[3Xin2] Poster session 1

[3Xin2-103] Dataset Development of Vision-Language Model for Patent Data

〇Kazuya Ando¹, Tsukito Mizoguchi¹, Haruki Ishikawa¹, Akira Iyoda¹, Seiya Kawano², Koichiro Yoshino², Hirofumi Nonaka¹ (1.Aichi Instetute Technology, 2.Guardian Robot Project, RIKEN)

Keywords:Patent, Vision-Language Model, Image Recognition, Multi-Modal, Patent Figure

In this study, we developed a dataset for the development of image-language models of text-drawing pairs in patent documents. Specifically, we created a large image-language dataset by mapping patent drawings to explanatory text using standardized expressions in patents.