Case-based reasoning offers special advantages for continuous control applications, but these applications also have special requirements that demand extensions to the case based reasoning paradigm This article describes a case-based reasoning support system for control of telephone traffic and examines issues it raises. We present different stages of the methodological approach, based on knowledge acquisition and case-based reasoning, developed to design the diagnosis support system and trace their motivation to the requirements of a continuous control application. The specific domain which we are applying knowledge acquisition and case-based reasoning to is the management of traffic flow in the standard urban public switched telephone network of the Ile de France. Main research objective is to place at the network managers disposal an intelligent system able to capitalize and re-use past incidents, in order to assist them in their diagnosis and decision-making activities. This system is developed within an interdisciplinary research co-operation supported by the CNET (the France Telecom research centre) and the CNRS (the French National Board for Scientific Research).
Design methodology, activity analysis, knowledge modelling, case-based reasoning, incident case, diagnosis support system, network traffic control..
All articles published by Studies in Informatics and Control (SIC) are published in accordance with the terms and conditions of the Creative Commons Attribution License (CC BY-NC-SA 4.0).