Dynamic representation of information for a decision support system

This paper presents a system designed to help deciders manage cases of crisis. The system represents, characterises and interprets the dynamic evolution of information describing a given situation and displays the results of its analysis. The core of the system is made up of three multiagent systems (MAS): one MAS for the static and dynamic representation of the information (current situation), the second MAS for dynamically regrouping sets of agents of the former MAS and the upper MAS for matching results between the second NIAS and scenarios stored in the persistent memory of the system in order to have a deeper analysis of the situation. The case based reasoning of this last MAS sends its results to the user as a view of the current situation linked to some views of similar situations. In this paper, we will focus on the representation of information MAS. This MAS is dynamic in order to be able to take into account the changes in the description of the information. Current information is represented by a layer of factual agents which is fed by the composite semantic features constituting the atomic data elements of information. The aim of the set of factual agents is both to be a real snapshot of the situation at any time and to model the evolution of information dynamically.