Leveraging large language models for enabling design by analogy: a computational framework

Design by Analogy (DbA) is a powerful method for fostering innovation by transferring knowledge from a source domain to solve problems in a target domain. However, traditional DbA approaches face significant challenges, including resource-intensive database management, linguistic and representational differences across domains, and the complexity of access and mapping processes. These limitations hinder scalability and efficiency, particularly for cross-domain analogies. Recent advancements in Artificial Intelligence (AI), especially Large Language Models (LLMs), offer promising solutions by facilitating efficient knowledge retrieval, bridging linguistic gaps, and enhancing semantic reasoning. This paper explores the potential of AI technologies to address these challenges, proposing a framework for analogical reasoning.