基于查询-概念的用户兴趣模型构建  

Construction of User Interest Model Based on Queries and Concept

作　　者：宋天勇 赵辉[1] 郑山红[1] 王国春[1] 

机构地区：[1]长春工业大学计算机科学与工程学院,长春130012

出　　处：《吉林大学学报（信息科学版）》2015年第3期310-314,共5页Journal of Jilin University（Information Science Edition）

基　　金：吉林省科技厅自然科学基金资助项目(20130101060JC);吉林省教育厅"十二五"科学技术研究基金资助项目(2014132;2014125)

摘　　要：针对查询-概念二分图因概念抓取和查询词权重设计不足而导致构建的用户兴趣模型不合理的问题,提出一种基于查询-概念二分图的用户兴趣建模算法。通过tf×idf公式抓取概念,并利用用户对查询词的浏览时间计算查询词的权重,确保改进后的查询-概念二分图能更准确地表示用户的查询意图。实验结果表明,该算法构建的用户兴趣更为合理。Bipartite graph of queries and concept is insufficient in concept grabbing and calculating weight of thequery words, which cause the user interest model construction not reasonable. The improved bipartite graph of queries and concept will represent the user＇s query intent more accurate by using ff×idf grasping concepts and calculating the weight of query query words through user＇s browsing time. A user interest modeling algorithm based on improved bipartite graph of queries and concept was proposed. And experiments verified that user interest model constructed by this algorithm is more reasonable.

关 键 词：查询-概念二分图 浏览时间 用户兴趣模型 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]