This paper describes a web page recommendation model for the semantic web which collects the annotation information in the web pages, uses the annotations to classify the web pages and stores the web page s uniform resource locator and its type in a database.

In this paper, we designed an intelligent web page recommender system, which include three sub-systems of data preprocessing, clustering, and web page recommendation.

The Web page recommendation systems can effectively predict users\' next clicking results in information retrieval process and the research will be beneficial to many applications ranging from intelligent recommendation to improving effectiveness of search engines.

The algorithm possesses preferable speed of response to satisfy the need of real time web page recommendation and also can be executed without training in advance.

Furthermore, technologies are presented of users online testing method and personalized page distribution as well as roaming among different areas.

A new clustering algorithm based on competitive agglomeration was proposed to improve Web user s efficiency and get useful personalized Web recommending.