Embedding Knowledge Graph of Patent Metadata to Measure Knowledge Proximity

TL;DR

This paper develops a knowledge graph embedding approach using patent metadata to quantify and analyze the proximity between entities in the US Patent Database, aiding in understanding innovation and domain expansion.

Contribution

It operationalizes knowledge proximity with a novel graph embedding method applied to patent data, enabling improved prediction and analysis of entity relationships.

Findings

Embedding models effectively predict entity relationships.

Cosine similarity captures knowledge proximity accurately.

Embeddings reveal insights into inventor and assignee domain expansion.

Abstract

Knowledge proximity refers to the strength of association between any two entities in a structural form that embodies certain aspects of a knowledge base. In this work, we operationalize knowledge proximity within the context of the US Patent Database (knowledge base) using a knowledge graph (structural form) named PatNet built using patent metadata, including citations, inventors, assignees, and domain classifications. We train various graph embedding models using PatNet to obtain the embeddings of entities and relations. The cosine similarity between the corresponding (or transformed) embeddings of entities denotes the knowledge proximity between these. We compare the embedding models in terms of their performances in predicting target entities and explaining domain expansion profiles of inventors and assignees. We then apply the embeddings of the best-preferred model to associate homogeneous (e.g., patent-patent) and heterogeneous (e.g., inventor-assignee) pairs of entities.