首页> 外国专利> A non - hierarchical data analysis method by data mining

A non - hierarchical data analysis method by data mining

机译:一种数据挖掘的非分层数据分析方法。

摘要

In the method of analyzing non-hierarchical data by data mining of the present invention, N constituent factors are classified into M clusters, and the distance between two clusters is arbitrarily defined as the shortest distance among the distances between any two data belonging to each cluster. After grouping the clusters with similarity, the given data is grouped into K clusters, and the difference between each cluster and the distance is minimized. The present invention is hypothesized by classifying N constituent factors into M clusters and randomly defining the distance between two clusters as the shortest distance among the distances between any two data belonging to each cluster, and grouping the clusters having the highest similarity. The hypothesis of discovering itself has a remarkable effect of providing a non-hierarchical technique applying the data mining method of discovering itself.
机译:在本发明的通过数据挖掘来分析非分层数据的方法中,将N个构成因素分类为M个簇,并且将两个簇之间的距离任意地定义为属于每个簇的任何两个数据之间的距离中的最短距离。 。在将相似度的聚类分组后,将给定的数据分组为K个聚类,并且将每个聚类与距离之间的差异最小化。通过将N个构成因素分类为M个聚类并且将两个聚类之间的距离随机定义为属于每个聚类的任何两个数据之间的距离中的最短距离,并且将具有最高相似性的聚类进行分组来假设本发明。发现自己的假设具有显着的效果,即使用发现自己的数据挖掘方法提供一种非分层技术。

著录项

  • 公开/公告号KR20200080957A

    专利类型

  • 公开/公告日2020-07-07

    原文格式PDF

  • 申请/专利权人 동서대학교 산학협력단;

    申请/专利号KR20180170976

  • 发明设计人 황기현;

    申请日2018-12-27

  • 分类号G06F16/35;G06N5/02;

  • 国家 KR

  • 入库时间 2022-08-21 11:06:30

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