Pre-process for Architecture and Knowledge Co-design of an Intelligent Agent System

Abstract

An agent based system is a complex software system with some functional constrains, designing and building such a system is a complex task. This article presents a method for agent architecture and knowledge co-design. A use-case approach is used to elicit system requirements from user’s point of view, and the related use cases are assigned to corresponding roles. After the role model is refined by an analyzer, the agent architecture and high-level agent knowledge can be derived from the role model. Well-designed agent knowledge plays an important part for agent system to solve problems and make decisions. An ontology approach is used to represent the knowledge of agents and the ontology is implemented by conceptual graph. In a multi-agent system (MAS), the ontology also has the property of knowledge sharing and reuse that facilitate cooperation and negotiation among agents. The contribution of this article is a proposal to a systematic approach for implicit requirement analysis and a possibility for agent architecture and knowledge co-design for agent-based systems.