JP-2026075496-A - Computer system and method for supporting the generation of deliverables

JP2026075496AJP 2026075496 AJP2026075496 AJP 2026075496AJP-2026075496-A

Abstract

[Problem] To generate source code using generation AI that has common content and reflects changes in the design document. [Solution] The computer system is connected to a task execution program and maintains a database that stores traceability information. Traceability information is data in which the identification information of the input information is associated with the identification information of the deliverable and the task information, and the task information includes prompts. The computer system receives the identification information of the changed input information, refers to the database to search for traceability information that includes the identification information of the input information, generates a new prompt based on the task information contained in the traceability information, obtains a new deliverable by inputting the new prompt to the task execution program, and outputs a new deliverable with the identification information of the deliverable contained in the traceability information attached. [Selection Diagram] Figure 1

Inventors

鈴木康文
川上真澄
呉宇浩

Assignees

株式会社日立製作所

Dates

Publication Date: 20260508
Application Date: 20241022

Claims (5)

A computer system that supports the generation of deliverables in software development, The system comprises a processor, a storage device connected to the processor, and a network interface connected to the processor. It accepts prompts generated based on input information used to generate the aforementioned deliverables as input, and is connected in a communicative manner to a task execution program that performs the task of generating the aforementioned deliverables. Maintain a database that stores traceability information, The traceability information is data in which the identification information of the input information is associated with the identification information of the deliverable generated based on the input information, and task information relating to the task performed to generate the deliverable, The task information includes the prompt, The aforementioned processor, We accept change information, including identification information of the changed input information. Referencing the database, retrieve the traceability information, which includes the identification information of the input information contained in the change information. Based on the task information contained in the retrieved traceability information, a new prompt is generated. By entering the new prompt into the task execution program, a new deliverable is obtained. A computer system characterized by outputting a new deliverable to which identification information of the deliverable included in the retrieved traceability information has been added.
A computer system according to claim 1, The task execution program executes the task using a large-scale language model, The task information includes the type of the large-scale language model and the prompts input to the large-scale language model. The aforementioned processor, The new prompt is entered into the task execution program along with the type of large-scale language model included in the retrieved traceability information. The system generates task information including the type of large-scale language model included in the retrieved traceability information and the new prompt. The traceability information is generated by associating the identification information of the input information included in the change information, the identification information of the deliverable included in the retrieved traceability information, and the task information. A computer system characterized by storing the generated traceability information in the database.
A computer system according to claim 2, The aforementioned processor, The interface for displaying the aforementioned new prompt is presented to the user, If a request to modify the new prompt is received from the user, the modifications will be included in the task information. A computer system characterized in that, if the retrieved traceability information includes the modification, it generates the prompt containing information about the modification.
A computer system according to claim 2, It is connected in a way that allows access to a version control system that manages the change history of the aforementioned input information and the aforementioned deliverables, The traceability information includes the generation of the deliverable, The aforementioned change information is generated by the version control system that receives the changed input information. The aforementioned processor, Access the version control system and obtain the modified input information and the artifact of a newer generation than the artifact included in the retrieved traceability information. A computer system characterized by generating a new prompt that includes a learning instruction for the relationship between the modified input information and the deliverable obtained from the version control system.
A method for supporting the generation of deliverables in software development executed by a computer system, The aforementioned computer system, The system comprises a processor, a storage device connected to the processor, and a network interface connected to the processor. It accepts prompts generated based on input information used to generate the aforementioned deliverables as input, and is connected in a communicative manner to a task execution program that performs the task of generating the aforementioned deliverables. Maintain a database that stores traceability information, The traceability information is data in which the identification information of the input information is associated with the identification information of the deliverable generated based on the input information, and task information relating to the task performed to generate the deliverable, The task information includes the prompt, The method for supporting the generation of the aforementioned deliverables is: The processor receives change information including identification information of the changed input information, The processor performs the steps of referring to the database to retrieve the traceability information, which includes the identification information of the input information included in the change information, The processor generates a new prompt based on the task information contained in the retrieved traceability information. The processor obtains a new artifact by inputting the new prompt to the task execution program, The processor outputs a new deliverable to which identification information of the deliverable included in the retrieved traceability information has been added; A method for supporting the generation of deliverables, characterized by including the following:

Description

This invention relates to a support technology for software development using generative AI. Software development using generative AI is known. For example, the technology described in Patent Document 1 is known. Patent Document 1 describes that "a computer, according to a program, receives a summary prompt indicating an overview of the program code to be generated. The computer then inputs the received summary prompt into a natural language processing model to obtain a detailed prompt indicating detailed specifications of the program code. Finally, the computer inputs the obtained detailed prompt into the natural language processing model to obtain the program code." Patent No. 7564601 This figure shows an example of the system configuration of Example 1.This figure shows an example of the hardware configuration of the computer that constitutes the software development support system of Example 1.This figure shows an example of the data structure of the traceability information DB in Example 1.This is a flowchart illustrating an example of the process performed by the target deliverable identification unit in Example 1.This flowchart illustrates an example of the processing performed by the prompt generation unit in Example 1.This figure shows an example of a screen displayed by the prompt generation unit of Example 1.This is a flowchart illustrating an example of the processing performed by the task execution unit in Example 1.This is a flowchart illustrating an example of the processing performed by the traceability information generation unit in Example 1.This flowchart illustrates an example of the process performed by the prompt generation unit in Example 2. The following describes embodiments of the present invention with reference to the drawings. However, the present invention is not limited to the embodiments described below. Those skilled in the art will readily understand that the specific configuration can be modified without departing from the spirit or intent of the present invention. In the invention described below, identical or similar components or functions are denoted by the same reference numerals, and redundant descriptions are omitted. The designations "First," "Second," "Third," etc., used in this specification are for identifying constituent elements and do not necessarily limit their number or order.