针对Pagerank算法在Web结构挖掘中存在的需要大量迭代的问题,提出一种新的方法.该方法通过对原始Pagerank值的计算公式进行改进,降低了迭代次数.实验表明,在云计算环境下,新方法减少了网络通信和访问HDFS的消耗,在时间花费上优于传统的Pagerank算法.
With the advent of the era of cloud computing, it is a new important research topic to discuss the problem of the web mining based the cloud computing. A new method is proposed to solve the large number of iterations problems in the Web structure mining for the Pagerank algorithm. Through improving the formula of the original pagerank value, it reduces the number of iterations. The experiments show that this method reduces the network traffic and the consumption of accessing HDFS in the cloud computing enviroment, and it is superior to the original Pagerank algorithm in the time consumption.