3. The method according to claim 2, characterized in that The risk factor information is subjected to risk labeling processing according to a preset risk mapping rule to obtain a risk label corresponding to the risk factor information, including: For each of the risk factor information, the risk factor information is quantified using a preset risk assessment rule to obtain a risk factor corresponding to the risk factor information; A risk label is obtained according to each of the risk factor information and the risk factor corresponding to the risk factor information.

4. The method according to claim 2, characterized in that: The risk factor information is subjected to risk labeling processing according to a preset risk mapping rule to obtain a risk label corresponding to the risk factor information, including: Using a pre-trained risk assessment model to perform feature extraction processing on each of the risk factor information and the initial business data, to obtain risk feature information corresponding to each of the risk factor information; The risk characteristic information is classified and processed to obtain the risk label.

5. The method according to claim 1, characterized in that The generating of the post-supervision task based on the feature tag and the tag business data includes: Selecting a target feature tag from the feature tags; Extracting target tag business data from the tag business data corresponding to the target feature tag according to the target feature tag and a preset extraction scale; The post-supervision task is generated according to the target tag business data.

6. The method according to claim 1, characterized in that The method further comprises: Obtaining the real-time task progress corresponding to the post-supervision task from the task platform; Based on the real-time task progress, the initial business data is updated to obtain updated task data; The update task data is stored in a data warehouse.

7. A business post-supervision device, characterized in that: The device comprises: A data acquisition module, used to acquire initial business data; A label generation module, used for labeling the initial business data to obtain label business data, wherein the label business data includes the initial business data and a feature label corresponding to the initial business data; The task publishing module is used to generate a post-supervision task based on the feature tag and the tagged business data, and send it to the task platform. The post-supervision task is used for auditors to review the initial business data.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images