| PageRank算法的并行实现 |
| |
| 引用本文： | 闫建红.PageRank算法的并行实现[J].太原师范学院学报(自然科学版),2014(2):53-57. |
| |
| 作者姓名： | 闫建红 |
| |
| 作者单位： | 太原师范学院计算机科学与技术系,山西太原030012 |
| |
| 基金项目： | 山西省大学生创新项目; 山西省科技基础条件平台建设项目（2012091003-0104）; 山西省科技攻关计划项目（20110321024-02） |
| |
| 摘 要： | 针对当前大数据时代的背景,信息数据的海量化现象与日俱增,为了实现数据搜索的低成本、高效率,对Google搜索引擎的PageRank算法进行了综合性的研究分析,分别介绍了MapReduce框架和Hadoop实现平台,在此基础上,在Hadoop平台详细分析了基于MapReduce的PageRank算法的并行实现过程,以实现海量数据的并行处理,极大地提高了搜索引擎的性能.
|
| 关 键 词： | 搜索引擎 PageRank 并行实现 Hadoop MapReduce |
Parallel Implementation of PageRank |
| |
| Yan Jianhong.Parallel Implementation of PageRank[J].Journal of Taiyuan Normal University:Natural Science Edition,2014(2):53-57. |
| |
| Authors: | Yan Jianhong |
| |
| Institution: | Yan Jianhong (Department of Computer Science, Taiyuan Normal University, Taiyuan 030012,China) |
| |
| Abstract: | Under the background of the big data,the information data quantity grows with each passing day.To enhance the efficiency and lower cost,the PageRank algorithm of the Google＇s Search Engine is studied.The paper introduces MapReduce frame and Hadoop platform,and analyzes parallel processing of the PageRank algorithm based on the MapReduce which runs in the Hadoop.It greatly improved the quality and the efficiency of the Google＇s Search Engine. |
| |
| Keywords: | search engine Page Rank parallel implementation Hadoop MapReduce |
| 本文献已被 CNKI 维普 等数据库收录！ |
