Risk data processing method, device and storage medium

Abstract

The present application provides a method, device and storage medium for processing risk data. The method includes: obtaining risk feedback data on business data; inputting the risk feedback data into the audit classification model in the N-th level storage component, and classifying and summarizing the risk feedback data to generate ledger data of the N-th level risk feedback data, wherein N is a positive integer greater than 1; inputting the ledger data of the N-th level risk feedback data into the audit classification model in the N-1-th level storage component, and classifying and summarizing the ledger data of the N-th level risk feedback data to generate ledger data of the N-1-th level risk feedback data, until the ledger data of the first-level risk feedback data is generated; wherein, the category of the audit classification model in the N-1-th level storage component is obtained by the category to which the ledger data of the N-th level risk feedback data belongs, so the present application can fully understand the overall situation of risk processing through the ledger data of the first-level risk feedback data.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a method, device, and storage medium for processing risk data. Background Art

[0002] With the rapid development of network communications technology, the volume of communications services has increased significantly, and with it, the amount of risk data, or audit work orders, has also increased. For example, users fail to undergo real-name verification when applying for communications services, or the services they apply for do not match their rates. Operators' grassroots auditors are required to verify and rectify risk data according to business rules and provide feedback on the rectification progress.

[0003] In order to understand the overall processing of risk data, audit management personnel need to check the rectification status of each audit work order one by one, which makes it impossible to fully understand the overall situation of risk processing. Summary of the Invention

[0004] This application provides a risk data processing method, device and storage medium to solve the problem that the existing rectification status of each audit work order is checked one by one, and the overall situation of risk management cannot be fully understood.

[0005] In a first aspect, the present application provides a method for processing risk data, comprising:

[0006] Obtain risk feedback data on business data;

[0007] Input the risk feedback data into the audit classification model in the Nth-level storage component, and classify and summarize the risk feedback data to generate the Nth-level risk feedback data ledger data, where N is a positive integer greater than 1;

[0008] The ledger data of the N-th level risk feedback data is input into the audit classification model in the N-1-th level storage component, and the ledger data of the N-th level risk feedback data is classified and summarized to generate the ledger data of the N-1-th level risk feedback data, until the ledger data of the first-level risk feedback data is generated; wherein, the category of the audit classification model in the N-1-th level storage component is obtained from the category to which the ledger data of the N-th level risk feedback data belongs.

[0009] In a second aspect, the present application provides a risk data processing device, comprising:

[0010] Acquisition module, used to obtain risk feedback data on business data;

[0011] An input module, used to input risk feedback data into the audit classification model in the Nth level storage component;

[0012] A generation module is used to classify and summarize the risk feedback data to generate the ledger data of the Nth level risk feedback data, where N is a positive integer greater than 1;

[0013] The input module is also used to input the ledger data of the Nth level risk feedback data into the audit classification model in the N-1th level storage component;

[0014] The generation module is also used to classify and summarize the ledger data of the Nth level risk feedback data to generate the ledger data of the N-1th level risk feedback data, until the ledger data of the first level risk feedback data is generated; wherein, the category of the audit classification model in the N-1th level storage component is obtained from the category to which the ledger data of the Nth level risk feedback data belongs.

[0015] In a third aspect, the present application provides a risk data processing device, comprising: a processor, a memory, wherein code is stored in the memory, and the processor runs the code stored in the memory to execute a risk data processing method as described in any one of the first aspects.

[0016] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the risk data processing method as described in any one of the first aspects.

[0017] The present application provides a method, device and storage medium for processing risk data, the method comprising: obtaining risk feedback data on business data, inputting the risk feedback data into an audit classification model in an N-th level storage component, and classifying and summarizing the risk feedback data to generate ledger data for the N-th level risk feedback data, wherein N is a positive integer greater than 1. The ledger data of the N-th level risk feedback data is input into the audit classification model of the N-1-th level storage component, and the ledger data of the N-th level risk feedback data is classified and summarized to generate ledger data for the N-1-th level risk feedback data, until the ledger data for the first-level risk feedback data is generated. The method provided in the embodiment of the present application generates ledger data for N-level risk feedback data, and since the category of the audit classification model in the N-1-th level storage component is obtained from the category to which the ledger data for the N-th level risk feedback data belongs, the overall situation of risk processing can be fully understood through the generated ledger data for the first-level risk feedback data, and the overall situation of risk processing at each level can also be viewed through the generated ledger data for the N-th level risk feedback data. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0019] Figure 1A schematic diagram of a risk data processing scenario provided in an embodiment of the present application;

[0020] Figure 2 A risk data processing method provided in this application embodiment Figure 1 ;

[0021] Figure 3 A risk data processing method provided in this application embodiment Figure 2 ;

[0022] Figure 4 A risk data processing method provided in this application embodiment Figure 3 ;

[0023] Figure 5 A schematic diagram of hierarchical storage of risk data provided in an embodiment of the present application;

[0024] Figure 6 A schematic diagram of a risk data processing device provided in an embodiment of the present application Figure 1 ;

[0025] Figure 7 A schematic diagram of a risk data processing device provided in an embodiment of the present application Figure 2 .

[0026] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0027] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0028] With the rapid development of network communications technology, the volume of communications services has increased significantly. When handling communications services, if staff fail to follow relevant business regulations, certain risks may arise. After risk remediation, existing technology requires verifying the rectification status of each risk item one by one, making it difficult to fully understand the overall risk management situation.

[0029] Based on the above problems, the present application provides a method for processing risk data, which inputs the risk feedback data of the business data into the audit classification model in the N-th level storage component, and generates the ledger data of the N-th level risk feedback data, where N is a positive integer greater than 1. The ledger data of the N-th level risk feedback data can reflect the overall situation of the N-th level risk processing. The ledger data of the N-th level risk feedback data is input into the audit classification model in the N-1-th level storage component, and the ledger data of the N-th level risk feedback data is classified and summarized to generate the ledger data of the N-1-th level risk feedback data, until the ledger data of the first-level risk feedback data is generated. The present application generates the ledger data of the N-th level risk feedback data, and since the category of the audit classification model in the N-1-th level storage component is obtained by the category to which the ledger data of the N-th level risk feedback data belongs, the overall situation of the risk processing can be fully understood through the ledger data of the generated first-level risk feedback data, and the overall situation of the risk processing at each level can also be understood through the ledger data of each level of risk feedback data.

[0030] Figure 1 A schematic diagram of a risk data processing scenario provided in an embodiment of the present application is shown as follows: Figure 1 As shown, based on the massive risk feedback data after keyword tagging, the data classification and collection module classifies and summarizes the risk feedback data according to keywords, and generates ledger data for risk feedback data at all levels, until the ledger data for the first-level risk feedback data is generated. The ledger data for the first-level risk feedback data may include revenue loss ledger data, audit income ledger data, etc. The overall situation of risk handling can be understood through the ledger data of the first-level risk feedback data. The keyword recognition module is used to identify keywords in the risk feedback data and compare them with the keywords in the keyword database. If a keyword that is not included in the keyword database is identified, the keyword is added to the keyword database. The keyword database management module is used to collect and manage keywords in the keyword database.

[0031] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0032] Figure 2 A risk data processing method provided in this application embodiment Figure 1 The method of the embodiment of the present application can be executed by a risk data processing device and can be implemented by hardware, software, or a combination of hardware and software. Figure 2 As shown, the method of this embodiment may include:

[0033] S201: Obtain risk feedback data on business data.

[0034] Business data is data generated when staff members handle business operations. This can be communications data generated when handling communications services or data from other business types. In one implementation scenario, risk data is generated when staff members fail to follow business handling rules.

[0035] Risk feedback data is feedback data that provides feedback on the rectification status after the risks in the risk data are rectified.

[0036] One feasible implementation method for obtaining risk feedback data is to input business data into a risk model, which then outputs risk data. Risk data is analyzed and tagged based on keywords to obtain risk feedback data.

[0037] S202: Input the risk feedback data into the audit classification model in the Nth level storage component, and classify and summarize the risk feedback data to generate the Nth level risk feedback data ledger data, where N is a positive integer greater than 1.

[0038] The audit classification model is used to categorize and aggregate risk feedback data or risk feedback ledger data based on keywords, generating N-level risk feedback ledger data. The N-level risk feedback ledger data provides an overview of the overall risk handling situation at that level.

[0039] In one implementation scenario, when classifying the storage components, the classification can be performed based on the geographical location where the business data is generated. For example, the classification can be performed based on the district, county, city, or province where the business data is generated.

[0040] The classification of storage components, that is, the size of the N value, can be determined based on actual business data scale, software and hardware conditions, and other actual conditions.

[0041] S203: Input the ledger data of the N-th level risk feedback data into the audit classification model in the N-1-th level storage component, and classify and summarize the ledger data of the N-th level risk feedback data to generate the ledger data of the N-1-th level risk feedback data, until the ledger data of the first-level risk feedback data is generated; wherein, the category of the audit classification model in the N-1-th level storage component is obtained from the category to which the ledger data of the N-th level risk feedback data belongs.

[0042] The category to which the N-th level risk feedback data belongs may include the geographic location information of the industry business data in the keyword, the identification information of the risk model, or the risk parameters corresponding to the business data. The category of the audit classification model in the N-1-th level storage component is obtained from the category to which the ledger data of the N-th level risk feedback data belongs, so that the ledger data of the N-1-th level risk feedback data includes one or more ledger data of the N-th level risk feedback data within the same category.

[0043] The first-level risk feedback data ledger summarizes the overall status of risk management for business data. For example, the first-level risk feedback data ledger may include first-level revenue loss ledger data and first-level audit income ledger data. The first-level revenue loss ledger data can be used to understand the overall revenue loss caused by the risk, while the first-level audit income ledger data can be used to understand the overall income generated after the risk is audited.

[0044] In one implementation scenario, when generating ledger data of risk feedback data, the ledger data of N-level risk feedback data includes the ledger data of first-level risk feedback data, and the risk feedback data can be classified and summarized based on risk models and keywords.

[0045] The embodiment of the present application provides a method for processing risk data, obtaining risk feedback data for business data, inputting the risk feedback data into the audit classification model in the N-th level storage component, and classifying and summarizing the risk feedback data to generate ledger data for the N-th level risk feedback data. The ledger data for the N-th level risk feedback data is input into the audit classification model in the N-1-th level storage component, and the ledger data for the N-th level risk feedback data is classified and summarized to generate ledger data for the N-1-th level risk feedback data, until the ledger data for the first-level risk feedback data is generated. The method of the present application generates ledger data for N-level risk feedback data, and the category of the audit classification model in the N-1-th level storage component is obtained from the category to which the ledger data for the N-th level risk feedback data belongs. Therefore, the overall situation of risk processing can be fully understood through the ledger data for the first-level risk feedback data, and the overall situation of risk processing at each level can also be viewed through the ledger data for the risk feedback data generated at each level.

[0046] Based on the above embodiment, an embodiment is provided below to describe in detail the process of processing risk data.

[0047] Figure 3 A risk data processing method provided in this application embodiment Figure 2 ,like Figure 3 As shown, the method provided in the embodiment of the present application may include:

[0048] S301: Input the acquired business data into the risk model to obtain risk data of the business data.

[0049] Risk models are models that detect anomalies in business data. There can be one or more risk models, and each model can be used to detect different types of risk data. For example, a user development risk model can be used to detect whether real-name users are included in business data, while a marketing risk model can be used to detect the illegal distribution of business discount policies.

[0050] After telecommunications service personnel process telecommunications services for users, they input the service data into the risk model. In one implementation scenario, if the staff member fails to comply with service regulations, the generated service data is input into the risk model, which then outputs the corresponding risk data. Examples include situations where a user fails to activate telecommunications services using their real name, or where the telecommunications services a user has applied for do not match the fees charged for those services.

[0051] S302: Analyze the risk data to obtain risk verification data.

[0052] Among the risk data output by the risk model, there may be abnormal data that needs to be rectified, and there may also be normal data that does not require rectification. Therefore, it is necessary to analyze the risk data to determine whether there is a risk in the risk data.

[0053] When performing data analysis on risk data, the risk data can be analyzed according to business processing rules.

[0054] S303: Mark the risk verification data according to keywords to generate risk feedback data.

[0055] In order to classify and summarize the risk verification data, the risk verification data can be marked according to the keywords in the keyword database. After the risk verification data is marked, the risk verification data can be classified and summarized according to the marked keywords.

[0056] Keywords include one or more of the following: geographic location information where the business data was generated, identification information of the risk model, and risk parameters corresponding to the business data. The geographic location information where the business data was generated may include the province and city where the business data was generated. The identification information of the risk model may include the name of the risk model. Risk parameters corresponding to the business data may include revenue loss, recovered revenue loss, and audit income.

[0057] S304: Input the risk feedback data into the audit classification model in the Nth level storage component, and identify the keywords included in the risk feedback data in a preset keyword database.

[0058] Since the risk feedback data is obtained by marking the risk verification data according to keywords, the keywords contained in the risk feedback data can be identified in the keyword database.

[0059] In one implementation scenario, if the keyword database does not contain the keyword, the keyword is updated to the keyword database, thereby updating the keyword contained in the keyword database.

[0060] S305: Classify and summarize the risk feedback data according to keywords to generate the ledger data of the Nth level risk feedback data.

[0061] The Nth-level risk feedback data ledger provides an overview of the overall Nth-level risk management situation. For example, by categorizing and aggregating risk feedback data based on the keyword "revenue loss," Nth-level revenue loss ledger data can be generated. This data provides an overview of the Nth-level revenue loss situation.

[0062] The ledger data of the Nth level risk feedback data includes: risk models and their corresponding keywords. The risk models are used to distinguish the risk models of the risk data in the output keywords.

[0063] S306: Input the ledger data of the N-th level risk feedback data into the audit classification model in the N-1-th level storage component, and classify and summarize the ledger data of the N-th level risk feedback data to generate the ledger data of the N-1-th level risk feedback data, until the ledger data of the first-level risk feedback data is generated; wherein, the category of the audit classification model in the N-1-th level storage component is obtained from the category to which the ledger data of the N-th level risk feedback data belongs.

[0064] The category of the audit classification model in the N-1th level storage component is obtained by the category to which the ledger data of the N-th level risk feedback data belongs, so that the ledger data of the N-1th level risk feedback data includes the ledger data of one or more N-th level risk feedback data within the same category. For example, the province to which the audit classification model in the N-1th level storage component belongs can be obtained based on the prefecture-level city to which the N-th level risk feedback data belongs, so that the generated ledger data of the N-1th level risk feedback data includes the ledger data of the N-th level risk feedback data belonging to one or more prefecture-level cities in the same province.

[0065] The first-level risk feedback data ledger summarizes the overall status of risk management for business data. In one implementation scenario, the first-level risk feedback data ledger uses risk models and their corresponding keywords as the primary dimensions, summarizing the aggregated data corresponding to any keyword within any risk model. Therefore, the first-level risk feedback data ledger provides a comprehensive understanding of risk management.

[0066] An embodiment of the present application provides a method for processing risk data, wherein acquired business data is input into a risk model to obtain risk data for the business data. Data analysis is performed on the risk data to obtain risk verification data. The risk verification data is labeled according to keywords to generate risk feedback data. The risk feedback data is input into an audit classification model in a level N storage component, and keywords contained in the risk feedback data are identified from a preset keyword database. The risk feedback data is classified and summarized according to the keywords to generate ledger data for level N risk feedback data. The ledger data for level N risk feedback data is input into an audit classification model in a level N-1 storage component, and the ledger data for level N risk feedback data is classified and summarized to generate ledger data for level N-1 risk feedback data, until ledger data for level one risk feedback data is generated. Because the categories of the audit classification model in the level N-1 storage component are derived from the categories to which the level N risk feedback data belongs, the overall risk management situation can be fully understood through the ledger data for the level one risk feedback data. The overall risk management situation for each level can also be viewed through the ledger data for each level of risk feedback data generated.

[0067] Based on the above embodiment, a specific embodiment is provided below to describe the risk data processing process in detail.

[0068] Figure 4 A risk data processing method provided in this application embodiment Figure 3 ,like Figure 4 As shown, the method of this embodiment is specifically as follows:

[0069] S401: Obtain risk feedback data on business data.

[0070] Business data is data generated when staff handle business, and can be communication business data generated when handling communication business.

[0071] Risk feedback data is the feedback provided after the risks in the risk data have been processed and the risk rectification status has been reported. Risk feedback data can be obtained in real time, allowing for timely understanding of the risk handling status.

[0072] It should be noted that before obtaining risk feedback data, the feedback data needs to be marked according to keywords.

[0073] Keywords include one or more of the following: geographic location information where the business data was generated, identification information of the risk model, and risk parameters corresponding to the business data. The geographic location information where the business data was generated may include the province and city where the business data was generated. The identification information of the risk model may include the name of the risk model. Risk parameters corresponding to the business data may include revenue loss, recovered revenue loss, and audit income.

[0074] S402: Input the risk feedback data into the audit classification model in the third-level storage component, identify the keywords contained in the risk feedback data in the preset keyword database, classify and summarize the risk feedback data according to the keywords, and generate ledger data of the risk feedback data at the municipal level.

[0075] When classifying and summarizing risk feedback data, since keywords such as revenue loss, recovered revenue loss, and audit income contain specific values, it is also necessary to summarize the values ​​contained in revenue loss, recovered revenue loss, and audit income, so that the overall revenue loss, recovered revenue loss, and audit income can be viewed.

[0076] The embodiment of the present application classifies the storage components according to the geographical location where the business data is generated, that is, the city where the business data is generated - the province to which it belongs - the whole country, and divides the storage components into three levels. The schematic diagram of the hierarchical storage of risk data is as follows: Figure 5 shown.

[0077] It should be noted that the storage components can be classified according to the actual data size, hardware and software conditions, etc.

[0078] S403: Input the ledger data of the prefecture-level risk feedback data into the audit classification model in the second-level storage component, and classify and summarize the ledger data of the prefecture-level risk feedback data to generate the ledger data of the provincial-level risk feedback data.

[0079] In one implementation scenario, the ledger data of prefecture-level risk feedback data generated by prefecture-level cities belonging to the same province can be classified and summarized to generate ledger data of provincial-level risk feedback data. For example, Fuzhou, Xiamen, Guangzhou, Zhuhai and Shenzhen have all generated ledger data of prefecture-level risk feedback data. Since Fuzhou and Xiamen belong to Fujian Province, the ledger data of prefecture-level risk feedback data corresponding to Fuzhou and Xiamen can be classified and summarized to generate ledger data of provincial-level risk feedback data corresponding to Fujian Province. Guangzhou, Zhuhai and Shenzhen belong to Guangdong Province, so the ledger data of prefecture-level risk feedback data corresponding to Guangzhou, Zhuhai and Shenzhen can be classified and summarized to generate ledger data of provincial-level risk feedback data corresponding to Guangdong Province.

[0080] S404: Input the ledger data of the provincial-level risk feedback data into the audit classification model in the first-level storage component, and classify and summarize the ledger data of the provincial-level risk feedback data to generate the ledger data of the headquarters-level risk feedback data.

[0081] The headquarters-level risk feedback data ledger uses risk model and keyword as its primary dimensions, summarizing the aggregated data corresponding to any keyword within any risk model. For example, the headquarters-level risk feedback data ledger aggregates nationwide data for keywords such as risk data volume, revenue loss, and audit revenue. Therefore, using the headquarters-level risk feedback data ledger, you can query the aggregated data for any keyword within any risk model, as well as the detailed information on any risk handling within that keyword.

[0082] The embodiment of the present application provides a method for risk data processing, which obtains risk feedback data for business data, inputs the risk feedback data into the audit classification model in the third-level storage component, identifies the keywords contained in the risk feedback data in a preset keyword database, classifies and summarizes the risk feedback data according to the keywords, and generates ledger data for prefecture-level risk feedback data. The ledger data of the prefecture-level risk feedback data is input into the audit classification model in the second-level storage component, and the ledger data of the prefecture-level risk feedback data is classified and summarized to generate ledger data for provincial-level risk feedback data. The ledger data of the provincial-level risk feedback data is input into the audit classification model in the first-level storage component, and the ledger data of the provincial-level risk feedback data is classified and summarized to generate ledger data for headquarters-level risk feedback data. The method of the embodiment of the present application generates ledger data for prefecture-level risk feedback data, ledger data for provincial-level risk feedback data, and ledger data for headquarters-level risk feedback data. Through the ledger data of the headquarters-level risk feedback data, the overall situation of risk management across the country, as well as the overall revenue loss and overall audit income caused by the risk, can be viewed. The overall situation of risk management within each province and each prefecture-level city can also be viewed.

[0083] Figure 6 A schematic diagram of a risk data processing device provided in an embodiment of the present application Figure 1 .like Figure 6 As shown, an embodiment of the present application provides a risk data processing device 600 , which may include: an acquisition module 601 , an input module 602 , and a generation module 603 .

[0084] Acquisition module 601, used to obtain risk feedback data on business data;

[0085] Input module 602, used to input risk feedback data into the audit classification model in the Nth level storage component;

[0086] A generation module 603 is used to classify and summarize the risk feedback data to generate ledger data of the Nth level risk feedback data, where N is a positive integer greater than 1;

[0087] The input module 602 is further used to input the ledger data of the Nth level risk feedback data into the audit classification model in the N-1th level storage component;

[0088] Generation module 603 is also used to classify and summarize the ledger data of the Nth level risk feedback data to generate the ledger data of the N-1th level risk feedback data, until the ledger data of the first level risk feedback data is generated; wherein, the category of the audit classification model in the N-1th level storage component is obtained from the category to which the ledger data of the Nth level risk feedback data belongs.

[0089] In a possible implementation, the generating module 603 is specifically configured to:

[0090] Identifying keywords contained in risk feedback data in a preset keyword database;

[0091] Risk feedback data is classified and summarized according to keywords to generate ledger data of N-th level risk feedback data.

[0092] Optionally, when the generation module 603 identifies keywords included in the risk feedback data in a preset keyword database, it is specifically configured to:

[0093] If the keyword database does not contain the keyword, the keyword is updated to the keyword database.

[0094] In a possible implementation, the acquisition module 601 is specifically configured to:

[0095] Input the acquired business data into the risk model to obtain risk data of the business data;

[0096] Conduct data analysis on risk data to obtain risk verification data;

[0097] Mark risk verification data according to keywords to generate risk feedback data.

[0098] The device of this embodiment can be used to perform the following Figures 2 to 4 The implementation principles and technical effects of the method embodiments shown are similar and will not be described in detail here.

[0099] Figure 7 A schematic diagram of a risk data processing device provided in an embodiment of the present application Figure 2 .like Figure 7As shown, an embodiment of the present application provides a risk data processing device 700 including a processor 701 and a memory 702 , wherein the processor 701 and the memory 702 are connected via a bus 703 .

[0100] During the specific implementation process, the memory 702 stores codes, and the processor 701 runs the codes stored in the memory 702 to execute the risk data processing method of the above method embodiment.

[0101] The specific implementation process of the processor 701 can be found in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here in this embodiment.

[0102] In the above Figure 7 In the illustrated embodiment, it should be understood that processor 701 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASICs), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly executed by a hardware processor or by a combination of hardware and software modules within the processor.

[0103] The memory 702 may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk storage.

[0104] Bus 703 can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Bus 703 can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, bus 703 in the drawings of this application is not limited to a single bus or a single type of bus.

[0105] An embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the risk data processing method of the above-mentioned method embodiment.

[0106] The computer-readable storage medium can be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The computer-readable storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0107] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0108] An embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the risk data processing method provided in any of the above embodiments of the present application.

[0109] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0110] It should be understood that the present application is not limited to the exact structure described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for processing risk data, characterized in that: include: Obtain risk feedback data on business data, wherein the risk feedback data is feedback data on the rectification status after the risks in the risk data are rectified; Inputting the risk feedback data into the audit classification model in the Nth level storage component, and identifying keywords contained in the risk feedback data in a preset keyword database; Classify and summarize the risk feedback data according to the keywords to generate the N-th level risk feedback data ledger data, where N is a positive integer greater than 1; The Nth level risk feedback data ledger data includes a risk model and corresponding keywords, and the risk model is used to distinguish and output risk data in the keywords; Inputting the ledger data of the N-th level risk feedback data into the audit classification model in the N-1-th level storage component, and classifying and aggregating the ledger data of the N-th level risk feedback data to generate ledger data of the N-1-th level risk feedback data, until the ledger data of the first-level risk feedback data is generated; wherein the category of the audit classification model in the N-1-th level storage component is obtained by the category to which the ledger data of the N-th level risk feedback data belongs; the ledger data of the first-level risk feedback data includes the first-level revenue loss ledger data and the first-level audit income ledger data; The identifying the keywords contained in the risk feedback data in a preset keyword database includes: If the keyword database does not contain the keyword, the keyword is updated to the keyword database.

2. The method according to claim 1, characterized in that The obtaining of risk feedback data on business data includes: Inputting the acquired business data into the risk model to obtain risk data of the business data; Performing data analysis on the risk data to obtain risk verification data; The risk verification data is marked according to the keywords to generate risk feedback data.

3. The method according to claim 1, characterized in that The keywords include one or more of the following: geographic location information for generating the business data, identification information of the risk model, and risk parameters corresponding to the business data.

4. A risk data processing device, characterized in that: include: An acquisition module is used to acquire risk feedback data on business data, wherein the risk feedback data is feedback data on the rectification status after the risks in the risk data are rectified; An input module, configured to input the risk feedback data into the audit classification model in the Nth level storage component; A generation module, configured to classify and summarize the risk feedback data to generate ledger data of level N risk feedback data, where N is a positive integer greater than 1; The Nth level risk feedback data ledger data includes a risk model and corresponding keywords, and the risk model is used to distinguish and output risk data in the keywords; The input module is further configured to input the ledger data of the Nth level risk feedback data into the audit classification model in the N-1th level storage component; The generation module is further configured to classify and summarize the ledger data of the N-th level risk feedback data to generate ledger data of the N-1th level risk feedback data, until the ledger data of the first-level risk feedback data is generated; wherein the category of the audit classification model in the N-1th level storage component is obtained by the category to which the ledger data of the N-th level risk feedback data belongs; the ledger data of the first-level risk feedback data includes the first-level income loss ledger data and the first audit income ledger data; The generating module is specifically configured to identify keywords contained in the risk feedback data in a preset keyword database; classify and summarize the risk feedback data according to the keywords to generate the ledger data of the Nth level risk feedback data; The generating module is further configured to update the keyword to the keyword database if the keyword database does not contain the keyword.

5. A risk data processing device comprising: A processor and a memory, wherein the memory stores code, and the processor runs the code stored in the memory to execute the risk data processing method according to any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the risk data processing method according to any one of claims 1 to 3.

7. A computer program product, characterized in that The method comprises a computer program, which is used to implement the risk data processing method according to any one of claims 1 to 3 when the computer program is executed by a processor.

Images