Knowledge Acquisition Advisor (KA 2): An interactive knowledge-acquisition tool for expert system development

Abstract

A new interactive knowledge acquisition tool, called Knowledge Acquisition Advisor (KA 2), is presented in this paper. The new tool will help knowledge engineers to conduct effective knowledge-elicitation interviews with domain experts through structured knowledge acquisition for both analytic and synthetic problems. A graphic modeling data structure, called Knowledge Graph is proposed, which allows knowledge engineers to model domain problems with their images and understanding. By using Knowledge Graph, knowledge engineers are able to decompose a domain problem into several components, to model the feature of each component, and to explore their relations by linking them with sets of questions. These questions can later be employed to guide the KA interview. Moreover, KA 2 is particularly useful for interview through computer networks, so the knowledge acquisition can take place remotely.