Representing Experience-Based Reasoning by Contextual Graphs

Abstract

Experts’ experience concerns the progressive elaboration of a context-specific model during the decision-making process. However, context modeling generally stays implicit because experts focus on the result of the decision-making. Modeling context within a decision-making process supposes a uniform representation of knowledge, reasoning and contexts. In the Contextual-Graphs formalism, a decision-making episode is represented as a contextual graph in which each path represents a practice developed by an actor in a specific working context for reaching the decision. By incremental accumulation of the practices developed by experts, a contextual graph becomes a living experience base with the decision-making process. Such an experience base may be used by experts for collaborative decision-making, or by future experts for training how to behave in the different ways to make a decision according to the variants of the working context. The experience base can be exploited by an intelligent assistant system for proposing an effective support to decision makers by a new type of simulation, compared to previous knowledge-based systems. Several applications have been developed in the last 10 years, including the last two being a project in medicine for supporting pathologists in breast cancer diagnosis, and a project for decision-makers in a command and control room.