用时效曲线拟合改进PageRank算法  

An Improvement of PageRank Algorithm Based on the Curve Fitting of Aging

作　　者：白似雪[1] 万晶[1] 

机构地区：[1]南昌大学计算机科学与技术系,江西南昌330031

出　　处：《南昌大学学报（工科版）》2009年第3期234-237,251,共5页Journal of Nanchang University(Engineering & Technology)

基　　金：国家自然科学基金资助项目(60863002)

摘　　要：简要分析了PageRank的思想及其优缺点。基于信息时效性特征,对Web资源的几类典型的时效曲线变化规律进行了研究。采用分段曲线拟合的形式得到Web页面的时效重要度计算方法,同时给出了Web页面信息时效重要度模型。并与传统的PageRank算法相结合,对Web页面的排序方法进行了改进。该模型对页面的排序有明显的改善,其结果较好地满足了查询者的心理期待。The ideas and the advantages and disadvantages of the PageRank algorithm are briefly analyzed in this paper. It studies the changing regulations of some typical aging curve of Web sources based on the aging features of information, gets the calculation method for the aging importance of Web pages using sub-curve fitting. A model is given to describe the importance of Web pages. This method is used to improve web pages ranking method combined with the traditional PageRank algorithm. The model can improve the ranking of Web pages obviously, the results of the query can well meet the psychology expects.

关 键 词：PAGERANK 时效性 曲线拟合 WEB结构挖掘 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]