Technology Knowledge Graph Based on Patent Data

The growing developments in general semantic networks (or knowledge graphs) have motivated us to build a large-scale comprehensive knowledge graph of engineering data for engineering knowledge discovery, technology search and retrieval, and artificial intelligence for engineering design and innovation. Specially, we constructed a technology knowledge graph (TKG) that covers the elemental concepts in all domains of technology and their semantic associations by mining the complete U.S. patent database from 1976. This paper presents natural language processing techniques to extract terms from massive patent texts and word embedding models to vectorize such terms and establish their semantic relationships. We report and evaluate the TKG technology knowledge graph for retrieving terms, semantic similarity and analogy. The TKG may serve as an infrastructure to support a wide range of applications, e.g., technical text summaries, search query predictions, relational knowledge discovery, and design ideation support, in the context of engineering and technology. To support such applications, we made the TKG public via an online interface for public users to retrieve technology-related terms and their relevancies.