A CBR application: service productivity improvement by sharing experience

Field service is now recognized as one of the most important corporate activities in order to improve customer satisfaction and to compete successfully world-wide competition. Sharing repair experience with a state-of-the-art computer technology is a key issue to improve the productivity of field service. We have developed a diagnostic expert system, named Doctor, which employs case-based reasoning (CBR) and lists the most necessary ten service parts from a product type and some symptoms acquired from a service-request call. In this paper, we describe the Doctor system and explain how accurate and reliable product-type case-bases are generated and updated from the troubleshooting experience and the generic case base, i.e., general diagnostic knowledge. We also demonstrate the effectiveness of our system with experimental results using real repair cases.<<ETX>>

[1]  Mary Czerwinski,et al.  Compaq Quicksource: Providing the Consumer with the Power of AI , 1993, AI Mag..

[2]  Benjamin J. Kaipers,et al.  Qualitative Simulation , 1989, Artif. Intell..

[3]  Shigenobu Kobayashi,et al.  Knowledge compilation and refinement for fault diagnosis , 1991, IEEE Expert.

[4]  A. Rewari AI in corporate service and support , 1993 .

[5]  Paul S. Rosenbloom,et al.  Improving Rule-Based Systems Through Case-Based Reasoning , 1991, AAAI.

[6]  R. L. Kashyap,et al.  Diagnosing novel faults , 1989, Proceedings. Second International Conference on Data and Knowledge Systems for Manufacturing and Engineering.

[7]  Larry A. Rendell,et al.  The Feature Selection Problem: Traditional Methods and a New Algorithm , 1992, AAAI.

[8]  J. Ross Quinlan,et al.  Decision trees and decision-making , 1990, IEEE Trans. Syst. Man Cybern..

[9]  Kristian J. Hammond,et al.  CHEF: A Model of Case-Based Planning , 1986, AAAI.