An agent-based design of a NL-interaction for intelligent assistance in an e-commerce scenario

The work described in this paper is comprised in the ADVICE project, which consists of the development of a new interface for a craftsmanship tools e-commerce system. One of the main aspects of the buying-selling interaction in the web is the capability of the web site of generating some kind of trust feeling in the buyer, just like a human shop assistant would do in a person-to-person interaction. Things like understanding the buyer needs, being able to give him technical advice, assisting him in the final decision are not easy things to achieve in a web selling site. Natural language (NL) techniques can play a crucial role in providing this kind of enhancements. Another good motivation to integrate natural language technology in this kind of sites is to make the interaction easy to those people less confident with the Internet or even computer technologies. Inexperienced users feel much more comfortable expressing themselves and receiving information in natural language rather than through the human standard ways. This paper is devoted to show the current state of the Natural Language Component of the Interface Agent and the Interaction Agent in the developed prototype that supports the intelligent assistance by complementing the current shop system functionality