公开(公告)号：US12288143B2

公开(公告)日：2025-04-29

申请号：US17930046

申请日：2022-09-06

Applicant: Palantir Technologies Inc.

Inventor： Daniel Erenrich ,  Matthew Elkherj

IPC: G06N5/04 ,  G06N20/00

Abstract: Systems and methods are provided for selecting training examples to increase the efficiency of supervised active machine learning processes. Training examples for presentation to a user may be selected according to measure of the model's uncertainty in labeling the examples. A number of training examples may be selected to increase efficiency between the user and the processing system by selecting the number of training examples to minimize user downtime in the machine learning process.

公开(公告)号：US11436523B2

公开(公告)日：2022-09-06

申请号：US16027161

申请日：2018-07-03

Applicant: Palantir Technologies Inc.

Inventor： Daniel Erenrich ,  Matthew Elkherj

IPC: G06N5/04 ,  G06N20/00

Abstract: Systems and methods are provided for selecting training examples to increase the efficiency of supervised active machine learning processes. Training examples for presentation to a user may be selected according to measure of the model's uncertainty in labeling the examples. A number of training examples may be selected to increase efficiency between the user and the processing system by selecting the number of training examples to minimize user downtime in the machine learning process.

公开(公告)号：US11209971B1

公开(公告)日：2021-12-28

申请号：US16931976

申请日：2020-07-17

Applicant: Palantir Technologies Inc.

Inventor： Andrew Pettit ,  Adam Schexnayder ,  Ashwin Sreenivas ,  Daniel Spangenberger ,  Gary Lin ,  Joules Nahas ,  Lucas Lemanowicz ,  Matthew Elkherj ,  Natasha Armbrust ,  Tomer Kremerman ,  Tinlok Pang ,  Yehonatan Steinmetz

IPC: G06F3/0482 ,  G06F3/0484 ,  G06F16/245 ,  G06F16/25 ,  G06Q30/02 ,  G06F16/242 ,  G06F16/248 ,  G06F16/9032

Abstract: Systems and methods are disclosed for systems and user interfaces for rapid analysis of viewership information. One of the methods includes accessing databases storing viewership information associated with segments, with each segment being associated with common features of viewers. Measures of association between the segment and content items are maintained for each segment. An interactive user interface is presented via a user device, the interactive user interface enabling creation of a customized viewing audience. The interactive user interface receives user input indicating a segment, identifies similar segments based on associations between features of the segment and of other segments, and presents the identified segments. Analysis information associated with the segments is presented for at least one of the one or more segments, with the segments being included in the customized viewing audience.

公开(公告)号：US10311074B1

公开(公告)日：2019-06-04

申请号：US15590956

申请日：2017-05-09

Applicant: Palantir Technologies Inc.

Inventor： Mitchell Beard ,  Allen Chang ,  Chris Hammett ,  Jeremy Liu ,  Matthew Elkherj ,  Ryan Beiermeister ,  Ryan Smith ,  Tatyana Gordeeva ,  William Ayers

IPC: G06F16/20 ,  G06F16/25 ,  G06F16/248 ,  G06F16/2455 ,  G06F16/2457 ,  G06Q10/06

Abstract: Systems and methods are provided for identifying and compiling information relating to an entity for investigative analysis. The system may comprise one or more processors and a memory storing instructions that, when executed by the one or more processors, cause the system to search, in one or more data sources, with a plurality of known characteristics of an entity to obtain a first plurality of records, identify from the first plurality of records a subset of records that match the known characteristics with a substantial confidence, compile the subset of records to form a unified record representing the entity and conduct a second search with information from the unified record to obtain a second plurality of search results.

公开(公告)号：US20190163709A1

公开(公告)日：2019-05-30

申请号：US16261250

申请日：2019-01-29

Applicant: Palantir Technologies Inc.

Inventor： Matthew Elkherj ,  Ashley Einspahr ,  Breanna Bunge ,  Chris Hammett ,  Erika Crawford Tom ,  Mitchell Beard ,  Ryan Beiermeister ,  Seelig Sinton ,  Sharon Hao ,  William Ayers

IPC: G06F16/951 ,  G06F16/38

Abstract: Systems and methods are provided for identifying relevant information for an entity, referred to as a seed entity. A plurality of search queries can be generated each comprising a property of a seed entity or one of the entities associated with the seed entity (seed-linked entities). Preferably, a collection of search queries includes ones representing different properties of the seed entity and properties of different seed-linked entities. Optionally, the collection of search queries is optimized to reduce search burden. Searches can then be conducted with the search queries in one or more data sources to obtain a plurality of search results, wherein each search result comprises a hit entity and one or more entities associated with the hit entity (hit-linked entity). For each of the search results, a score can be determined taking as input (a) likelihood of match between the seed entity and the hit entity or between a seed-linked entity and a hit-linked entity, (b) presence of a new entity in the search result not present in the search queries or a difference between the new entity and an entity present in the search queries, and (c) characteristic of the new entity in the search result. Based on the scores, high priority search results can be presented a user for further analysis.

公开(公告)号：US10127289B2

公开(公告)日：2018-11-13

申请号：US15233149

申请日：2016-08-10

Applicant: Palantir Technologies Inc.

Inventor： Lawrence Manning ,  Rahul Mehta ,  Daniel Erenrich ,  Guillem Palou Visa ,  Roger Hu ,  Xavier Falco ,  Rowan Gilmore ,  Eli Bingham ,  Jason Prestinario ,  Yifei Huang ,  Daniel Fernandez ,  Jeremy Elser ,  Clayton Sader ,  Rahul Agarwal ,  Matthew Elkherj ,  Nicholas Latourette ,  Aleksandr Zamoshchin

IPC: G06F17/30

Abstract: Computer implemented systems and methods are disclosed for automatically clustering and canonically identifying related data in various data structures. Data structures may include a plurality of records, wherein each record is associated with a respective entity. In accordance with some embodiments, the systems and methods further comprise identifying clusters of records associated with a respective entity by grouping the records into pairs, analyzing the respective pairs to determine a probability that both members of the pair relate to a common entity, and identifying a cluster of overlapping pairs to generate a collection of records relating to a common entity. Clusters may further be analyzed to determine canonical names or other properties for the respective entities by analyzing record fields and identifying similarities.

公开(公告)号：US09836694B2

公开(公告)日：2017-12-05

申请号：US14843734

申请日：2015-09-02

Applicant: Palantir Technologies, Inc.

Inventor： Duncan Robertson ,  Alexander Sparrow ,  Mike Lewin ,  Meline Von Brentano ,  Matthew Elkherj ,  Rafael Cosman

IPC: G06N5/04 ,  G06N99/00 ,  G06Q10/04 ,  G06Q10/10 ,  G06Q50/26 ,  G06F17/00

CPC classification number: G06N5/04 ,  G06F3/0481 ,  G06N5/048 ,  G06N99/005 ,  G06Q10/04 ,  G06Q10/10 ,  G06Q50/26 ,  G06Q50/265

Abstract: A computer-based crime risk forecasting system and corresponding method are provided for generating crime risk forecasts and conveying the forecasts to a user. With the conveyed forecasts, the user can more effectively gauge both the level of increased crime threat and its potential duration. The user can then leverage the information conveyed by the forecasts to take a more proactive approach to law enforcement in the affected areas during the period of increased crime threat.

公开(公告)号：US11797627B2

公开(公告)日：2023-10-24

申请号：US17948905

申请日：2022-09-20

Applicant: Palantir Technologies Inc.

Inventor： Mitchell Beard ,  Jeffrey Bagdis ,  Christopher Brahms ,  Ashley Einspahr ,  Clare Adrien ,  Arvind Raju ,  Matthew Elkherj

IPC: G06F16/95 ,  G06F16/9535 ,  G06F16/248

CPC classification number: G06F16/9535 ,  G06F16/248

Abstract: Systems and methods are provided for performing context-based keyword searching using a search bar. Based on search terms received via the search bar, the system may be configured to provide suggested search parameters to associate with that search term. The suggested search parameters may each include a type of data and/or a filter to associate with the search term (e.g., name, phone number, date of birth, etc.). The one or more suggested search parameters may be identified based on the search term itself, a list of possible types of data or filters, a preliminary search of one or more datasets, a record of one or more previous searches performed, requirements associated with one or more searchable datasets, the format of user input received via the search bar, and/or one or more other factors.

公开(公告)号：US11714869B2

公开(公告)日：2023-08-01

申请号：US17564056

申请日：2021-12-28

Applicant: Palantir Technologies Inc.

Inventor： Matthew Elkherj ,  Ashley Einspahr ,  Breanna Bunge ,  Chris Hammett ,  Erika Crawford Tom ,  Mitchell Beard ,  Ryan Beiermeister ,  Seelig Sinton ,  Sharon Hao ,  William Ayers ,  Seth Robinson

IPC: G06F16/951 ,  G06F16/38

CPC classification number: G06F16/951 ,  G06F16/38

Abstract: Systems and methods are provided for identifying relevant information for an entity, referred to as a seed entity. A plurality of search queries can be generated each comprising a property of a seed entity or one of the entities associated with the seed entity (seed-linked entities). Preferably, a collection of search queries includes ones representing different properties of the seed entity and properties of different seed-linked entities. Optionally, the collection of search queries is optimized to reduce search burden. Searches can then be conducted with the search queries in one or more data sources to obtain a plurality of search results, wherein each search result comprises a hit entity and one or more entities associated with the hit entity (hit-linked entity). For each of the search results, a score can be determined taking as input (a) likelihood of match between the seed entity and the hit entity or between a seed-linked entity and a hit-linked entity, (b) presence of a new entity in the search result not present in the search queries or a difference between the new entity and an entity present in the search queries, and (c) characteristic of the new entity in the search result. Based on the scores, high priority search results can be presented a user for further analysis.

公开(公告)号：US11704325B2

公开(公告)日：2023-07-18

申请号：US17812984

申请日：2022-07-15

Applicant: Palantir Technologies Inc.

Inventor： Lawrence Manning ,  Rahul Mehta ,  Daniel Erenrich ,  Guillem Palou Visa ,  Roger Hu ,  Xavier Falco ,  Rowan Gilmore ,  Eli Bingham ,  Jason Prestinario ,  Yifei Huang ,  Daniel Fernandez ,  Jeremy Elser ,  Clayton Sader ,  Rahul Agarwal ,  Matthew Elkherj ,  Nicholas Latourette ,  Aleksandr Zamoshchin

IPC: G06F16/00 ,  G06F16/2457 ,  G06F16/35 ,  G06F16/9535 ,  G06F16/28 ,  G06F18/23

CPC classification number: G06F16/24578 ,  G06F16/285 ,  G06F16/35 ,  G06F16/9535 ,  G06F18/23

Abstract: Computer implemented systems and methods are disclosed for automatically clustering and canonically identifying related data in various data structures. Data structures may include a plurality of records, wherein each record is associated with a respective entity. In accordance with some embodiments, the systems and methods further comprise identifying clusters of records associated with a respective entity by grouping the records into pairs, analyzing the respective pairs to determine a probability that both members of the pair relate to a common entity, and identifying a cluster of overlapping pairs to generate a collection of records relating to a common entity. Clusters may further be analyzed to determine canonical names or other properties for the respective entities by analyzing record fields and identifying similarities.