Generative Transformers for Design Concept Generation
This addresses the problem of limited inspiration in computer-aided design tools for designers, though it is incremental by applying existing NLG techniques to a new domain.
The study tackled automating early-stage design concept generation by using generative pre-trained transformers (GPT) to synthesize new concepts from textual data, achieving good performance in generating novel and useful concepts as shown by human and data-driven evaluations.
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.