Abstract
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).
| Original language | English |
|---|---|
| Article number | 121559 |
| Journal | Technological Forecasting and Social Change |
| Volume | 177 |
| ISSN | 0040-1625 |
| DOIs | |
| Publication status | Published - Apr 2022 |
Bibliographical note
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
Keywords
- Natural-language processing
- Patent data
- Patent landscaping
- Patent quality
- Technological similarity
- Technology network