A Cognitive Agent Architecture for Medical Care

摘要

The design of the intelligent agent is an important research direction within multi-agent systems (MAS), where the behavior of a society of agents is described by modeling the individuals and their interactions from a local, agent-based perspective. Thus, finding appropriate architectures for these individuals is one of the fundamental research issues within agent design. Several works are focused on the functional aspects of the cognitive agent based on its internal architecture with no interest to the formal modeling of the cognitive agent components. This paper describes the design and the implementation of a layered agent architecture for decision support applications in general and for distributed medical care in particular. Three important characteristics which shaped the design are identified: distribution of data and control, information uncertainly, and dynamic environment. To provide appropriate decision support, the architecture combines a number of artificial intelligence and agent techniques That is a symbolic decision procedure for decision making with incomplete and contradictory information, a concept of accountability for task allocation, and a set of communication protocols for inter-agent interaction.