Web Mining in the EVA Intelligent Agent Architecture

This paper describes the architecture of the fourth version of the Evolutionary Virtual Agent (EVA). This new light-weight java-based implementation is based on a dynamical rule-based subsumption architecture, an XML knowledge base and a scheme kernel for scripting behavior rules. Using this architecture, the agent is able to answer questions in natural language while learning a user’s profile. It also extracts relevant information from the web through search engines queries and use them in the flow of conversation. This paper describes the architecture and analyses its web mining process.

• Type: Conference
• Year: 2007
• Where: IAT
• Authors: Philippe Millet, Jean-Claude Heudin
• Keywords: Evolutionary Virtual Agent, IAT 2007, Intelligent Agent, Light-weight Java-based Implementation, Rule-based Subsumption Architecture