公开(公告)号：US09135658B2

公开(公告)日：2015-09-15

申请号：US14264445

申请日：2014-04-29

Applicant: Palantir Technologies, Inc.

Inventor： Matthew Sprague ,  Michael Kross ,  Adam Borochoff ,  Parvathy Menon ,  Michael Harris

IPC: G06Q40/00 ,  G06Q40/02 ,  G06F17/30 ,  G06Q20/40 ,  G06Q30/00

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: Techniques are disclosed for prioritizing a plurality of clusters. Prioritizing clusters may generally include identifying a scoring strategy for prioritizing the plurality of clusters. Each cluster is generated from a seed and stores a collection of data retrieved using the seed. For each cluster, elements of the collection of data stored by the cluster are evaluated according to the scoring strategy and a score is assigned to the cluster based on the evaluation. The clusters may be ranked according to the respective scores assigned to the plurality of clusters. The collection of data stored by each cluster may include financial data evaluated by the scoring strategy for a risk of fraud. The score assigned to each cluster may correspond to an amount at risk.

Abstract translation: 公开了用于优先考虑多个聚类的技术。 优先化集群通常可以包括识别用于对多个集群进行优先级排序的评分策略。 每个集群都是从种子生成的，并存储使用种子检索的数据集合。 对于每个集群，根据评分策略评估集群存储的数据集合的元素，并根据评估将分数分配给集群。 可以根据分配给多个聚类的各个分数对聚类进行排名。 由每个集群存储的数据的收集可以包括通过得分策略评估的财务数据以获得欺诈的风险。 分配给每个集群的分数可能对应于处于风险中的金额。

公开(公告)号：US20150046870A1

公开(公告)日：2015-02-12

申请号：US14242559

申请日：2014-04-01

Applicant: Palantir Technologies, Inc.

Inventor： Joshua Goldenberg ,  Brian Ngo ,  Bill Dwyer ,  Parvathy Menon ,  Gregory Martin ,  Zach Bush ,  Allen Chang ,  Mike Boland

IPC: G06F3/0481 ,  G06F3/0484

CPC classification number: G06F3/04855 ,  G06F3/0481 ,  G06F3/04812 ,  G06F3/0482 ,  G06F3/04845 ,  G06F3/04847 ,  G06F17/30 ,  G06F17/30994

Abstract: A context-sensitive viewing system is disclosed in which various data visualizations, also referred to a contextual views, of a common set of data may be viewed by a user on an electronic device. Data in the system may comprise data objects and associated properties and/or metadata, and may be stored in one or more electronic data stores. As a user of the system views and manipulates a first contextual view of a set of data objects, one or more other contextual views of the same set of data objects may be updated accordingly. Updates to the secondary contextual views may, in various embodiments, happen real-time. Further, the secondary contextual views may be visible to the user simultaneously with the primary contextual view. A user may switch from one view to another, and may manipulate data in any view, resulting in updates in the other views.

Abstract translation: 公开了一种上下文敏感的观看系统，其中用户可以在电子设备上查看公共数据集的各种数据可视化，也称为上下文视图。 系统中的数据可以包括数据对象和相关联的属性和/或元数据，并且可以存储在一个或多个电子数据存储中。 当系统的用户查看和操纵一组数据对象的第一上下文视图时，可以相应地更新同一组数据对象的一个​​或多个其他上下文视图。 在各种实施例中，辅助上下文视图的更新可以实时发生。 此外，辅助上下文视图可以与主要上下文视图同时对用户可见。 用户可以从一个视图切换到另一个视图，并且可以在任何视图中操纵数据，导致其他视图中的更新。

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。