基于K-Means的搜索结果聚类方法  

A Search Results Clustering Method Based on K-Means

作　　者：刘宇征 邵家玉[1] 

机构地区：[1]东南大学自动化学院,江苏南京210096

出　　处：《工业控制计算机》2018年第3期65-66,69,共3页Industrial Control Computer

摘　　要：K-Means算法是一种常用的聚类算法。通过分析传统K-Means聚类算法可知,该算法随机选取聚类中心并需要手动设定聚类个数,因此容易出现局部最优、稳定性差,适用范围窄的问题。为了改善聚类结果,对K-Means算法进行了改进,根据文本距离确定初始聚类中心,并在初始聚类完成后,对聚类进行合并,形成最终的聚类结果。实验结果表明,改进后的K-Means算法提高了聚类的查准率和查全率。K-Means algorithm is one of common clustering algorithms.Through the analysis of the traditional K-Means algorithm,the algorithm selects the cluster center randomly and set the number of clusters manually,so it has deficiencies of local optimum,poor stability and narrow application range.In order to improve the clustering results,this paper improves K-Means clustering algorithm.The initial clustering centers are determined according to the text distance and the clusters are merged after the initial clustering is completed to form the final clustering results.

关 键 词：搜索结果 聚类 K-MEANS 聚类中心 合并聚类 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]