利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

9 条记录 (耗时 0.018 秒)

    SYSTEM FOR ANONYMIZING AND AGGREGATING PROTECTED INFORMATION
    1.
    发明申请
    SYSTEM FOR ANONYMIZING AND AGGREGATING PROTECTED INFORMATION 有权
    用于不间断和聚集保护信息的系统

    公开(公告)号：US20160342812A1

    公开(公告)日：2016-11-24

    申请号：US14716154

    申请日：2015-05-19

    申请人： Accenture Global Services Limited

    发明人： Cecil O'Dell Lynch ,  Dennis James Carroll ,  Andrew John Truscott ,  German Acuna

    IPC分类号： G06F21/62 ,  G06F17/30 ,  H04L9/32 ,  G06F19/00

    CPC分类号： G06F21/6254 ,  G06F17/30598 ,  G06F17/30604 ,  G06F19/00 ,  G16H10/60 ,  H04L9/3242 ,  H04L63/0407 ,  H04L63/0421 ,  H04L2209/24 ,  H04L2209/42 ,  H04W12/02

    摘要： A system for anonymizing and aggregating protected information (PI) from a plurality of data sources includes a master index server coupled to a data repository. The master index server receives an anonymized records associated with an individual from a plurality of data hashing appliances. The system includes a cluster matching engine that applies a plurality of rules to hashed data elements of the received record for comparing hashed data elements of the record with hashed data elements of a plurality of clusters of anonymized records associated with different individuals stored in the data repository to determine whether the individual associated with the received record corresponds to an n) individual associated with one of the clusters of anonymized records. When a match is found, the cluster matching engine adds the received record to the cluster of anonymized records associated with that individual.

    摘要翻译： 用于从多个数据源中匿名化和聚合保护信息（PI）的系统包括耦合到数据存储库的主索引服务器。 主索引服务器从多个数据哈希装置接收与个人相关联的匿名记录。 该系统包括集群匹配引擎，其将多个规则应用于所接收的记录的散列数据元素，用于将记录的散列数据元素与存储在数据存储库中的不同个体相关联的多个匿名记录簇的散列数据元素进行比较 以确定与所接收的记录相关联的个体是否对应于与匿名记录的聚类之一相关联的n个个体。 当找到匹配时，集群匹配引擎将接收的记录添加到与该个人相关联的匿名记录的集群中。

    System for anonymizing and aggregating protected information
    6.
    发明授权
    System for anonymizing and aggregating protected information 有权

    公开(公告)号：US10346640B2

    公开(公告)日：2019-07-09

    申请号：US15803316

    申请日：2017-11-03

    申请人： Accenture Global Services Limited

    发明人： Cecil O'Dell Lynch ,  Dennis James Carroll ,  Andrew John Truscott ,  German Acuna

    IPC分类号： G06F17/00 ,  H04L29/06 ,  G06F21/62 ,  G06F16/28 ,  H04W12/02 ,  H04L9/32 ,  G16H10/60

    摘要： A system for anonymizing and aggregating protected information (PI) from a plurality of data sources includes a master index server coupled to a data repository. The master index server receives an anonymized records associated with an individual from a plurality of data hashing appliances. The system includes a cluster matching engine that applies a plurality of rules to hashed data elements of the received record for comparing hashed data elements of the record with hashed data elements of a plurality of clusters of anonymized records associated with different individuals stored in the data repository to determine whether the individual associated with the received record corresponds to an individual associated with one of the clusters of anonymized records. When a match is found, the cluster matching engine adds the received record to the cluster of anonymized records associated with that individual.

    Versatile Data Model
    8.
    发明申请
    Versatile Data Model 审中-公开
    多功能数据模型

    公开(公告)号：US20160063043A1

    公开(公告)日：2016-03-03

    申请号：US14472932

    申请日：2014-08-29

    申请人： Accenture Global Services Limited

    发明人： Dennis Carroll ,  Cecil Lynch ,  German Acuna ,  Anh-Hoang Vo ,  Thomas D. Perry

    IPC分类号： G06F17/30

    CPC分类号： G06F16/2246 ,  G06F16/212 ,  G06F16/25 ,  G06F16/282

    摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing a data model, a data file and user input to provide a populated data model, the populated data model including: a data content table having one or more navigation columns and one or more content columns, at least one navigation column including one or more key values of a key node, and at least one content column including data values of a plurality of data values, and a foreign key table having one or more navigation columns and one or more relationship columns, at least one navigation column including one or more key values of a foreign key node, and the one or more relationship columns associating at least one key node of the data content table to a respective foreign key node.

    摘要翻译： 方法，系统和装置，包括在计算机存储介质上编码的用于处理数据模型的计算机程序，数据文件和用户输入以提供填充的数据模型，所填充的数据模型包括：具有一个或多个 导航列和一个或多个内容列，包括关键节点的一个或多个键值的至少一个导航列，以及包括多个数据值的数据值的至少一个内容列，以及包含多个数据值的外键列 导航列和一个或多个关系列，包括外键节点的一个或多个键值的至少一个导航列，以及将数据内容表的至少一个关键节点与各个外键节点相关联的一个或多个关系列 。

    Predictive Model Generator
    9.
    发明申请
    Predictive Model Generator 审中-公开
    预测模型发生器

    公开(公告)号：US20160055412A1

    公开(公告)日：2016-02-25

    申请号：US14464330

    申请日：2014-08-20

    申请人： Accenture Global Services Limited

    发明人： Dennis Carroll ,  Cecil Lynch ,  German Acuna ,  Anh-Hoang Vo

    IPC分类号： G06N5/04 ,  G06F19/00

    CPC分类号： G06N5/04 ,  G16H50/20 ,  G16H50/30 ,  G16H50/70

    摘要： Methods, systems, and apparatuses, including computer programs encoded on a computer storage medium, can be implemented to perform actions including receiving input data defining a predictive model, the predictive model including multiple features. The actions further include weighting the predictive model iteratively for each feature, using actual data including values for each feature for multiple entities within a population, by iteratively adjusting a current weight for the feature by a momentum until the momentum equals zero, the momentum being iteratively adjusted by a momentum factor based on whether a model score improves, the model score being calculated based on the actual data. The actions further include calculating a value score for the entity using the weighted predictive model.

    摘要翻译： 可以实现包括在计算机存储介质上编码的计算机程序的方法，系统和装置，以执行包括接收定义预测模型的输入数据的动作，所述预测模型包括多个特征。 动作进一步包括通过使用动量等于零的动量迭代地调整特征的当前权重，使用实际数据包括群体内的多个实体的每个特征的值来迭代地对每个特征加权预测模型，该动量被迭代地 根据模型得分是否改善，通过动量因子进行调整，模型得分根据实际数据计算。 这些动作进一步包括使用加权预测模型计算实体的价值得分。