-
公开(公告)号:US12238136B2
公开(公告)日:2025-02-25
申请号:US18504392
申请日:2023-11-08
Applicant: Palantir Technologies Inc.
Inventor: Harkirat Singh , Geoffrey Stowe , Stefan Bach , Matthew Sprague , Michael Kross , Adam Borochoff , Parvathy Menon , Michael Harris
IPC: G06Q40/00 , G06F16/23 , G06F16/242 , G06F16/2457 , G06F16/2458 , G06F16/26 , G06F16/28 , G06F16/335 , G06F16/35 , G06F16/355 , G06F16/9535 , G06Q10/10 , G06Q20/38 , G06Q20/40 , G06Q30/018 , G06Q40/02 , G06Q40/03 , G06Q40/10 , G06Q40/12 , H04L9/40
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.
-
公开(公告)号:US20240146761A1
公开(公告)日:2024-05-02
申请号:US18504392
申请日:2023-11-08
Applicant: Palantir Technologies Inc.
Inventor: Harkirat Singh , Geoffrey Stowe , Stefan Bach , Matthew Sprague , Michael Kross , Adam Borochoff , Parvathy Menon , Michael Harris
IPC: H04L9/40 , G06F16/23 , G06F16/242 , G06F16/2457 , G06F16/2458 , G06F16/26 , G06F16/28 , G06F16/335 , G06F16/35 , G06F16/9535 , G06Q10/10 , G06Q20/38 , G06Q20/40 , G06Q30/018 , G06Q40/00 , G06Q40/02 , G06Q40/03 , G06Q40/10 , G06Q40/12
CPC classification number: H04L63/145 , G06F16/23 , G06F16/244 , G06F16/24578 , G06F16/2465 , G06F16/26 , G06F16/283 , G06F16/285 , G06F16/287 , G06F16/288 , G06F16/335 , G06F16/35 , G06F16/355 , G06F16/9535 , G06Q10/10 , G06Q20/382 , G06Q20/4016 , G06Q30/0185 , G06Q40/00 , G06Q40/02 , G06Q40/03 , 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.
-
公开(公告)号:US11336681B2
公开(公告)日:2022-05-17
申请号:US16898850
申请日:2020-06-11
Applicant: Palantir Technologies Inc.
Inventor: Harkirat Singh , Geoffrey Stowe , Brendan Weickert , Matthew Sprague , Michael Kross , Adam Borochoff , Parvathy Menon , Michael Harris
IPC: G06Q40/00 , H04L29/06 , G06F16/2457 , G06F16/23 , G06F16/242 , G06F16/28 , G06F16/9535 , G06Q10/10 , G06Q40/02 , G06F16/335 , G06F16/35 , G06F16/26 , G06F16/2458 , G06Q20/40 , G06Q30/00 , G06Q20/38
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.
-
公开(公告)号:US20180270264A1
公开(公告)日:2018-09-20
申请号:US15961431
申请日:2018-04-24
Applicant: Palantir Technologies Inc.
Inventor: David Cohen , Jason Ma , Bing Jie Fu , Ilya Nepomnyashchiy , Steven Berler , Alex Smaliy , Jack Grossman , James Thompson , Julia Boortz , Matthew Sprague , Parvathy Menon , Michael Kross , Michael Harris , Adam Borochoff
CPC classification number: H04L63/1425 , G06F16/285 , G06Q40/12 , H04L63/1408 , H04L63/145
Abstract: Embodiments of the present disclosure relate to a data analysis system that may automatically generate memory-efficient clustered data structures, automatically analyze those clustered data structures, and provide results of the automated analysis in an optimized way to an analyst. The automated analysis of the clustered data structures (also referred to herein as data clusters) may include an automated application of various criteria or rules so as to generate a compact, human-readable analysis of the data clusters. The human-readable analyses (also referred to herein as “summaries” or “conclusions”) of the data clusters may be organized into an interactive user interface so as to enable an analyst to quickly navigate among information associated with various data clusters and efficiently evaluate those data clusters in the context of, for example, a fraud investigation. Embodiments of the present disclosure also relate to automated scoring of the clustered data structures.
-
公开(公告)号:US20160344758A1
公开(公告)日:2016-11-24
申请号:US14473920
申请日:2014-08-29
Applicant: Palantir Technologies Inc.
Inventor: David Cohen , Jason Ma , Bing Jie Fu , Ilya Nepomnyashchiy , Steven Berler , Alex Smaliy , Jack Grossman , James Thompson , Julia Boortz , Matthew Sprague , Parvathy Menon , Michael Kross , Michael Harris , Adam Borochoff
IPC: H04L29/06 , G08B21/18 , G06F3/0484
CPC classification number: G08B21/18 , G06F3/04842 , H04L63/0281 , H04L63/1433 , H04L63/145
Abstract: Embodiments of the present disclosure relate to a data analysis system that may automatically generate memory-efficient clustered data structures, automatically analyze those clustered data structures, and provide results of the automated analysis in an optimized way to an analyst. The automated analysis of the clustered data structures (also referred to herein as data clusters) may include an automated application of various criteria or rules so as to generate a compact, human-readable analysis of the data clusters. The human-readable analyses (also referred to herein as “summaries” or “conclusions”) of the data clusters may be organized into an interactive user interface so as to enable an analyst to quickly navigate among information associated with various data clusters and efficiently evaluate those data clusters in the context of, for example, a fraud investigation. Embodiments of the present disclosure also relate to automated scoring of the clustered data structures.
Abstract translation: 本公开的实施例涉及一种数据分析系统,其可以自动生成存储器有效的集群数据结构,自动分析这些集群数据结构,并以优化的方式向分析者提供自动化分析的结果。 集群数据结构(本文中也称为数据集群)的自动化分析可以包括各种标准或规则的自动应用,以便生成数据集群的紧凑的,人类可读的分析。 可以将数据集群的可读分析(也称为“摘要”或“结论”)组织成交互式用户界面,以使分析人员能够在与各种数据集群相关联的信息之间快速导航,并有效地评估 这些数据集群在例如欺诈调查的背景下。 本公开的实施例还涉及聚类数据结构的自动评分。
-
公开(公告)号:US09171334B1
公开(公告)日:2015-10-27
申请号:US14139628
申请日:2013-12-23
Applicant: Palantir Technologies, Inc.
Inventor: Alexander Visbal , Adam Borochoff , Jacob Albertson , Trevor Austin , Christopher Rogers , Daniel Campos , Matthew Sprague , Michael Kross , 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。
-
公开(公告)号:US11848760B2
公开(公告)日:2023-12-19
申请号:US17658893
申请日:2022-04-12
Applicant: Palantir Technologies Inc.
Inventor: Harkirat Singh , Geoffrey Stowe , Brendan Weickert , Matthew Sprague , Michael Kross , Adam Borochoff , Parvathy Menon , Michael Harris
IPC: G06Q40/00 , H04L9/40 , G06F16/2457 , G06F16/23 , G06F16/242 , G06F16/28 , G06F16/9535 , G06Q10/10 , G06Q40/02 , G06Q40/10 , G06F16/335 , G06F16/35 , G06F16/26 , G06F16/2458 , G06Q40/03 , G06Q20/40 , G06Q30/018 , G06Q40/12 , G06Q20/38
CPC classification number: H04L63/145 , G06F16/23 , G06F16/244 , G06F16/2465 , G06F16/24578 , G06F16/26 , G06F16/283 , G06F16/285 , G06F16/287 , G06F16/288 , G06F16/335 , G06F16/35 , G06F16/355 , G06F16/9535 , G06Q10/10 , G06Q20/382 , G06Q20/4016 , G06Q30/0185 , G06Q40/00 , G06Q40/02 , G06Q40/03 , 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.
-
公开(公告)号:US20200304522A1
公开(公告)日:2020-09-24
申请号:US16898850
申请日:2020-06-11
Applicant: Palantir Technologies Inc.
Inventor: Harkirat Singh , Geoffrey Stowe , Brendan Weickert , Matthew Sprague , Michael Kross , Adam Borochoff , Parvathy Menon , Michael Harris
IPC: H04L29/06 , G06Q40/00 , G06F16/2457 , G06F16/23 , G06F16/242 , G06F16/28 , G06F16/9535 , G06Q10/10 , G06Q40/02 , G06F16/335 , G06F16/35 , G06F16/26 , G06F16/2458 , G06Q20/40 , G06Q30/00 , G06Q20/38
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.
-
公开(公告)号:US10721268B2
公开(公告)日:2020-07-21
申请号:US16239081
申请日:2019-01-03
Applicant: Palantir Technologies Inc.
Inventor: Harkirat Singh , Brendan Weickert , Matthew Sprague , Michael Kross , Adam Borochoff , Parvathy Menon , Michael Harris
IPC: G06Q40/00 , H04L29/06 , G06F16/2457 , G06F16/23 , G06F16/242 , G06F16/28 , G06F16/9535 , G06Q10/10 , G06Q40/02 , G06F16/335 , G06F16/35 , G06F16/26 , G06F16/2458 , G06Q20/40 , G06Q30/00 , G06Q20/38
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.
-
公开(公告)号:US20190052648A1
公开(公告)日:2019-02-14
申请号:US14928512
申请日:2015-10-30
Applicant: Palantir Technologies Inc.
Inventor: Geoff Stowe , Harkirat Singh , Stefan Bach , Matthew Sprague , Michael Kross , Adam Borochoff , Parvathy Menon , Michael Harris
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.
-
-
-
-
-
-
-
-
-