Enhancing patent retrieval using text and knowledge graph embeddings: a technical note
L. Siddharth, Guangtong Li, Jianxi Luo
Abstract
Patent retrieval influences several applications within engineering design research, education, and practice as well as applications that concern innovation, intellectual property, and knowledge management etc. In this article, we propose a method to retrieve patents relevant to an initial set of patents, by synthesising state-of-the-art techniques among natural language processing and knowledge graph embedding. Our method involves a patent embedding approach that captures text, citation, and inventor information, which individually represent different facets of knowledge communicated through a patent document. We obtain text embeddings through Sentence-BERT applied to titles and abstracts. We obtain citation and inventor embeddings through TransE that is trained using the corresponding knowledge graphs. We identify using a classification task that the concatenation of text, citation, and inventor embeddings offers a plausible representation of a patent. While the proposed patent embedding could be used to associate a pair of patents, we observe using a recall task that multiple initial patents could be associated with a target patent using mean cosine similarity, which could then be utilised to rank all target patents and retrieve the most relevant ones. We apply the proposed patent retrieval method to a set of patents corresponding to a product family and an inventor's portfolio.