Cultural Product Design Concept Generation with Symbolic Semantic Information Expression Using GPT

Authors

Yang Yin, Modern Industrial Design Institute,Zhejiang University,Hangzhou, ChinaFollow
Shiying Ding, School of Software Technology,Zhejiang University,Ningbo, ChinaFollow
Xiyuan Zhang, Modern Industrial Design Institute,Zhejiang University,Hangzhou, ChinaFollow
Chenan Wang, College of Computer Science and Technology, Zhejiang University, Hangzhou, ChinaFollow
Xinyu Li, Modern Industrial Design Institute,Zhejiang University,Hangzhou, ChinaFollow
Ruiyi Cai, Modern Industrial Design Institute,Zhejiang University,Hangzhou, ChinaFollow
Yuancong Shou, School of Software Technology,Zhejiang University,Ningbo, ChinaFollow
Yiwu Qiu, Hangzhou Zaowuyun Technology Co. Ltd., Hangzhou, ChinaFollow
Chunlei Chai, Modern Industrial Design Institute,Zhejiang University,Hangzhou, ChinaFollow

Abstract

Products imbued with traditional cultural semantic information hold significance in commerce, culture, and the dissemination of information. However, the integration of implicit cultural semantics into the design process of cultural products poses a significant challenge. Key issues include the inaccurate expression of implicit semantics and the inadequacy of semantic information retrieval and inspi-ration. Therefore, we adopt a datadriven approach to achieve symbolic semantic expression in generating and inspiring design concepts for cultural products. In this paper, we utilize the generative pretrained transformer (GPT-3.5) as the base language model (PLM). By analyzing semantic information features in layers and mapping, we identify two design concept generators, fine-tuning them for the automatic retrieval and expression of semantic information. This is undertaken to generate cultural product designs in a natural language form. The method under-goes experimental evaluation, and the results demonstrate that our approach can generate cultural product design concepts containing accurate cultural information.

Keywords

applications of large language models; natural language processing; cultural product design; symbolic semantics

DOI

https://doi.org/10.21606/drs.2024.508

Citation

Yin, Y., Ding, S., Zhang, X., Wang, C., Li, X., Cai, R., Shou, Y., Qiu, Y., and Chai, C. (2024) Cultural Product Design Concept Generation with Symbolic Semantic Information Expression Using GPT, in Gray, C., Ciliotta Chehade, E., Hekkert, P., Forlano, L., Ciuccarelli, P., Lloyd, P. (eds.), DRS2024: Boston, 23–28 June, Boston, USA. https://doi.org/10.21606/drs.2024.508

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License

Conference Track

Research Paper