Agent-Based Composite Services in DAML-S: the Behavior-Oriented Design of an Intelligent Semantic Web

Abstract

Abstract. Many researchers are working towards the goal of a semantic Weba Web that provides information in a way that is useful to artificial intelligences. A semantic Web would allow artificial agents to do the work of searching for and organizing services required by humans or organizations. DAML-S is a Web service ontology intended to facilitate the semantic Web by describing the properties and capabilities of Web-available services in an unambiguous, computerinterpretable form. In this paper, we propose that an important new perspective on the semantic Web can be obtained by regarding its content as behavioral intelligence. The services encoded in DAML-S can then be viewed as specifications either for extensions of the user agents attempting to exploit the services, or as independent, collaborative agents that can be 'awakened' to assist the user agents. We draw on our experience in agent development to elaborate the specification, particularly of the process ontology of DAML-S, in order to support this vision.

Where Should Complexity Go? Cooperation in Complex Agents with Minimal Communication

“…Gajos [21] describes a system that does this within an intelligent environment -IMA-like coordination is used to coordinate care for both individual users and individual rooms. Bryson et al [12] propose a similar solution, where an individual user agent's action-selection may temporarily absorb as a module agent-like services discovered on the Web.…”

Goal Preservation by Choreography-Driven Matchmaking

“…Temporal logic is used to express both the constraints and the goal to achieve, enabling the automatic synthesis of a composition of activities. Finally, works like [18,6] propose approaches for goal-driven service composition based on planning. However, this task is accomplished without reference to any choreography.…”

Reasoning about Communicating Agents in the Semantic Web

“…Some work in this direction has already been carried on in [19], where, within the context of the DAML-S project [5], the reasoning techniques supported by GOLOG, an agent language based on the situation calculus, are applied to produce composite and customized services. Actually, when a service is described in terms of the function that it executes, with its preconditions and effects, the use of agents that can reason about the consequences of its invocation is a natural choice: a rational agent is by definition characterized by a high-level of autonomy, it has an own internal state containing information about the world and about its goals, it can reason about how to behave for fulfilling them, it can react to alterations of the environment.…”