AutoTRIZ: Artificial Ideation with TRIZ and Large Language Models

arXiv:2403.13002v1 Announce Type: cross
Abstract: Researchers and innovators have made enormous efforts in developing ideation methods, such as morphological analysis and design-by-analogy, to aid engineering design ideation for problem solving and innovation. Among these, TRIZ stands out as the most well-known approach, widely applied for systematic innovation. However, the complexity of TRIZ resources and concepts, coupled with its reliance on users' knowledge, experience, and reasoning capabilities, limits its practicability. This paper proposes AutoTRIZ, an artificial ideation tool that leverages large …

abstract analogy analysis artificial arxiv complexity cs.ai cs.cl cs.hc design engineering engineering design however ideation innovation language language models large language large language models researchers type