结合文档处理与查询处理技术的Web服务搜索方法  

Approach integrating document processing with query processing technique for Web service search

作　　者：赵文玉[1] 周栋[1] 曹步清[1] 刘建勋[1] ZHAO Wenyu, ZHOU Dong, CAO Buqing, LIU Jianxun(School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan 411201, Chin)

机构地区：[1]湖南科技大学计算机科学与工程学院,湖南湘潭411201

出　　处：《计算机集成制造系统》2018年第7期1830-1837,共8页Computer Integrated Manufacturing Systems

基　　金：国家自然科学基金资助项目(61300129;61572187);教育部留学回国人员科研启动基金资助项目(教外司留[2013]1792);湖南省教育厅资助项目(16K030);湖南省教育厅创新平台开放基金项目(17K033);湖南省自然科学基金项目(2017JJ2101;2018JJ2139;2017JJ2098);湖南省研究生科研创新资助项目(CX2016B575);湖南科技大学科学研究基金项目(KJ1839)~~

摘　　要：为了提高Web服务搜索结果的准确性和改善用户的查询体验,使用文档处理技术与查询处理技术一直是Web服务搜索研究中的热点课题。为此,本文提出一种结合两种技术的Web服务搜索方法。考虑文档与文档之间的关系,通过正则化框架,融合第一轮检索结果分数,实现搜索结果列表中文档重排序;基于排名靠前文档构建扩展词集合,从构建扩展词集合中选取候选扩展词进行查询词扩展。在NTCIR数据集上的实验结果表明,该方法能够有效提高Web服务搜索中排名顶端结果的准确率。To improve the accuracy of Web service and the query experience of users,document processing technique and query processing technique are hot research topic in Web service search. For this reason, an approach which integrated document processing technique and query processing technique for Web service search was proposed. By considering the relationships between documents and the normalized framework, the re-rank documents in searching list based on the initial results was realized. The candidate terms from expansion terms set based on top documents were selected to expand the query. The experiments were conducted on NTCIR dataset, and the results showed that the proposed method could better improve precision for top results.

关 键 词：Web服务搜索 文档处理技术 查询词处理技术 正则化框架 扩展词集合 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]