Achieving Rapid Knowledge Acquisition in a High- Volume Call Centre

Ripple Down Rules (RDR) has been applied to a number of domains. In this paper we consider a new application area that presents a number of new challenges. Our application is a high-volume call centre that provides a service / help desk function in a complex problem domain. We propose that the combined use of multiple classification ripple-down-rules (MCRDR) together with a web-enabled hyperlinkrich browser front-end will provide an effective tool to help call-centre knowledge workers cut through the potential information overload presented by both intraand inter-nets; speed up the processes of knowledge acquisition and re-use; and assist with decision support and problem resolution. We consider the implementation issues faced by corporations in their transition from a simple call / defect-tracking model to a much enriched knowledge-centered model and we examine the role MCRDR can play in the call-centre context including workflow integration, accessibility, usability, and incentives. In order to improve the fit with our application area, we suggest a number of variations to the MCRDR theme. Our implementation and evaluation of these ideas is ongoing.

[1]  Ray Bareiss,et al.  Exemplar-Based Knowledge Acquisition: A Unified Approach to Concept Representation, Classification, and Learning , 1990 .

[2]  Byeong Ho Kang,et al.  Multiple Classification Ripple Down Rules : Evaluation and Possibilities , 2000 .

[3]  Evangelos Simoudis,et al.  Using case-based retrieval for customer technical support , 1992, IEEE Expert.

[4]  Alexey Tsymbal,et al.  A Review of Explanation and Explanation in Case-Based Reasoning , 2003 .

[5]  Ralph Barletta,et al.  Building a case-based help desk application , 1993, IEEE Expert.

[6]  P. Compton,et al.  A philosophical basis for knowledge acquisition , 1990 .

[7]  Claude Sammut,et al.  An expert system for ion chromatography developed using machine learning and knowledge in context , 1993 .

[8]  Byeong Ho Kang,et al.  Help Desk System with Intelligent Interface , 1997, Appl. Artif. Intell..

[9]  R. Wille.  Concept lattices and conceptual knowledge systems , 1992 .

[10]  Timothy L. Acorn,et al.  Smart: Support: Management Automated Reasoning Technology for Compaq Customer Service , 1992, IAAI.

[11]  Hideo Shimazu,et al.  Case-Based Retrieval Interface Adapted to Customer-Initiated Dialogues in Help Desk Operations , 1994, AAAI.

[12]  G Edwards,et al.  Peirs: A pathologist‐maintained expert system for the interpretation of chemical pathology reports , 1993, Pathology.

[13]  Ghassan Beydoun,et al.  NRDR for the Acquisition of Search Knowledge , 1997, Australian Joint Conference on Artificial Intelligence.

[14]  Mihye Kim,et al.  Document management and retrieval for specialised domains : an evolutionary user-based approach , 2003 .