Business processing method and device based on AI test, equipment, medium and product

Through AI tools, the knowledge base is loaded and tasks are generated in business processing, which solves the problem of insufficient knowledge base in the existing technology, improves the efficiency and accuracy of business processing, enhances the ability to integrate with the automated test platform, and improves the user experience .

CN118964211AInactive Publication Date: 2024-11-15SHENZHEN FARBEN INFORMATION TECH CO LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202411186842.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-28
Publication Date
2024-11-15
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing business processing models lack a massive knowledge base and mature models that integrate multiple fields, resulting in poor application results and insufficient integration capabilities with the automated test platform, affecting user experience and efficiency.

Method used

Receive business processing requests through AI tools, load business knowledge base, generate business tasks to be executed, and execute tasks through AI tools to obtain processing results, solving the problem of insufficient knowledge base and improving the efficiency and accuracy of business processing.

Benefits of technology

It realizes efficient response to business processing requests, improves application effect, enhances the integration capability with the automated test platform, and improves user experience and processing efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118964211A_ABST
    Figure CN118964211A_ABST
Patent Text Reader

Abstract

The invention discloses a service processing method and device based on AI testing, equipment, a medium and a product, and relates to the technical field of AI intelligence, the method is applied to an automatic testing platform, the automatic testing platform comprises an AI tool, and the method comprises the following steps: receiving a service processing request of a user; based on the business processing request, performing configuration loading through the AI tool to obtain a business knowledge base, and generating a to-be-executed business task according to the business knowledge base; and executing the to-be-executed business task through the AI tool to obtain a business processing result. Therefore, configuration loading is performed on the received service processing request through the AI tool to obtain the service knowledge base for service processing, then the service task to be executed is generated according to the service knowledge base, and finally the service processing result is obtained by executing the service task to be executed through the AI tool, so that the service processing efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of AI intelligent technology, and in particular to a business processing method, device, equipment, medium and product based on AI testing. Background Art

[0002] With the rapid development of informatization and digitalization, big data technology has become an important force in promoting the development of various industries, especially models that assist users in business processing. As one of the core technologies in the field of natural language processing (NLP), it aims to provide accurate services through intelligent analysis and processing of massive data.

[0003] However, in actual business scenarios, such models have high requirements for databases, lack of massive knowledge base training data and mature models that integrate multiple professional fields, and lack the ability to integrate with existing automated testing platforms (interfaces, performance, UI automation). As a result, the application effect in practice is poor, affecting the actual user experience.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a business processing method, device, equipment, medium and product based on AI testing, aiming to solve the technical problem of lack of a massive knowledge base integrating professional knowledge in multiple fields for business processing when responding to business processing requests, resulting in poor actual application effects.

[0006] To achieve the above objectives, the present application proposes a business processing method based on AI testing, the method is applied to an automated testing platform, the automated testing platform includes an AI tool, and the method includes: Receive business processing requests from users; Based on the business processing request, configuration loading is performed through the AI ​​tool to obtain a business knowledge base, and a business task to be executed is generated according to the business knowledge base; The business task to be executed is executed by the AI ​​tool to obtain a business processing result.

[0007] In one embodiment, the step of performing configuration loading through the AI ​​tool based on the business processing request to obtain a business knowledge base, and generating a business task to be executed according to the business knowledge base includes: Reading the business processing request through the AI ​​tool to obtain the business industry, service content, and the service organization corresponding to the business industry; The preset summary knowledge base is called according to the business industry and service organization to obtain a business knowledge base; Task generation is performed according to the business knowledge base and service content to obtain business tasks to be executed.

[0008] In one embodiment, the step of generating tasks according to the business knowledge base and service content to obtain business tasks to be executed includes: The service case set is read through the business knowledge base and the service content to obtain a reading result; If the reading result is that the service case set has related service cases, extracting the related service cases to obtain service processes and interface call information; Task generation is performed according to the service process and interface call information to obtain the business tasks to be executed.

[0009] In one embodiment, after the step of reading the test case through the business knowledge base and the service content to obtain the reading result, the method further includes: If the reading result is that the service case set does not have a relevant service case, information about the missing case is sent to the development end, and the development end performs code development based on the business knowledge base and service content to obtain a development result; Receiving the development result sent by the development end; Generate a test case according to the development result, and test the test case through the AI ​​tool to obtain a test result; When the test result is passed, the test case is output as a service case, and the service case is stored in the service case set.

[0010] In one embodiment, the step of generating a test case according to the development result, and testing the test case by the AI ​​tool to obtain the test result includes: Perform test planning according to the development results to obtain a test plan, and query and obtain relevant business interfaces and business scenarios based on the test plan; Customizing and transforming the relevant business interface to obtain a business interface; Generate a business test process according to the business scenario, and output test cases based on the business interface and the business test process; Testing the test case by using the AI ​​tool; When the business test process is completed and the business interface call is normal, the output test result is passed.

[0011] In one embodiment, after the step of executing the to-be-executed business task by the AI ​​tool to obtain a business processing result, the method further includes: Sending the business processing result and the service case to the development end, and the development end improving the environment configuration and parameters of the service case based on the business processing result to obtain a final service case; The final service case sent by the development end is received, and the service case set and the summary database are updated based on the final service case.

[0012] In addition, to achieve the above-mentioned purpose, the present application also proposes a service processing device based on AI testing, which is applied to an automated testing platform, and the automated testing platform includes an AI tool, and the device includes: A receiving module, used for receiving a user's business processing request; A generation module, configured to load the configuration through the AI ​​tool based on the business processing request, obtain a business knowledge base, and generate a business task to be executed according to the business knowledge base; The processing module is used to execute the business task to be executed through the AI ​​tool to obtain a business processing result.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a business processing device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the business processing method based on AI testing as described above.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the business processing method based on AI testing as described above are implemented.

[0015] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the business processing method based on AI testing as described above.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: The embodiments of the present application propose a business processing method, device, equipment, storage medium and computer program product based on AI testing, which receives a business processing request from a user; based on the business processing request, configures and loads the AI ​​tool to obtain a business knowledge base, and generates a business task to be executed based on the business knowledge base; executes the business task to be executed through the AI ​​tool to obtain a business processing result. Thus, the received business processing request is configured and loaded through the AI ​​tool to obtain a business knowledge base for business processing, and then the business task to be executed is generated based on the business knowledge base, and finally the business processing result is obtained by executing the business task to be executed through AI, which solves the problem of poor actual application effect due to the lack of a comprehensive and professional massive knowledge base in multiple fields when responding to business processing requests, and improves the efficiency of business processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] 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.

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] Figure 1 A flowchart of the first embodiment of the business processing method based on AI testing of this application is provided; Figure 2 This is a schematic diagram of an access task template involved in the business processing method based on AI testing in this application; Figure 3 A flowchart of the second embodiment of the business processing method based on AI testing of this application is provided; Figure 4 A schematic diagram of generating a test plan for the business processing method based on AI testing for this application; Figure 5 A schematic diagram of generating a business interface for the business processing method based on AI testing in this application; Figure 6 This is a schematic diagram of the interface test involved in the business processing method based on AI test in this application; Figure 7 This is a schematic diagram of the business scenario involved in the business processing method based on AI testing in this application; Figure 8 A brief flowchart of a business processing method based on AI testing provided in Example 2 of the present application; Fig. 9 This is a schematic diagram of the actual business processing involved in the business processing method based on AI testing in this application; Fig.10 This is a schematic diagram of the module structure of a service processing device based on AI testing in an embodiment of the present application; Fig.11 This is a schematic diagram of the device structure of the hardware operating environment involved in the business processing method based on AI testing in an embodiment of the present application.

[0020] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0022] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0023] The main solution of the embodiment of the present application is: read the business processing request through the AI ​​tool to obtain the business industry, service content and service organization corresponding to the business industry; call the preset summary knowledge base according to the business industry and service organization to obtain the business knowledge base; generate tasks according to the business knowledge base and service content to obtain the business tasks to be executed. Read the service case set through the business knowledge base and service content to obtain the reading result; if the reading result is that there are relevant service cases in the service case set, extract the relevant service cases to obtain the service process and interface call information; generate tasks according to the service process and interface call information to obtain the business tasks to be executed. If the reading result is that there are no relevant service cases in the service case set, send the missing case information to the development end, and the development end performs code development based on the business knowledge base and service content to obtain the development result; receive the development result sent by the development end; generate a test case according to the development result, and test the test case through the AI ​​tool to obtain the test result; if the test result is passed, output the test case as a service case, and store the service case in the service case set. Conduct test planning based on the development results to obtain a test plan, and query the relevant business interfaces and business scenarios based on the test plan; customize the relevant business interfaces to obtain business interfaces; generate business test processes based on the business scenarios, and output test cases based on the business interfaces and business test processes; test the test cases through the AI ​​tool; and output the test results as passed when the business test process is completed and the business interface call is normal. Send the business processing results and service cases to the development end, and the development end improves the environment configuration and parameters of the service case based on the business processing results to obtain the final service case; receive the final service case sent by the development end, and update the service case set and summary database based on the final service case.

[0024] This solves the problem of lack of a comprehensive professional massive knowledge base in multiple fields for business processing when responding to business processing requests, resulting in poor actual application effects, realizes business processing, and improves the accuracy of business processing. Based on the scheme of the present invention, starting from the fact that current business processing lacks comprehensive professional massive knowledge base training data and mature models in multiple fields, resulting in poor application effects in practice and lack of perfect integration with existing automated testing platforms (interfaces, performance, UI automation), thus low efficiency, a business processing method based on AI testing is designed, and the effectiveness of the business processing method based on AI testing of the present invention is verified when processing the business. Finally, the efficiency of business processing by the method of the present invention is significantly improved.

[0025] In this embodiment, for ease of description, the following description is made using a business processing device based on an AI test as the execution subject.

[0026] Since the actual business scenarios in the existing technology have high requirements for business processing models and databases, the timeliness of the processing models and databases cannot be guaranteed during use, resulting in poor business processing results. In other words, there is a lack of massive knowledge base training data and mature models that integrate multiple professional fields, and a lack of integration capabilities with existing automated testing platforms (interfaces, performance, UI automation), which leads to poor application results in practice, affects the actual user experience, and reduces efficiency.

[0027] The present application provides a solution, which uses AI tools to respond to business processing requests in an automated testing platform, loads the corresponding business knowledge base, and generates business tasks to be executed based on the business knowledge base. Finally, AI calls the corresponding business processing model to execute the business tasks to be executed, obtains the business processing results, and provides users with better services.

[0028] It can be seen from the above embodiments that the present application receives a business processing request from a user; based on the business processing request, the AI ​​tool is configured and loaded to obtain a business knowledge base, and a business task to be executed is generated according to the business knowledge base; the business task to be executed is executed by the AI ​​tool to obtain a business processing result. Thus, the received business processing request is configured and loaded by the AI ​​tool to obtain a business knowledge base for business processing, and then a business task to be executed is generated according to the business knowledge base, and finally the business task to be executed by AI is executed to obtain a business processing result, which solves the problem of poor actual application effect due to the lack of a comprehensive and professional massive knowledge base in multiple fields when responding to business processing requests, and improves the efficiency of business processing.

[0029] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a business processing device based on AI testing, etc. The following takes a business processing device based on AI testing as an example to illustrate this embodiment and the following embodiments.

[0030] Based on this, the embodiment of the present application provides a business processing method based on AI testing, referring to Figure 1 , Figure 1 This is a flowchart of the first embodiment of the business processing method based on AI testing in this application.

[0031] In this embodiment, the service processing method based on AI testing includes steps S01 to S03: Step S01, receiving a user's service processing request; Before explaining the present embodiment, it should be clear that with the rapid development of informatization and digitalization, big data technology has become an important force in promoting the development of various industries, especially models that assist users in business processing. As one of the core technologies in the field of natural language processing (NLP), it aims to provide accurate services through intelligent analysis and processing of massive data. However, in actual business scenarios, such models have high requirements for databases, lack of comprehensive professional massive knowledge base training data and mature models in multiple fields, and lack of integration capabilities with existing automated testing platforms (interfaces, performance, UI automation), resulting in poor application effects in practice and affecting the actual user experience.

[0032] Therefore, this embodiment gives priority to receiving user business processing, wherein the business processing request received in this embodiment is based on the business provided by the enterprise, and the enterprise may include banks, government affairs, online shopping platforms, shopping malls, etc., and the services they provide are different. Therefore, this embodiment takes a bank as an example, and the business processing request here is illustrated by the scenario of bank account opening. The platform for receiving the business processing request in this embodiment can be provided by JAVA, GO, PythonSDK integration and Chrome browser plug-in, and it should be specifically set according to actual business needs.

[0033] Step S02: Based on the business processing request, configuration loading is performed through the AI ​​tool to obtain a business knowledge base, and a business task to be executed is generated according to the business knowledge base; The business processing request includes the industry and content of the business processing that the user is processing. After understanding these, the corresponding configuration can be loaded through the AI ​​tool to obtain the business knowledge base corresponding to the business processing request. Then, the corresponding business tasks to be executed can be generated based on the business knowledge database. Among them, AI (Artificial Intelligence) is a branch of computer science that aims to create systems that can simulate and execute human intelligent behavior. AI includes multiple sub-fields, mainly including: (1) Machine Learning: Using algorithms to enable computers to learn and improve from data without explicit programming. It specifically includes supervised learning, unsupervised learning, and reinforcement learning. (2) Natural Language Processing (NLP): enables computers to understand, generate and process human language, such as speech recognition, language translation and sentiment analysis; (3) Computer Vision: enables computers to “see” and understand the content of images and videos. Applications include facial recognition, image classification, and object detection. (4) Expert Systems: They imitate the decision-making process of experts and are usually used to solve problems in specific fields. (5) Robotics: involves the design and manufacture of robots that can perform tasks that usually require perception, processing and action capabilities.

[0034] Step S03: Execute the business task to be executed through the AI ​​tool to obtain a business processing result.

[0035] After obtaining the pending business tasks, the corresponding business processing results can be obtained by executing the tasks through AI tools. It should be clear that the corresponding interface call relationship and task execution process have been recorded in the pending business tasks, so the AI ​​tool can execute the tasks based on the content recorded in the pending business tasks to obtain the final business processing results.

[0036] Specifically, the above step S02, based on the business processing request, configures and loads the AI ​​tool to obtain a business knowledge base, and generates a business task to be executed according to the business knowledge base, includes: Step S021, reading the business processing request through the AI ​​tool to obtain the business industry, service content and the service organization corresponding to the business industry; Step S022, calling a preset summary knowledge base according to the business industry and service organization to obtain a business knowledge base; Step S023: generating tasks according to the business knowledge base and service content to obtain business tasks to be executed.

[0037] After receiving the business processing request, AI can read it to obtain the business industry (such as finance, medical care, and education), service content (such as the user needs to open an account, apply for a medical insurance card, or select a school), and the service agency corresponding to the business industry (for example, opening an account in the financial industry requires opening an account in the corresponding bank, etc.); Then, the summary knowledge base can be called based on the business industry (finance) and service agency (bank) to obtain the business knowledge base (i.e., various business processing conditions of the banking industry in the financial industry, etc.). It should be clear that the summary knowledge base in this embodiment is a knowledge base that brings together multiple industries, such as finance, Internet, automobiles, communications, intelligent manufacturing, and public services. Therefore, the business knowledge base can be called accordingly when performing business processing; Finally, the business tasks to be executed can be generated according to the service content (bank account opening) required by the user and the business knowledge base to obtain the business tasks to be executed.

[0038] More specifically, the above step S023, the step of generating tasks according to the business knowledge base and service content to obtain business tasks to be executed, includes: Step S0231, reading the service case set through the business knowledge base and service content to obtain a reading result; Step S0232: if the reading result indicates that the service case set has related service cases, extract the related service cases to obtain service processes and interface call information; Step S0233: Generate tasks according to the service process and interface call information to obtain business tasks to be executed.

[0039] In the actual business processing process, there may be corresponding processing experience in the past. For example, when a company handles bank card business for new employees, due to the high repetitiveness, the service case set can be read through the business knowledge base and service content to obtain the reading result. Among them, the service case set is pre-constructed. Since the corresponding industries and the business handled are numerous, the service case set can also be divided according to the actual industries and institutions. The reading result is explained in two ways in this embodiment. The first is that the relevant service case is read, and the second is that the relevant service case cannot be read.

[0040] Then, when the reading result shows that there are relevant service cases in the service case set, the relevant service cases are extracted to obtain the corresponding service process and interface call information. It should be clear that the specific business handling situations may be somewhat different, but the service process in this embodiment is universal, that is, when the user applies for a card, the information that needs to be entered (such as ID number, mobile phone number, name, occupation, etc.) is universal, and the interface call information can also be changed according to the actual business scenario. For example, in the loan business, it is necessary to connect with a qualification verification certificate. For example, the company's loan can be queried through the corresponding official channels; Finally, tasks can be generated based on the service process and interface call information obtained from the relevant service cases to obtain the business tasks to be executed.

[0041] Further, the solution in this embodiment is as follows Figure 2 As shown: First, after receiving the user's business processing request, the template configuration that completes the business processing is accessed, and the corresponding template configuration is accessed after reading the business processing request; Then, select the industry corresponding to the business request, such as the financial industry, and then select the knowledge base corresponding to the financial industry, such as the business handling knowledge base of a banking institution; Then, based on the business handling knowledge base, generate tasks to be executed through custom task templates; Then, after executing the task to be executed, the execution result is obtained. At this time, some industry personnel can intervene manually to supplement and correct the execution result to a certain extent; Finally, in this embodiment, the supplemented and corrected execution results are imported into the own knowledge base for learning, so as to facilitate subsequent business processing.

[0042] This embodiment adopts the above scheme, specifically by receiving the business processing request of the user; based on the business processing request, the AI ​​tool is configured and loaded to obtain the business knowledge base, and the business task to be executed is generated according to the business knowledge base; the business task to be executed is executed by the AI ​​tool to obtain the business processing result. Thus, the received business processing request is configured and loaded by the AI ​​tool to obtain the business knowledge base for business processing, and then the business task to be executed is generated according to the business knowledge base, and finally the business task to be executed is executed by AI to obtain the business processing result, which solves the problem of poor actual application effect due to the lack of a comprehensive and professional massive knowledge base in multiple fields for business processing when responding to business processing requests, and improves the efficiency of business processing.

[0043] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 3 , step S0231, reading the service case set through the business knowledge base and service content, after obtaining the reading result, the business processing method based on AI testing also includes steps S0234~S0237: Step S0234, if the reading result is that the service case set does not have a relevant service case, then information about the missing case is sent to the development end, and the development end performs code development based on the business knowledge base and service content to obtain a development result; Step S0235, receiving the development result sent by the development end; Step S0236, generating a test case according to the development result, and testing the test case through the AI ​​tool to obtain a test result; Step S0237: if the test result is passed, output the test case as a service case, and store the service case in the service case set.

[0044] In the process of business processing, it may involve business expansion or the handling of unpopular business. At this time, if the reading result is that there is no relevant service case in the service case set, the information about the missing case can be sent to the development end. The development end in this embodiment includes but is not limited to actual operation and maintenance personnel and code developers, etc. Therefore, when the operation and maintenance personnel of the development end receive the business processing request, they can propose design requirements based on the business knowledge base and service content, and the code developers will develop the code to obtain the development results; The automated testing platform then receives the development results sent by the development end, generates corresponding test cases based on the development results, and sends them to AI to test the test cases to obtain the test results, that is, the test status of the business processing; If the test result is passed, the test case is output as a service case, and the service case is stored in a service case set to facilitate subsequent calling of the service case.

[0045] Specifically, the above step S0236, generating a test case according to the development result, and testing the test case by the AI ​​tool, the step of obtaining the test result includes: Step S02361, performing test planning according to the development result to obtain a test plan, and querying and obtaining relevant business interfaces and business scenarios based on the test plan; Step S02362, customizing and transforming the relevant business interface to obtain a business interface; Step S02363, generating a business test process according to the business scenario, and outputting a test case based on the business interface and the business test process; Step S02364, testing the test case by using the AI ​​tool; Step S02365, when the business test process is executed and the business interface call is normal, the test result is output as passed.

[0046] After the development results are obtained in this embodiment, it is necessary to carry out test planning for the actual test content to obtain the following Figure 4 The test plan shown includes the corresponding plan content, responsible persons, test phases and descriptions, among which the description specifically includes the relevant business interfaces and business scenarios that need to be called by the test plan.

[0047] After understanding the relevant business interfaces and business scenarios, a test process can be generated according to the business scenarios, and test cases can be output based on the business interfaces and business test processes. Figure 5 As shown, it includes specific request information, request parameters, and response content.

[0048] Finally, the test case can be tested by the AI ​​tool. It should be clear that the more important thing in the case test is the call of the interface, so the interface test in this embodiment is as follows: Figure 6 As shown, the business to be performed this time is account information query AcctlnfQry (Account Information Query), which includes response tests for multiple request parameters. In this embodiment, three request headers are used as examples for explanation. The three requests all contain corresponding QUERY parameters, REST parameters and request bodies. Among them, the request header is a concept in the HTTP protocol, which is used to provide additional information about the request when the client sends a request to the server. The QUERY parameter refers to the data passed as part of the query string in the HTTP request. The REST parameter (sometimes also called path parameter or routing parameter) is a parameter used to pass information in the URL path. They are usually used as part of the URL to identify resources or specify operations. Unlike the QUERY parameter, the REST parameter is directly embedded in the URL path instead of being passed through the query string. The request body is the part of the HTTP request used to carry data. The content of the request body can be in different formats, such as JSON, XML, and form data. When the business interface call is normal, the output test result is passed.

[0049] More specifically, in step S03 in the above embodiment, after the step of executing the to-be-executed business task by the AI ​​tool to obtain the business processing result, the method further includes: Step S04, sending the business processing result and the service case to the development end, and the development end improving the environment configuration and parameters of the service case based on the business processing result to obtain a final service case; Step S05: receiving the final service case sent by the development end, and updating the service case set and the summary database based on the final service case.

[0050] After obtaining the business processing results, the specific service situation may need to be improved, so the obtained business processing results and service cases are sent to the development end. The service case in this embodiment is as follows: Figure 7As shown, the current service case includes a total of 3 steps, namely step ① query user post (the data of the post request is placed in the request body, which is suitable for processing large amounts of data or sensitive information), step ② user login interface and step, using GET request, ③ user query interface, using GET request, (GET request is a method used in the HTTP protocol to obtain resources from the server. It is usually used to retrieve data from the server rather than submit data to the server), where each API can be copied accordingly for use in subsequent scenarios, and corresponding coding can also be left for the API.

[0051] After receiving the service case, the development end can make corresponding improvements to the environment configuration and parameters of the service case, such as changing the interface call function to make it respond faster, and finally obtain the improved final service case; The automated testing platform then receives the final service case sent by the development end, and updates the service case set and the summary database based on the final service case, so that the automated testing platform can respond faster when receiving business processing requests.

[0052] This embodiment adopts the above scheme, specifically, if the reading result is that there is no relevant service case in the service case set, then the information of the missing case is sent to the development end, and the development end performs code development based on the business knowledge base and service content to obtain the development result; receives the development result sent by the development end; generates a test case according to the development result, and tests the test case through the AI ​​tool to obtain the test result; if the test result is passed, outputs the test case as a service case, and stores the service case in the service case set. Thus, the received business processing request is configured and loaded through the AI ​​tool to obtain the business knowledge base for business processing, and then the business task to be executed is generated according to the business knowledge base. Finally, the business processing result is obtained by executing the business task to be executed through AI, which solves the problem of poor actual application effect due to the lack of a massive knowledge base integrating multiple fields of expertise when responding to business processing requests, and improves the efficiency of business processing.

[0053] For example, to help understand the implementation process of the business processing method based on AI testing obtained by combining this embodiment with the above-mentioned embodiment 1, please refer to Figure 8 , Figure 8 A brief flowchart of a business processing method based on AI testing is provided, specifically: In the automated testing platform, AI is accessed through JAVA, GO, PythonSDK integration and Chrome browser plug-in. The browser side supports fast pluggable component functions. In addition, the server side also provides lightweight access to JAVA, GO and PythonSDK, etc., which can be accessed by simply configuring the FarAI service configuration (FarAI management-side automated testing service configuration includes: environment management, service address, port communication protocol, message format, routing configuration, SecretKey, which refers to the key used to encrypt and decrypt data); After the server configuration is complete, you can: ①Open FarAI (i.e. AI tool); ② In AI, it can be done through user dialogue or one-stop service (user inputs requirements and AI executes). In this embodiment, the user dialogue method is used for explanation. After accessing AI, AI provides corresponding templates for users to select, such as selecting corresponding major categories and minor categories (such as finance-banking); ③The corresponding knowledge base will then be loaded, such as the bank knowledge base, securities knowledge base, and insurance knowledge base, etc. It should be noted here that AI will select templates and knowledge bases in different combinations according to the user's choice, and will provide corresponding prompt boxes for users to know the accuracy of the current business processing. For example, after the user declares to apply for a second-class card, the accuracy of selecting "Finance-Bank" can be as high as 99%, that is, the number of times this scenario is used and the accuracy have been verified accordingly. It should be clear that FarAI will use different combinations of models and underlying knowledge bases according to the user's choice, and delete different results according to the user's output. In addition, reasonable selection can improve the accuracy of FarAI's output, reduce the system's resource overhead, and improve computing efficiency. Furthermore, the knowledge base can also be imported into the enterprise's own knowledge base according to the template configuration on the FarAI management end; ④ The user inputs the business type and service content to be performed, and the customized input template will generate the corresponding business task to be executed. For example, after the user selects "Account Service-Second Class Card Opening", AI will load the corresponding business task to be executed. Among them, in the selection of business type, FarAI has maintained a set of standard business classifications in the library based on the accumulation of different industries. Users can also add, delete, modify, and check cursive according to their own situation. In addition, the output template can also be dynamically adjusted according to the specific business scenario and the existing automated testing platform specifications. The specific output template configuration can be (1) task configuration: task name, task plan, (2) test type configuration: interface case, scenario case, performance test script, UI test script, (3) output case configuration: interface case template, scenario case template, performance test case (*.jmx), UI test case (*.py); ⑤Execute the pending business tasks and obtain the execution results; ⑥ After manually (development side) optimizing the execution results, environment configuration, parameters, etc., they are put into storage, that is, added to the summary database (including cloud database and self-maintained database, etc.). Among them, the specific optimization operations performed by the development side can include (1) confirmation and modification of environment configuration, (2) confirmation and modification of related parameters (request header, request body, pre-operation, assertion and mock, etc.), (3) the final confirmed results can be saved to a new knowledge base, updating the summary knowledge base, and continuously self-learning and improving, (4) the knowledge base also provides online cloud upgrade services.

[0054] More specifically, this embodiment is described using an electronic wallet payment scenario. Fig. 9 As shown: First, the user initiates a payment request on the online shopping platform. At this time, the automated testing platform will call the interface to query the user's account information (including the query of the second and third types of accounts, which can be set according to actual business needs). It should be noted that when querying, the enterprise service bus (that is, the external interface) queries the enterprise core system to obtain specific account opening information, and randomly returns the results to the automated testing platform; Then, check whether there is a normal Class II account in the returned result. If not, jump to the account opening process or end the process directly; Then, the corresponding account signing information is sent to the user, who decides to sign the contract. If the user refuses to sign the contract, the process will be transferred to quick payment, and the payment will be completed through processes such as entering the transaction password, SMS notification, and SMS verification. If the user decides to sign the contract, the process will be transferred to quick payment signing; Then, if the contract is signed successfully, check whether the balance meets the order amount. If it is not enough, proceed to the recharge process; Finally, after the contract is signed, the corresponding order payment will be made, including entering the password, entering the verification code and other operations.

[0055] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the business processing method based on AI testing of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0056] This application also provides a business processing device based on AI testing, please refer to Fig.10 , the device is applied to an automated testing platform, the automated testing platform includes an AI tool, and the device includes: The receiving module 10 is used to receive a user's service processing request; A generating module 20, configured to load configuration through the AI ​​tool based on the business processing request, obtain a business knowledge base, and generate a business task to be executed according to the business knowledge base; The processing module 30 is used to execute the business task to be executed through the AI ​​tool to obtain a business processing result.

[0057] The business processing device based on AI testing provided by the present application adopts the business processing method based on AI testing in the above-mentioned embodiment, which can solve the technical problem that there is a lack of a comprehensive and professional massive knowledge base in multiple fields for business processing when responding to business processing requests, resulting in poor actual application effects. Compared with the prior art, the beneficial effects of the business processing device based on AI testing provided by the present application are the same as the beneficial effects of the business processing method based on AI testing provided by the above-mentioned embodiment, and the other technical features of the business processing device based on AI testing are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0058] The present application provides a business processing device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the business processing method based on AI testing in the above-mentioned embodiment 1.

[0059] Reference below Fig.11 , which shows a schematic diagram of the structure of a business processing device suitable for implementing an embodiment of the present application. The business processing device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.11 The business processing device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0060] like Fig.11As shown, the business processing device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the business processing device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the business processing device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a business processing device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0061] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0062] The business processing device provided by the present application adopts the business processing method based on AI testing in the above embodiment, which can solve the technical problem that there is a lack of a comprehensive and professional massive knowledge base in multiple fields for business processing when responding to business processing requests, resulting in poor actual application effects. Compared with the prior art, the beneficial effects of the business processing device provided by the present application are the same as the beneficial effects of the business processing method based on AI testing provided in the above embodiment, and the other technical features in the business processing device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0063] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0064] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0065] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the business processing method based on AI testing in the above-mentioned embodiment.

[0066] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0067] The above-mentioned computer-readable storage medium may be included in the business processing device; or it may exist independently without being installed in the business processing device.

[0068] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the business processing device, the business processing device: receives the user's business processing request; based on the business processing request, performs configuration loading through the AI ​​tool to obtain a business knowledge base, and generates a business task to be executed according to the business knowledge base; executes the business task to be executed through the AI ​​tool to obtain a business processing result.

[0069] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0070] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0071] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0072] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned business processing method based on AI testing, and can solve the technical problem of poor practical application effect caused by the lack of a comprehensive and professional massive knowledge base in multiple fields for business processing when responding to business processing requests. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the business processing method based on AI testing provided by the above-mentioned embodiment, and will not be elaborated here.

[0073] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned business processing method based on AI testing when executed by a processor.

[0074] The computer program product provided by this application can solve the technical problem that when responding to business processing requests, there is a lack of a massive knowledge base that integrates multiple professional fields to perform business processing, resulting in poor actual application effects. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the business processing method based on AI testing provided in the above embodiment, and will not be repeated here.

[0075] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A business processing method based on AI testing, It is characterized in that The method is applied to an automated testing platform, the automated testing platform includes an AI tool, and the method includes: Receive business processing requests from users; Based on the business processing request, configuration loading is performed through the AI ​​tool to obtain a business knowledge base, and a business task to be executed is generated according to the business knowledge base; The business task to be executed is executed by the AI ​​tool to obtain a business processing result.

2. The method according to claim 1, It is characterized in that The step of performing configuration loading through the AI ​​tool based on the business processing request to obtain a business knowledge base, and generating a business task to be executed according to the business knowledge base includes: Reading the business processing request through the AI ​​tool to obtain the business industry, service content, and the service organization corresponding to the business industry; The preset summary knowledge base is called according to the business industry and service organization to obtain a business knowledge base; Task generation is performed according to the business knowledge base and service content to obtain business tasks to be executed.

3. The method according to claim 2, It is characterized in that The step of generating tasks according to the business knowledge base and service content to obtain business tasks to be executed includes: The service case set is read through the business knowledge base and the service content to obtain a reading result; If the reading result is that the service case set has related service cases, extracting the related service cases to obtain service processes and interface call information; Task generation is performed according to the service process and interface call information to obtain the business tasks to be executed.

4. The method according to claim 3, It is characterized in that After the step of reading the test case through the business knowledge base and the service content to obtain the reading result, the method further includes: If the reading result is that the service case set does not have a relevant service case, information about the missing case is sent to the development end, and the development end performs code development based on the business knowledge base and service content to obtain a development result; Receiving the development result sent by the development end; Generate a test case according to the development result, and test the test case through the AI ​​tool to obtain a test result; When the test result is passed, the test case is output as a service case, and the service case is stored in the service case set.

5. The method according to claim 4, It is characterized in that The step of generating a test case according to the development result, and testing the test case by the AI ​​tool to obtain the test result comprises: Perform test planning according to the development results to obtain a test plan, and query and obtain relevant business interfaces and business scenarios based on the test plan; Customizing and transforming the relevant business interface to obtain a business interface; Generate a business test process according to the business scenario, and output test cases based on the business interface and the business test process; Testing the test case by using the AI ​​tool; When the business test process is completed and the business interface call is normal, the output test result is passed.

6. The method according to claim 4, It is characterized in that After the step of executing the to-be-executed business task by the AI ​​tool to obtain a business processing result, the method further includes: Sending the business processing result and the service case to the development end, and the development end improving the environment configuration and parameters of the service case based on the business processing result to obtain a final service case; The final service case sent by the development end is received, and the service case set and the summary database are updated based on the final service case.

7. A business processing device based on AI testing, It is characterized in that The device is applied to an automated testing platform, the automated testing platform includes an AI tool, and the device includes: A receiving module, used for receiving a user's business processing request; A generation module, configured to load the configuration through the AI ​​tool based on the business processing request, obtain a business knowledge base, and generate a business task to be executed according to the business knowledge base; The processing module is used to execute the business task to be executed through the AI ​​tool to obtain a business processing result.

8. A business processing device, It is characterized in that The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the business processing method based on AI testing as described in any one of claims 1 to 6.

9. A storage medium, It is characterized in that The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the business processing method based on AI testing as described in any one of claims 1 to 6 are implemented.

10. A computer program product, It is characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the business processing method based on AI testing as claimed in any one of claims 1 to 6 are implemented.

Citation Information

Patent Citations

  • Test case construction method and device and electronic equipment

    CN111930623A

  • Automatic testing method, system and equipment based on AI and storage medium

    CN117609062A

  • Aerial document analysis and test case generation system driven by large model agent

    CN117909243A

  • Method for applying knowledge from a skilled worker via a master expert machine to a master / slave expert machine control for repetitive activity

    US6272396B1