Developing Troubleshooting Systems Using Ontologies

Development of troubleshooting software is an attractive area of research for agent based system developers. In this project, we attempt to use ontologies extracted from different textual resources to automatically construct a troubleshooting virtual expert. In our solution, we verify the information about the structure of the system extracted from the textual document, then generate a conversation with the user in order to identify the problem and recommend appropriate remedies. To illustrate the approach, we have built knowledge base for a simple use case. A special parser generates conversations that can help the user solve software configuration problems.