An Analogy reasoning model for Semantic Link Network

Abstract

Analogy reasoning is one of the most important reasoning means of human thinking. How to implement analogy reasoning automatically with computers has been a hot topic in artificial intelligence and psychology. This paper proposes a mathematic model for analogy reasoning over semantic link network (SLN). We propose a reliable analogy theorem over SLN based on the category theory and some algorithms have been developed to implement analogical reasoning by constructing a semantic functor between SLNs. Meanwhile, we also discuss some analogy conjecture models and algorithms which may be unreliable but useful to giving some suggestions for solving a given problem. A study cases is proposed to show the validity and efficiency of the proposed theorem and the algorithms.