Product-Service Systems (PSS), which integrate products and services into a unified business model, have attracted attention as a means of responding to intensified market competition and increasingly diverse customer needs. In PSS design, capturing customer requirements in the early stages is crucial, and methods such as personas and scenarios have been proposed to support this process. However, these methods often rely heavily on the experience and skills of individual designers, which can reduce the overall productivity of PSS design. This study proposes a method to support designers in extracting customer requirements by leveraging Large Language Models (LLMs), with the aim of improving the productivity of PSS design. An experiment was conducted to validate the effectiveness of the proposed method. The results indicate that the proposed approach enhances the efficiency of the requirement extraction process in PSS design. Specifically, by designing appropriate prompt procedures and content, the required time for requirement extraction was significantly reduced. In addition, the use of LLMs to complement the designer’s knowledge contributed to improving the quality of the extracted requirements.
Yoshida et al. (Wed,) studied this question.