[2A6-GS-10] AI application: Marketing

[2A6-GS-10-03] Interactive fashion styling system using ChatGPT

〇Takumi Irie¹, Kouki Noguchi¹, Tatsuki Kawamoto¹, Taiga Matsui², Naoto Morimoto², Keita Ishikawa², Tomohiro Takagi¹ (1. Meiji University, 2. airCloset, Inc.)

Keywords:Large Language Model, Dialogue, Multimodal, Fashion

In online personal styling, stylists provide fashion styling based on the client’s characteristics, purpose of use, season, and various other factors. Known client's information about styling might not be enough, or it might be interpreted in various ways, and stylists have to infer the client’s essential needs. To solve this matter, we construct interactive fashion styling system using ChatGPT. The objective of our system is to resolve these matters in client's information, obtain the client’s agreement for styling direction, and enable stylists to provide more appropriate styling for clients. We use two ChatGPTs for two types of tasks; one for dialogue management and the other for response generation. In addition, we use Retrieval-Augmented Generation (RAG) to introduce fashion knowledge into ChatGPT. In this way, the system realized high degree of flexibility and adaptability. We confirmed that the system using ChatGPT is superior to the conventional method in quantitative evaluations.