ONTOLOGY-BASED KNOWLEDGE CAPTURE FOR ENGINEERING KNOWLEDGE MANAGEMENT SYSTEMS

摘要

The objective of this paper is to introduce a framework for developing an Automatic Ontology-Based Knowledge Capture System. First, the tacit knowledge will be captured from experts of domain knowledge and stored as Ontology. The proposed methodology to support the process of capturing tacit knowledge is based on Group Technology, Formal Concept Analysis, Ontology Engineering and relevant technologies. This captured tacit knowledge will be then used by an Ontology-Based Knowledge Extraction (OBKE) tool to automatically extract data, information and knowledge from unstructured engineering documents (i.e. capture explicit knowledge). Different from the other approaches, this tool allows data to be extracted from the view point of an expert of the domain by using an Ontology model, which is constructed by experts of domain, as a 'filter' to extract data from 'the flow of words' on a given unstructured engineering document. By following this way, data will be extracted with respect to domain knowledge faster and more efficiently than other approach. By matching the obtained semantic annotations with the concepts and properties in the Ontology model, the desired data will be extracted to support populating Ontology. In this paper, knowledge and domain of TFT-LCD display is selected as a target and object from which an OBKE tool is built up to help an Engineering Knowledge Management System to carry out the tasks.