Reproduce “Engineering Knowledge Graph from Patent Database” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
L Siddharth, Lucienne T.M. Blessing, Kristin L. Wood, Jianxi Luo
The authors build an engineering knowledge graph by extracting labeled entity-relationship-entity facts from US patent claims. It matches 80.7% of terms in a 2,704-term engineering dictionary, compared with 72.3% for TechNet; formatting corrections raise reported coverage to 82.7%. The graph contains 288,807,731 entities and 794,956,771 relationships, but evaluation does not measure fact accuracy or design performance.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.