Processing

Please wait...

Settings

Settings

Goto Application

1. WO2021112930 - TRAINING OPTICAL CHARACTER DETECTION AND RECOGNITION MODELS FOR ROBOTIC PROCESS AUTOMATION

Publication Number WO/2021/112930
Publication Date 10.06.2021
International Application No. PCT/US2020/047169
International Filing Date 20.08.2020
IPC
G06K 9/00 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
G06K 9/20 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
20Image acquisition
G06N 20/00 2019.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
CPC
G06F 9/45512
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
9Arrangements for program control, e.g. control units
06using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
44Arrangements for executing specific programs
455Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
45504Abstract machines for programme code execution, e.g. Java virtual machine [JVM], interpreters, emulators
45508Runtime interpretation or emulation, e g. emulator loops, bytecode interpretation
45512Command shells
G06K 2209/01
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
2209Indexing scheme relating to methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
01Character recognition
G06K 9/72
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
72using context analysis based on the provisionally recognised identity of a number of successive patterns, e.g. a word
Applicants
  • UIPATH, INC. [US]/[US]
Inventors
  • LAZA, Dorin, Andrei
  • NGUYEN, Trong, Canh
Agents
  • LEONARD, Michael, Aristo, II
  • PATEL, Sheetal, S.
Priority Data
16/700,49402.12.2019US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) TRAINING OPTICAL CHARACTER DETECTION AND RECOGNITION MODELS FOR ROBOTIC PROCESS AUTOMATION
(FR) FORMATION DE MODÈLES DE DÉTECTION ET DE RECONNAISSANCE OPTIQUE DE CARACTÈRES POUR AUTOMATISATION DE PROCESSUS ROBOTIQUES
Abstract
(EN)
Techniques for training an optical character recognition (OCR) model to detect and recognize text in images for robotic process automation (RPA) are disclosed. A text detection model and a text recognition model may be trained separately and then combined to produce the OCR model. Synthetic data and a smaller amount of real, human-labeled data may be used for training to increase the speed and accuracy with which the OCR text detection model and the text recognition model can be trained. After the OCR model has been trained, a workflow may be generated that includes an activity calling the OCR model, and a robot implementing the workflow may be generated and deployed.
(FR)
La présente invention concerne des techniques de formation d’un modèle de reconnaissance optique de caractères (OCR) pour détecter et reconnaître un texte dans des images en vue d’une automatisation de processus robotiques (RPA). Un modèle de détection de texte et un modèle de reconnaissance de texte peuvent être formés séparément et ensuite combinés pour produire un modèle OCR. Des données synthétiques et une plus petite quantité de données réelles, marquées par une personne, peuvent être utilisées pour la formation afin d’augmenter la vitesse et la précision avec lesquelles le modèle de détection de texte par OCR et le modèle de reconnaissance de texte peuvent être formés. Après que le modèle OCR a été formé, un flux de travail, qui inclut une activité appelant le modèle OCR, peut être généré, et un robot mettant en œuvre le flux de travail peut être généré et déployé.
Also published as
Latest bibliographic data on file with the International Bureau