Personalized scheduling algorithm based on user profile for meta search engine;

This paper combines document concept set with semantic concept hierarchy tree which has been defined in adance to establish each branch s standardization expression in the concept hierarchy tree through machine learning,and excavates the theme semantic concept set in document,and maps the concept to concept hierarchy tree to establish the user profile model.

By mining the user profile in client computer,then combining user profile and traditional LCA,the method could resolve the defect of LCA.

Information based on user interest model of personalized service system

This paper combines user interest model and Web service discovery,puts forward a model which can satisfy users individuation requirement.

An improved method which can be used to transfer Viewingtime into user interest level nonlinearly.

During the course of searching, It integrates users interests by using agent technology.

Then,the problem of acquiring users interests,storage method of users interests,personal search model based on vector space and realization of personal history records are solved.

Combine with that,quantitative relations of this two behaviors and user interest degree is proposed.

The experiments used to real data set show web log mining algorithm adding user interest degree is effective and feasible.

The concepts of user interests and their transitions,and the structure of UIDB(shorted for user interests database) are presented,the issues about how to implement are investigated,and those about how to create UIDB by user answers selections,update and refine UIDB by user s feedback information,and the analysis and mining of the data in web sever LOG files are discussed in this paper.