arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.03468cs.CL
收藏

用于设计概念生成的生成式Transformers

Generative Transformers for Design Concept Generation

Singapore University of Technology and Design(新加坡科技设计大学)

Qihao Zhu, Jianxi Luo

摘要:

在早期设计阶段,产生新颖和有用的概念是必不可少的,以探索各种各样的设计机会,这通常需要先进的设计思维能力和设计师的广泛知识。越来越多的计算机辅助工具的工作已经探索了从设计数据中检索知识和知识。然而,它们只能从有限的方面为设计师提供激励。本研究探讨人工智能领域中的自然语言生成(NLG)技术的最新进展,以自动化早期设计概念的生成。具体而言,提出了一种新的方法,利用生成预训练的Transformer(GPT),利用知识和推理从文本数据,并将它们转换成新的概念,在可理解的语言。三个概念生成任务被定义为利用不同的知识和推理:领域知识综合,问题驱动的综合,类比驱动的综合。人类和数据驱动的评估实验表明,在生成新颖和有用的概念方面表现良好。

英文摘要:

Generating novel and useful concepts is essential during the early design stage to explore a large variety of design opportunities, which usually requires advanced design thinking ability and a wide range of knowledge from designers. Growing works on computer-aided tools have explored the retrieval of knowledge and heuristics from design data. However, they only provide stimuli to inspire designers from limited aspects. This study explores the recent advance of the natural language generation (NLG) technique in the artificial intelligence (AI) field to automate the early-stage design concept generation. Specifically, a novel approach utilizing the generative pre-trained transformer (GPT) is proposed to leverage the knowledge and reasoning from textual data and transform them into new concepts in understandable language. Three concept generation tasks are defined to leverage different knowledge and reasoning: domain knowledge synthesis, problem-driven synthesis, and analogy-driven synthesis. The experiments with both human and data-driven evaluation show good performance in generating novel and useful concepts.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑