首页> 外国专利> Anonymization Device for Preserving Utility of Data and Method thereof

Anonymization Device for Preserving Utility of Data and Method thereof

机译:保存数据效用的匿名化装置及其方法

摘要

Disclosed is an anonymizing device. The anonymizing device includes a generalization unit generalizing a record by expanding a range of data of a quasi-identifier among the data of the record about an individual which comprises at least one piece of data individually classified by the quasi-identifier or sensitive attribute. The generalization unit generalizes that a first generalization level of the generalized record is equal to or less than a predetermined value. The generalized data of each of the generalized record has a second generalization level determined in accordance with the ratio of difference between the maximum and minimum values of a numerical attribute domain and the difference of the maximum and minimum values of the data generalized when the quasi-identifier is a numerical attribute. When the quasi-identifier is a categorical attribute, each generalized data of the generated record has a second generalization level determined in accordance with the ratio of the value in which 1 is subtracted from the number of leaf nodes of a classification tree about the categorical attribute to a value in which 1 is subtracted from the leaf node of the node corresponding to the generalized data in the classification tree. The first generalization level is defined as the value in which a sum of the second generalization level is divided by a number (n) of the quasi-identifier. The predetermined value is a real number in a range of 0 to 1. The purpose of the present invention is to provide the anonymizing device preventing anonymized data from being excessively generalized.
机译:公开了一种匿名设备。匿名化装置包括通过扩展关于个人的记录数据中的准标识符的数据范围来概括记录的概括单元,该个体的数据包括至少一个由准标识符或敏感属性单独分类的数据。概括单元概括概括化记录的第一概括级别等于或小于预定值。每个广义记录的广义数据都具有第二泛化级别,该泛化级别根据数值属性域的最大值和最小值之差与准值时广义化的数据的最大值和最小值之差之比确定。标识符是数字属性。当准标识符是分类属性时,生成的记录的每个广义数据都具有第二泛化级别,该第二泛化级别根据与分类属性有关的分类树的叶节点数减去1的值的比率确定取一个值,其中从与分类树中的广义数据对应的节点的叶节点减去1。第一泛化等级被定义为其中第二泛化等级的总和除以准标识符的数量(n)的值。预定值是0到1范围内的实数。本发明的目的是提供一种防止匿名数据被过度泛化的匿名设备。

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