Development of an intelligent agent system modeling

It is a complex and repeated procedure to search some appropriate information. Moreover, because the user's interests are changed as time goes, the real time modeling of a user's interests should be necessary. In this paper, we propose IREA system that can search and filter documents that users are interested from the Web. And then it constructs the user's interest model by a modified spreading neural network. Based on this network. IREA can easily produce some queries to search Web documents, and it ranks them. The conventional spreading neural network doesn't have a visualization function, so that the users couldn't know how to be configured his or her interest model by the network. To solve this problem, IREA gives a visualization function being shown how to be made his interest user model to many users.