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.