Patent analysis with text mining for TRIZ

Abstract

Patent is an important knowledge source for industrial research and product development on account of its innovation and practicability. In TRIZ theory, a product design problem can be considered as one or more Contradictions. But the Contradictions and corresponding Inventive Principles are rather abstract and general. It will be more helpful for innovators to solve the problem if they obtain related examples from published patents that have solved the Contradictions. In order to search the relevant patens according to Contradictions and Inventive Principles automatically, text mining is used to analyze patent documents. In this paper, a computer-aided methodology to classify patents according to Contradictions and Inventive Principles is proposed.