个性化信息推荐服务中用户潜在兴趣挖掘研究  

Mining Users Potential Interested in Personalized Information Recommendation Service

作　　者：何金晶[1] 

机构地区：[1]西安电子科技大学经济管理学院,陕西西安710071

出　　处：《现代情报》2013年第4期7-11,16,共6页Journal of Modern Information

基　　金：国家自然科学基金项目"基于社区的P2P信息资源的语义检索策略与模型研究"(项目编号:71003080)的研究成果之一

摘　　要：如何准确分析用户行为,向用户提供满意的网页信息,一直以来都是个性化信息推荐系统设计的目标。本文在分析现有个性化信息推荐模型的基础上,针对以往研究在推荐兴趣时仅根据语义相关度进行协助性信息推荐,而忽略用户行为规律所包含的潜在兴趣信息的不足,尝试提出一个结合Web语义挖掘和FP-tree规则发现技术的个性化信息推荐模型。该模型利用本体对语义的明确化描述,在挖掘用户行为信息时获取用户兴趣偏好的语义信息,并利用FP-tree技术根据以获取的语义信息推理出用户兴趣行为模式,从而在信息推荐时不仅能准确理解用户兴趣偏好,也能根据用户潜在兴趣规律,推荐给用户更全面的网页信息。How to analyze user behavior accurately to provide user webpage with satisfaction has been a design goal of personalized information recommendation system.Based on the analysis of the existing personalized information recommendation models,a new model of personal recommendation system based on Web Semantic Mining was presented in this paper.By the combination of Web semantic mining and FP-tree technology,what the model has been solved was the disadvantage of ignoring user potential interest when the previous studies recommend information to users.And the limitation that recommend webpage to user just according to user access sequence had also been broken through.

关 键 词：Web语义挖掘 个性化信息推荐 FP-TREE 用户潜在兴趣 

分 类 号：G252.0[文化科学—图书馆学]