-
公开(公告)号:US12079352B2
公开(公告)日:2024-09-03
申请号:US17226014
申请日:2021-04-08
Applicant: Palantir Technologies Inc.
Inventor: Anton Apostolatos , Adam Lieskovský , Florian Diegruber , Francisco Ferreira , Joseph Kane , Joanna Peller , Kelvin Lau , Maciej Laska , Mikael Ibrahim Mofarrej , Max-Philipp Schrader , Philipp Hoefer , Spencer McCollester , Viktor Nordling
CPC classification number: G06F21/604 , G06F16/258
Abstract: A computer-implemented method enforces data security constraints in a data pipeline. The data pipeline takes one or more source datasets as input and performs one or more data transformations on them. The method includes using data defining one or more data security constraints to configure the data pipeline to perform a data transformation on a restricted subset of entries of the source datasets. The restriction is defined by the data defining one or more data security constraints. The method further includes performing the data transformation according to the configuration to produce one or more transformed datasets. The method further includes using the data defining one or more data security constraints to perform a verification on one or more of the transformed datasets to ensure that entries in the one or more of the transformed datasets are restricted as defined by the one or more data security constraints.
-
公开(公告)号:US20250110786A1
公开(公告)日:2025-04-03
申请号:US18794966
申请日:2024-08-05
Applicant: Palantir Technologies Inc.
Inventor: Max-Philipp Schrader , Sriram Krishnan , Megha Arora , Pavlo Tyshevskyi , Johannes Beil , Alexander Edwards , David Kebudi , Montgomery Evans , Anirvan Mukherjee
Abstract: Computer-implemented systems and methods are disclosed, including systems and methods for automatically solving computational tasks or problems. A computer-implemented method may include: providing an agent service that utilizes a plurality of agents to process one or more tasks; receiving, by a first agent, a request to handle a first task; obtaining, by the first agent, a first accessory to handle the first task; assigning, by the first agent, at least a portion of the first task to a second agent; sharing, by the first agent, the first accessory to the second agent; and processing, by the second agent, at least the portion of the first task using the first accessory to generate a processing result.
-
公开(公告)号:US20220198032A1
公开(公告)日:2022-06-23
申请号:US17226014
申请日:2021-04-08
Applicant: Palantir Technologies Inc.
Inventor: Anton Apostolatos , Adam Lieskovský , Florian Diegruber , Francisco Ferreira , Joseph Kane , Joanna Peller , Kelvin Lau , Maciej Laska , Mikael Ibrahim Mofarrej , Max-Philipp Schrader , Philipp Hoefer , Spencer McCollester , Viktor Nordling
Abstract: A computer-implemented method enforces data security constraints in a data pipeline. The data pipeline takes one or more source datasets as input and performs one or more data transformations on them. The method includes using data defining one or more data security constraints to configure the data pipeline to perform a data transformation on a restricted subset of entries of the source datasets. The restriction is defined by the data defining one or more data security constraints. The method further includes performing the data transformation according to the configuration to produce one or more transformed datasets. The method further includes using the data defining one or more data security constraints to perform a verification on one or more of the transformed datasets to ensure that entries in the one or more of the transformed datasets are restricted as defined by the one or more data security constraints.
-
公开(公告)号:US20250110753A1
公开(公告)日:2025-04-03
申请号:US18794904
申请日:2024-08-05
Applicant: Palantir Technologies Inc.
Inventor: Johannes Beil , Pavlo Tyshevskyi , Max-Philipp Schrader , Sriram Krishnan , Michael Zullo , Rushad Heerjee , Anirvan Mukherjee
Abstract: Computer-implemented systems and methods are disclosed, including systems and methods for automatically solving problems. A computer-implemented method may include: by an agent service configured to interact with an LLM to complete a run: providing an LLM with access to a state machine, executing an initial state of the state machine with the LLM, determining a subsequent state of the state machine based on at least an initial LLM output, and executing the subsequent state of the state machine.
-
公开(公告)号:US20240354646A1
公开(公告)日:2024-10-24
申请号:US18639394
申请日:2024-04-18
Applicant: Palantir Technologies Inc.
Inventor: Alexander Edwards , Anirvan Mukherjee , David Kebudi , Megha Arora , Sriram Krishnan , Max-Philipp Schrader , Jessica Winssinger , Philipp Hoefer
IPC: G06N20/00
CPC classification number: G06N20/00
Abstract: Disclosed herein is a method of providing feedback to a machine learning model. The method includes allowing a user to observe an output of a trained machine learning model; allowing the user to input feedback to the machine learning model based on the output, wherein the feedback is on at least one of a model level or on a training dataset level; and incorporating the feedback into the machine learning model to improve the machine learning model, wherein the method is performed using one or more processors. Disclosed herein are one or more computer-readable storage media including computer executable instructions which when executed by the one or more processors cause the one or more processors to perform the method. Disclosed herein is a computer system which includes one or more processors and one or more computer-readable storage media which include computer executable instructions which when executed by the one or more processors cause the one or more processors to perform the method.
-
-
-
-