{"title":"与生成式人工智能协作,改进需求变更","authors":"Yuan Kong, Nan Zhang, Zhenhua Duan, Bin Yu","doi":"10.1016/j.csi.2025.104013","DOIUrl":null,"url":null,"abstract":"<div><div>Requirements Change (RC) is a critical aspect of the software development process, involving modifications throughout almost the entire software life cycle. Despite its significance, RC remains a highly challenging process due to the complexity of software systems and the inherent uncertainty associated with changes. While Large Language Models (LLMs) have demonstrated promising potential in various fields, particularly in Software Engineering (SE), there is limited research on LLMs for SE specifically addressing real software systems RC. To solve this, we propose an innovative approach, named Satisfy Requirements Change (SRC), which utilizes prompt engineering to improve the RC of actual software systems through human-machine collaboration. Specifically, ChatGPT is prompted to complete the entire RC process, encompassing system modeling, confirmation positioning, program modification, and property verification. Additionally, we conduct a RC application case on a real Java system and demonstrate through case study that our approach is effective in improving RC.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"94 ","pages":"Article 104013"},"PeriodicalIF":4.1000,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Collaboration with Generative AI to improve Requirements Change\",\"authors\":\"Yuan Kong, Nan Zhang, Zhenhua Duan, Bin Yu\",\"doi\":\"10.1016/j.csi.2025.104013\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Requirements Change (RC) is a critical aspect of the software development process, involving modifications throughout almost the entire software life cycle. Despite its significance, RC remains a highly challenging process due to the complexity of software systems and the inherent uncertainty associated with changes. While Large Language Models (LLMs) have demonstrated promising potential in various fields, particularly in Software Engineering (SE), there is limited research on LLMs for SE specifically addressing real software systems RC. To solve this, we propose an innovative approach, named Satisfy Requirements Change (SRC), which utilizes prompt engineering to improve the RC of actual software systems through human-machine collaboration. Specifically, ChatGPT is prompted to complete the entire RC process, encompassing system modeling, confirmation positioning, program modification, and property verification. Additionally, we conduct a RC application case on a real Java system and demonstrate through case study that our approach is effective in improving RC.</div></div>\",\"PeriodicalId\":50635,\"journal\":{\"name\":\"Computer Standards & Interfaces\",\"volume\":\"94 \",\"pages\":\"Article 104013\"},\"PeriodicalIF\":4.1000,\"publicationDate\":\"2025-04-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computer Standards & Interfaces\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S092054892500042X\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Standards & Interfaces","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S092054892500042X","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE","Score":null,"Total":0}
Collaboration with Generative AI to improve Requirements Change
Requirements Change (RC) is a critical aspect of the software development process, involving modifications throughout almost the entire software life cycle. Despite its significance, RC remains a highly challenging process due to the complexity of software systems and the inherent uncertainty associated with changes. While Large Language Models (LLMs) have demonstrated promising potential in various fields, particularly in Software Engineering (SE), there is limited research on LLMs for SE specifically addressing real software systems RC. To solve this, we propose an innovative approach, named Satisfy Requirements Change (SRC), which utilizes prompt engineering to improve the RC of actual software systems through human-machine collaboration. Specifically, ChatGPT is prompted to complete the entire RC process, encompassing system modeling, confirmation positioning, program modification, and property verification. Additionally, we conduct a RC application case on a real Java system and demonstrate through case study that our approach is effective in improving RC.
期刊介绍:
The quality of software, well-defined interfaces (hardware and software), the process of digitalisation, and accepted standards in these fields are essential for building and exploiting complex computing, communication, multimedia and measuring systems. Standards can simplify the design and construction of individual hardware and software components and help to ensure satisfactory interworking.
Computer Standards & Interfaces is an international journal dealing specifically with these topics.
The journal
• Provides information about activities and progress on the definition of computer standards, software quality, interfaces and methods, at national, European and international levels
• Publishes critical comments on standards and standards activities
• Disseminates user''s experiences and case studies in the application and exploitation of established or emerging standards, interfaces and methods
• Offers a forum for discussion on actual projects, standards, interfaces and methods by recognised experts
• Stimulates relevant research by providing a specialised refereed medium.