公开(公告)号：US20230081135A1

公开(公告)日：2023-03-16

申请号：US18051035

申请日：2022-10-31

Applicant: Palantir Technologies Inc.

Inventor： David Lisuk ,  Daniel Erenrich ,  Guodong Xu ,  Luis Voloch ,  Rahul Agarwal ,  Simon Slowik ,  Aleksandr Zamoshichin ,  Andre Frederico Cavalheiro Menck ,  Anirvan Mukherjee ,  Daniel Chin

IPC: G06F16/18 ,  G06N7/00 ,  G06F16/13 ,  G06F16/188 ,  G06F30/00

Abstract: A model management system provides a centralized repository for storing and accessing models. The model management system receives an input to store a model object in a first model state generated based on a first set of known variables. The model management system generates a first file including a first set of functions defining the first model state and associates the first file with a model key identifying the model object. The model management system receives an input to store the model object in a second model state having been generated based on the first model state and a second set of known variables. The model management system generates a second file including a second set of functions defining the second model state and associates the second file with the model key. The model management system identifies available versions of the model object based on the model key.

公开(公告)号：US20220107980A1

公开(公告)日：2022-04-07

申请号：US17550921

申请日：2021-12-14

Applicant: Palantir Technologies Inc.

Inventor： David Lisuk ,  Eric Porter ,  Aditya Shashi ,  Ilai Soloducho ,  John Wiseheart ,  Guodong Xu ,  Maciej Foks

IPC: G06F16/903 ,  G06N20/00 ,  G06F16/9032 ,  G06F40/205 ,  G06F16/2457 ,  G06F40/40 ,  G06F16/9038

Abstract: A data analysis system presents a user interface to allow a user to provide a natural language query pertaining to a dataset, wherein the dataset is associated with a data object model comprising a plurality of objects and receives, via the user interface, user input specifying the natural language query. The data analysis system further modifies, in the user interface, the user input to visually indicate one or more portions of the natural language query that each represent one of the plurality of objects and presents, in the user interface, a response to the natural language query, the response being based on data from the dataset, the data corresponding to the one of the plurality of objects.

公开(公告)号：US20210055977A1

公开(公告)日：2021-02-25

申请号：US16990233

申请日：2020-08-11

Applicant: Palantir Technologies, Inc.

Inventor： David Lisuk ,  Simon Slowik

IPC: G06F9/54 ,  H04L29/06 ,  G06N20/00 ,  G06F9/455

Abstract: One or more virtual machines are launched at an application platform. At each of the one or more virtual machines, a machine learning model execution environment is instantiated for an instance of a machine learning model. A respective instance of the machine learning model is loaded to each machine learning model execution environment. Each loaded instance of the machine learning model is associated with an application programming interface (API) endpoint which can receive input data for the loaded instance of the machine learning model from a client device and return output data produced by the loaded instance of the machine learning model based on the input data.

公开(公告)号：US12045678B2

公开(公告)日：2024-07-23

申请号：US18139663

申请日：2023-04-26

Applicant: Palantir Technologies Inc.

Inventor： David Lisuk ,  Simon Slowik

IPC: G06F9/54 ,  G06F9/455 ,  G06N20/00 ,  H04L67/133

CPC classification number: G06F9/547 ,  G06F9/45558 ,  G06N20/00 ,  H04L67/133 ,  G06F2009/45562 ,  G06F2009/45591 ,  G06F2009/45595

Abstract: One or more virtual machines are launched at an application platform. At each of the one or more virtual machines, a machine learning model execution environment is instantiated for an instance of a machine learning model. A respective instance of the machine learning model is loaded to each machine learning model execution environment. Each loaded instance of the machine learning model is associated with an application programming interface (API) endpoint which can receive input data for the loaded instance of the machine learning model from a client device and return output data produced by the loaded instance of the machine learning model based on the input data.

公开(公告)号：US12008047B2

公开(公告)日：2024-06-11

申请号：US17550921

申请日：2021-12-14

Applicant: Palantir Technologies Inc.

Inventor： David Lisuk ,  Eric Porter ,  Aditya Shashi ,  Ilai Soloducho ,  John Wiseheart ,  Guodong Xu ,  Maciej Foks

IPC: G06F16/903 ,  G06F16/2457 ,  G06F16/9032 ,  G06F16/9038 ,  G06F40/205 ,  G06F40/40 ,  G06N20/00

CPC classification number: G06F16/90344 ,  G06F16/24578 ,  G06F16/90332 ,  G06F16/9038 ,  G06F40/205 ,  G06F40/40 ,  G06N20/00

Abstract: A data analysis system presents a user interface to allow a user to provide a natural language query pertaining to a dataset, wherein the dataset is associated with a data object model comprising a plurality of objects and receives, via the user interface, user input specifying the natural language query. The data analysis system further modifies, in the user interface, the user input to visually indicate one or more portions of the natural language query that each represent one of the plurality of objects and presents, in the user interface, a response to the natural language query, the response being based on data from the dataset, the data corresponding to the one of the plurality of objects.

公开(公告)号：US20230259416A1

公开(公告)日：2023-08-17

申请号：US18139663

申请日：2023-04-26

Applicant: Palantir Technologies Inc.

Inventor： David Lisuk ,  Simon Slowik

IPC: G06F9/54 ,  G06N20/00 ,  G06F9/455 ,  H04L67/133

CPC classification number: G06F9/547 ,  G06N20/00 ,  G06F9/45558 ,  H04L67/133 ,  G06F2009/45562 ,  G06F2009/45591 ,  G06F2009/45595

Abstract: One or more virtual machines are launched at an application platform. At each of the one or more virtual machines, a machine learning model execution environment is instantiated for an instance of a machine learning model. A respective instance of the machine learning model is loaded to each machine learning model execution environment. Each loaded instance of the machine learning model is associated with an application programming interface (API) endpoint which can receive input data for the loaded instance of the machine learning model from a client device and return output data produced by the loaded instance of the machine learning model based on the input data.

公开(公告)号：US20220179723A1

公开(公告)日：2022-06-09

申请号：US17680859

申请日：2022-02-25

Applicant: Palantir Technologies Inc.

Inventor： David Lisuk ,  Simon Slowik

IPC: G06F9/54 ,  G06N20/00 ,  G06F9/455 ,  H04L67/133

Abstract: One or more virtual machines are launched at an application platform. At each of the one or more virtual machines, a machine learning model execution environment is instantiated for an instance of a machine learning model. A respective instance of the machine learning model is loaded to each machine learning model execution environment. Each loaded instance of the machine learning model is associated with an application programming interface (API) endpoint which can receive input data for the loaded instance of the machine learning model from a client device and return output data produced by the loaded instance of the machine learning model based on the input data.

公开(公告)号：US11288110B2

公开(公告)日：2022-03-29

申请号：US16990233

申请日：2020-08-11

Applicant: Palantir Technologies, Inc.

Inventor： David Lisuk ,  Simon Slowik

IPC: G06F9/54 ,  G06N20/00 ,  G06F9/455 ,  H04L67/133

Abstract: One or more virtual machines are launched at an application platform. At each of the one or more virtual machines, a machine learning model execution environment is instantiated for an instance of a machine learning model. A respective instance of the machine learning model is loaded to each machine learning model execution environment. Each loaded instance of the machine learning model is associated with an application programming interface (API) endpoint which can receive input data for the loaded instance of the machine learning model from a client device and return output data produced by the loaded instance of the machine learning model based on the input data.

公开(公告)号：US20240411628A1

公开(公告)日：2024-12-12

申请号：US18742927

申请日：2024-06-13

Applicant: Palantir Technologies Inc.

Inventor： David Lisuk ,  Simon Slowik

IPC: G06F9/54 ,  G06F9/455 ,  G06N20/00 ,  H04L67/133

Abstract: One or more virtual machines are launched at an application platform. At each of the one or more virtual machines, a machine learning model execution environment is instantiated for an instance of a machine learning model. A respective instance of the machine learning model is loaded to each machine learning model execution environment. Each loaded instance of the machine learning model is associated with an application programming interface (API) endpoint which can receive input data for the loaded instance of the machine learning model from a client device and return output data produced by the loaded instance of the machine learning model based on the input data.

公开(公告)号：US20240403103A1

公开(公告)日：2024-12-05

申请号：US18674650

申请日：2024-05-24

Applicant: Palantir Technologies Inc.

Inventor： Jakob Frick ,  Sriram Krishnan ,  Thomas Powell ,  David Lisuk ,  Mayada Gonimah

IPC: G06F9/455 ,  G06F3/0484

Abstract: Computer-implemented systems and methods are disclosed, including for integration and management of computer-based models in a model management. A computer-implemented method may include, for example, receiving one or more inputs including requesting to add a first model to a defined modeling objective, specifying a first model location, and/or providing a first model adapter configuration. In response to the one or more user inputs, the method may further include storing or providing access to information associated with the first model, associating the first model with a defined modeling objective, and/or implementing the first model adapter configuration to provide communication with the first model.