摘要
传统的协作过滤方法存在的主要问题是需要人为地提供评价,论文设计的协作过滤方法对其进行了改进,根据用户模式自动获取用户评价,构建评价矩阵。将设计的协作过滤方法应用到个性化信息推荐,提出一种基于协作过滤的Web智能信息推荐方法(WIIRM)。WIIRM考虑用户访问页面的时间特性,不需要用户注册,在推荐时考虑页面的新颖性,同时实现离线处理与在线推荐的结合。实验结果表明,WIIRM是有效的。
The paper improves the traditional collaborative filtering method which needs artificial evaluation. The advanced method could gain evaluation value automatically through user pattern and establish evaluation matrix. This paper applies designed collaborative faltering method to personalized information recommendation, and proposes a Web intelligent information recommendation method based on colladorative filtering （WIIRM）. WIIRM consideres the time of page calling and novelty of page. It could supply reconenendation service for unauthorized users. Meanwhile, it combines off-line processing and on-line recommendation. The experimental results indicates that WIIRM is effective.
出处
《图书情报工作》
CSSCI
北大核心
2010年第19期115-118,110,共5页
Library and Information Service
基金
教育部人文社会科学基金项目"图书馆2.0个性化信息服务与服务集成研究"(项目编号:09yjc870032)研究成果之一
关键词
智能信息推荐
个性化信息服务
协作过滤
intelligent information recommendation personalized information service collaborative filtering
