Deep Web查询接口选择  

Deep Web query interface selecting

作　　者：郑冬冬[1] 崔志明[1] 

机构地区：[1]苏州大学智能化信息处理及应用研究所,江苏苏州215006

出　　处：《计算机应用》2006年第9期2024-2027,共4页journal of Computer Applications

基　　金：教育部高校博士学科点科研基金资助项目(20040285016);江苏省高技术研究计划资助项目(BG2005019);教育部科研重点资助项目(205059)

摘　　要：越来越多的信息隐藏在W eb查询接口之后,在此情况下如何寻找与用户查询最相关的数据源接口就变得越来越重要。文中提出了一种Deep W eb查询接口选择算法,该算法是完全依赖于查询接口特征的。给定大量异构的Deep W eb数据源,目标是选择与用户查询最相关的查询接口集。通过对实际查询接口特征的观察,发现了查询接口上谓词间的相关性。基于此发现,设计了一种基于共同出现谓词相关度模型的数据源选择算法,用于选择与用户查询最相关的查询接口集。As Web develops, more and more data has become available under Web query interface. Therefore, how to find the data-sources that are most relevant to the user＇s requirements has become more and more important. This paper presented a Deep Web query interface selection arithmetic, which completely depended on the characteristics of query interface. Given numerous heterogeneous Deep Web data sources, we aimed at selecting sources most relevant to the user＇s requirements. By allowing the users to input an imprecise initial query, our system found appropriate sources for them. We observed the characteristics of query interface and found out the relationships between predicates. Based on this discovery, an algorithm based on co-occurrence predicate model for capturing the relevance of attributes was designed. select the sources most relevant to the user＇s requirments.

关 键 词：谓词模型 接口对象 动态选择 

分 类 号：TP311.132[自动化与计算机技术—计算机软件与理论]