Abstract
AbstractThis paper builds a patent-based knowledge graph, patent-KG, to represent the knowledge facts in patents for engineering design. The arising patent-KG approach proposes a new unsupervised mechanism to extract knowledge facts in a patent, by searching the attention graph in language models. The extracted entities are compared with other benchmarks in the criteria of recall rate. The result reaches the highest 0.8 recall rate in the standard list of mechanical engineering related technical terms, which means the highest coverage of engineering words.
Publisher
Cambridge University Press (CUP)
Reference33 articles.
1. World Intellectual Property Organization. 2019. World Intellectual Property Indicators 2019 [Online]. Available: https://www.wipo.int/publications/en/details.jsp?id=4464 [Accessed August 23, 2021].
2. Siddharth, L. , Blessing, L. T. M. , Wood, K. L. & Luo, J. J. a. E.-P. 2021. Engineering Knowledge Graph from Patent Database. Available: https://ui.adsabs.harvard.edu/abs/2021arXiv210606739S [Accessed June 01, 2021].
3. Clark, K. , Khandelwal, U. , Levy, O. & Manning, C. D. J. a. E.-P. 2019. What Does BERT Look At? An Analysis of BERT's Attention. Available: https://ui.adsabs.harvard.edu/abs/2019arXiv190604341C [Accessed June 01, 2019].
4. TechNet: Technology semantic network based on patent data;Sarica;Expert Systems with Applications,2020
5. Shi, F. 2018. A Data-Driven Text Mining and Semantic Network Analysis for Design Information Retrieval.
Cited by
7 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献