面向大规模Web服务网络的社团发现算法

Community Discovery of Large-scale Web Service Network

社团结构是复杂网络中普遍存在的结构.互联网上存在着大量的开放web服务,这些服务通过用户的需求的交互连接,形成了一个复杂的交互网络.发现并利用这些web服务交互网络上的社团结构有助于理解这类复杂软件系统的行为.针对基于web服务行为信息构成服务网络,研究web服务社团发现算法,分析了由用户需求驱动形成的服务社团的结构特征.首先基于web服务结构描述文档信息,构造了web服务交互网络,然后提出一种基于服务协同关系的服务社团发现算法.在真实的w eb服务数据集上进行了实验分析,说明了该算法应用于服务网络的合理性与有效性.

An important feature of complex networks is that they are generally composed of highly interconnected sub-networks called community. It is very useful and significant to comprehend the features of networks community for analyzing and applications. In this paper, we propose an algorithm for community discovery of web service network. These communities are naturally formed in common by services related on a special topic. First,ee construct web service structure networks based on web service description documents. Then,we propose a community discovery algorithm based on service cooperation relationships. Finally,extensive experiments on real datasets show that the efficiency of proposed method.