首页> 外国专利> METHOD OF CLUSTERING MULTI-DIMENSIONAL RELATED DATA IN A COMPUTER DATABASE BY COMBINING THE TWO VERTICES OF A GRAPH CONNECTED BY AN EDGE HAVING THE HIGHEST SCORE

METHOD OF CLUSTERING MULTI-DIMENSIONAL RELATED DATA IN A COMPUTER DATABASE BY COMBINING THE TWO VERTICES OF A GRAPH CONNECTED BY AN EDGE HAVING THE HIGHEST SCORE

机译:通过结合具有最高得分的边缘连接的两个图形在计算机数据库中聚类多维相关数据的方法

摘要

A method of clustering multi-dimensional relateddata performed by identifying features from a collectionof data, each of said features being represented by avertex (31, 32, 33, 34, 35), selecting pairs of featuresthat it is desirable to cluster together, connecting the pairof vertices representing every selected pair of featuresby an edge (40, 41, 42, 43), assigning a score to everyedge according to a predetermined formula, selectingan edge having the highest score, creating a new vertexby merging the vertices connected by the selected edge(17), creating new edges between the new vertex andthe vertices previously connected to the merged vertices,and repeating this procedure until every edge has apredetermined score.
机译:多维关联的聚类方法通过识别集合中的特征执行的数据数据,每个上述特征由一个顶点(31、32、33、34、35),选择特征对希望将它们聚集在一起,将线对连接起来代表每个选定特征对的顶点的集合边缘(40、41、42、43),为每个根据预定公式计算边缘,选择得分最高的边,创建一个新顶点通过合并由选定边连接的顶点(17),在新顶点和先前连接到合并顶点的顶点,并重复此过程,直到每个边缘都有一个预定分数。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号