(19)
(11) EP 4 187 504 A8

(12) CORRECTED EUROPEAN PATENT APPLICATION
Note: Bibliography reflects the latest situation

(15) Correction information:
Corrected version no 1 (W1 A1)

(48) Corrigendum issued on:
26.07.2023 Bulletin 2023/30

(43) Date of publication:
31.05.2023 Bulletin 2023/22

(21) Application number: 22190160.6

(22) Date of filing: 12.08.2022
(51) International Patent Classification (IPC): 
G06V 30/413(2022.01)
 G06V 10/82(2022.01)
(52) Cooperative Patent Classification (CPC):
G06V 30/413; G06V 10/82
(84) Designated Contracting States:
AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR
Designated Extension States:
BA ME
Designated Validation States:
KH MA MD TN

(30) Priority: 26.11.2021 CN 202111425339

(71) Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.
Beijing 100085 (CN)

(72) Inventors:
  • LIU, Shanshan
    Beijing, 100085 (CN)
  • QIAO, Meina
    Beijing, 100085 (CN)
  • WU, Liang
    Beijing, 100085 (CN)
  • LYU, Pengyuan
    Beijing, 100085 (CN)
  • FAN, Sen
    Beijing, 100085 (CN)
  • ZHANG, Chengquan
    Beijing, 100085 (CN)
  • YAO, Kun
    Beijing, 100085 (CN)

(74) Representative: Nederlandsch Octrooibureau 
P.O. Box 29720
2502 LS The Hague
2502 LS The Hague (NL)

   


(54) METHOD FOR TRAINING TEXT CLASSIFICATION MODEL, APPARATUS, STORAGE MEDIUM AND COMPUTER PROGRAM PRODUCT


(57) The present disclosure provides a method for training a text classification model, a method for recognizing text content and apparatuses thereof, and relates to the technical field of artificial intelligence, in particular to the technical fields of deep learning and computer vision, and may be applied to scenarios such as optical character recognition or text recognition. The method for training includes: acquiring a set of to-be-trained images, the set of to-be-trained images including at least one sample image; determining predicted position information and predicted attribute information of each text line in each sample image based on each sample image; and training to obtain the text classification model, based on the annotation position information and the annotation attribute information of each text line in each sample image, and the predicted position information and the predicted attribute information of each text line in each sample image, and the text classification model is used to detect attribute information of each text line in an to-be-recognized image. The method improves the accuracy of training, so that when attribute information of a text line is determined based on the text classification model, the reliability of classification is improved.