公开(公告)号：US12210828B2

公开(公告)日：2025-01-28

申请号：US18630990

申请日：2024-04-09

Applicant: INTUIT INC.

Inventor： Dominic Miguel Rossi ,  Hui Fang Lee ,  Tharathorn Rimchala

IPC: G06F40/284 ,  G06N3/045 ,  G06N3/08

Abstract: A computing system generates a plurality of training data sets for generating the NLP model. The computing system trains a teacher network to extract and classify tokens from a document. The training includes a pre-training stage where the teacher network is trained to classify generic data in the plurality of training data sets and a fine-tuning stage where the teacher network is trained to classify targeted data in the plurality of training data sets. The computing system trains a student network to extract and classify tokens from a document by distilling knowledge learned by the teacher network during the fine-tuning stage from the teacher network to the student network. The computing system outputs the NLP model based on the training. The computing system causes the NLP model to be deployed in a remote computing environment.

公开(公告)号：US12087068B2

公开(公告)日：2024-09-10

申请号：US18454032

申请日：2023-08-22

Applicant: INTUIT INC.

Inventor： Dominic Miguel Rossi ,  Xiao Xiao

IPC: G06V30/412 ,  G06T7/194 ,  G06V30/14 ,  G06V30/146 ,  G06V30/18 ,  G06V30/19 ,  G06V30/414

CPC classification number: G06V30/19173 ,  G06T7/194 ,  G06V30/1448 ,  G06V30/146 ,  G06V30/18 ,  G06V30/19127 ,  G06V30/19147 ,  G06V30/1916 ,  G06V30/414 ,  G06T2207/20021 ,  G06T2207/20072 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30176

Abstract: A processor may receive an image and identify a plurality of characters in the image using a machine learning (ML) model. The processor may generate at least one word-level bounding box indicating one or more words including at least a subset of the plurality of characters and/or may generate at least one field-level bounding box indicating at least one field including at least a subset of the one or more words. The processor may overlay the at least one word-level bounding box and the at least one field-level bounding box on the image to form a masked image including a plurality of optically-recognized characters and one or more predicted fields for at least a subset of the plurality of optically-recognized characters.

公开(公告)号：US11977842B2

公开(公告)日：2024-05-07

申请号：US17246277

申请日：2021-04-30

Applicant: INTUIT INC.

Inventor： Dominic Miguel Rossi ,  Hui Fang Lee ,  Tharathorn Rimchala

IPC: G06F40/284 ,  G06N3/045 ,  G06N3/08

CPC classification number: G06F40/284 ,  G06N3/045 ,  G06N3/08

Abstract: A computing system generates a plurality of training data sets for generating the NLP model. The computing system trains a teacher network to extract and classify tokens from a document. The training includes a pre-training stage where the teacher network is trained to classify generic data in the plurality of training data sets and a fine-tuning stage where the teacher network is trained to classify targeted data in the plurality of training data sets. The computing system trains a student network to extract and classify tokens from a document by distilling knowledge learned by the teacher network during the fine-tuning stage from the teacher network to the student network. The computing system outputs the NLP model based on the training. The computing system causes the NLP model to be deployed in a remote computing environment.

公开(公告)号：US11830264B2

公开(公告)日：2023-11-28

申请号：US17649467

申请日：2022-01-31

Applicant: INTUIT INC.

Inventor： Dominic Miguel Rossi ,  Xiao Xiao

IPC: G06V30/412 ,  G06V30/19 ,  G06V30/14 ,  G06V30/146 ,  G06T7/194 ,  G06V30/18 ,  G06V30/414

CPC classification number: G06V30/19173 ,  G06T7/194 ,  G06V30/146 ,  G06V30/1448 ,  G06V30/18 ,  G06V30/1916 ,  G06V30/19127 ,  G06V30/19147 ,  G06V30/414 ,  G06T2207/20021 ,  G06T2207/20072 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30176

Abstract: A processor may receive an image and identify a plurality of characters in the image using a machine learning (ML) model. The processor may generate at least one word-level bounding box indicating one or more words including at least a subset of the plurality of characters and/or may generate at least one field-level bounding box indicating at least one field including at least a subset of the one or more words. The processor may overlay the at least one word-level bounding box and the at least one field-level bounding box on the image to form a masked image including a plurality of optically-recognized characters and one or more predicted fields for at least a subset of the plurality of optically-recognized characters.

公开(公告)号：US20220351088A1

公开(公告)日：2022-11-03

申请号：US17246383

申请日：2021-04-30

Applicant: Intuit Inc.

Inventor： Sricharan Kallur Palli Kumar ,  Thrathorn Rimchala ,  Hui Chen ,  Preeti Duraipandian ,  Dominic Miguel Rossi

IPC: G06N20/20 ,  G06N3/04 ,  G06K9/00 ,  G06K9/62 ,  G06K9/34

Abstract: A method may include extracting, from a document, a first key-value pair including a key and a first value and corresponding to a first confidence score, extracting a second key-value pair including the key and a second value corresponding to a second confidence score, classifying a first match probability for the first key-value pair and a second match probability for the second key-value pair, generating a first calibrated confidence score for the first confidence score and a second calibrated confidence score for the second confidence score by transforming, using precision lookup tables constructed from training records, the first match probability to the first calibrated confidence score and the second match probability to second calibrated confidence score, selecting, using the first and second calibrated confidence scores, one of the first key-value pair and the second key-value pair, and presenting, in a graphical user interface (GUI), the selected key-value pair.