An improved patent similarity measurement based on entities and semantic relations

作者：

Highlights：

• An improved patent similarity measurement on the basis of entities and semantic relations is proposed.

• Semantic direction of each sequence structure and the word order information of each component are taken into account.

• Extensive experimental results show that our approach is significantly more accurate.

摘要

•An improved patent similarity measurement on the basis of entities and semantic relations is proposed.•Semantic direction of each sequence structure and the word order information of each component are taken into account.•Extensive experimental results show that our approach is significantly more accurate.

论文关键词：Patent similarity measurement,Semantic analysis,Entities and semantic relations

论文评审过程：Received 21 May 2020, Revised 2 January 2021, Accepted 8 January 2021, Available online 6 February 2021, Version of Record 6 February 2021.

论文官网地址：https://doi.org/10.1016/j.joi.2021.101135