Requirements Modeling Aided by ChatGPT: An Experience in Embedded Systems
Kun Ruan, Xiaohong Chen, Zhi Jin
Abstract
Requirements modeling is a crucial tool for requirements analysis and has been demonstrated to aid in the comprehension and analysis of requirements. However, constructing requirements models from natural language descriptions in user requirements documents can be a time-consuming task. With the growing attention given to large language models, they have become an integral component of natural language processing. Consequently, utilizing large language models to facilitate the construction of high-quality requirement models is appealing. This paper presents an automated framework for requirement model generation that incorporates ChatGPT-based zero-shot learning to extract requirement models from requirement texts and subsequently compose them using predefined rules. The framework defines the requirement extraction task of ChatGPT by designing appropriate prompt, and it generates requirement models by employing composition rules. Furthermore, a case study on a digital home system is conducted to validate the feasibility of the framework in assisting requirements modeling.