您的位置:山东大学 -> 科技期刊社 -> 《山东大学学报(理学版)》

J4 ›› 2011, Vol. 46 ›› Issue (5): 49-53.

• SEWM 2011 会议 • 上一篇    下一篇

基于用户兴趣及术语间关系的查询扩展方法

徐建民1,3,陈振亚2,崔琰3   

  1. 1.天津大学系统工程研究所, 天津 300072; 2. 河北大学图书馆, 河北 保定 071002;
    3. 河北大学数学与计算机学院, 河北 保定 071002
  • 收稿日期:2010-12-06 发布日期:2011-05-25
  • 作者简介:徐建民(1966- ),男,教授,主要从事信息检索、不确定信息处理的研究. Email:yy.csi@mail.hbu.edu.cn
  • 基金资助:

    中国博士后科学基金资助项目(20070420700);河北省自然科学基金资助项目(F2011201146)

Query expansion method based on the user interest and term relation

XU Jian-min1,3, CHEN Zhen-ya2, CUI Yan3   

  1. 1. Institute of Systems Engineering, Tianjin University, Tianjin 300072, China;
    2. Hebei University Library, Baoding 071002, Hebei, China;
    3. School of Mathematic and Computer, Hebei University, Baoding 071002,  Hebei, China
  • Received:2010-12-06 Published:2011-05-25

摘要:

针对传统查询扩展方法无法根据不同用户的需求进行检索的不足,提出一种基于用户兴趣和术语间关系进行查询扩展的方法。通过对用户浏览的网页文档及得到的网页日志进行挖掘得到一系列代表用户兴趣的术语,根据与初始查询词存在同义关系的用户兴趣术语及其权重对初始查询词权重进行调整,利用兴趣术语中与初始查询词存在本体关联关系的术语对初始查询进行扩展。实验结果表明,该方法相对于传统查询扩展方法在一定程度上提高了信息检索的查全率和查准率。

关键词: 查询扩展;网页日志;用户兴趣;同义词;本体关联

Abstract:

The traditional query expansion method  can not retrieve information according to different users’ requirement, so a new query expansion method is proposed on the basis of users’ interest and term relation. A series of terms reflecting users’ interest are obtained by mining the web log records, and the weights of original queries′  are adjusted according to the synonym relativity between these terms and the original words, then the original queries are expanded by using the ontology relevance relativity between these terms and the original words.  Experimental results show that the approach can enhance the accuracy ratio and the recall compared to the traditional query expansion method.

Key words:  query expansion; web log; user interest; synonym; ontology relevance

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!