Automatic Semantic Web Service Composition via Agent Intention Execution in AgentSpeak

Abstract

AI planning is the main stream method for automatic semantic web service composition (SWSC) research. However, planning based SWSC method can only return service composition upon user requirement description and lacks flexibility to deal with environment change. Deliberate agent architecture, such as BDI agent, is hopeful to make SWSC more intelligent. In this paper, we propose an automatic SWSC enabling method for AgentSpeak agent. Firstly, conversion algorithm from OWL-S web service description to agent's plan set (OWLS2APS) is presented. Target service is converted to agent's goal and related services are converted into agent's plan set. Then, SWSC is automatically performed through agent's intention formation. Agent invokes web service according to service sequence converted back from its intention. Agent can behave rationally with rules or ask for human intervention when SWSC or service invocation is not feasible. At last, a case study on enterprise credit rating service composition is presented to illustrate the method.