基于语义相似度的Web数据库不精确查询方法  

Semantic Similarity-based Approach for Answering Imprecise Queries over Web Databases

作　　者：孟祥福[1] 张霄雁[1] 马宗民[2] 张志艳[1] 

机构地区：[1]辽宁工程技术大学电子与信息工程学院,葫芦岛125105 [2]东北大学信息科学与工程学院,辽宁110819

出　　处：《计算机科学》2012年第4期154-158,共5页Computer Science

基　　金：国家青年科学基金项目(61003162)资助

摘　　要：为了解决普通用户对于Web数据库的不精确查询问题,提出了一种基于语义相似度的Web数据库不精确查询方法。对于一个给定查询,该方法首先在查询历史中找出一个(或若干)与其相似度高于给定放松阈值的查询,然后从数据库中找出与这些查询相匹配的元组作为当前查询的不精确查询的结果,最后将这些查询结果按其对初始查询的满足程度进行排序。实验结果表明,提出的不同查询之间的语义相似度评估方法性能稳定、评估结果合理,不精确查询方法具有较高的查全率和排序准确性。To deal with the problem of answering the Web database imprecise queries,this paper proposed a semantic similarity-based Web database imprecise query approach.For a given query,one or several similar queries in the query history will be found firstly,and the similarity of each similar query to the original query is greater than the given relaxa-tion threshold.Then,the tuples matched to these queries are treated as the imprecise query results to the current query.Finally,the result tuples are ranked according to their satisfaction to the original query.Results of experiments de-monstrate that the query similarity measuring method proposed is stable and reasonable,and the imprecise query method proposed has higher recall and the ranking accuracy as well.

关 键 词：WEB数据库 不精确查询 关联规则 语义相似度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]