公开(公告)号：US12033041B2

公开(公告)日：2024-07-09

申请号：US17896281

申请日：2022-08-26

Applicant: Databricks, Inc.

Inventor： Benjamin Thomas Wilson ,  Corey Zumar

IPC: G06N20/00 ,  G06F18/20 ,  G06F18/2132

CPC classification number: G06N20/00 ,  G06F18/21322 ,  G06F18/285 ,  G06F18/21326

Abstract: The present application discloses a method, system, and computer system for building a model associated with a dataset. The method includes receiving a data set, the dataset comprising a plurality of keys and a plurality of key-value relationships, determining a plurality of models to build based at least in part on the dataset, wherein determining the plurality of models to build comprises using the dataset format information to identify the plurality of models, building the plurality of models, and optimizing at least one of the plurality of models.

公开(公告)号：US20250061378A1

公开(公告)日：2025-02-20

申请号：US18738025

申请日：2024-06-09

Applicant: Databricks, Inc.

Inventor： Benjamin Thomas Wilson ,  Corey Zumar

IPC: G06N20/00 ,  G06F18/20 ,  G06F18/2132

Abstract: The present application discloses a method, system, and computer system for building a model associated with a dataset. The method includes receiving a data set, the dataset comprising a plurality of keys and a plurality of key-value relationships, determining a plurality of models to build based at least in part on the dataset, wherein determining the plurality of models to build comprises using the dataset format information to identify the plurality of models, building the plurality of models, and optimizing at least one of the plurality of models.

公开(公告)号：US20250124236A1

公开(公告)日：2025-04-17

申请号：US18518155

申请日：2023-11-22

Applicant: Databricks, Inc.

Inventor： Ridhima Gupta ,  Prithvi Kannan ,  Sunish Sohil Sheth ,  Kasey Uhlenhuth ,  Hubert Zub ,  Corey Zumar

IPC: G06F40/40 ,  G06F40/103 ,  G06F40/30

Abstract: A method for evaluating textual output of one or more machine-learned language models is presented. The method includes receiving, from a user of a client device, a first prompt for input to one or more machine-learned language models, providing the first prompt to the one or more models for execution, and receiving a set of generated responses to the first prompt from the one or more models. The method further includes generating a user interface (UI) on the client device displaying the first prompt and generated responses as a table user interface element. The method applies a selected evaluation function to the generated response to evaluate the response with respect to an evaluation objective and identifies words that influence the evaluation. The method generates one or more UI elements on the UI to display the results of the evaluation for the generated responses.

公开(公告)号：US20230244991A1

公开(公告)日：2023-08-03

申请号：US17896281

申请日：2022-08-26

Applicant: Databricks, Inc.

Inventor： Benjamin Thomas Wilson ,  Corey Zumar

IPC: G06N20/00 ,  G06K9/62

CPC classification number: G06N20/00 ,  G06K9/6227 ,  G06K9/6235 ,  G06K2009/6237

Abstract: The present application discloses a method, system, and computer system for building a model associated with a dataset. The method includes receiving a data set, the dataset comprising a plurality of keys and a plurality of key-value relationships, determining a plurality of models to build based at least in part on the dataset, wherein determining the plurality of models to build comprises using the dataset format information to identify the plurality of models, building the plurality of models, and optimizing at least one of the plurality of models.

公开(公告)号：US20230244982A1

公开(公告)日：2023-08-03

申请号：US17587793

申请日：2022-01-28

Applicant: Databricks Inc.

Inventor： Benjamin Thomas Wilson ,  Corey Zumar

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: The present application discloses a method, system, and computer system for tuning a set of models. The method includes determining a set of one or more models to optimize, determining a plurality of optimizer modules with which to optimize the set of one or more models, causing the plurality of optimizer modules to respectively perform a respective optimizing process with respect to at least one model of the set of one or more models, and deploying an optimized model obtained based at least in part on optimizing metrics of the set of the one or more models.

公开(公告)号：US20230244720A1

公开(公告)日：2023-08-03

申请号：US17587820

申请日：2022-01-28

Applicant: Databricks Inc.

Inventor： Benjamin Thomas Wilson ,  Corey Zumar

IPC: G06F16/903 ,  G06N20/00

CPC classification number: G06F16/90335 ,  G06N20/00

Abstract: The present application discloses a method, system, and computer system for querying a model associated with a dataset. The method includes providing an input interface via which a first entity inputs a dataset, receiving the dataset, and providing a selection interface that exposes to a second entity the plurality of models determined for the dataset and/or the plurality of results corresponding to the plurality of models using the index entries. The dataset comprises a plurality of keys and a plurality of key-value relationships, and the dataset is formatted according to a predefined format, wherein index entries are generated for a plurality of models and a plurality of results corresponding to the plurality of models.

公开(公告)号：US11468369B1

公开(公告)日：2022-10-11

申请号：US17587806

申请日：2022-01-28

Applicant: Databricks Inc.

Inventor： Benjamin Thomas Wilson ,  Corey Zumar

IPC: G06N20/00 ,  G06K9/62

Abstract: The present application discloses a method, system, and computer system for building a model associated with a dataset. The method includes receiving a data set, the dataset comprising a plurality of keys and a plurality of key-value relationships, determining a plurality of models to build based at least in part on the dataset, wherein determining the plurality of models to build comprises using the dataset format information to identify the plurality of models, building the plurality of models, and optimizing at least one of the plurality of models.