公开(公告)号：US20240338521A1

公开(公告)日：2024-10-10

申请号：US18629693

申请日：2024-04-08

Applicant: Snowflake Inc.

Inventor： Michal Gdak ,  Ganeshan Ramachandran Iyer ,  Tomasz Malisz ,  Mikolaj Niedbala ,  Pawel Pollak ,  Saurin Shah ,  Jan Tomasz Topinski

IPC: G06F40/226

CPC classification number: G06F40/226

Abstract: Systems and methods for: processing a current electronic document, using a set of machine-learning (ML) models, to extract a set of values for a set of data points based on a schema, where the schema describes the set of data points to be extracted from electronic documents; determining whether to select the current electronic document for human validation based on the schema; and adding the current electronic document to a human validation queue in response to determining to select the current electronic document for human validation based on the schema.

公开(公告)号：US20240338577A1

公开(公告)日：2024-10-10

申请号：US18416379

申请日：2024-01-18

Applicant: Snowflake Inc.

Inventor： Michal Gdak ,  Ganeshan Ramachandran Iyer ,  Tomasz Malisz ,  Mikolaj Niedbala ,  Pawel Pollak ,  Saurin Shah ,  Jan Tomasz Topinski ,  Daria Wieteska

IPC: G06N5/022

CPC classification number: G06N5/022

Abstract: Systems and methods for generating a machine-learning (ML) model for extracting information from one or more electronic documents, where the ML model can be used as a data object, which can be part of a database command or as part of a document information extraction process that is continuously running (e.g., document information extraction pipeline).

公开(公告)号：US11922328B1

公开(公告)日：2024-03-05

申请号：US18472883

申请日：2023-09-22

Applicant: Snowflake Inc.

Inventor： Michal Gdak ,  Ganeshan Ramachandran Iyer ,  Tomasz Malisz ,  Mikolaj Niedbala ,  Pawel Pollak ,  Saurin Shah ,  Jan Tomasz Topinski ,  Daria Wieteska

IPC: G06N5/022

CPC classification number: G06N5/022

Abstract: Systems and methods for generating a machine-learning (ML) model for extracting information from one or more electronic documents, where the ML model can be used as a data object, which can be part of a database command or as part of a document information extraction process that is continuously running (e.g., document information extraction pipeline).

公开(公告)号：US12236355B2

公开(公告)日：2025-02-25

申请号：US18416379

申请日：2024-01-18

Applicant: Snowflake Inc.

Inventor： Michal Gdak ,  Ganeshan Ramachandran Iyer ,  Tomasz Malisz ,  Mikolaj Niedbala ,  Pawel Pollak ,  Saurin Shah ,  Jan Tomasz Topinski ,  Daria Wieteska

IPC: G06N20/00 ,  G06N5/022

Abstract: Systems and methods for generating a machine-learning (ML) model for extracting information from one or more electronic documents, where the ML model can be used as a data object, which can be part of a database command or as part of a document information extraction process that is continuously running (e.g., document information extraction pipeline).