基于扩展概念格的Web关系挖掘  

Web Relationship Mining Based on Extended Concept Lattice

作　　者：姜峰[1] 范玉顺[1] 

机构地区：[1]清华大学自动化系计算机集成制造国家工程中心,北京100084

出　　处：《软件学报》2010年第10期2432-2444,共13页Journal of Software

基　　金：国家自然科学基金No.60674080;国家高技术研究发展计划(863)No.2007AA04Z150~~

摘　　要：针对Web服务因缺少有效的组织和管理机制而产生的应用瓶颈问题,引入基于概念覆盖度函数的扩展概念格,通过构建基于输入和输出参数的Web服务集的扩展概念格模型,给出了Web服务间等价、替代和流关系的离线挖掘算法以及增量和减量的在线更新算法.在真实Web服务集上的测试结果表明,扩展概念格模型是Web服务集的一种有效的组织形式,可用于Web服务关系的自动挖掘和维护,从而为Web服务的选择、优化和组合提供智能支持.The lack of an efficient Web organization and management mechanism has become the bottleneck of Web applications. To address the problem, this paper proposes an extended concept lattice model based on Web input and output messages for service relationship mining. Concept coverage functionality is created and introduced into normal concept lattice. Off-Line algorithms for Web relations including equivalence, replacement, and flow relations mining, as well as their on-line update algorithms, are given. Experiment on real Web registry center shows that the extended concept lattice model is a highly efficient organization mechanism for Web relationships. Real Web registry center automatically mines, is expected to provide intelligent support for service choices, optimizations and composition.

关 键 词：概念格 形式概念分析 服务管理 关系挖掘 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]