A multi-agent based intelligent system for Internet shopping

The prosperity of electronic commerce has changed the traditional trading behaviors and more and more people are willing to conduct Internet shopping. This paper presents an agent-based shopping system for Internet commerce. The aim of it is to automate shopping process by assisting customers to have commodity information retrieval and comparison in the massive information environment of the Internet. In this system, several information technologies have been used, including intelligent agent, multi-attribute decision model, preference acquiring model and Web application. The system consists of five types of agents that can interact with each other: interface agent, buyer manager, buyer agent, evaluation agent and preference agent. These agents collaborate with each other by the message delivery mechanism and make the whole system works together. The system framework has been built adopting the technology of the software reuse, thus promoting the reuse of each agent component. The results show that it can provide personalized information services and help customers save enormous time for Internet shopping.