Context-sensitive Web service discovery over the bipartite graph model  

作　　者：Rong ZHANG Koji ZETTSU Yutaka KIDAWARA Yasushi KIYOKI Aoying ZHOU 

机构地区：[1]Software Engineering Institute, East China Normal University, Zhongshan 200062, China [2]National Institute of Information and Communications Technology, Kyoto 619-0289, Japan [3]Keio University, Kanagawa 252-8520, Japan

出　　处：《Frontiers of Computer Science》2013年第6期875-893,共19页中国计算机科学前沿（英文版）

摘　　要：As service oriented architecture （SOA） matures, service consumption demand leads to an urgent requirement for service discovery. Unlike Web documents, services are intended to be executed to achieve objectives and/or desired goals of users. This leads to the notion that service discovery should take the ＂usage context＂ of service into account as well as service content （descriptions） which have been well explored. In this paper, we introduce the concept of service context which is used to represent service usage. In query processing, both service content and service context are ex- amined to identify services. We propose to represent ser- vice context by a weighted bipartite graph model. Based on the bipartite graph model, we reduce the gap between query space and service space by query expansion to improve re- call. We also design an iteration algorithm for result ranking by considering service contextsefulness as well as contentrelevance to improve precision. Finally, we develop a service search engine implementing this mechanism, and conduct some experiments to verify our idea.As service oriented architecture （SOA） matures, service consumption demand leads to an urgent requirement for service discovery. Unlike Web documents, services are intended to be executed to achieve objectives and/or desired goals of users. This leads to the notion that service discovery should take the ＂usage context＂ of service into account as well as service content （descriptions） which have been well explored. In this paper, we introduce the concept of service context which is used to represent service usage. In query processing, both service content and service context are ex- amined to identify services. We propose to represent ser- vice context by a weighted bipartite graph model. Based on the bipartite graph model, we reduce the gap between query space and service space by query expansion to improve re- call. We also design an iteration algorithm for result ranking by considering service contextsefulness as well as contentrelevance to improve precision. Finally, we develop a service search engine implementing this mechanism, and conduct some experiments to verify our idea.

关 键 词：Web service usage context bipartite graph model context-usefulness 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论] TP301.6[自动化与计算机技术—计算机科学与技术]