Test plan information generation method, system, device, storage medium and product

Abstract

The disclosed embodiments disclose a method, system, device, storage medium and product for generating test scheme information. The method comprises: determining at least one task execution tool to be called based on test requirement information, wherein the test requirement information includes functional requirement information corresponding to a function to be tested of a test object, and at least one task execution tool is used to generate at least one scheme sub-information required for testing the function to be tested; sending functional requirement information to at least one task execution tool respectively, so that at least one task execution tool generates scheme sub-information respectively based on the functional requirement information; integrating at least one scheme sub-information to obtain test scheme information for testing the function to be tested, thereby reducing the amount of information that needs to be processed by an intelligent agent and helping to improve the efficiency of generating test schemes.

Description

Technical Field

[0001] The present disclosure relates to software testing technology, and in particular to a method, system, device, storage medium and product for generating test scheme information. Background Art

[0002] During the software development test delivery process, the test plan needs to be determined according to the requirements to test the software system. The test plan is used to indicate the information to be used for the test and how to perform the test. For example, it includes confirmation of test key points, test plan, test data, test environment, test cases and other plan information.

[0003] In the related technology, an agent can be used to execute the process of generating test plan information. When the agent automatically generates the test plan information, the requirement document can be analyzed, and the test plan information can be generated based on the analysis results of the requirement document. However, since the test plan information may include information from multiple stages, the agent needs to perform multiple rounds of analysis and thinking, which is time-consuming. In addition, during the multiple rounds of thinking, there is easily interference from invalid information, and the generated test plan is less effective. Summary of the invention

[0004] The embodiments of the present disclosure provide a method, system, device, storage medium and product for generating test scheme information to solve the above technical problems to a certain extent.

[0005] In one aspect of an embodiment of the present disclosure, a method for generating test scheme information is provided, the method being used for an intelligent agent, the method comprising:

[0006] Determine at least one task execution tool to be called based on the test requirement information, wherein the test requirement information includes functional requirement information corresponding to the function to be tested of the test object, and the at least one task execution tool is used to generate at least one solution sub-information required to test the function to be tested;

[0007] sending the functional requirement information to the at least one task execution tool respectively, so that the at least one task execution tool generates the solution sub-information respectively based on the functional requirement information;

[0008] The at least one solution sub-information is integrated to obtain test solution information for testing the function to be tested.

[0009] In an exemplary embodiment, the task execution tool is used to store the generated solution sub-information in a database;

[0010] The step of integrating the at least one solution sub-information to obtain test solution information for testing the function to be tested includes:

[0011] receiving at least one task execution result returned by the at least one task execution tool, wherein the task execution result is used to indicate whether the task execution tool successfully generates the solution sub-information;

[0012] In response to the task execution result indicating that the task execution tool successfully generates the solution sub-information, acquiring the solution sub-information generated by the corresponding task execution tool from the database;

[0013] The acquired solution sub-information is integrated to obtain the test solution information.

[0014] In an exemplary embodiment, the method further comprises:

[0015] In response to the task execution result indicating that the solution sub-information generated by the task execution tool is abnormal, task abnormality information is output, where the task abnormality information is used to indicate that there is an abnormality in the task of generating the solution sub-information executed by the task execution tool.

[0016] In an exemplary embodiment, the step of integrating the at least one solution sub-information to obtain test solution information for testing the function to be tested includes:

[0017] Send the at least one task execution result to the information integration tool, so that the information integration tool responds to the task execution result indicating that the task execution tool successfully generates the solution sub-information, obtains the solution sub-information generated by the corresponding task execution tool from the database, and integrates the obtained solution sub-information to obtain the test solution information.

[0018] In an exemplary embodiment, the test requirement information includes demand information for test solution information;

[0019] The step of determining at least one task execution tool to be called based on the test requirement information includes:

[0020] Extracting preset key information from the test requirement information to obtain at least one task target information, wherein the task target information is used to indicate the solution sub-information to be generated, and the preset key information includes the demand information;

[0021] Based on the at least one task target information, determine the at least one task execution tool to be called.

[0022] In an exemplary embodiment, the functional requirement information includes a requirement link;

[0023] The sending the functional requirement information to the at least one task execution tool respectively so that the at least one task execution tool generates the solution sub-information respectively based on the functional requirement information, comprises:

[0024] The requirement link is sent to at least one of the task execution tools respectively, so that the task execution tool obtains the requirement document based on the requirement link, and extracts key information from the requirement document to obtain requirement key information, and generates the solution sub-information based on the requirement key information. The requirement key information is the valid information required to be used by the task execution tool in the process of generating the solution sub-information.

[0025] In an exemplary embodiment, the method further comprises:

[0026] Receiving an input requirement text, wherein the requirement text includes the test requirement information;

[0027] Performing intent recognition on the demand text to obtain an intent recognition result;

[0028] The step of determining at least one task execution tool to be called based on the test requirement information includes:

[0029] In response to the intention recognition result indicating that test plan information needs to be generated, at least one task execution tool that needs to be called is determined based on the test requirement information.

[0030] Another aspect of the present embodiment provides a system for generating test scheme information, the system comprising an agent and at least one task execution tool;

[0031] The agent is used to determine at least one task execution tool to be called based on test requirement information, wherein the test requirement information includes function requirement information corresponding to the function to be tested of the test object; send the function requirement information to the at least one task execution tool respectively; integrate at least one solution sub-information to obtain test solution information for testing the function to be tested;

[0032] The at least one task execution tool is used to generate at least one solution sub-information required for testing the function to be tested based on the function requirement information.

[0033] In an exemplary embodiment, the system further comprises a database;

[0034] The task execution tool is further used to store the generated solution sub-information in the database; send a task execution result to the agent, the task execution result is used to indicate whether the task execution tool successfully generates the solution sub-information;

[0035] The intelligent agent is also used to receive at least one task execution result returned by the at least one task execution tool; in response to the task execution result indicating that the task execution tool successfully generated the solution sub-information, obtain the solution sub-information generated by the corresponding task execution tool from the database; and integrate the obtained solution sub-information to obtain the test solution information.

[0036] In an exemplary embodiment, the system further includes an information integration tool;

[0037] The agent is further configured to send the at least one task execution result returned by the at least one task execution tool to the information integration tool after receiving the at least one task execution result returned by the at least one task execution tool;

[0038] The information integration tool is used to obtain the solution sub-information generated by the corresponding task execution tool from the database in response to the task execution result indicating that the task execution tool successfully generated the solution sub-information, and to integrate the obtained solution sub-information to obtain the test solution information.

[0039] Another aspect of this embodiment provides a device for generating test scheme information, the device being used for an intelligent agent, the device comprising:

[0040] A tool determination module, configured to determine at least one task execution tool to be called based on test requirement information, wherein the test requirement information includes function requirement information corresponding to a function to be tested of the test object, and the at least one task execution tool is configured to generate at least one solution sub-information required to test the function to be tested;

[0041] A requirement sending module, used to send the functional requirement information to the at least one task execution tool respectively, so that the at least one task execution tool generates the solution sub-information respectively based on the functional requirement information;

[0042] The information integration module is used to integrate the at least one solution sub-information to obtain test solution information for testing the function to be tested.

[0043] Another aspect of this embodiment provides an electronic device, including:

[0044] Memory for storing computer programs;

[0045] The processor is used to execute the computer program stored in the memory, and when the computer program is executed, the method for generating test scheme information described in any of the above embodiments is implemented.

[0046] Another aspect of this embodiment provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for generating test scheme information described in any of the above embodiments is implemented.

[0047] Another aspect of this embodiment provides a computer program product, including a computer program, which, when executed by a processor, implements the method for generating test scheme information described in any of the above embodiments.

[0048] In the disclosed embodiment, during the process of the intelligent agent executing the test solution information generation task, the task execution tool to be called is determined using the test requirement information, and the functional requirement information is sent to the task execution tool, so that each task execution tool generates solution sub-information based on the functional requirement information, that is, the intelligent agent can disassemble and issue the test solution information generation task, so that each task execution tool respectively executes the generation task of different solution sub-information, thereby reducing the amount of information that the intelligent agent needs to process, and helping to improve the generation efficiency of the test solution information. In addition, the process of each task execution tool executing the solution sub-information generation task is executed independently, which can avoid the impact of the abnormal generation of some solution sub-information on the execution of other generated tasks, and help to improve the stability of task execution, thereby helping to improve the integrity and accuracy of the test solution information generation.

[0049] The technical solution of the present disclosure is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings, which constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0051] The present disclosure may be more clearly understood from the following detailed description with reference to the accompanying drawings, in which:

[0052] Figure 1 A flowchart of a method for generating test scheme information provided by an exemplary embodiment of the present disclosure;

[0053] Figure 2 A flowchart of an information integration process provided for an exemplary embodiment of the present disclosure;

[0054] Figure 3 A flowchart of a process of determining a task execution tool to be called provided by an exemplary embodiment of the present disclosure;

[0055] Figure 4 A schematic diagram of the architecture of an analysis impact interface of a task execution tool provided by an exemplary embodiment of the present disclosure;

[0056] Figure 5A schematic diagram of the structure of a system for generating test scheme information provided by an exemplary embodiment of the present disclosure;

[0057] Figure 6 A schematic diagram of the structure of a system for generating test scheme information provided by another exemplary embodiment of the present disclosure;

[0058] Figure 7 A schematic diagram of an architecture for automatically generating test solution information provided by an exemplary embodiment of the present disclosure;

[0059] Figure 8 A schematic diagram of the structure of a device for generating test scheme information provided by an exemplary embodiment of the present disclosure;

[0060] Fig. 9 A schematic structural diagram of an electronic device provided by an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0061] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure unless otherwise specifically stated.

[0062] Those skilled in the art can understand that the terms "first" and "second" in the embodiments of the present disclosure are only used to distinguish different steps, devices or modules, etc., and neither represent any specific technical meaning nor indicate the necessary logical order between them.

[0063] It should also be understood that in the embodiments of the present disclosure, “plurality” may refer to two or more than two, and “at least one” may refer to one, two, or more than two.

[0064] It should also be understood that any component, data or structure mentioned in the embodiments of the present disclosure can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0065] In addition, the term "and / or" in the present disclosure is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present disclosure generally indicates that the associated objects before and after are in an "or" relationship.

[0066] It should also be understood that the description of the various embodiments in the present disclosure focuses on the differences between the various embodiments, and the same or similar aspects thereof can be referenced to each other, and for the sake of brevity, they will not be described one by one.

[0067] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0068] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0069] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0070] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0071] The disclosed embodiments can be applied to electronic devices such as terminal devices, computer systems, servers, etc., which can operate with many other general or special computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, servers, etc. include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, small computer systems, large computer systems, and distributed cloud computing technology environments including any of the above systems, etc.

[0072] Electronic devices such as terminal devices, computer systems, servers, etc. can be described in the general context of computer system executable instructions (such as program modules) executed by computer systems. Generally, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in a distributed cloud computing environment, where tasks are performed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media including storage devices.

[0073] In the related technology, an intelligent agent based on a large language model (LLM) (also called a large model) is used to perform the test plan information generation task. During this process, the intelligent agent needs to perform multiple rounds of analysis on the requirement document to determine the requirement information required to generate different solution sub-information. The processing time is relatively long, and if there is an abnormality in the process of generating a solution sub-information, the intelligent agent will regard it as a failure to execute the test plan generation task, causing the task execution to be interrupted and other solution sub-information to be unable to be generated normally, affecting the stability of task execution.

[0074] In the disclosed embodiment, a method for generating test scheme information is provided, in which an intelligent agent performs the disassembly and distribution of the test scheme generation task, so that each task execution tool can perform information analysis on its own, obtain the required information, and reduce the amount of information processing by the intelligent agent. In addition, the task execution process of each task execution tool is separated, and the generation task of the test scheme sub-information can be independently executed respectively. The intelligent agent integrates the test scheme sub-information generated by each task execution tool, which can avoid the influence of the abnormality of one scheme sub-information generation task on other scheme sub-information generation tasks, and improve the stability of task operation. The specific implementation method can refer to the following embodiment.

[0075] like Figure 1 As shown, it shows a flow chart of a method for generating test scheme information provided by an exemplary embodiment of the present disclosure. The method provided by the embodiment of the present disclosure can be used in an electronic device. In one example, it can be used in an intelligent agent running in an electronic device, such as Figure 1 As shown, the following steps 101-103 are included:

[0076] Step 101: Determine at least one task execution tool to be called based on test requirement information.

[0077] Optionally, the test requirement information includes generating functional requirement information corresponding to the function to be tested of the test object. The function to be tested of the test object includes at least one function possessed by the test object, and the functional requirement information includes requirements that the function to be tested needs to meet. Illustratively, the test object may be software, the function to be tested is a software interface interaction function, and the functional requirement information is the requirements that the software interface interaction function needs to meet. In a possible implementation, the functional requirement information may be at least one of a requirement document, a requirement link, and a requirement document fragment, wherein the requirement link is used to link to the web page address corresponding to the requirement document.

[0078] Test solution information (also called test strategy information) refers to the solution information required to be used in the process of testing whether the function to be tested meets the functional requirements. The test solution information may include all the information required to complete the test, or it may be partial solution information required for some test links, such as determining the test solution environment, executing the test solution link, and other different test links. The test solution information may be composed of at least one solution sub-information. Schematically, the test solution information may include at least one of the solution sub-information such as the impact interface information, test case, test environment information, and test data information.

[0079] In a possible implementation, the test requirement information may be information input by a user. When the user has a requirement for automatically generating test solution information, the test requirement information may be input into the intelligent agent. The intelligent agent responds to receiving the test requirement information and determines at least one task execution tool to be called according to the test requirement information. Different task execution tools are used to generate different solution sub-information required to test the function to be tested. Illustratively, the task execution tools may include tools for automatically analyzing impact interfaces, tools for automatically generating test cases, tools for automatically determining test environment information, and tools for automatically determining test data information.

[0080] Step 102 : sending the functional requirement information to at least one task execution tool respectively, so that at least one task execution tool generates solution sub-information based on the functional requirement information respectively.

[0081] After the agent determines the task execution tool to be called, it will call each task execution tool to start executing the test solution information generation task. In this process, the functional requirement information included in the test requirement information is sent to each task execution tool. After receiving the functional requirement information, the task execution tool starts to execute the solution sub-information generation task, that is, to generate the corresponding solution sub-information based on the functional requirement information. In one example, different task execution tools are used to generate different solution sub-information.

[0082] In one example, after receiving the functional requirement information, the task execution tool performs information analysis on the functional requirement information, extracts the required requirement information from the functional requirement information, and generates corresponding solution sub-information based on the extracted information. The requirement information that different task execution tools need to extract depends on the information target to be generated. When generating different information targets (i.e., different solution sub-information), the required requirement information is also different.

[0083] Step 103: integrate at least one solution sub-information to obtain test solution information for testing the function to be tested.

[0084] In one possible implementation, the intelligent agent can obtain at least one solution sub-information generated by at least one task execution tool, perform information integration on the at least one solution sub-information, and obtain test solution information. Different solution sub-information belongs to different modules of the test solution information. The information integration is used to integrate different solution sub-information into standardized test solution information, such as integrating into a test solution document that meets preset specification requirements.

[0085] The intelligent agent can asynchronously obtain the solution sub-information generated by each task execution tool. The process of each task execution tool executing the task is independent, avoiding the impact of the abnormality of one task execution tool on the execution of tasks by other task execution tools, which helps to improve the stability of the overall task execution.

[0086] In the disclosed embodiment, during the process of the intelligent agent executing the test solution information generation task, the task execution tool to be called is determined using the test requirement information, and the functional requirement information is sent to the task execution tool, so that each task execution tool generates solution sub-information based on the functional requirement information, that is, the intelligent agent can disassemble and issue the test solution information generation task, so that each task execution tool respectively executes the generation task of different solution sub-information, thereby reducing the amount of information that the intelligent agent needs to process, and helping to improve the generation efficiency of the test solution information. In addition, the process of each task execution tool executing the solution sub-information generation task is executed independently, which can avoid the impact of the abnormal generation of some solution sub-information on the execution of other generated tasks, and help to improve the stability of task execution, thereby helping to improve the integrity and accuracy of the test solution information generation.

[0087] In one possible implementation, after the task execution tool executes the task of generating solution sub-information, the execution result is output in dual streams, and the task execution result used to characterize whether the execution is successful is fed back to the intelligent agent, and the generated solution sub-information is stored in a database. The intelligent agent obtains the corresponding solution sub-information from the database for information integration based on the task execution results fed back by each task execution tool.

[0088] That is, the task execution tool is used to return the task execution result to the agent after generating the solution sub-information, and store the solution sub-information in the database. Figure 2 As shown, the process of integrating the solution sub-information generated by each task execution tool to obtain the test solution information includes steps 201-203:

[0089] Step 201: Receive at least one task execution result returned by at least one task execution tool.

[0090] The task execution result is used to indicate whether the task execution tool successfully generates the solution sub-information. In a possible implementation, after the task execution tool executes the solution sub-information generation task, it sends the task execution result to the agent. Optionally, the task execution result includes task execution completion or task execution exception. Task execution completion is used to indicate that the solution sub-information is successfully generated, and task execution exception is used to indicate that there is an exception in the generation of the solution sub-information.

[0091] The agent can receive the task execution results returned by each task execution tool. In this process, each task execution tool directly returns the task execution results, and the agent does not need to analyze the solution sub-information output by each task execution tool. This allows the agent to obtain task execution exception information in a timely manner and provide timely feedback to the user, so that the user can handle it in a timely manner.

[0092] Step 202 , in response to the task execution result indicating that the task execution tool successfully generates solution sub-information, the solution sub-information generated by the corresponding task execution tool is obtained from a database.

[0093] In a possible implementation, the agent may integrate the successfully generated solution sub-information. In response to the task execution result indicating that the corresponding task execution tool successfully generates the solution sub-information, that is, the task execution result returned by the task execution tool is that the task execution is completed, the agent may obtain the solution sub-information generated by the task execution tool from the database.

[0094] In a possible implementation, the task execution tool stores valid solution sub-information in a database, wherein the valid solution sub-information may be successfully generated solution sub-information. When the solution sub-information is stored in the database, it may be stored in association with a tool identifier corresponding to the task execution tool. After receiving the result of task execution completion, the agent obtains the tool identifier of the task execution tool, and obtains the solution sub-information generated by the task execution tool from the database based on the tool identifier.

[0095] Step 203: integrate the acquired sub-information of each solution to obtain test solution information.

[0096] In a possible implementation, after receiving the task execution results returned by each task execution tool and acquiring corresponding solution sub-information from a database based on the task execution results, information integration is performed on each acquired solution sub-information to obtain structurally standardized test solution information.

[0097] In one example, the process of information integration includes structural standardization processing, and structural standardization refers to processing the display structure of the solution sub-information so that it meets the pre-set display structure requirements. Optionally, the structural standardization processing includes at least one of format standardization processing and interactive standardization processing. During the format standardization processing, the display format of each solution sub-information is processed, such as the format of the title, paragraph, text, etc. Interactive standardization processing refers to interactive processing of each solution sub-information, so that the user can perform interactive operations on the displayed solution sub-information, such as editing operations, adding operations, deleting operations, etc.

[0098] After the structural standardization processing is performed on each solution sub-information, the processed standard solution sub-information is combined to obtain the test solution information.

[0099] In a possible implementation, the intelligent agent obtains solution sub-information from a database based on the task execution result, and integrates the solution sub-information to obtain test solution information.

[0100] In another possible implementation, an information integration tool is provided, and the information integration tool integrates the solution sub-information. Specifically, the agent sends at least one task execution result to the information integration tool, so that the information integration tool obtains the solution sub-information generated by the corresponding task execution tool from the database in response to the task execution result indicating that the task execution tool successfully generates the solution sub-information, and integrates the obtained solution sub-information to obtain the test solution information.

[0101] After receiving the task execution results returned by each task execution tool, the agent sends the task execution results of each task execution tool to the information integration tool, and the information integration tool dynamically determines the solution sub-information to be obtained from the database based on each task execution result. In a possible implementation, when the task execution result returned by the task execution tool is that the task execution is completed, the information integration tool obtains the solution sub-information stored by the task execution tool from the database based on the tool identifier of the task execution tool.

[0102] In the disclosed embodiment, the task execution tool stores the generated solution sub-information in a database and returns the task execution results to the intelligent agent, which can reduce the amount of data transmitted to the intelligent agent and help reduce the amount of occupied tokens, thereby avoiding the impact of token excess on the output test solution information caused by the task execution tool output content being truncated.

[0103] In addition, returning the task execution results to the agent can reduce the agent's reasoning and analysis process, eliminate the need for the agent to analyze the validity of the solution sub-information, reduce the agent's task processing time, and help improve the efficiency of test solution generation.

[0104] In the above embodiment, when the task execution result indicates that the task execution tool successfully generates the solution sub-information, the corresponding solution sub-information can be obtained from the database. In a possible implementation, the task execution result may also include a task execution abnormality result. When the task execution abnormality result is received, abnormal information can be output to prompt the user. In response to the task execution result indicating that the task execution tool generates the solution sub-information abnormally, task abnormality information is output. The task abnormality information is used to indicate that there is an abnormality in the task execution tool executing the solution sub-information generation task. Optionally, the task abnormality information includes the tool identifier of the abnormal task execution tool, so that the user can intuitively know the abnormal tool and task.

[0105] In one possible implementation, the task execution tool may store abnormal content information in a database after a task execution exception occurs. After the intelligent agent receives the result of the task execution exception, it obtains the abnormal content information from the database based on the tool identifier of the task execution tool, and outputs the task exception information based on the abnormal content information. That is, the output task exception information may include the abnormal content information, so that the user can quickly analyze the cause of the task execution exception based on the abnormal content information.

[0106] In the disclosed embodiment, the agent determines at least one task execution tool to be called based on the test requirement information. In a possible implementation, the test requirement information includes information on the request for the test solution information, wherein the request for the test solution information is used to indicate the specific information request for generating the test solution information, such as the need to know the impact interface, the need to generate test cases, the need to obtain test environment data, etc. The agent can determine the task execution tool to be called based on the request information for the test solution information. Figure 3 As shown, the process of determining the task execution tool includes steps 301-302:

[0107] Step 301: extract preset key information from the test requirement information to obtain at least one task target information.

[0108] The task target information is used to indicate the solution sub-information that needs to be generated.

[0109] Optionally, the preset key information includes the demand information for the test scheme information. In a possible implementation, the demand information in the test requirement information can be extracted. The task target information can be the specific information target to be generated, such as a "test case".

[0110] In one possible implementation, the test requirement information includes functional requirement information and information on the request for test plan information. Exemplarily, the test requirement information input by the user includes a requirement link corresponding to the requirement document, and an indication of specific information to be obtained, such as "https: / / xxx.xxx.xxx, test cases to be obtained". By extracting preset key information, the information "test cases to be obtained" can be extracted, and the task target information is determined to be "test cases".

[0111] Step 302: Determine at least one task execution tool to be called based on at least one task target information.

[0112] After extracting the task target information, it is determined that the task execution tool to be called is a task execution tool that can output the task target information. Combined with the above example, it is determined that the task execution tool to be called is a tool for automatically generating test cases.

[0113] In a possible implementation, when multiple task target information is extracted, the corresponding task execution tool can be determined based on each task target information. Exemplarily, when the task target information includes "test case" and "test environment", the task execution tool to be called includes a tool that can automatically generate test cases and a tool that automatically generates a test environment.

[0114] In another possible case, the test requirement information does not include the information on the requirements for the test solution information, and the task execution tool to be called can be determined based on the default output settings. In one example, the default output settings indicate the test solution information included in the generation of a complete test solution, and it can be determined that the task execution tool to be called includes various tools for generating different solution sub-information in the complete test solution. Schematically, the test solution information included in the complete test solution includes: impact interface, test case, test environment information, test data information, risk assessment information, business tool recommendation information, etc.

[0115] In a possible implementation, the functional requirement information includes a requirement link, and the requirement link is sent to at least one task execution tool respectively, so that the task execution tool obtains a requirement document based on the requirement link, and extracts key information from the requirement document to obtain requirement key information, and generates solution sub-information based on the requirement key information. The requirement key information is valid information required to be used by the task execution tool in the process of generating solution sub-information.

[0116] The requirement link is a web address link corresponding to the requirement document. After sending the requirement link to the task execution tool, the task execution tool obtains the requirement document according to the requirement link. In combination with the above embodiment, the test requirement information includes the requirement link and the demand information for the test solution information. The intelligent agent can extract key information from the demand information of the test solution information, obtain the task target information, and then determine the task execution tool, and then send the requirement link to each task execution tool respectively.

[0117] In the disclosed embodiment, the information input into the intelligent agent includes the requirement link and the request information for the test plan information. The intelligent agent can determine the task execution tool to be called according to the input information. Compared with the method of inputting the requirement document, the information input into the intelligent agent can be reduced, the token occupation can be reduced, the analysis time of the intelligent agent can be reduced, and the token limit can be avoided. The impact of incomplete input information on the output plan information can be avoided, which helps to improve the efficiency of generating the test plan information, and helps to improve the completeness and accuracy of the generated test plan information.

[0118] In a possible implementation, the task execution tool includes a pre-trained neural network model for automatically generating test solution information. Optionally, the task execution tool may include an LLM model (i.e., a large language model) for automatically generating test solution sub-information. The LLM model may be a pre-trained model for automatically generating solution sub-information. In one example, the LLM model may be trained using sample data to obtain a model for automatically generating solution sub-information, wherein each training sample in the sample data includes a sample requirement document and sample solution sub-information. For example, when training an LLM model for analyzing an impact interface, the training sample includes a sample requirement document and a sample impact interface. The LLM model is trained using sample data containing multiple training samples so that the LLM model can automatically analyze the impact interface based on the input requirement document.

[0119] In a possible implementation, after the task execution tool obtains the requirement document, it can extract key information from the requirement document to obtain the requirement key information, and input the requirement key information into the LLM model to generate solution sub-information. In a possible implementation, the solution sub-information output by the LLM model can also be modified by using the Retrieval Augmented Generation (RAG) technology in combination with the knowledge base to obtain the final solution sub-information.

[0120] The key information of requirements extracted by the task execution tools that generate different solution sub-information is different. Schematically, when analyzing the impact interface, the key information of requirements extracted includes service environment address information, code git information, basic information of related projects, and requirement function information; when generating test cases, the key information of requirements extracted includes requirement function information; when generating test environment data, the key information of requirements extracted includes service environment address information, code git information, etc.

[0121] In combination with the above example, when analyzing the impact interface, the extracted key requirement information can be input into the corresponding first LLM model. The first LLM model is a model for analyzing the impact interface obtained by training based on a training sample including sample key requirement information and sample impact interface. The first LLM model analyzes the impact interface based on the input key requirement information, and then combines all the interface information of the project stored in the knowledge base to compare the analyzed impact interface with all the real interfaces included in the project to obtain the real impact interface. That is, the impact interface output by the first LLM model is corrected in combination with the knowledge base to improve the accuracy of the output result.

[0122] When generating test cases, the extracted key requirement information can be input into the corresponding second LLM model. The second LLM model is a model for generating test cases that is pre-trained based on training samples including sample key requirement information and sample test cases. The second LLM model automatically generates test cases based on the input key requirement information, and then combines the relevant historical test cases stored in the knowledge base to correct the test cases output by the second LLM model to improve the accuracy of generated test cases.

[0123] When obtaining the test environment information, the extracted key requirement information can be input into the corresponding third LLM model. The third LLM model is a model for obtaining test environment information obtained by training based on a training sample including sample key requirement information and sample environment information. The third LLM model automatically generates test environment information based on the input key requirement information, and then combines the test environment information used by the projects and codes stored in the knowledge base to correct the test environment information output by the third LLM model to improve the accuracy of the generated environment information.

[0124] In one example, if Figure 4 As shown, it shows a schematic diagram of the architecture of the task execution tool analysis impact interface provided by an exemplary embodiment of the present disclosure. After the task execution tool for automatically analyzing the impact interface obtains the requirement document, it extracts key information to obtain the requirement key information related to the analysis impact interface, wherein the requirement key information includes service environment address information, code git information, basic information of related projects, and requirement function information, and then performs structured prompt design on the extracted requirement key information to obtain the input text. Through the structured prompt design, the information input to the first LLM model includes the necessary information required for the model to execute the task. Specifically, through the structured prompt design, the input information input to the first LLM model includes at least one of the target to be processed by the first LLM model, the optional processing method of the first LLM model, the requirement of the output result of the first LLM model, and the auxiliary information (for example, the definition of special nouns) that assists the first LLM model in identifying the requirement key information, so that the first LLM model can more accurately understand and analyze the input text and output the processing results that are more in line with user requirements, for example, output the standardized impact interface.

[0125] The input text designed with a structured prompt is input into the first LLM model, and the first LLM model performs an interface analysis task to obtain an impact interface. All interface information is stored in the knowledge base. The RAG technology can be used to query all real interfaces corresponding to the project in the knowledge base, and the impact interface output by the first LLM model can be compared with the real interface obtained by the query to determine the real interface affected. During the comparison process, the output result of the first LLM model can be processed into javascript object notation (json) structure information to obtain an interface described in natural language. Based on the json structure information, all real interfaces corresponding to the project are queried in the knowledge base to correct the impact interface output by the LLM model.

[0126] In a possible implementation, after the user inputs the requirement text, the agent first performs intent recognition on the input requirement text, and after recognizing the intent to generate test solution information, determines at least one task execution tool to be called based on the test requirement information. The process may include the following steps 401-403:

[0127] Step 401: receiving an input requirement text, wherein the requirement text includes test requirement information.

[0128] Step 402: perform intent recognition on the demand text to obtain an intent recognition result.

[0129] In a possible implementation, the fourth LLM model can be used to identify the intent of the requirement text. The fourth LLM model used for intent identification is a model pre-trained based on a training sample including a sample input text and a sample intent label, and can be used to identify whether the input text indicates the existence of a test solution information generation requirement. Furthermore, the fourth LLM model can be combined with prompt and few-shot to assist in intent identification.

[0130] In a possible implementation, by designing a prompt for the input text, the fourth LLM model can more accurately identify the user's intention. In one example, the input text after prompt design may include at least one of the LLM model's intention recognition target key points, the intention recognition execution method, and prompt information for assisting in identifying the text's intention (such as the meaning of a specific noun in the text). The intention recognition target key points can be used to indicate the key points that the LLM model needs to pay attention to when performing intent recognition on the user's input text, and the intention recognition execution method can indicate the execution steps of the LLM model for intent recognition.

[0131] In another possible implementation, a few-shot technology can also be used to assist the fourth LLM model in intent recognition, and a small number of intent recognition examples can be provided to the fourth LLM model through the few-shot technology, so that the fourth LLM model can more accurately recognize the user's intent in combination with the examples. Among them, an intent recognition example may include user input text and intent recognition results. Schematically, an intent recognition example may include: "Input text: https: / / xxx.xxx.xxx, generate test cases; user intent: test plan information needs to be generated." By providing intent recognition examples for reference by the fourth LLM model, the fourth LLM model can more accurately recognize the user's intent.

[0132] Step 403 , in response to the intention recognition result indicating that test solution information needs to be generated, at least one task execution tool to be called is determined based on the test requirement information.

[0133] When the intent recognition result indicates that test plan information needs to be generated, the intelligent agent then analyzes the test requirement information included in the requirement text to determine the task execution tool to be called.

[0134] In this embodiment, the intelligent agent performs intent recognition on the input text, and then extracts key information when the intent to generate test plan information is identified. Based on the extracted task objective information, the task execution tool to be called is determined. There is no need to analyze the large amount of information included in the original requirement document, which helps to improve the efficiency of generating test plan information.

[0135] like Figure 5 As shown, it shows a schematic diagram of the structure of a system for generating test scheme information provided by an exemplary embodiment of the present disclosure, the system comprising an intelligent agent 51 and at least one task execution tool 52.

[0136] Intelligent agent 51 is used to determine at least one task execution tool to be called based on test requirement information, where the test requirement information includes functional requirement information corresponding to the function to be tested of the test object; send the functional requirement information to at least one task execution tool respectively; integrate at least one solution sub-information to obtain test solution information for testing the function to be tested.

[0137] The task execution tool 52 is used to generate solution sub-information required for testing the function to be tested based on the function requirement information.

[0138] After the agent 51 sends the function requirement information to at least one task execution tool 52, the at least one task execution tool can generate at least one solution sub-information required for testing the function to be tested based on the function requirement information. In a possible implementation, each task execution tool generates different solution sub-information, and then the agent 51 can integrate the at least one solution sub-information to obtain the test solution information for testing the function to be tested.

[0139] In a possible implementation, Figure 6 As shown, the system for generating test scheme information further includes a database 53 .

[0140] The task execution tool 52 is also used to store the generated solution sub-information in a database; and send the task execution result to the intelligent agent, where the task execution result is used to indicate whether the task execution tool has successfully generated the solution sub-information.

[0141] In a possible implementation, the task execution tool may execute in parallel the processes of storing solution sub-information in a database and sending task execution results to the agent.

[0142] Intelligent agent 51 is also used to receive at least one task execution result returned by at least one task execution tool; in response to the task execution result indicating that the task execution tool successfully generates solution sub-information, obtain the solution sub-information generated by the corresponding task execution tool from the database; integrate the obtained solution sub-information to obtain test solution information.

[0143] The intelligent agent 51 is also used to output task abnormality information in response to the task execution result indicating that the task execution tool generates the plan sub-information abnormally, and the task abnormality information is used to indicate that there is an abnormality in the task execution tool executing the plan sub-information generation task.

[0144] In a possible implementation, Figure 6 As shown, the system also includes an information integration tool 54 .

[0145] The intelligent agent 51 is further used to send at least one task execution result to the information integration tool after receiving at least one task execution result returned by at least one task execution tool.

[0146] The information integration tool 54 is used to obtain the solution sub-information generated by the corresponding task execution tool from the database in response to the task execution result indicating that the task execution tool successfully generates the solution sub-information, and integrate the obtained solution sub-information to obtain the test solution information.

[0147] The system for generating test scheme information in the embodiment of the present disclosure corresponds to the embodiment of the method for generating test scheme information in the present disclosure, and the relevant contents can be referenced to each other, which will not be repeated here. The beneficial technical effects corresponding to the device for generating test scheme information in the embodiment of the present disclosure can refer to the corresponding beneficial technical effects of the corresponding exemplary method part, which will not be repeated here.

[0148] In an exemplary embodiment, Figure 7 As shown, it shows a schematic diagram of the architecture for automatically generating test plan information. In the process of automatically generating test plan information, the user can input the demand text into the intelligent agent based on the LLM model (including the fourth LLM model mentioned above), the demand text includes test demand information, the test demand information includes demand links and appeal information for test plan information, the intelligent agent performs intent recognition on the demand text, and after determining the intention of generating test plan information, performs key information extraction to obtain task target information, and determines the task execution tools to be called according to the task target information, including tool one, tool two and tool three, wherein tool one is a tool for analyzing the impact interface, tool two is a tool for generating test cases, and tool three is a tool for obtaining test environment information and test data information.

[0149] The agent sends the requirement link to tool 1, tool 2 and tool 3 respectively. Tool 1, tool 2 and tool 3 obtain the requirement document based on the requirement link, generate the corresponding solution sub-information based on the requirement document, return the task execution result to the agent, and store the valid solution sub-information in the database. After receiving the task execution result returned by each tool, the agent sends the task execution result to the information integration tool. The information integration tool determines the task execution tool that has successfully generated the solution sub-information based on the received task execution result, obtains the valid test solution sub-information from the database based on the tool identifier of the task execution tool, integrates the test solution sub-information, obtains the test solution information and outputs it.

[0150] In the disclosed embodiment, the agent can disassemble and distribute the test solution information generation task, so that each task execution tool can execute it separately, reducing the amount of information that the agent needs to process. In addition, the task execution tool outputs the execution result in two streams, stores the generated solution sub-information in the database, and returns the task execution result to the agent, which can reduce the amount of data transmitted to the agent and help reduce the amount of occupied tokens, thereby avoiding the impact of the output content of the task execution tool being truncated due to token overlimit on the output test solution information.

[0151] In addition, returning the task execution results to the agent can reduce the agent's reasoning and analysis process, reduce the agent's task processing time, and help improve the efficiency of generating test plan information, compared to outputting the entire test plan information to the agent. In this way, the execution process of each task execution tool can be carried out independently, avoiding the impact of abnormal tools on the normal execution of other tools, and improving the stability of task operation.

[0152] Figure 8 1 is a schematic diagram of a structure of a device for determining test scheme information provided by an exemplary embodiment of the present disclosure. The device can be used for the intelligent agent involved in the above embodiment. The device includes:

[0153] A tool determination module 801 is used to determine at least one task execution tool to be called based on test requirement information, wherein the test requirement information includes function requirement information corresponding to a function to be tested of a test object, and the at least one task execution tool is used to generate at least one solution sub-information required to test the function to be tested;

[0154] The requirement sending module 802 is used to send the functional requirement information to the at least one task execution tool respectively, so that the at least one task execution tool generates the solution sub-information respectively based on the functional requirement information;

[0155] The information integration module 803 is used to integrate the at least one solution sub-information to obtain test solution information for testing the function to be tested.

[0156] In an exemplary embodiment, the task execution tool is used to store the generated solution sub-information in a database;

[0157] The information integration module 803 is also used for:

[0158] receiving at least one task execution result returned by the at least one task execution tool, wherein the task execution result is used to indicate whether the task execution tool successfully generates the solution sub-information;

[0159] In response to the task execution result indicating that the task execution tool successfully generates the solution sub-information, acquiring the solution sub-information generated by the corresponding task execution tool from the database;

[0160] The acquired solution sub-information is integrated to obtain the test solution information.

[0161] In an exemplary embodiment, the apparatus further comprises:

[0162] The information output module is used to output task abnormality information in response to the task execution result indicating that the sub-information of the solution generated by the task execution tool is abnormal, wherein the task abnormality information is used to indicate that there is an abnormality in the task of generating the sub-information of the solution executed by the task execution tool.

[0163] In an exemplary embodiment, the information integration module 803 is further used to:

[0164] Send the at least one task execution result to the information integration tool, so that the information integration tool responds to the task execution result indicating that the task execution tool successfully generates the solution sub-information, obtains the solution sub-information generated by the corresponding task execution tool from the database, and integrates the obtained solution sub-information to obtain the test solution information.

[0165] In an exemplary embodiment, the test requirement information includes demand information for test solution information;

[0166] The tool determination module 801 is further used for:

[0167] Extracting preset key information from the test requirement information to obtain at least one task target information, wherein the task target information is used to indicate the solution sub-information to be generated, and the preset key information includes the demand information;

[0168] Based on the at least one task target information, determine the at least one task execution tool to be called.

[0169] In an exemplary embodiment, the functional requirement information includes a requirement link;

[0170] The demand sending module 802 is further used for:

[0171] The requirement link is sent to at least one of the task execution tools respectively, so that the task execution tool obtains the requirement document based on the requirement link, and extracts key information from the requirement document to obtain requirement key information, and generates the solution sub-information based on the requirement key information. The requirement key information is the valid information required to be used by the task execution tool in the process of generating the solution sub-information.

[0172] In an exemplary embodiment, the apparatus further comprises:

[0173] A text receiving module, used for receiving an input requirement text, wherein the requirement text includes the test requirement information;

[0174] An intention recognition module is used to perform intention recognition on the demand text to obtain an intention recognition result;

[0175] The tool determination module 801 is further used for:

[0176] In response to the intention recognition result indicating that test plan information needs to be generated, at least one task execution tool that needs to be called is determined based on the test requirement information.

[0177] The device for generating test scheme information in the embodiment of the present disclosure corresponds to the embodiment of the method for generating test scheme information in the present disclosure, and the relevant contents can be referred to each other, which will not be repeated here. The beneficial technical effects corresponding to the device for generating test scheme information in the embodiment of the present disclosure can refer to the corresponding beneficial technical effects of the corresponding exemplary method part, which will not be repeated here.

[0178] In addition, an embodiment of the present disclosure further provides an electronic device, including:

[0179] Memory for storing computer programs;

[0180] The processor is used to execute the computer program stored in the memory, and when the computer program is executed, the method for generating test scheme information described in any of the above embodiments of the present disclosure is implemented.

[0181] Fig. 9 This is a schematic diagram of the structure of an application embodiment of the electronic device disclosed in the present invention. Fig. 9 To describe the electronic device according to the embodiment of the present disclosure. Fig. 9 As shown, the electronic device includes one or more processors and memory.

[0182] The processor may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0183] The memory may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor may execute the program instructions to implement the method for generating test scheme information of the various embodiments of the present disclosure described above and / or other desired functions.

[0184] In one example, the electronic device may further include: an input device and an output device, and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0185] In addition, the input device may also include, for example, a keyboard, a mouse, and the like.

[0186] The output device can output various information to the outside, including the determined distance information, direction information, etc. The output device can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0187] Of course, to simplify, Fig. 9 Only some of the components related to the present disclosure in the electronic device are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device may further include any other appropriate components.

[0188] In addition to the above-mentioned methods and devices, an embodiment of the present disclosure may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps in the method for generating test scheme information according to various embodiments of the present disclosure described in the above part of this specification.

[0189] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the disclosed embodiments, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0190] In addition, an embodiment of the present disclosure may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enables the processor to execute the steps in the method for generating test scheme information according to various embodiments of the present disclosure described in the above part of this specification.

[0191] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0192] A person of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, etc., various media that can store program codes.

[0193] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, and are not limitations. The above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.

[0194] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0195] The block diagrams of the devices, apparatuses, equipment, and systems involved in this disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including," "comprising," "having," and the like are open words, referring to "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or," and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0196] The method and apparatus of the present disclosure may be implemented in many ways. For example, the method and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present disclosure may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present disclosure. Therefore, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

[0197] It should also be noted that in the apparatus, device and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0198] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0199] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for generating test scheme information, characterized in that: The method is used for an intelligent agent, and the method comprises: Determine at least one task execution tool to be called based on the test requirement information, wherein the test requirement information includes functional requirement information corresponding to the function to be tested of the test object, and the at least one task execution tool is used to generate at least one solution sub-information required to test the function to be tested; sending the functional requirement information to the at least one task execution tool respectively, so that the at least one task execution tool generates the solution sub-information respectively based on the functional requirement information; The at least one solution sub-information is integrated to obtain test solution information for testing the function to be tested.

2. The method according to claim 1, characterized in that The task execution tool is used to store the generated solution sub-information in a database; The step of integrating the at least one solution sub-information to obtain test solution information for testing the function to be tested includes: receiving at least one task execution result returned by the at least one task execution tool, wherein the task execution result is used to indicate whether the task execution tool successfully generates the solution sub-information; In response to the task execution result indicating that the task execution tool successfully generates the solution sub-information, acquiring the solution sub-information generated by the corresponding task execution tool from the database; The acquired solution sub-information is integrated to obtain the test solution information.

3. The method according to claim 2, characterized in that The method further comprises: In response to the task execution result indicating that the solution sub-information generated by the task execution tool is abnormal, task abnormality information is output, where the task abnormality information is used to indicate that there is an abnormality in the task of generating the solution sub-information executed by the task execution tool.

4. The method according to claim 2, characterized in that: The step of integrating the at least one solution sub-information to obtain test solution information for testing the function to be tested includes: Send the at least one task execution result to the information integration tool, so that the information integration tool responds to the task execution result indicating that the task execution tool successfully generates the solution sub-information, obtains the solution sub-information generated by the corresponding task execution tool from the database, and integrates the obtained solution sub-information to obtain the test solution information.

5. The method according to any one of claims 1 to 4, characterized in that: The test requirement information includes the request information for the test solution information; The step of determining at least one task execution tool to be called based on the test requirement information includes: Extracting preset key information from the test requirement information to obtain at least one task target information, wherein the task target information is used to indicate the solution sub-information to be generated, and the preset key information includes the demand information; Based on the at least one task target information, determine the at least one task execution tool to be called.

6. The method according to any one of claims 1 to 4, characterized in that: The functional requirement information includes a requirement link; The sending the functional requirement information to the at least one task execution tool respectively so that the at least one task execution tool generates the solution sub-information respectively based on the functional requirement information, comprises: The requirement link is sent to at least one of the task execution tools respectively, so that the task execution tool obtains the requirement document based on the requirement link, and extracts key information from the requirement document to obtain requirement key information, and generates the solution sub-information based on the requirement key information. The requirement key information is the valid information required to be used by the task execution tool in the process of generating the solution sub-information.

7. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Receiving an input requirement text, wherein the requirement text includes the test requirement information; Performing intent recognition on the demand text to obtain an intent recognition result; The step of determining at least one task execution tool to be called based on the test requirement information includes: In response to the intention recognition result indicating that test plan information needs to be generated, at least one task execution tool that needs to be called is determined based on the test requirement information.

8. A system for generating test plan information, characterized in that: The system includes an agent and at least one task execution tool; The agent is used to determine at least one task execution tool to be called based on the test requirement information, wherein the test requirement information includes function requirement information corresponding to the function to be tested of the test object; and send the function requirement information to the at least one task execution tool respectively; Integrate at least one solution sub-information to obtain test solution information for testing the function to be tested; The at least one task execution tool is used to generate at least one solution sub-information required for testing the function to be tested based on the function requirement information.

9. The system according to claim 8, characterized in that The system also includes a database; The task execution tool is further used to store the generated solution sub-information in the database; send a task execution result to the agent, the task execution result is used to indicate whether the task execution tool successfully generates the solution sub-information; The intelligent agent is also used to receive at least one task execution result returned by the at least one task execution tool; in response to the task execution result indicating that the task execution tool successfully generated the solution sub-information, obtain the solution sub-information generated by the corresponding task execution tool from the database; and integrate the obtained solution sub-information to obtain the test solution information.

10. The system according to claim 9, characterized in that The system also includes an information integration tool; The agent is further configured to send the at least one task execution result returned by the at least one task execution tool to the information integration tool after receiving the at least one task execution result returned by the at least one task execution tool; The information integration tool is used to obtain the solution sub-information generated by the corresponding task execution tool from the database in response to the task execution result indicating that the task execution tool successfully generated the solution sub-information, and to integrate the obtained solution sub-information to obtain the test solution information.

11. An electronic device, characterized in that: include: Memory for storing computer programs; A processor is used to execute the computer program stored in the memory, and when the computer program is executed, the method for generating test scheme information described in any one of claims 1 to 7 is implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for generating test scheme information described in any one of claims 1 to 7 is implemented.

13. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for generating test scheme information described in any one of claims 1 to 7 is implemented.

Images