中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

9 records (took 0.022 seconds)

    User interface for visualization of an attrition value
    1.
    发明授权
    User interface for visualization of an attrition value 有权

    公开(公告)号：US10832218B1

    公开(公告)日：2020-11-10

    申请号：US15091368

    申请日：2016-04-05

    Applicant: Palantir Technologies Inc.

    Inventor： Richard Hsu ,  Brendan Weickert ,  Krishnan Aiyer

    IPC: G06Q10/00 ,  G06Q10/10 ,  G06F17/18 ,  G06Q10/06

    Abstract: Aspects of the present disclosure involve approaches for calculating an attrition value of a population on the probability that attrition will occur within a predefined time period, and additionally, to calculate an individual attrition value of various features of the population based on their contribution to the calculated attrition value of the population. A computer, such as a server, may receive a cohort definition that includes one or more features and corresponding feature values from a third-party data source or client device. A cohort definition defines a subset of users from among the population of users, based on various combinations of features and feature values.

    Trend data clustering
    8.
    发明授权
    Trend data clustering 有权
    趋势数据聚类

    公开(公告)号：US09177344B1

    公开(公告)日：2015-11-03

    申请号：US14139640

    申请日：2013-12-23

    Applicant: Palantir Technologies, Inc.

    Inventor： Harkirat Singh ,  Brendan Weickert ,  Matthew Sprague ,  Michael Kross ,  Adam Borochoff ,  Parvathy Menon ,  Michael Harris

    IPC: G06Q40/00 ,  G06Q40/02

    CPC classification number: G06F17/3053 ,  G06F17/30345 ,  G06F17/30412 ,  G06F17/30539 ,  G06F17/30572 ,  G06F17/30598 ,  G06F17/30601 ,  G06F17/30604 ,  G06F17/30699 ,  G06F17/30705 ,  G06F17/3071 ,  G06F17/30867 ,  G06Q10/10 ,  G06Q20/4016 ,  G06Q30/0185 ,  G06Q40/00 ,  G06Q40/02 ,  G06Q40/025 ,  G06Q40/10 ,  G06Q40/123

    Abstract: In various embodiments, systems, methods, and techniques are disclosed for generating a collection of clusters of related data from a seed. Seeds may be generated based on seed generation strategies or rules. Clusters may be generated by, for example, retrieving a seed, adding the seed to a first cluster, retrieving a clustering strategy or rules, and adding related data and/or data entities to the cluster based on the clustering strategy. Various cluster scores may be generated based on attributes of data in a given cluster. Further, cluster metascores may be generated based on various cluster scores associated with a cluster. Clusters may be ranked based on cluster metascores. Various embodiments may enable an analyst to discover various insights related to data clusters, and may be applicable to various tasks including, for example, tax fraud detection, beaconing malware detection, malware user-agent detection, and/or activity trend detection, among various others.

    Abstract translation: 在各种实施例中，公开了用于从种子生成相关数据集合的集合的系统，方法和技术。 可以根据种子生成策略或规则生成种子。 可以通过例如检索种子，将种子添加到第一群集，检索群集策略或规则，以及基于聚类策略将相关数据和/或数据实体添加到群集来生成群集。 可以基于给定簇中的数据的属性来生成各种聚类分数。 此外，可以基于与集群相关联的各种聚类分数来生成集群组合。 群集可能会根据群集元素进行排名。 各种实施例可以使分析人员能够发现与数据集群相关的各种见解，并且可以适用于各种任务，包括例如税欺诈检测，信标恶意软件检测，恶意软件用户代理检测和/或活动趋势检测 其他。

    Malware data clustering
    9.
    发明授权
    Malware data clustering 有权
    恶意软件数据集群

    公开(公告)号：US08788407B1

    公开(公告)日：2014-07-22

    申请号：US14139603

    申请日：2013-12-23

    Applicant: Palantir Technologies, Inc.

    Inventor： Harkirat Singh ,  Geoff Stowe ,  Brendan Weickert ,  Matthew Sprague ,  Michael Kross ,  Adam Borochoff ,  Parvathy Menon ,  Michael Harris

    IPC: G06Q40/00

    CPC classification number: G06F17/3053 ,  G06F17/30345 ,  G06F17/30412 ,  G06F17/30539 ,  G06F17/30572 ,  G06F17/30598 ,  G06F17/30601 ,  G06F17/30604 ,  G06F17/30699 ,  G06F17/30705 ,  G06F17/3071 ,  G06F17/30867 ,  G06Q10/10 ,  G06Q20/4016 ,  G06Q30/0185 ,  G06Q40/00 ,  G06Q40/02 ,  G06Q40/025 ,  G06Q40/10 ,  G06Q40/123

    Abstract: In various embodiments, systems, methods, and techniques are disclosed for generating a collection of clusters of related data from a seed. Seeds may be generated based on seed generation strategies or rules. Clusters may be generated by, for example, retrieving a seed, adding the seed to a first cluster, retrieving a clustering strategy or rules, and adding related data and/or data entities to the cluster based on the clustering strategy. Various cluster scores may be generated based on attributes of data in a given cluster. Further, cluster metascores may be generated based on various cluster scores associated with a cluster. Clusters may be ranked based on cluster metascores. Various embodiments may enable an analyst to discover various insights related to data clusters, and may be applicable to various tasks including, for example, tax fraud detection, beaconing malware detection, malware user-agent detection, and/or activity trend detection, among various others.

    Abstract translation: 在各种实施例中，公开了用于从种子生成相关数据集合的集合的系统，方法和技术。 可以根据种子生成策略或规则生成种子。 可以通过例如检索种子，将种子添加到第一群集，检索群集策略或规则，以及基于聚类策略将相关数据和/或数据实体添加到群集来生成群集。 可以基于给定簇中的数据的属性来生成各种聚类分数。 此外，可以基于与集群相关联的各种聚类分数来生成集群组合。 群集可能会根据群集元素进行排名。 各种实施例可以使分析人员能够发现与数据集群相关的各种见解，并且可以适用于各种任务，包括例如税欺诈检测，信标恶意软件检测，恶意软件用户代理检测和/或活动趋势检测 其他。

Patent Agency Ranking