A Generic Multi-Agent Architecture for Interactive Diagnostic Tasks with Clarification

Le résumé fourni par la source

A reusable multi-agent architecture is presented for diagnostic tasks that are supported by a system that interacts with the user at two levels: at the level of the task itself and at the level of clarification of the process. Three agents are distinguished: a user, a diagnostic support agent and a clarification support agent. The user and the diagnostic support agent co-operate on the basis of a shared diagnostic task model; the user and the clarification support agent co-operate on the basis of a shared clarification task model. 1. Introduction The design of systems to support experts in complex decision tasks requires analysis of the task as a whole, including the co-operation between the user and the decision support system. During analysis, the acquisition of a shared task model of a task can play an important role, a model shared by the user (who also is an expert) and the designer. This shared task model is used to design the architecture of a support system, and the interactio...

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.