To Developed Tool, an Intelligent Agent for Automatic Knowledge Acquisition in Rule-based Expert System

Abstract

The complex stage in building expert system is knowledge acquisition from domain experts and translated it to representation approach in knowledge base of expert system. In this paper we present an automatic way to extract knowledge from domain experts directly and converted it to facts and rules in knowledge base for rule-based expert system using intelligent agent. That means, the construct of proposed system consists of three steps, in first step we are construct a Diagnosis Domain Tool for Expert System (DDTES) (a piece of software which contains the user interface, inference engine and a format for declarative knowledge in knowledge base). Secondly we are construct Knowledge Acquisition Agent (KAA) able to interview with domain experts to extract problem solving knowledge in specific diagnosis domain and converted it to production rules in knowledge base. Finally we captured complete rule-based expert system from combination the results of two previous steps which can works and produce advices in that domain. The proposed (DDTES) and (KAA) are implemented and executed by using Visual Prolog programming language Ver.7.1.