公开(公告)号：US12100231B2

公开(公告)日：2024-09-24

申请号：US17178705

申请日：2021-02-18

申请人： FUJIFILM BUSINESS INNOVATION CORP.

发明人： Fumi Kosaka ,  Tadao Michimura ,  Shigeru Okada ,  Masanori Yoshizuka

IPC分类号： G06V30/26 ,  G06F40/174 ,  G06T7/00 ,  G06T11/40 ,  G06V30/10 ,  G06V30/412

CPC分类号： G06V30/26 ,  G06F40/174 ,  G06T7/0002 ,  G06V30/10 ,  G06V30/412 ,  G06T11/40 ,  G06T2207/10008 ,  G06T2207/30176

摘要： An information processing apparatus includes a processor configured to acquire recognized items obtained by recognizing characters in a first image showing a reading target including one or more first fields in which characters are written and a second field in which a name or a signature is written, if any one of the first fields is inadequate, create a second image having blank fields for the inadequate first field and the second field, if the second field is inadequate, create a second image having a blank field for the second field, and output the created second image.

公开(公告)号：US12087070B2

公开(公告)日：2024-09-10

申请号：US17454729

申请日：2021-11-12

申请人： Microsoft Technology Licensing, LLC

发明人： Jenna Hong ,  Apurva Sandeep Gandhi ,  Gilbert Antonius ,  Tra My Nguyen ,  Ryan Serrao ,  Biyi Fang ,  Sheng Yi

IPC分类号： G06F40/284 ,  G06V10/22 ,  G06V30/32 ,  G06V30/412

CPC分类号： G06V30/36 ,  G06F40/284 ,  G06V10/22 ,  G06V30/333 ,  G06V30/412

摘要： A computer system is provided that includes one or more processors configured to receive user input for inked content to a digital canvas, and process the inked content to determine one or more writing regions. Each writing region includes recognized text and one or more document layout features associated with that writing region. The one or more processors are further configured to tokenize a target writing region of the one or more writing regions into a sequence of tokens, process the sequence of tokens of the target writing region using a task extraction subsystem that operates on tokens representing both the recognized text and the one or more document layout features of the target writing region, segment the target writing region into one or more sentence segments, and classify each of the one or more sentence segments as a task sentence or a non-task sentence.

公开(公告)号：US20240296690A1

公开(公告)日：2024-09-05

申请号：US18664807

申请日：2024-05-15

申请人： ZenPayroll, Inc.

发明人： Quentin Louis Raoul Balin

IPC分类号： G06V30/412 ,  G06V10/24 ,  G06V10/48 ,  G06V30/414 ,  G06V30/416

CPC分类号： G06V30/412 ,  G06V10/242 ,  G06V10/48 ,  G06V30/414 ,  G06V30/416

摘要： An image processing system accesses an image of a completed form document. The image of the form document includes one or more features, such as form text, at particular locations within the image. The image processing system accesses a template of the form document and computes a rotation and zoom of the image of the form document relative to the template of the form document based on the locations of the features within the image of the form document relative to the locations of the corresponding features within the template of the form document. The image processing system performs a rotation operation and a zoom operation on the image of the form document, and extracts data entered into fields of the modified image of the form document. The extracted data can be then accessed or stored for subsequent use.

公开(公告)号：US12080091B2

公开(公告)日：2024-09-03

申请号：US18331990

申请日：2023-06-09

申请人： Open Text SA ULC

发明人： Matthias Theodor Middendorf ,  Gisela Barbara Cäcilie Hammann ,  Carsten Peust

IPC分类号： G06F17/00 ,  G06F16/22 ,  G06F16/25 ,  G06F16/93 ,  G06F18/21 ,  G06F40/174 ,  G06F40/177 ,  G06F40/186 ,  G06F40/216 ,  G06F40/274 ,  G06N20/00 ,  G06V30/19 ,  G06V30/412 ,  G06V30/414 ,  G06V30/416

CPC分类号： G06V30/416 ,  G06F16/2282 ,  G06F16/258 ,  G06F16/93 ,  G06F18/217 ,  G06F40/174 ,  G06F40/177 ,  G06F40/186 ,  G06F40/216 ,  G06F40/274 ,  G06N20/00 ,  G06V30/1916 ,  G06V30/412 ,  G06V30/414

摘要： A bipartite application implements a table auto-completion (TAC) algorithm on the client side and the server side. A client module runs a local model of the TAC algorithm on a user device and a server module runs a global model of the TAC algorithm on a server machine. The local model is continuously adapted through on-the-fly training, with as few as one negative example, to perform TAC on the client side, one document at a time. Knowledge thus learned by the local model is used to improve the global model on the server side. The global model can be utilized to automatically and intelligently extract table information from a large number of documents with significantly improved accuracy, requiring minimal human intervention even on complex tables.

公开(公告)号：US12067039B1

公开(公告)日：2024-08-20

申请号：US18327636

申请日：2023-06-01

申请人： Instabase, Inc.

发明人： Jessica Andersen Campos ,  Eric Han ,  Hariharan Thirugnanam ,  Subash Chandran Thirumaran ,  Timothy Serkes ,  Alagu Chockalingam ,  Varun Jain

IPC分类号： G06F16/00 ,  G06F16/332 ,  G06F16/35 ,  G06V30/412

CPC分类号： G06F16/3328 ,  G06F16/358 ,  G06V30/412

摘要： Systems and methods for providing user interfaces for configuration of a flow for extracting information from documents via a large language model are disclosed. Exemplary implementations may: present a user interface configured to obtain entry of user input from a user to select a set of exemplary documents; select one or more document classifications for the set of exemplary documents; select one or more extraction fields that correspond to individual queries; navigate between different portions of the user interface; present the set of document classifications; present a particular individual document in the user interface; present a set of extraction fields in the user interface, wherein the individual extraction fields present individual replies obtained from the large language model in reply to the individual queries; and/or perform other steps.

公开(公告)号：US20240265721A1

公开(公告)日：2024-08-08

申请号：US18369744

申请日：2023-09-18

申请人： ID Metrics Group Incorporated

发明人： Richard Austin Huber, Jr. ,  Satya Prakash Mallick ,  Matthew William Flagg ,  Koustubh Sinhal

IPC分类号： G06V30/40 ,  G06F18/24 ,  G06V10/22 ,  G06V10/98 ,  G06V30/412

CPC分类号： G06V30/40 ,  G06F18/24 ,  G06V10/225 ,  G06V10/993 ,  G06V30/412

摘要： Methods for detecting digital or physical tampering of an imaged physical credential include the actions of: receiving a digital image representing a physical credential having one or more high value regions, the digital image including an array of pixels; processing the digital image with a tamper detector to generate an output corresponding to an intrinsic characteristic of the digital image, the tamper detector configured to perform a pixel-level analysis of the high value regions of the digital image with respect to a predetermined tampering signature; and determining, based on the output from the tamper detector, whether the digital image has been digitally tampered with.

公开(公告)号：US20240257550A1

公开(公告)日：2024-08-01

申请号：US18686233

申请日：2022-08-25

申请人： Google LLC

发明人： Henri Rebecq ,  Federico Tombari ,  Diego Martin Arroyo

IPC分类号： G06V30/416 ,  G06V10/44 ,  G06V10/82 ,  G06V30/412

CPC分类号： G06V30/416 ,  G06V10/44 ,  G06V10/82 ,  G06V30/412

摘要： A method including receiving an image representing a document including a plurality of layout components, identifying textual information associated with the plurality of layout components, identifying visual information associated with the plurality of layout components, combining the textual information with the visual information, and predicting a reading order of the plurality of layout components based on the combined textual information and visual information using a self-attention encoder/decoder.

公开(公告)号：US20240249543A1

公开(公告)日：2024-07-25

申请号：US18100334

申请日：2023-01-23

申请人： SAP SE

发明人： Sivakanth Jayaram ,  Shruthi Annappa ,  Prasanna Bhat Mavinakuli

IPC分类号： G06V30/412 ,  G06V10/82 ,  G06V30/19 ,  G06V30/413

CPC分类号： G06V30/412 ,  G06V10/82 ,  G06V30/19147 ,  G06V30/413

摘要： Example methods and systems are directed to data extraction from input data objects. A data extraction schema may define at least a first feature and a second feature. The first feature may be associated with a first machine learning model and the second feature may be associated with a second machine learning model. A first input data object is accessed. The first machine learning model may be used to extract a first output data object associated with the first feature from the first input data object, based on the data extraction schema. The second machine learning model may be used to extract a second output data object associated with the second feature from the first input data object, based on the data extraction schema. The first output data object and the second output data object may be presented on a user interface.

公开(公告)号：US20240233223A1

公开(公告)日：2024-07-11

申请号：US18339263

申请日：2023-06-22

申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

发明人： Nikolaos Livathinos ,  Maksym Lysak ,  Ahmed Samy Nassar ,  Peter Willem Jan Staar

IPC分类号： G06T11/60 ,  G06F40/174 ,  G06F40/177 ,  G06F40/186 ,  G06F40/205 ,  G06F40/284 ,  G06V10/774 ,  G06V30/412

CPC分类号： G06T11/60 ,  G06F40/174 ,  G06F40/177 ,  G06F40/186 ,  G06F40/205 ,  G06F40/284 ,  G06V10/774 ,  G06V30/412

摘要： The present disclosure relates to a method for automatically generating table images. The method includes determining a table configuration including a number of rows of the table, a number of columns of the table and a spanning area of the table, the spanning area indicating a fraction of spanning cells in the table. The table may be generated in accordance with the table configuration. Content may be inserted into cells of the table using a selected content template. An image table of an appearance of the table may be created and the image table may be provided.

公开(公告)号：US20240232505A1

公开(公告)日：2024-07-11

申请号：US18615813

申请日：2024-03-25

申请人： Google LLC

发明人： Alexander James Faaborg ,  Brett Barros

IPC分类号： G06F40/106 ,  G06F3/01 ,  G06F18/21 ,  G06F18/214 ,  G06F40/30 ,  G06V30/10 ,  G06V30/412 ,  G10L13/02

CPC分类号： G06F40/106 ,  G06F3/013 ,  G06F18/214 ,  G06F18/217 ,  G06F40/30 ,  G06V30/412 ,  G10L13/02 ,  G06V30/10

摘要： Gaze data collected from eye gaze tracking performed while training text was read may be used to train at least one layout interpretation model. In this way, the at least one layout interpretation model may be trained to determine current text that includes words arranged according to a layout, process the current text with the at least one layout interpretation model to determine the layout, and output the current text with the words arranged according to the layout.