计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (9): 212-215.DOI: 10.3778/j.issn.1002-8331.2009.09.062

• 工程与应用 • 上一篇    下一篇

中文专利侵权检索模型研究

汪雪锋1,刘玉琴2,刘 佳1   

  1. 1.北京理工大学 管理与经济学院,北京 100081
    2.工业与信息化部 软件与集成电路促进中心,北京 100038
  • 收稿日期:2008-10-14 修回日期:2009-01-22 出版日期:2009-03-21 发布日期:2009-03-21
  • 通讯作者: 汪雪锋

Research on Chinese patent infringement retrieval model

WANG Xue-feng1,LIU Yu-qin2,LIU Jia1   

  1. 1.School of Management and Economics,Beijing Institute of Technology,Beijing 100081,China
    2.Software and Integrated Circuit Promotion Center,Ministry of Industry and Information Technology Beijing 100038,China
  • Received:2008-10-14 Revised:2009-01-22 Online:2009-03-21 Published:2009-03-21
  • Contact: WANG Xue-feng

摘要: 结合中文专利权利要求的结构特征,首次将中文专利按照“分割词”重新分类,以重新划分的“新类别”进行词性选择,构造向量空间,设计了中文专利侵权检索模型,通过我国集成电路封装技术领域的发明专利进行技术侵权检索实证分析与对比实验,实验结果显示该模型的检索效果明显优于一般的侵权检索方法。

关键词: 专利侵权检索, 分割词, 专利类别, 向量空间

Abstract: Based on the structure information of patent’s claims,the model of Chinese patent infringement retrieval is proposed.In the model,Chinese patents are reclassified firstly by the forty “split words” which are extracted from patent database from view of retrieval.Different types of word are selected to construct vector space.An empirical patent infringement illustration and contrast experiment about integrate circuit technology in China are conducted and the results show this approach is effective.

Key words: patent infringement retrieval, split words, patent classification, vector space