Test case writing method and device based on large model

Abstract

The invention relates to the technical field of test case writing, and discloses a test case writing method and device based on a large model, and the method comprises the steps: obtaining a test requirement document; the test requirement document and a preset association database are input into a test case large model, a corresponding test case is generated, and the association database comprises a relational database and / or a vector database; and inputting the generated test case into a test sequence large model to generate a corresponding test sequence. According to the method, the test case and the test sequence can be automatically compiled, the test efficiency is greatly improved, the labor cost of compiling the test case is reduced, the influence of human factors on the result in the case compiling and sequence building process is reduced, the work quality of compiling the test case is improved, and digital intelligence of the electronic and electrical test front end is realized.

Description

Technical Field

[0001] The present disclosure relates to the technical field of test case writing, and in particular to a test case writing method and device based on a large model. Background Art

[0002] In recent years, the level of automotive intelligence has steadily increased, and cockpit-related functions have rapidly developed. Hardware has evolved from traditional hard buttons to more visual and intelligent central control screens. Functionality has evolved from simple Bluetooth and radio to integrated entertainment, lifestyle, and service functions, including heads-up displays, smart navigation, and audio-visual entertainment. Throughout the entire electronic and electrical development phase, cockpit functions employ an agile, iterative development model, resulting in frequent functional changes. This presents new challenges and opportunities for cockpit electronic and electrical functional testing and verification. The original test case writing approach involved submitting functional specifications, manually writing, reviewing, and releasing test cases for subsequent test execution. This entire process was labor-intensive and limited by the skills of the test case writers. This resulted in uncontrollable test case quality and slow updates and iterations, making it difficult to meet the testing needs of the rapidly evolving automotive cockpit functionality. Summary of the Invention

[0003] The purpose of the present disclosure is to provide a test case writing method and device based on a large model, so as to at least solve the technical problems existing in the prior art that the test case writing process is time-consuming and labor-intensive, the test case quality is uncontrollable, the changes and updates are slow, and it is difficult to meet the testing needs of the rapid development of automobile cockpit functions.

[0004] To solve the above technical problems, the present disclosure provides a test case writing method based on a large model, including:

[0005] Obtain test requirements documents;

[0006] Inputting the test requirement document and a preset associated database into a test case macro model to generate corresponding test cases, wherein the associated database includes a relational database and / or a vector database;

[0007] The generated test cases are input into the test sequence macro model to generate corresponding test sequences.

[0008] In some embodiments, the vector database includes at least one of a vector model, a communication matrix, regulatory documents, and proprietary material.

[0009] In some embodiments, inputting the test requirement document and preset database information into the test case macro model includes:

[0010] The test requirement document and the preset associated database are input into the test case macro model through prompt engineering.

[0011] In some embodiments, inputting the test requirement document and the preset associated database into the test case macro model through prompting engineering includes:

[0012] The test case large model calls the relational database through an API interface;

[0013] Inputting the vector database into the test case macro model in the form of a query;

[0014] The relational database and / or the vector database and the test requirement document are assembled into prompt words.

[0015] In some embodiments, the method further comprises:

[0016] Acquire empirical data generated by test cases to obtain a model fine-tuning dataset, wherein the empirical data includes empirical test requirements and project cases;

[0017] The model fine-tuning dataset is input into the test case large model, and the test case large model is optimized according to the model fine-tuning dataset.

[0018] In some embodiments, after generating the corresponding test case, the method further includes:

[0019] The test cases are presented in a visual interface in the form of test cases one by one.

[0020] In some embodiments, after generating the corresponding test sequence, the method further includes:

[0021] The test sequence is sent to a sequence detection tool so as to calibrate the test sequence through the sequence detection tool, wherein the calibration includes eliminating test sequences that cannot be applied to automated testing.

[0022] In some embodiments, the method further comprises:

[0023] Perform test preparation before test execution, including configuring tool connections and configuring model variable mapping;

[0024] Upload the tool connections and model variable mappings to the project configuration.

[0025] In some embodiments, during test execution, the method further includes:

[0026] identifying a currently idle test environment in the test environment according to the test execution instruction corresponding to the test sequence;

[0027] Invoke a test tool in the current idle test environment to execute a test.

[0028] The present disclosure also provides a test case writing device based on a large model, including:

[0029] An acquisition module is configured to acquire a test requirement document;

[0030] a test case generation module configured to input the test requirement document and a preset associated database into a test case macro model to generate corresponding test cases, wherein the associated database includes a relational database and / or a vector database;

[0031] The test sequence generation module is configured to input the generated test case into the test sequence macro model to generate a corresponding test sequence.

[0032] An embodiment of the present disclosure also provides an electronic device, comprising at least a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned large model-based test case writing method when executing the computer program on the memory.

[0033] The embodiment of the present disclosure also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the above-mentioned large model-based test case writing method is implemented.

[0034] The test case writing method and device based on the big model provided by the embodiment of the present disclosure obtain a test requirement document; input the test requirement document and a preset associated database into the test case big model to generate a corresponding test case; input the generated test case into the test sequence big model to generate a corresponding test sequence. Through the training and application of the AI ​​big model, the automatic writing of test cases and test sequences can be realized, the testing efficiency is greatly improved, the labor cost of test case writing is reduced, the influence of human factors on the results during case writing and sequence construction is reduced, the quality of test case writing work is improved, the front-end of electronic and electrical testing is realized, and the testing needs of the rapid development of automobile cockpit functions are met; at the same time, the test requirement document and the preset associated database are combined and input into the test case big model, which can better assist the big model in automatically writing test cases and improve the accuracy of test case writing. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0036] Figure 1A flowchart of a method for writing test cases based on a large model according to an embodiment of the present disclosure;

[0037] Figure 2 An architectural diagram of a test case writing system based on a large model according to an embodiment of the present disclosure;

[0038] Figure 3 Another flowchart of the test case writing method based on the big model according to an embodiment of the present disclosure;

[0039] Figure 4 A flowchart of test execution of the test platform according to an embodiment of the present disclosure;

[0040] Figure 5 A schematic diagram of the structure of a test case writing device based on a large model according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0041] Various aspects and features of the present disclosure are described herein with reference to the accompanying drawings.

[0042] It should be understood that various modifications may be made to the embodiments disclosed herein. Therefore, the above description should not be considered as limiting, but merely as an example of an embodiment. Other modifications within the scope and spirit of the present disclosure will occur to those skilled in the art.

[0043] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the general description of the present disclosure given above and the detailed description of the embodiments given below, serve to explain the principles of the present disclosure.

[0044] These and other characteristics of the present disclosure will become apparent from the following description of a preferred form of embodiment given as a non-limiting example with reference to the accompanying drawings.

[0045] It should also be understood that although the present disclosure has been described with reference to certain specific examples, those skilled in the art will be able to realize many other equivalent forms of the present disclosure that have the characteristics recited in the claims and are therefore within the scope of protection defined thereby.

[0046] The above and other aspects, features and advantages of the present disclosure will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings.

[0047] Specific embodiments of the present disclosure will be described hereinafter with reference to the accompanying drawings; however, it should be understood that the claimed embodiments are merely examples of the present disclosure, which may be implemented in a variety of ways. Well-known and / or repetitive functions and structures are not described in detail to avoid obscuring the present disclosure with unnecessary or redundant detail. Therefore, the specific structural and functional details claimed herein are not intended to be limiting, but rather serve merely as a basis and representative basis for teaching those skilled in the art to variously employ the present disclosure with substantially any suitable detailed structure.

[0048] This description may use the phrases "in one embodiment," "in another embodiment," "in a further embodiment," or "in other embodiments," each of which may refer to one or more of the same or different embodiments according to the present disclosure.

[0049] Example 1

[0050] Figure 1 and Figure 3 A flowchart of a test case writing method based on a large model according to an embodiment of the present disclosure is shown. Figure 2 FIG1 shows an architecture diagram of a test case writing system based on a large model according to an embodiment of the present disclosure. Figures 1 to 3 As shown, the embodiment of the present disclosure provides a test case writing method based on a large model, including:

[0051] S101: Obtain test requirement document.

[0052] Among them, the test case writing method based on the large model is applied to the back-end server, such as Figure 2 As shown, the front-end page, back-end server and AI big model constitute the test case writing system. After obtaining the test requirement document, the user (such as a test engineer) imports the document into the system through the front-end visual interactive interface (referred to as the front-end interface). The front-end interface sends the test requirement document to the back-end server through a text protocol request.

[0053] like Figure 3 As shown, the back-end server may include a requirement management module, which disassembles the test requirement information in the test requirement document and displays the test requirements in a tree structure mode through the front-end page for easy viewing by test engineers.

[0054] S102: Input the test requirement document and a preset associated database into a test case macro model to generate corresponding test cases, wherein the associated database includes a relational database and / or a vector database.

[0055] After receiving the above-mentioned test requirement document, the back-end server can combine the test requirement document and the preset associated database and input them into the test case big model. The test case big model processes the data to obtain the test case for testing. After the test case big model generates the test case, it will feed back the generated test case to the back-end server.

[0056] The associated database is the key data information that affects the test. In this step, the test requirement document is combined with the associated database and input into the test case model, which can better assist the model in automatically writing test cases.

[0057] Optional, such as Figure 2 As shown, the vector database includes at least one of a vector model, a communication matrix, regulatory documents, and proprietary materials. The vector database stores data in a high-dimensional embedding form of text, images, or other types of data to enable fast similarity searches.

[0058] S103: Input the generated test case into the test sequence macro model to generate a corresponding test sequence.

[0059] After the backend server receives the test case generated by the test case large model, it can input the generated test case into the test sequence large model to generate a test sequence for testing. Figure 3 As shown, the back-end server may include a test case management module. The test cases generated by the test case big model are released to the test case management module. The test case management module gives the test cases to the test sequence big model. The automated test sequences generated by the test sequence big model are saved in the sequence management module in the back-end server.

[0060] The test case writing method based on the big model provided by the embodiment of the present disclosure obtains a test requirement document; inputs the test requirement document and a preset associated database into the test case big model to generate a corresponding test case; inputs the generated test case into the test sequence big model to generate a corresponding test sequence. Through the training and application of the AI ​​big model, the automatic writing of test cases and test sequences can be realized, which greatly improves the testing efficiency, reduces the labor cost of test case writing, reduces the influence of human factors on the results during the case writing and sequence construction process, improves the quality of test case writing work, realizes the digitalization of the electronic and electrical testing front-end, and meets the testing needs of the rapid development of automobile cockpit functions; at the same time, combining the test requirement document and the preset associated database and inputting them into the test case big model can better assist the big model in automatically writing test cases and improve the accuracy of test case writing.

[0061] It is understood that in this embodiment, the test case macromodel and the test sequence macromodel can be the same AI macromodel, capable of both test case writing and test sequence construction; the test case macromodel and the test sequence macromodel can also be different AI macromodels. The test case writing system can be an independent test case writing system or a test platform capable of both test case writing and test case execution.

[0062] In some embodiments, as Figure 2 As shown, in step S102, the test requirement document and the preset database information are input into the test case macro model, including:

[0063] S1021: Input the test requirement document and the preset associated database into the test case macro model through a prompting project.

[0064] By delivering data in the form of prompt engineering, the identifiability of data in the test case large model is ensured.

[0065] In some embodiments, as Figure 2 As shown, in step S1021, the test requirement document and the preset associated database are input into the test case macro model through the prompting project, including:

[0066] S201: The test case model calls the relational database through an API interface;

[0067] S202: Inputting the vector database into the test case macro model in the form of a query;

[0068] S203: Assemble the relational database and / or the vector database and the test requirement document into prompt words.

[0069] The vector database can send data related to the test requirement document to the test case big model through query. The test case big model can combine it with the test requirement document and the relational database to form a prompt to prompt the test case big model with the context of input information and parameter information of the input model.

[0070] In some embodiments, as Figure 2 As shown, the method further includes:

[0071] S301: Acquire empirical data generated by test cases to obtain a model fine-tuning dataset, wherein the empirical data includes empirical test requirements and project cases;

[0072] S302: Input the model fine-tuning dataset into the test case large model, and optimize the test case large model according to the model fine-tuning dataset.

[0073] Experienced test engineers can import empirical test requirements and modified project use case information into the model fine-tuning database to obtain a model fine-tuning dataset. They can then inject test cases that meet the preset test requirements back into the test case master model to fine-tune the test case master model. This allows the test case master model to continuously undergo AI training based on empirical data, resulting in a more accurate and reliable test case master model.

[0074] In some embodiments, after generating the corresponding test case, the method further includes:

[0075] S104: Displaying the test cases one by one through a visual interface.

[0076] like Figure 2 As shown, the back-end server can reversely (compared to the test requirement input) provide the test cases generated by the test case big model to the test engineer for review through the visual interface. Relevant users can modify, rewrite, and correct the test cases online and offline through the visual interface, and can reversely inject the rewritten test cases into the test case big model, so that the test case big model can be trained with the user's rewriting results to obtain a more accurate test case big model.

[0077] In some embodiments, after generating the corresponding test sequence, the method further includes:

[0078] S401: Send the test sequence to a sequence detection tool so as to calibrate the test sequence through the sequence detection tool, wherein the calibration includes eliminating test sequences that cannot be applied to automated testing.

[0079] like Figure 3 As shown, the sequence management module can send the generated test sequence to the sequence detection tool for calibration detection, thereby providing a more accurate test sequence for subsequent test execution.

[0080] In some embodiments, the method further comprises:

[0081] S501: Perform test preparation before test execution, including configuring tool connection and configuring model variable mapping;

[0082] S502: Upload the tool connection and model variable mapping to the project configuration.

[0083] like Figure 4As shown, in this embodiment, the test platform can realize use case writing, test preparation, and test execution. Based on the big model, the test platform can automatically generate test cases, and then automatically generate test sequences based on the generated test cases and improve the test sequences. The improved sequence files can be further input into the big model, realizing a closed-loop process of automatic test case and test sequence generation.

[0084] Before executing a test, perform test preparation, configure tool connections and model variable mappings, and upload these configurations to the project configuration. After the test set is established, test cases can be manually selected, and test case usage can be linked to the test case writing section. After building the test set according to the project configuration, run the test set to execute the test.

[0085] In some embodiments, during test execution, the method further includes:

[0086] S601: Identify a current idle test environment in a test environment according to a test execution instruction corresponding to the test sequence;

[0087] S602: Calling a test tool in the current idle test environment to execute a test.

[0088] like Figure 4 As shown, the test execution module can complete new project creation and automatically generate test plans through a large AI model, with a one-way flow between projects, plans, execution, results, and reports. During test execution, after binding test equipment to the newly created test environment, the bound test equipment can be screened, identifying currently idle test environments and using idle equipment bound to them for test execution. After the test execution instructions are intelligently issued, the test platform can call the test tools to perform test execution and pass the results to the project interface, updating test result information in real time, achieving automated and intelligent testing.

[0089] In summary, in the test case writing method based on the big model provided by the embodiment of the present disclosure, the test case big model can perform model iterative optimization through prompt engineering, knowledge enhancement, adaptive fine-tuning and other technologies to realize automatic and accurate writing of test cases; the written test cases can generate automated test sequences through the test sequence big model, and calibrate and issue them to facilitate subsequent automated test execution, and can achieve efficient and high-quality test case writing and test sequence construction, providing an effective solution for intelligent testing of automotive electronics and electrical systems.

[0090] Example 2

[0091] Figure 5 A schematic diagram of the structure of a test case writing device based on a large model according to an embodiment of the present disclosure is shown. Figure 5 As shown, the embodiment of the present disclosure provides a test case writing device based on a large model, comprising:

[0092] An acquisition module 10 is configured to acquire a test requirement document;

[0093] A test case generation module 20 is configured to input the test requirement document and a preset associated database into a test case macro model to generate corresponding test cases, wherein the associated database includes a relational database and / or a vector database;

[0094] The test sequence generation module 30 is configured to input the generated test cases into the test sequence macro model to generate corresponding test sequences.

[0095] In some embodiments, the test case generation module 20 is further configured to:

[0096] The test requirement document and the preset associated database are input into the test case macro model through prompt engineering.

[0097] In some embodiments, the test case generation module 20 is further configured to:

[0098] The test case large model calls the relational database through an API interface;

[0099] Inputting the vector database into the test case macro model in the form of a query;

[0100] The relational database and / or the vector database and the test requirement document are assembled into prompt words.

[0101] In some embodiments, the test case writing apparatus based on a large model further includes a model optimization module configured to:

[0102] Acquire empirical data generated by test cases to obtain a model fine-tuning dataset, wherein the empirical data includes empirical test requirements and project cases;

[0103] The model fine-tuning dataset is input into the test case large model, and the test case large model is optimized according to the model fine-tuning dataset.

[0104] In some embodiments, the test case generation module 20 is further configured to:

[0105] The test cases are presented in a visual interface in the form of test cases one by one.

[0106] In some embodiments, the test sequence generation module 30 is further configured to:

[0107] The test sequence is sent to a sequence detection tool so as to calibrate the test sequence through the sequence detection tool, wherein the calibration includes eliminating test sequences that cannot be applied to automated testing.

[0108] In some embodiments, the test case writing apparatus based on the large model further includes a test preparation module configured to:

[0109] Perform test preparation before test execution, including configuring tool connections and configuring model variable mapping;

[0110] Upload the tool connections and model variable mappings to the project configuration.

[0111] In some embodiments, the test case writing apparatus based on the large model further includes a test execution module configured to:

[0112] identifying a currently idle test environment in the test environment according to the test execution instruction corresponding to the test sequence;

[0113] Invoke a test tool in the current idle test environment to execute a test.

[0114] The test case writing device based on a big model provided in the embodiment of the present disclosure corresponds to the test case writing method based on a big model in the above-mentioned embodiment. Any optional items in the embodiment of the test case writing method based on a big model are also applicable to the embodiment of the test case writing device based on a big model, and will not be repeated here.

[0115] Example 3

[0116] An embodiment of the present disclosure also provides an electronic device, comprising at least a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned large model-based test case writing method when executing the computer program on the memory.

[0117] In some embodiments, the processor that executes the computer program may be a processing device including one or more general-purpose processing devices, such as a microprocessor, a central processing unit (CPU), a graphics processing unit (GPU), etc. More specifically, the processor may be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a processor that runs other instruction sets, or a processor that runs a combination of instruction sets. The processor may also be one or more special-purpose processing devices, such as an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a digital signal processor (DSP), a system on a chip (SoC), etc.

[0118] The memory may be read-only memory (ROM), random access memory (RAM), phase-change random access memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), electrically erasable programmable read-only memory (EEPROM), other types of random access memory (RAM), flash disks or other forms of flash memory, cache, registers, static memory, compact disk read-only memory (CD-ROM), digital versatile disks (DVD) or other optical storage, magnetic tape cassettes or other magnetic storage devices, or any other possible non-transitory medium used to store information or instructions that can be accessed by a computer device.

[0119] Example 4

[0120] An embodiment of the present disclosure further provides a computer-readable storage medium storing a computer program, which implements the above-mentioned large model-based test case writing method when executed by a processor.

[0121] The computer-readable storage medium of the embodiments of the present disclosure may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any combination thereof. In the embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device, for example, the memory described above.

[0122] The computer programs of the embodiments of the present disclosure may be organized into one or more computer-executable components or modules. Any number and combination of such components or modules may be used to implement various aspects of the present disclosure. For example, various aspects of the present disclosure are not limited to the specific computer-executable instructions or specific components or modules shown in the accompanying drawings and described herein. Other embodiments may include different computer-executable instructions or components with more or less functionality than shown and described herein.

[0123] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

Claims

1. A test case writing method based on a large model, characterized in that: include: Obtain test requirements documents; Inputting the test requirement document and a preset associated database into a test case macro model to generate corresponding test cases, wherein the associated database includes a relational database and / or a vector database; The generated test cases are input into the test sequence macro model to generate corresponding test sequences.

2. The test case writing method based on a large model according to claim 1, characterized in that: The vector database includes at least one of a vector model, a communication matrix, regulatory documents, and proprietary materials.

3. The test case writing method based on a large model according to claim 1, characterized in that: Input the test requirement document and preset database information into the test case macro model, including: The test requirement document and the preset associated database are input into the test case macro model through prompt engineering.

4. The test case writing method based on a large model according to claim 3 is characterized in that: Inputting the test requirement document and the preset associated database into the test case macro model through a prompting project includes: The test case large model calls the relational database through an API interface; Inputting the vector database into the test case macro model in the form of a query; The relational database and / or the vector database and the test requirement document are assembled into prompt words.

5. The test case writing method based on a large model according to claim 1 is characterized in that: The method further comprises: Acquire empirical data generated by test cases to obtain a model fine-tuning dataset, wherein the empirical data includes empirical test requirements and project cases; The model fine-tuning dataset is input into the test case large model, and the test case large model is optimized according to the model fine-tuning dataset.

6. The test case writing method based on a large model according to claim 1, characterized in that: After generating the corresponding test case, the method further includes: The test cases are presented in a visual interface in the form of test cases one by one.

7. The test case writing method based on a large model according to claim 1, characterized in that: After generating the corresponding test sequence, the method further includes: The test sequence is sent to a sequence detection tool so as to calibrate the test sequence through the sequence detection tool, wherein the calibration includes eliminating test sequences that cannot be applied to automated testing.

8. The test case writing method based on a large model according to claim 1 is characterized in that: The method further comprises: Perform test preparation before test execution, including configuring tool connections and configuring model variable mapping; Upload the tool connections and model variable mappings to the project configuration.

9. The test case writing method based on a large model according to claim 1, characterized in that: During test execution, the method further includes: identifying a currently idle test environment in the test environment according to the test execution instruction corresponding to the test sequence; Invoke a test tool in the current idle test environment to execute a test.

10. A test case writing device based on a large model, characterized in that: include: An acquisition module is configured to acquire a test requirement document; a test case generation module configured to input the test requirement document and a preset associated database into a test case macro model to generate corresponding test cases, wherein the associated database includes a relational database and / or a vector database; The test sequence generation module is configured to input the generated test case into the test sequence macro model to generate a corresponding test sequence.

Images