基于聚类分析算法的海量关系数据可视化技术研究

The study on massive relational data visualization technology based on clustering analysis algorithm

信息可视化及大数据可视化主要研究大规模非数值型信息资源的视觉展示,以达到帮助人们理解并分析数据。基于对海量的关系型数据进行有效挖掘的目的,采用将数据挖掘领域的聚类分析算法与力导引布局算法相结合的方法,提出了一种新的基于聚类分析算法的海量数据可视化方法。针对关系数据集做简单的统计和对比分析,然后通过聚类分析算法对其进行分簇,将得到的各主节点和权重、关系等数据通过力导引算法,写入弹性图布局中,最后基于图可视化的判断标准画出图布局的基本架构。通过ECharts和D3.js作为数据可视化呈现工具,并进行合理的质量评价,在选取10 000个数据情况下准确率达到了89%,证明了所提算法的快速性以及准确性。

Visualization of information and visualization of large data mainly focus on the visual display of large-scale non numerical information resources to help people understand and analyze data. The effective mining of massive relational data based on the method of data mining,clustering analysis algorithm and force field guide layout algorithm,proposes a new clustering algorithm based on data visualization method. According to the relationship between the data sets do simple statistics and comparative analysis,and then through the clustering algorithm on the cluster,will be the main node and weight,the relationship between data through the force directed algorithm,write elastic graph layout,finally based on graph visualization criteria to draw the basic framework of the layout. Through ECharts and D3.js as data visualization tools and reasonable quality evaluation,the accuracy rate of 10000 data cases is 89%,which proves the rapidity and accuracy of the proposed algorithm.