基于云平台的大数据资源挖掘技术研究  

Research on Large Data Resource Mining Technology Based on Cloud Platform

作　　者：薛蓓[1] 周延怀[1] 王晓兰[1] 

机构地区：[1]南京师范大学泰州学院,江苏泰州225300

出　　处：《计算机测量与控制》2017年第12期275-278,共4页Computer Measurement &Control

基　　金：2015年泰州市软科学研究计划项目(RKX201529)

摘　　要：针对云平台下大数据资源挖掘过程准确率低、耗时长等问题,对大数据资源挖掘技术进行改进研究;利用MST聚类法对云平台数据集进行预处理,根据数据间的关联性来增强检测结果,并提高数据索引效率,将数据间的邻接矩阵作为边的权值,生成全图的MST,获取评价数据资源挖掘准确度的标准,并得到k个最小生成子树,其中的一个子树就是数据集最优聚类结果;实验结果表明,所提方法有效提高了大数据挖掘准确性,使得数据资源得到了更高效的利用。In order to solve the problem of low precision and long time consuming in mining large data resources under the cloud plat- form, the mining technology of large data resources is improved. Preprocessing of the cloud platform data sets using MST clustering method to enhance the detection results according to the relevance between data and data, improve the efficiency of the index, the adjacency matrix data as edge weights, generating graph MST, obtain evaluation data mining accuracy standard, and get k a minimum spanning tree. The re- sults of the optimal clustering a sub tree, which is the data set. Experimental results show that the proposed method effectively improves the accuracy of large data mining, and makes data resources more efficient.

关 键 词：云平台 数据资源 挖掘 技术改进 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]