公开(公告)号：EP4404083A1

公开(公告)日：2024-07-24

申请号：EP24152425.5

申请日：2024-01-17

申请人： VelocityEHS Holdings, Inc.

发明人： PENFIELD, Julia ,  SUMAN, Aatish ,  TALREJA, Veeru ,  KHAN, Misbah Zahid

IPC分类号： G06F16/93 ,  G06F40/205 ,  G06F40/258 ,  G06F40/279 ,  G06F40/284 ,  G06F40/295 ,  G06F40/30 ,  G06V30/412 ,  G06V30/416

CPC分类号： G06F40/205 ,  G06F40/258 ,  G06F40/284 ,  G06F40/295 ,  G06V10/82 ,  G06V30/416 ,  G06F40/279 ,  G06F40/30 ,  G06V30/412 ,  G06F16/93

摘要： Systems and methods for automated indexing and extraction of information in digital documents are disclosed. A method may comprise selecting a page number of a digital document to identify a page containing targeted information; inputting an image of the page into a visual machine learning network (visual ML), wherein the visual ML is trained to recognize text associated with the targeted information in an image; identifying by the visual ML, a section of the image that contains the targeted information; inputting the page number, the digital document, and coordinates of the section into an extraction module; and extracting the targeted information by the extraction module from the section.

公开(公告)号：EP3882799B1

公开(公告)日：2024-05-01

申请号：EP21173472.8

申请日：2019-02-18

IPC分类号： G06F21/55 ,  H04W12/12 ,  G06F21/57 ,  H04L9/40

CPC分类号： H04W12/12 ,  G06F21/55 ,  G06F40/205 ,  G06F21/552 ,  G06F21/57 ,  H04L63/1408

公开(公告)号：EP4441666A1

公开(公告)日：2024-10-09

申请号：EP21823229.6

申请日：2021-11-27

申请人： ZOE Life Technologies AG

发明人： POLLERT, Heiner ,  SCHLOER, Hardy

IPC分类号： G06N5/02 ,  G06F16/907 ,  G06F40/30

CPC分类号： G06N5/022 ,  G06F40/295 ,  G06F40/205 ,  G06F40/20 ,  G06N20/00

公开(公告)号：EP4280063B1

公开(公告)日：2024-07-24

申请号：EP22210122.2

申请日：2022-11-29

IPC分类号： G06F11/07 ,  G06F40/284 ,  G06F40/279 ,  G06F40/30

CPC分类号： G06F11/0793 ,  G06F11/079 ,  G06F11/0787 ,  G06F11/0769 ,  G06F40/279 ,  G06F40/205

公开(公告)号：EP4425316A2

公开(公告)日：2024-09-04

申请号：EP24172839.3

申请日：2017-04-27

申请人： Coda Project, Inc.

发明人： BOUCHER, Melissa Ming-Sak ,  BRITTON, Jeremy Edward ,  BAYES, Luke ,  CASO, Monica F. ,  DENEUI, Alexander W. ,  ECK, Christopher Leland ,  ELLIS, Nigel Robin ,  FORTES, Filipe P. ,  GREENSPAN, David Lilja ,  HOBBS, Brett Robert ,  HUDSON, Matthew B. ,  JAMES, Timothy Andrew ,  MENDES, Kenneth Francis ,  MEHROTRA, Shishir S. ,  O'BRIEN, Trevor Michael ,  SHACKLETON, Lane Patrick ,  SHI, Rhed ,  SIVARAMAKRISHNAN, Hariharan ,  STOWE, Jason Peter ,  TAMULONIS, Jason Andrew ,  VASISHTH, Himanshu ,  VYAGHRAPURI, Ramesh Krishna ,  WRIGHT, David Richard ,  ZHAN, Irvin ,  ZURAWICKI, Roger Mathieu

IPC分类号： G06F3/0482

CPC分类号： G06F3/04847 ,  G06F3/0482 ,  G06F16/93 ,  G06F3/0486 ,  G06F40/18 ,  G06F40/177 ,  G06F40/205 ,  G06F40/14

摘要： The present disclosure describes methods and systems for a document server communicatively coupled to at least one client computing device, a document comprising an operation log, wherein the operation log comprises at least one first sequential operation defining operations to create data values of the document, a document object model, wherein the document is at least partially positioned on at least one of the document server and a first client computing device of the at least one client computing device, and a formula engine, wherein the formula engine is structured to determine a calculation definition in response to the user formula value and the document object model.

公开(公告)号：EP4090052B1

公开(公告)日：2024-08-28

申请号：EP22183428.6

申请日：2017-08-31

IPC分类号： H04W4/00 ,  G10L17/22 ,  G10L15/00 ,  G06F21/62 ,  G06F40/205 ,  G10L15/26 ,  H04L67/63

CPC分类号： G10L15/26 ,  G06F21/6254 ,  G06F40/205 ,  H04L67/63

公开(公告)号：EP4369245A1

公开(公告)日：2024-05-15

申请号：EP23201621.2

申请日：2023-10-04

申请人： Tata Consultancy Services Limited

发明人： HOSUDURG, ANANTHA DESIK PURANAM ,  NAMAN, SUMIRAN ,  ROY, ASHIM ,  PATWARDHAN, NIKHIL GIRISH

IPC分类号： G06F40/295 ,  G06F40/205

CPC分类号： G06F40/295 ,  G06F40/205

摘要： Pre-trained models for Named Entity Recognition (NER) come with static NE classes, limited in number, and remain same irrespective of domain of the input text. Thus, domain specific training is required. Embodiments of the present disclosure provide a method and system for enhanced NER using a custom-built REGEX matcher and a heuristic entity ruler. The invention helps in discovering the NE's of the given text with pipeline-based approach with combination of models of NLP transformer, custom-built REGEX, and heuristic entity rules. The method automatically handles class resolution based on the heuristic entity ruler. The method enables a user to customize or add any new heuristic rules for entity ruler or custom regex as a knowledgebase to train the model with automatic relearning and unlearning. The extracted NEs are provided for further processing or masking in a structured format.

公开(公告)号：EP3992838B1

公开(公告)日：2024-07-31

申请号：EP21158035.2

申请日：2021-02-19

IPC分类号： G06F40/30 ,  G06F8/73

CPC分类号： G06F40/30 ,  G06F8/75 ,  G06F40/205 ,  G06F40/279 ,  G06N3/08 ,  G06N3/045

公开(公告)号：EP3436917B1

公开(公告)日：2024-06-26

申请号：EP17717289.7

申请日：2017-03-29

IPC分类号： G06F3/0488 ,  G06F17/10 ,  G09B7/02 ,  H04N21/432 ,  H04N21/4728 ,  H04N21/472 ,  H04N21/458

CPC分类号： G09B7/02 ,  H04N21/4325 ,  H04N21/47205 ,  H04N21/47217 ,  G06F3/04883 ,  G06F40/171 ,  G06F40/205 ,  G06F40/169 ,  G06V30/387

公开(公告)号：EP4369215A1

公开(公告)日：2024-05-15

申请号：EP22907900.9

申请日：2022-12-13

申请人： Samsung Electronics Co., Ltd.

发明人： SHIN, Haebin ,  LEE, Kangwook

IPC分类号： G06F16/25 ,  G06F16/28 ,  G06F16/22 ,  G06F40/205 ,  G06F40/279 ,  G06F40/30

CPC分类号： G06F40/205 ,  G06F40/279 ,  G06F40/30 ,  G06F16/2456

摘要： The present invention relates to an electronic device and a method of controlling same. The electronic device according to the present disclosure may comprise a memory and one or more processors, wherein the one or more processors: acquire a first data set and a second data set; acquire first vector information corresponding to entities included in the first data set and second vector information corresponding to entities included in the second data set on the basis of semantic information of the first data set and the second data set; acquire context information of the first data set and the second data set on the basis of class information of the first data set and the second data set; acquire third vector information corresponding to the entities included in the first data set and fourth vector information corresponding to the entities included in the second data set on the basis of the acquired context information; acquire first combinational vector information by combining the first vector information and the third vector information; acquire second combinational vector information by combining the second vector information and the fourth vector information; and generate a combined data set in which the first data set and the second data set are mapped to each other, on the basis of a first combinational vector and a second combinational vector.