图书情报工作 ›› 2018, Vol. 62 ›› Issue (5): 97-105.DOI: 10.13266/j.issn.0252-3116.2018.05.011

• 情报研究 • 上一篇    下一篇

基于图相似度的专利侵权检测方法研究

翟东升, 蔡文浩, 张杰, 郭程   

  1. 北京工业大学经济与管理学院 北京 100124
  • 收稿日期:2017-09-05 修回日期:2017-11-30 出版日期:2018-03-05 发布日期:2018-03-05
  • 作者简介:翟东升(ORCID:0000-0002-7941-5246),教授,博士生导师,博士,E-mail:zhaidongsheng@bjut.edu.cn;蔡文浩(ORCID:0000-0001-6973-8722),硕士研究生;张杰,副教授,硕士生导师,博士;郭程(ORCID:0000-0003-1205-0948),硕士研究生。
  • 基金资助:
    本文系广东省科技计划项目"基于专利语义分析的技术合作伙伴推荐服务平台"(项目编号:2017A040403027)研究成果之一。

A Method of Patent Infringement Detection Based on Graph Similarity

Zhai Dongsheng, Cai Wenhao, Zhang Jie, Guo Cheng   

  1. School of Economics and Management, Beijing University of Technology, Beijing 100124
  • Received:2017-09-05 Revised:2017-11-30 Online:2018-03-05 Published:2018-03-05

摘要: [目的/意义]针对如何准确进行专利侵权检测,提出一种基于图相似度的专利侵权检测方法。[方法/过程]将专利语义特征抽取为subject-action-object(SAO)结构并利用图论将其表示为图的形式,然后将图转换为邻接矩阵并计算邻接矩阵的相似性来完成专利侵权判定,最后利用专利样本数据比较该方法与传统方法的判定准确率。[结果/结论]实证研究结果表明,本研究提出的方法判定准确率更高,比传统的基于专利文本向量的方法准确率提升4.89%,可以作为专利侵权检测的有效方法。

关键词: 专利侵权, 图论, 图相似度, SAO, 邻接矩阵

Abstract: [Purpose/significance] Aimed at how to carry out patent infringement detection accurately, a patent infringement detection method based on graph similarity is proposed. [Method/process] The patent semantic feature is extracted into the Subject-Action-Object (SAO) structure and expressed as graph form by graph theory. Then the graph is transformed into adjacency matrix and the similarity of the adjacency matrix is calculated to complete the patent infringement judgment. Finally, it compare the accuracy of the method and the traditional method with the sample data. [Result/conclusion] The empirical results show that the proposed method is more accurate than the traditional method, and the accuracy rate is 4.89% higher than that of the method based on patented text vector. So the method proposed in this study can be used as an effective method of patent infringement detection.

Key words: patent infringement, graph theory, graph similarity, SAO, adjacency matrix

中图分类号: