计算机与现代化 ›› 2009, Vol. 1 ›› Issue (11): 60-62,6.doi:

• 网络与通信 • 上一篇    下一篇

基于聚类和用户兴趣分析结合的个性化元搜索

徐德兴,李建民,林振荣   

  1. 南昌大学计算机系,江西 南昌 330031
  • 收稿日期:2008-11-12 修回日期:1900-01-01 出版日期:2009-11-30 发布日期:2009-11-30

Personalized Search for Meta Search Engines Based on Clustering and User Interest Analysis

XU De-xing,LI Jian-min,LIN Zhen-rong   

  1. Department of Computer, Nanchang University, Nanchang 330031, China
  • Received:2008-11-12 Revised:1900-01-01 Online:2009-11-30 Published:2009-11-30

摘要: 随着Web信息的快速增长,搜索引擎已成为用户信息检索的主要工具。元搜索引擎综合了多个搜索引擎的搜索结果,提高了搜索的覆盖率,但是返回的结果往往数目庞大,并且很多结果与用户查询并不相关,这直接影响了用户检索的质量并增加了用户检索的代价。本文提出一种基于聚类的个性化元搜索引擎模型,系统通过对用户建立兴趣模型,对此模型进行聚类形成不同用户群,并对检索到的结果进行聚类处理,与用户模型聚类相结合返回给用户个性化的搜索结果。

关键词: 元搜索引擎, 兴趣模型, 个性化搜索

Abstract: As the amount of information on the Web increases rapidly, search engines become the major tools for information retrieval. Meta search engines are proposed to increase search coverage by combining several search engines. However, the problem of the information overload becomes more severe and returned results are irrelevant to user’s interests. So the paper presents a personalized meta-search engine model based on clustering and interests. This system constructs a personalized model for every user in order to form different custom crowd, and together with the clustering analysis of the searching results. The model can make search engine return more personalized searching results for users.

Key words: meta-search engine, interest model, personalized search