改进的非平均传递权值PageRank算法

Improved inequality transfer weight PageRank algorithm

为了有效提高搜索引擎对搜索结果排序的精确性,通过对传统PageRank算法分析,针对父页面平均传递页面权值给它所链接子页面及只考虑其直接链接页面的不足,提出基于深2度页面链接与内容和主题相关性分析的一种父页面非平均传递权值的PageRank算法。该算法有效地解决了搜索引擎对排序结果的权威性要求和相关性要求,使搜索结果排序更符合不同网页浏览者的需求,同时也为进一步扩展PageRank算法提供了新的空间。实验结果表明,改进后的算法可以获得优于传统算法搜索精确度。

To improve the accuracy of the paper analyses,by analyzing traditional PageRank algorithm,an improved PageRank algorithm—inequality transfer weight PageRank algorithm is proposed,which is based on the analysis of deep 2 degrees of links among pages and relevance among topics,in consideration of traditional PageRank algorithm transfer weight equally.The algorithm meets the relevance and authority requirements well of the search engine for the ranking result,which makes the rank of the search result fits all kinds of need.And it also provides new room for extending the algorithm of PangRank.Proved by experiment,better accuracy can be retrieved by the influence of weight factor and deep 2 degree of link.