Net of multi-agent expert systems with emergent control

摘要

An aperture to expertise as a social outcome is to minimize supervised control: control of an expert system society and control of an agent's society in multi-agent expert systems. The present paper starts this aperture with autonomous behavioral agents within Expert Systems that exhibit bottom-up emergent control. The behavior-agents are either reasoning agents or communicating agents. The reasoning agents have a blackboard Domain Working Memory or a Meta Working Memory. The Expert Systems communicate with each other in a net for the solution of a problem. A practical development has been made in the medical domain of interconsultation that shows expedient problem-solving behavior.