Information processing systems, information processing methods, and programs

Abstract

To enable support for test automation. [Solution] An information processing system comprising: a scenario generation unit that generates a scenario by giving a first prompt to a large-scale language model instructing it to generate a test scenario based on a test case describing the outline of the test; and a script generation unit that generates a script by giving a second prompt to the large-scale language model instructing it to generate a script that causes a computer to execute the test based on the scenario.

Description

Technical Field

[0001] The present invention relates to an information processing system, an information processing method, and a program.

Background Art

[0002] Patent Document 1 discloses generating test code according to test code generation rules.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in Patent Document 1, a design specification to which the rules are applicable is required.

[0005] The present invention has been made in view of such a background, and an object thereof is to provide a technology capable of assisting in test automation.

Means for Solving the Problems

[0006] The main invention of the present invention for solving the above problems is an information processing system, comprising: a scenario generation unit that gives a first prompt instructing to generate a scenario of the test to a large language model based on a test case describing an outline of the test, and generates the scenario; and a script generation unit that gives a second prompt instructing to generate a script for causing a computer to execute the test to the large language model based on the scenario, and generates the script.

[0007] Regarding other problems disclosed in the present application and methods for solving them, they will be clarified by the embodiments of the invention and the drawings. [Effects of the Invention]

[0008] According to the present invention, it is possible to support the automation of testing. [Brief explanation of the drawing]

[0009] [Figure 1] This figure shows an example of the overall configuration of an information processing system. [Figure 2] This figure shows an example of the hardware configuration of management server 2. [Figure 3] This figure shows an example of the software configuration for management server 2. [Figure 4] This is a diagram showing an example of an inquiry screen. [Figure 5] This diagram illustrates the operation of management server 2. [Figure 6] This is a diagram illustrating the script generation process. [Modes for carrying out the invention]

[0010] <System Overview> The following describes an information processing system according to one embodiment of the present invention. This information processing system supports program testing. In this embodiment, it is assumed that the system supports the testing of a web application. This information processing system uses a machine learning model capable of generating responses to instructions to infer the elements to be tested (hereinafter referred to as "target elements") and the operations on the target elements within the screen data (HTML) output by the web application, and proposes the elements and operations to be tested to the user. In this embodiment, the machine learning model is assumed to be a Large Language Model (LLM). Examples of LLMs include GPT, but the system is not limited to this. Furthermore, the machine learning model may be any machine learning model capable of performing the task of generating responses to instructions (prompts), even if it is not an LLM.

[0011] Figure 1 shows an example of the overall configuration of an information processing system. The information processing system in this embodiment includes a management server 2. The management server 2 is connected to the user terminal 1, the target server 3, and the generation server 4 via a communication network. The communication network is, for example, the internet and is constructed using public telephone networks, mobile phone networks, wireless communication channels, Ethernet (registered trademark), etc.

[0012] User terminal 1 is a computer operated by the user. User terminal 1 can be, for example, a smartphone, a tablet computer, or a personal computer.

[0013] Management Server 2 is a computer that provides support for testing. Management Server 2 may be a general-purpose computer such as a workstation or personal computer, or it may be logically implemented through cloud computing.

[0014] Target Server 3 is a computer that runs the program under test. In this embodiment, Target Server 3 is a server that runs a so-called web application. Target Server 3 may be a general-purpose computer such as a workstation or personal computer, or it may be logically implemented through cloud computing.

[0015] The generation server 4 is a computer that performs processing using LLM. The generation server 4 may be a general-purpose computer such as a workstation or personal computer, or it may be logically implemented by cloud computing. The generation server 4 is equipped with LLM and can, for example, provide an API, receive prompts from external sources, provide the received prompts to LLM to generate answers, and respond with the answers.

[0016] <Management Server> Figure 2 is a diagram showing an example of the hardware configuration of the management server 2. Note that the illustrated configuration is an example, and it may have other configurations. The management server 2 includes a CPU 201, a memory 202, a storage device 203, a communication interface 204, an input device 205, and an output device 206. The storage device 203 stores various types of data and programs, such as a hard disk drive, a solid state drive, or a flash memory. The communication interface 204 is an interface for connecting to a communication network, such as an adapter for connecting to Ethernet (registered trademark), a modem for connecting to a public telephone network, a wireless communication device for performing wireless communication, a USB (Universal Serial Bus) connector or an RS232C connector for serial communication, etc. The input device 205 inputs data, such as a keyboard, a mouse, a touch panel, a button, a microphone, etc. The output device 206 outputs data, such as a display, a printer, a speaker, etc. Note that each functional unit of the management server 2 described later is realized by the CPU 201 reading a program stored in the storage device 203 into the memory 202 and executing it, and each storage unit of the management server 2 is realized as a part of the storage area provided by the memory 202 and the storage device 203.

[0017] Figure 3 is a diagram showing an example of the software configuration of the management server 2. The management server 2 includes a document reception unit 211, a test case generation unit 212, a scenario generation unit 213, a script generation unit 214, an inquiry unit 215, and a script execution unit 216.

[0018] <Functional Unit> The document reception unit 211 receives documents relating to the subject of test (program). The documents may be specifications (product specifications) relating to the subject of test. In this embodiment, it is assumed that the specifications do not include detailed input / output data specifications or screen usage, but these detailed specifications may be included. The documents may include information other than specifications (additional information). For example, the documents may include product specifications for functions other than the subject of test. For example, the documents may include documents relating to programs other than product specifications. For example, the documents may include operating instructions or help documents. For example, the documents may include image information other than that included in the specifications, such as wireframes, image diagrams, and design documents. For example, the documents may include documents relating to laws, regulations, and rules that the program under test or the generated test cases and test scenarios must comply with. For example, the documents may include information written in natural language that the program under test or the test cases and test scenarios must comply with. For example, the documents may include text data and image data relating to the subject of test.

[0019] The test case generation unit 212 generates test cases based on the documents received by the document reception unit 211. A test case defines what is to be tested. For example, a test case can be a description of the test outline. For example, a test case can be the outline (epic) of a use case. For example, a test case may be the outline (epic) of a user story. The test case generation unit 212 can generate test cases by giving the LLM a prompt (test case generation prompt, third prompt) instructing it to generate test cases based on the documents.

[0020] The test case generation prompt can include generating test cases, documents (specification documents and additional information), and additional information described in natural language (such as the granularity of test cases). The prompt can also include conditions required for test cases. From the LLM, a list of test cases indicating what should be tested (an overview) can be obtained. In this embodiment, the test case generation unit 212 can send this test case generation prompt to the generation server 4 and receive the responses (test cases) generated according to the prompt in the generation server 4. The test case generation prompt can also include specifying the characteristics expected of the test cases. For example, instructions such as "covering the main functions" and "including positive and negative cases" can be included.

[0021] An example of a test case generation prompt is shown below.

[0022] Please create test cases for a web application based on the following information. Specification: (Contents of the web application specification) Expected characteristics: · Cover the main functions · Include positive and negative cases · Cover not only functional requirements but also non-functional requirements (performance, security, etc.) · Each test case should clarify the test target, procedure, and expected result. Test case format: · Output in the following format · Title · Description · Preconditions · Procedure · Expected result

[0023] Note that the information to be included in the test case generation prompt is not limited to the examples above. The information included in the prompt can be changed as appropriate depending on the characteristics of the application being tested and the purpose of the test. For example, when generating test cases specifically for security testing, information about the type of vulnerability and attack methods can be included in the prompt.

[0024] The scenario generation unit 213 generates test scenarios based on test cases (documents describing the test outline). The scenarios are assumed to be written in Gherkin notation. The scenario generation unit 213 can generate scenarios by providing the LLM with a prompt (scenario generation prompt, first prompt) instructing it to generate test scenarios based on the test cases.

[0025] The scenario generation prompt can include test cases and documents (specifications and additional information). The scenario generation prompt can also include conditions required for the test scenario. From the LLM, a test scenario written in Gherkin notation can be obtained. In this embodiment, the scenario generation unit 213 sends this scenario generation prompt to the generation server 4, and the generation server 4 can receive the response (scenario) generated in response to the prompt. The scenario generation prompt can also specify the characteristics expected of the test scenario. For example, it can include instructions such as "cover the main user operation flow" and "include exceptional cases."

[0026] A concrete example of a scenario generation prompt is shown below.

[0027] Based on the following information, create a test scenario for your web application. Test case: • Verify that the user can log in. • Verify that users can search for products. • Confirm that users can purchase products. specification: (Contents of the web application specifications) Expected characteristics: • To cover the main operational flows. • Include exceptional cases (such as login failures or product not being found). • Clearly state the expected results for each operation. Scenario format: • Write using Gherkin notation.

[0028] The script generation unit 214 generates a script that causes the computer to execute tests based on a scenario. The script can be, for example, a script executable with Playwright. The script generation unit 214 can generate a script by giving the LLM a prompt (script generation prompt, second prompt) instructing it to generate a script that causes the computer to execute tests based on a scenario.

[0029] The script generation prompt can include screen data of the program under test. In this embodiment, since the program under test is assumed to be a web application provided by the target server 3, the screen data can be, for example, text data written in HTML. Alternatively, in addition to or instead of HTML data, the screen data may include, for example, screenshot information of the screen displayed in a web browser. The script generation prompt may also include instructions to query for the identification of the target element if it is necessary to identify the element to be manipulated when generating the script. The script generation prompt may also include instructions to output if user input is required when generating the script. Furthermore, the script generation prompt may include specifications of the characteristics expected of the test script. For example, instructions such as "Use Playwright" or "Use the page object pattern" can be included. In this embodiment, the script generation unit 214 sends this script generation prompt to the generation server 4, and the generation server 4 can receive the response (script) generated in response to the prompt. If the response from the LLM includes a script (program code), the script generation unit 214 can append that script to the final script.

[0030] A concrete example of a script generation prompt is shown below.

[0031] Based on the following information, please create a test script for your web application using TypeScript. Test scenario: (Test scenario written in Gherkin notation) Screen information: (HTML of the screen being tested) Expected characteristics: • Use Playwright • Use the Page Object Pattern • Use Playwright's expect function for assertions.

[0032] In this embodiment, the test scripts generated are not limited to scripts using Playwright. The script generation unit 214 can generate various types of test scripts depending on the type of application under test, the purpose of the test, and the available test automation frameworks.

[0033] For example, when performing E2E testing on a web application, the script generation unit 214 can generate scripts using frameworks for automating web browser operations, such as Playwright, Selenium, Cypress, and Puppeteer. However, the scripts used to operate the web browser are not limited to these.

[0034] Furthermore, when testing mobile applications, the script generation unit 214 can generate scripts using frameworks for automating applications on mobile devices, such as Appium, Espresso, and XCUITest. However, the scripts for operating mobile applications are not limited to these.

[0035] Furthermore, when testing desktop applications, the script generation unit 214 can generate scripts using frameworks for automating desktop applications, such as WinAppDriver, AppiumDesktop, and AutoIT. Note that scripts for operating desktop applications are not limited to these.

[0036] In addition, the script generation unit 214 of this embodiment is not limited to a single automation framework when generating test scripts. For example, when performing tests that combine a web application and an API, the script generation unit 214 can also generate a script that combines multiple frameworks (e.g., Playwright and Postman) to automate both the web browser and the API.

[0037] The inquiry unit 215 queries the user for information necessary to generate the script. The inquiry unit 215 can query the user for the element to be manipulated in the script if it cannot determine which element to manipulate. The inquiry unit 215 can query the user for input data if it cannot generate input data for an element in the script. The inquiry unit 215 can query the user in response to the response from the LLM. If the response from the LLM to the script generation prompt includes a query for an element, the inquiry unit 215 can query the element to be manipulated. If the response from the LLM to the script generation prompt includes a request for input data, the inquiry unit 215 can prompt the user to input the input data (text data). For example, the inquiry unit 215 can send screen data including an input form to the user terminal 1, allowing the user terminal 1 to specify elements and input data from the input form.

[0038] The inquiry unit 215 can present an inquiry screen to the user when querying them for elements or input data. The inquiry screen displays the screen of the application under test, and allows the user to select specific elements or input data on that screen.

[0039] Figure 4 shows an example of an inquiry screen. The inquiry screen is displayed on user terminal 1. The inquiry screen 600 displays a screenshot 601 of the application being tested. On screenshot 601, the user can select elements they want to manipulate with a script using a mouse or touch panel.

[0040] The inquiry screen 600 also displays an element information field 602 for displaying information about the selected element, an operation type selection field 603 for selecting the type of operation to perform on the element, and a data input field 604 for entering data to be entered into the element. The user can confirm the selected element in the element information field 602, select an operation (click, text input, etc.) for the element in the operation type selection field 603, and enter input data in the data input field 604 as needed.

[0041] The inquiry screen 600 also displays a confirmation button 605 for confirming the selection or input result, and a reset button 606 for redoing the selection or input. By pressing the confirmation button 605, the user can send the selection or input result to the inquiry unit 215. By pressing the reset button 606, the user can clear the contents of the selection or input.

[0042] The inquiry unit 215 can pass element information and input data obtained from the user via the inquiry screen 600 to the script generation unit 214. The script generation unit 214 can then incorporate the obtained information into the script.

[0043] The script execution unit 216 executes the script generated by the script generation unit 214. The script execution unit 216 can output the execution result of the script as a test result.

[0044] <Operation> Figure 5 is a diagram illustrating the operation of the management server 2.

[0045] Management Server 2 receives various documents (materials) related to the test target (S301), and generates test cases by providing the LLM with a test case generation prompt that includes the received materials (S302). Management Server 2 receives the selection of one test case (S303), and generates a scenario by providing the LLM with a scenario generation prompt that includes the selected test case (S304). Management Server 2 generates a script by providing the LLM with a script generation prompt that includes the scenario (S305).

[0046] As described above, the information processing system of this embodiment can generate test cases, scenarios, and scripts simply by providing data related to the test target.

[0047] Figure 6 is a diagram illustrating the script generation process.

[0048] Management Server 2 reads the next block (one processing unit) from the scenario in order from the beginning (S321), and provides the LLM with a script generation prompt containing the read block to obtain a response (S322).

[0049] If the response obtained by the management server 2 is not a script (S323: NO), or if the response is a query for an element (S324: YES), the management server 2 queries the user for the element to be operated on (S325), includes the element specified by the user in the script generation prompt (S326), gives the script generation prompt to the LLM again to obtain the response (S327), and proceeds to step S323.

[0050] If the response obtained by the management server 2 is not a script (S323: NO), and the response is a query requesting input data (S324: NO), the management server 2 queries the user for input data (S328), includes the input data entered by the user in the script generation prompt (S329), proceeds to step S327, gives the script generation prompt to the LLM again to obtain a response, and proceeds to step S323.

[0051] If the response from LLM is a script (S323: YES), the management server 2 adds the submitted script to the final test script (S330). The management server 2 repeats the process from step S321 until all scenarios have been read (S331: NO).

[0052] As described above, the information processing system of this embodiment can generate scripts that automate operations on specific screens from abstract scenarios using LLM.

[0053] Although these embodiments have been described above, they are intended to facilitate understanding of the present invention and are not intended to limit its interpretation. The present invention can be modified and improved without departing from its spirit, and equivalents thereof are also included.

[0054] For example, the processing performed by each functional unit of the management server 2 described above may be executed by any of the functional units. Furthermore, different functional units may be added to perform some of the processing performed by each of the functional units described above. Also, the functional units of the management server 2 may be distributed across multiple computers.

[0055] Furthermore, the information stored in each memory unit of the management server 2 may be stored in any of the memory units. That is, the information stored in the multiple memory units mentioned above may be stored in a single memory unit, or a portion of the information stored in one memory unit may be stored in another memory unit.

[0056] In this embodiment, the application under test is not limited to web applications. The information processing system of this embodiment can support the automation of testing for various types of applications.

[0057] For example, the information processing system of this embodiment can be applied to the automation of testing for mobile applications. In this case, the document reception unit 211 can receive specifications, design documents, etc., for the mobile application. The script generation unit 214 can analyze the screen of the mobile application and identify elements on the screen.

[0058] Furthermore, the information processing system of this embodiment can also be applied to the automation of testing for desktop applications. In this case, the document reception unit 211 can receive specifications, design documents, etc., for the desktop application. The script generation unit 214 can analyze the GUI of the desktop application and identify elements such as windows and buttons.

[0059] Furthermore, the information processing system of this embodiment can also be applied to the automation of testing for various types of software systems, such as embedded systems and IoT devices. In this case, the document reception unit 211 can receive system specifications, design documents, communication protocol definitions, etc. The script generation unit 214 can generate test scripts based on the communication procedure and data format with the system.

[0060] <Example 1> Furthermore, in the above embodiment, the purpose of the test was not particularly limited when generating test cases and scenarios, but it is also possible to generate appropriate test cases and scenarios according to the purpose of the test.

[0061] For example, the test case generation unit 212 can include information indicating the purpose of the test in the test case generation prompt. The purpose of the test can be specified as, for example, regression testing, acceptance testing, integration testing, system testing, performance testing, security testing, etc. The test case generation unit 212 can instruct the LLM to generate test cases that satisfy the specified purpose of the test.

[0062] Similarly, the scenario generation unit 213 can include information indicating the test objective in the scenario generation prompt. The scenario generation unit 213 can instruct the LLM to generate a test scenario that satisfies the specified test objective.

[0063] For example, if the purpose is regression testing, the test case generation unit 212 and the scenario generation unit 213 can instruct the LLM to generate test cases and scenarios that comprehensively test the modified functions while satisfying the specifications of the program before the change.

[0064] Furthermore, when the purpose is acceptance testing, the test case generation unit 212 and the scenario generation unit 213 can instruct the LLM to generate test cases and scenarios that cover the user's main use cases.

[0065] <Modification 2> Furthermore, while the above embodiment assumed a web application as the application under test, it is not limited to this. The application under test may be other types of applications, such as mobile applications or desktop applications.

[0066] When testing a mobile application, screen data can include, for example, screenshots of the application or XML data that makes up the screen. The script generation unit 214 can generate test scripts for the mobile application based on this screen data. The test scripts can be generated to be executable using, for example, a mobile application test framework such as Appium.

[0067] When testing a desktop application, screen data can include, for example, screenshots of the application or property information of screen elements obtained from the OS's UI Automation API. The script generation unit 214 can generate test scripts for desktop applications based on this screen data. The test scripts can be generated to be executable using desktop application test frameworks such as WinAppDriver or PyAutoGUI.

[0068] <Variation 3> Furthermore, while the above embodiment assumed the application's GUI (Graphical User Interface) as the test target, it is not limited to this. The test target may also be the API (Application Programming Interface) provided by the application.

[0069] When an API is to be tested, the document reception unit 211 can receive the API specification. The API specification includes, for example, the names of the methods provided by the API, their arguments, return values, and error codes. The test case generation unit 212 can generate test cases for testing the API based on the API specification. For example, it can generate test cases that cover both normal and abnormal patterns for each method.

[0070] The scenario generation unit 213 can generate test scenarios for testing the API based on the generated test cases. The test scenarios may include, for example, the order in which each test case is executed, the settings for the test data, and the expected results.

[0071] The script generation unit 214 can generate a test script that sends an HTTP request to the API and verifies the response based on the generated test scenario. The test script can be, for example, one that can be executed using an API testing tool such as JMeter or Postman.

[0072] <Modification 4> Furthermore, while the above embodiment described a function for generating test cases, test scenarios, and test scripts using LLM, it is not limited to this. LLM may also be used to analyze the results of test execution.

[0073] For example, the management server 2 may be equipped with a test result analysis unit. The test result analysis unit analyzes the test results obtained as a result of the script execution unit 216 executing the test script. The test results include, for example, execution logs for each test case, detected errors, and performance measurements.

[0074] The test results analysis unit analyzes the test results and, if it detects a problem, can provide the LLM with an analysis prompt instructing it to identify the cause of the problem. The analysis prompt may include, for example, information about the test results or information about the application under test. Based on the provided information, the LLM estimates the cause of the problem and returns the result to the test results analysis unit.

[0075] Furthermore, the test results analysis unit can provide the LLM with analysis prompts instructing it to propose corrective actions for the identified problems. These analysis prompts can include, for example, information about the cause of the problem and information about the application under test. The LLM generates corrective actions based on the provided information and returns the results to the test results analysis unit. The corrective actions can include, for example, changes to the source code or changes to the configuration.

[0076] The test results analysis unit can display the causes of problems identified by the LLM and the suggested corrections on, for example, the screen of user terminal 1. This allows users who have run the tests to efficiently fix application defects by referring to the causes of problems and suggested corrections.

[0077] <Modification 5> Furthermore, while the above embodiment described a function for generating test-related information using LLM, it is not limited to this. LLM may also be used to generate documentation about the application under test.

[0078] For example, the management server 2 may be equipped with a new document generation unit. The document generation unit generates documents such as user manuals and tutorials related to the application under test.

[0079] The documentation generation unit can acquire information such as the specifications of the application under test, GUI screen data, and API specifications. Based on the acquired information, the documentation generation unit can provide the LLM with documentation generation prompts that instruct it to generate user manuals and tutorials. These prompts can include, for example, an overview of the application's functionality, instructions for operating key screens, explanations of input forms, and examples of API usage.

[0080] The LLM generates user manuals and tutorial drafts based on the given information and prompts, and returns the results to the document generation unit. The document generation unit can then make adjustments to the drafts generated by the LLM, such as formatting or adding figures and tables.

[0081] Furthermore, the document generation unit can use LLM to proofread user manuals and tutorial drafts. For example, it can provide LLM with proofreading prompts instructing it to check whether the draft contradicts the specifications. LLM can then compare the draft with the specifications and point out any inconsistencies.

[0082] The document generation unit can display the generated user manuals and tutorials on the screen of user terminal 1, for example, or output them to a file. This allows application developers to create documentation efficiently.

[0083] <Variation 6> Furthermore, while the above embodiment assumed that a script would be generated based on the scenario prior to the execution of the test, the script may also be generated while the test is being executed. In this case, the script generation unit 214 will generate the scripts sequentially from the beginning of the generated test scenario, and the script generation prompt will include, in addition to the scenario description, the screen of the application under test (which can be described in HTML in the case of a web application), and the state information of the page under test corresponding to the scenario description. When a script is generated by LLM, the script execution unit 216 will execute the script step by step and update the state information.

[0084] In this case, the script generation unit 214 may prompt the user each time for the element to be operated on and the operation content (and input data in the case of an input operation). The script generation unit 214 can include the element specified by the user and the operation on that element (and input data in the case of an input operation) in the script generation prompt and have the LLM generate a script.

[0085] <Disclosure Items> Furthermore, this disclosure also includes the following configurations. [Item 1] A scenario generation unit generates a scenario by giving a large-scale language model a first prompt instructing it to generate the test scenario based on a test case that outlines the test, A script generation unit generates the script by giving the large-scale language model a second prompt instructing it to generate a script that causes the computer to perform the test based on the scenario, An information processing system characterized by comprising the following features. [Item 2] The information processing system described in item 1, A document reception unit that receives documents related to the subject of the aforementioned test, A test case generation unit generates the test cases by giving the large-scale language model a third prompt instructing it to generate the test cases based on the aforementioned document, An information processing system characterized by comprising the following features. [Item 3] The information processing system described in item 1, If the script cannot determine the element to be operated on, it shall include a query section that prompts the user for information about the element. An information processing system characterized by the following. [Item 4] The information processing system described in item 1, If the script cannot generate input data for an element, it shall include a query unit that queries the user for the input data. An information processing system characterized by the following. [Item 5] The information processing system described in item 1, It includes a script execution unit that executes the aforementioned script, An information processing system characterized by the following. [Item 6] A step of generating a scenario by giving a large-scale language model a first prompt instructing it to generate the scenario of the test based on a test case that outlines the test, The steps include generating the script by giving the large-scale language model a second prompt instructing it to generate a script that causes the computer to perform the test based on the scenario, An information processing method characterized by a computer executing the following. [Item 7] A step of generating a scenario by giving a large-scale language model a first prompt instructing it to generate the scenario of the test based on a test case that outlines the test, The steps include generating the script by giving the large-scale language model a second prompt instructing it to generate a script that causes the computer to perform the test based on the scenario, A program that causes a computer to execute something. [Explanation of Symbols]

[0086] 1 User terminal 2 Management Server 3. Target Servers 4. Generation Server

Claims

1. A scenario generation unit generates a scenario by giving a first prompt to a large-scale language model instructing it to generate the test scenario based on a test case that describes the test outline, A script generation unit generates the script by giving the large-scale language model a second prompt instructing it to generate a script that causes the computer to execute the test based on the scenario, An information processing system characterized by comprising the following features.

2. The information processing system according to claim 1, A document reception unit that receives documents related to the subject of the aforementioned test, A test case generation unit generates the test cases by giving the large-scale language model a third prompt instructing it to generate the test cases based on the aforementioned document, An information processing system characterized by comprising the following features.

3. The information processing system according to claim 1, If the script cannot determine the element to be operated on, it shall include a query section that prompts the user for information about the element. An information processing system characterized by the following.

4. The information processing system according to claim 1, If the script cannot generate input data for an element, it shall include a query unit that queries the user for the input data. An information processing system characterized by the following.

5. The information processing system according to claim 1, It includes a script execution unit that executes the aforementioned script, An information processing system characterized by the following.

6. A step of generating a scenario by giving a large-scale language model a first prompt instructing it to generate the scenario based on a test case that outlines the test, The steps include generating the script by giving the large-scale language model a second prompt instructing it to generate a script that causes the computer to perform the test based on the scenario, An information processing method characterized by a computer executing the following.

7. A step of generating a scenario by giving a large-scale language model a first prompt instructing it to generate the scenario based on a test case that outlines the test, The steps include generating the script by giving the large-scale language model a second prompt instructing it to generate a script that causes the computer to perform the test based on the scenario, A program that causes a computer to execute something.

Images