Efficient Knowledge Base Construction Mechanism Based on Knowledge Map and Database Metaphor

  • Kim, Jin-Sung (School of Business Administration Jeonju University) ;
  • Lee, Kun-Chang (School of Business Administration Sungkyunkwan University) ;
  • Chung, Nam-Ho (Department of Business Administration Chungju National University)
  • Published : 2004.05.21

Abstract

Developing an efficient knowledge base construction mechanism as an input method for expert systems (ES) development is of extreme importance due to the fact that an input process takes a lot of time and cost in constructing an ES. Most ES require experts to explicit their tacit knowledge into a form of explicit knowledge base with a full sentence. In addition, the explicit knowledge bases were composed of strict grammar and keywords. To overcome these limitations, this paper proposes a knowledge conceptualization and construction mechanism for automated knowledge acquisition, allowing an efficient decision. To this purpose, we extended traditional knowledge map (KM) construction process to dynamic knowledge map (DKM) and combined this algorithm with relational database (RDB). In the experiment section, we used medical data to show the efficiency of our proposed mechanism. Each rule in the DKM was characterized by the name of disease, clinical attributes and their treatments. Experimental results with various disease show that the proposed system is superior in terms of understanding and convenience of use.

Keywords