Composition Oriented Semantic Relationships Mining Framework Research

Abstract

In order to improve the efficiency of service discovery and service composition, this paper proposes a Composition oriented Web services semantic relationships mining framework. Firstly, Web services need to be pretreated, which are filtered based on QoS; and then adopt the method of service functional clustering to generate service classes, which largely reduces the services search space and improve the efficiency of service discovery; Secondly, in order to excavate the semantic relationships between service classes that meet the business logic requirement, we need to set the composition rules between service classes; Finally, using two stages of mining algorithms to excavate the semantic relationships between service classes. Experimental results are given to validate the feasibility and validity of our framework.