Document Type



Web service plays an important role in implementing Service Oriented Architecture (SOA) for achieving dynamic business process. With the increased number of web services advertised in public repository, it is becoming vital to provide an efficient web service composition mechanism with respect to user’s requirement. In this paper, a service composition approach based on association rules is proposed in the sense of knowledge discovery. This approach includes two steps: firstly, frequent web services will be enumerated in the dataset of history service composition transactions. Secondly, execution path, the basic unit of composite service, will be generated based on concepts extracted from SOA domain and association rules implied in frequent services. In addition, frequent services mining algorithm is put forward based on a structure of Adjacent-Lattice, and experiments are given to show the effectiveness of the mining algorithm.