Technology opportunity discovery of proton exchange membrane fuel cells based on generative topographic mapping

Abstract

Technology opportunity discovery is a key factor in technological innovation that is closely related to the development of a country and has a great impact on promoting social progress. To find the unexplored areas of technology and present the detailed direction of technology development, this paper proposes a systematic approach to patent text data. It includes four stages. First, patent text data are collected and preprocessed by natural language process methods. Second, text mining is executed by the means of supervised machine learning methods. It is clustered with the k-mean++ algorithm after text representation as keywords vectors. Third, patents are visualized in two-dimensional space by the generative topographic mapping. Different from other work, Principal components analysis is used to transform complex multi-dimensional keyword vectors in two-dimensional space. Last, take proton exchange membrane fuel cells as an example. Discuss the meaning of each patent vacancy which be interpreted by its inverse mapping onto the original keyword vector and approved by experts. This approach not only saves time to identify patent vacancies but also increases objectivity and reliability. To some extent, it can help enterprises and researchers to identify the research and development strategy that focuses on innovation in the future.