您的位置:首页  > 论文页面

基于点击模型的查询扩展方法

发表时间:2018-11-30  浏览量:56  下载量:4
全部作者: 翟科科,张日崇
作者单位: 北京奇虎科技有限公司; 北京航空航天大学计算机学院
摘 要: 引入搜索用户点击模型,提出一种基于用户点击模型的查询扩展方法。该方法首先从用户查询日志挖掘出所有关联的查询句对,并以此为初步查询扩展候选,然后将用户查询的一系列点击行为抽象为表述该查询的语义特征,并使用这些点击行为语义特征构建用户查询的点击向量,最后通过提出的一种综合相似度测度来衡量查询扩展的置信度。实验结果表明,相比于传统的查询扩展方法,该方法可以有效地改善搜索引擎相关性结果的语义匹配问题。
关 键 词: 人工智能;查询扩展;信息检索;点击模型;日志挖掘
Title: Query expansion method based on click model
Author: ZHAI Keke, ZHANG Richong
Organization: Beijing Qihoo Technology Limited Company; School of Computer Science and Engineering, Beihang University
Abstract: The paper introduces the click model of search user, and proposes a query expansion method based on user click model. Firstly, the method extracts all the associated query sentence pairs from the user query log, and as a preliminary query extension candidate. Then, a series of click behaviors of user queries are abstracted to express the semantic features of the query, and these click action semantic features are used to construct the click vector of user queries. Finally, we propose a synthetic similarity measure to weigh the confidence of query expansion. Experimental results show that this method can effectively improve the semantic matching problem of search engine correlation results compared with the traditional query expansion methods.
Key words: artificial intelligence; query expansion; information retrieval; click model; log mining
发表期数: 2018年11月第22期
引用格式: 翟科科,张日崇. 基于点击模型的查询扩展方法[J]. 中国科技论文在线精品论文,2018,11(22):2213-2219.
 
0 评论数 0
暂无评论
友情链接