TY - JOUR
T1 - A text-embedding-based approach to measuring patent-to-patent technological similarity
AU - Hain, Daniel S.
AU - Jurowetzki, Roman
AU - Buchmann, Tobias
AU - Wolf, Patrick
N1 - Funding Information:
All code necessary to recreate our workflow, indicator creation, and analysis is freely available at https://github.com/daniel-hain/patent_embedding_research . All data is also available for download and use in third-party analysis. Financial support for ZSW’s research provided by BMBF Kopernikus ENavi (FKZ:03SFK4W0). – Workflow, Code, and Applications –
Publisher Copyright:
© 2022
PY - 2022/4
Y1 - 2022/4
N2 - This paper describes an efficiently scaleable approach to measuring technological similarity between patents by combining embedding techniques from natural language processing with nearest-neighbor approximation. Using this methodology, we are able to compute similarities between all existing patents, which in turn enables us to represent the whole patent universe as a technological network. We validate both technological signature and similarity in various ways and, using the case of electric vehicle technologies, demonstrate their usefulness in measuring knowledge flows, mapping technological change, and creating patent quality indicators. This paper contributes to the growing literature on text-based indicators for patent analysis. We provide thorough documentation of our methods, including all code, and indicators at https://github.com/AI-Growth-Lab/patent_p2p_similarity_w2v).
AB - This paper describes an efficiently scaleable approach to measuring technological similarity between patents by combining embedding techniques from natural language processing with nearest-neighbor approximation. Using this methodology, we are able to compute similarities between all existing patents, which in turn enables us to represent the whole patent universe as a technological network. We validate both technological signature and similarity in various ways and, using the case of electric vehicle technologies, demonstrate their usefulness in measuring knowledge flows, mapping technological change, and creating patent quality indicators. This paper contributes to the growing literature on text-based indicators for patent analysis. We provide thorough documentation of our methods, including all code, and indicators at https://github.com/AI-Growth-Lab/patent_p2p_similarity_w2v).
KW - Natural-language processing
KW - Patent data
KW - Patent landscaping
KW - Patent quality
KW - Technological similarity
KW - Technology network
UR - http://www.scopus.com/inward/record.url?scp=85124302402&partnerID=8YFLogxK
U2 - 10.1016/j.techfore.2022.121559
DO - 10.1016/j.techfore.2022.121559
M3 - Journal article
AN - SCOPUS:85124302402
SN - 0040-1625
VL - 177
JO - Technological Forecasting and Social Change
JF - Technological Forecasting and Social Change
M1 - 121559
ER -