Intelligent Agent and pattern matching
We propose a conversational agent that can act as a virtual representative of a web site interacting with visitors using natural languages. The agent consists of three main components: dialogue act categorization, structured pattern matching, and knowledge construction and representation. Dialogue acts are identified by automata which accept sequences of keywords defined for each of the dialogue acts. We use these DAs to identify the user’s intention. To make the DA analysis process more effective, subsumption architecture is used to control the interactions among the DA analysis modules. Pattern matching is used for matching the queries with responses rather than the conventional natural language processing techniques, where DA, keywords extracted from DA analysis, and the query are used. We apply this agent to the introduction of a web site. The results show that the conversational agent has the ability to present more adequate and friendly response.