首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于协作过滤的Web日志数据预处理研究
引用本文:纪良浩,王国胤,杨勇.基于协作过滤的Web日志数据预处理研究[J].重庆邮电学院学报(自然科学版),2006,18(5):646-649.
作者姓名:纪良浩  王国胤  杨勇
作者单位:重庆邮电大学计算机科学与技术研究所,重庆400065
基金项目:重庆市自然科学基金重点资助项目(2005BA2003)
摘    要:协作过滤是当今应用较为成功的个性化服务技术,Web日志可以为个性化服务技术提供重要的数据源,只要对日志数据进行高效预处理,就能提高协作过滤算法有效性和个性化服务质量。结合实际日志数据的处理,给出了基于协作过滤的Web日志数据预处理过程结构图和一种可行的数据预处理方法,该方法不仅可以提供更加干净、规则的数据源,而且在用户兴趣度量方面,弥补了以往诸多兴趣度量方法的不足,为协作过滤算法提供了更加准确的数据支持。

关 键 词:个性化服务  协作过滤  Web日志  数据预处理  用户兴趣
文章编号:1004-5694(2006)05-0646-04
收稿时间:2006-04-27
修稿时间:2006-09-06

Research of Web log data preprocessing based on collaborative filtering
JI Liang-hao, WANG Guo-yin, YANG Yong.Research of Web log data preprocessing based on collaborative filtering[J].Journal of Chongqing University of Posts and Telecommunications(Natural Sciences Edition),2006,18(5):646-649.
Authors:JI Liang-hao  WANG Guo-yin  YANG Yong
Institution:Institute of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, P. R. China
Abstract:Collaborative filtering is one of the most successful applications in the field of personalized service.The Web log can provide personalized service technology with important data resource.And the validity of collaborative filtering algorithm and the quality of personalized service will be improved as long as the effective preprocessing to log data has been done.On the foundation of dealing with material log data,it gives a structure figure and a method of data preprocessing based on collaborative filtering.This method can not only provide cleaner and more regular data source but also make up the defects of former interests measurement in the aspect of user's interests measurement,which provides a more precious sustainment for collaborative filtering algorithm.
Keywords:personalized service  collaborative filtering  Web log  data preprocessing  user' s interests
本文献已被 CNKI 维普 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号