公开(公告)号：US20230048495A1

公开(公告)日：2023-02-16

申请号：US17974183

申请日：2022-10-26

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Qunyi XIE ,  Xiameng QIN ,  Mengyi EN ,  Dongdong ZHANG ,  Ju HUANG ,  Yangliu XU ,  Yi CHEN ,  Kun YAO

IPC: G06V30/413 ,  G06V10/764 ,  G06V10/24 ,  G06V10/75 ,  G06V30/414

Abstract: A method and a platform of generating a document, an electronic device, and a storage medium are provided, which relate to a field of an artificial intelligence technology, in particular to fields of computer vision and deep learning technologies, and may be applied to a text recognition scenario and other scenarios. The method includes: performing a category recognition on a document picture to obtain a target category result; determining a target structured model matched with the target category result; and performing, by using the target structured model, a structure recognition on the document picture to obtain a structure recognition result, so as to generate an electronic document based on the structure recognition result, wherein the structure recognition result includes a field attribute recognition result and a field position recognition result.

公开(公告)号：US20220101642A1

公开(公告)日：2022-03-31

申请号：US17545765

申请日：2021-12-08

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Qunyi XIE ,  Yangliu XU ,  Xiameng QIN ,  Chengquan ZHANG

IPC: G06V30/19 ,  G06N20/00

Abstract: The disclosure discloses a method for character recognition, an electronic device, and a storage medium. The technical solution includes: obtaining a test sample image and a test sample character both corresponding to a test task; performing fine-tuning on a trained meta-learning model based on the test sample image and the test sample character to obtain a test task model; obtaining a test image corresponding to the test task; and generating a test character corresponding to the test image by inputting the test image into the test task model.

公开(公告)号：US20230042234A1

公开(公告)日：2023-02-09

申请号：US17972253

申请日：2022-10-24

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Yangliu XU ,  Qunyi Xie ,  Yi Chen ,  Xiameng Qin ,  Chengquan Zhang ,  Kun Yao

IPC: G06N3/08

Abstract: A method for training a model includes: obtaining a scene image, second actual characters in the scene image and a second construct image; obtaining first features and first recognition characters of characters obtained by performing character recognition on the scene image using the model to be trained; obtaining second features of characters obtained by performing character recognition on the second construct image using the training auxiliary model; and obtaining a character recognition model by adjusting model parameters of the model to be trained based on the first recognition characters, the second actual characters, the first features and the second features.

公开(公告)号：US20230215203A1

公开(公告)日：2023-07-06

申请号：US18168759

申请日：2023-02-14

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Pengyuan LV ,  Chengquan ZHANG ,  Shanshan LIU ,  Meina QIAO ,  Yangliu XU ,  Liang WU ,  Xiaoyan WANG ,  Kun YAO ,  Junyu Han ,  Errui DING ,  Jingdong WANG ,  Tian WU ,  Haifeng WANG

IPC: G06V30/19

CPC classification number: G06V30/19147 ,  G06V30/19167

Abstract: The present disclosure provides a character recognition model training method and apparatus, a character recognition method and apparatus, a device and a medium, relating to the technical field of artificial intelligence, and specifically to the technical fields of deep learning, image processing and computer vision, which can be applied to scenarios such as character detection and recognition technology. The specific implementing solution is: partitioning an untagged training sample into at least two sub-sample images; dividing the at least two sub-sample images into a first training set and a second training set; where the first training set includes a first sub-sample image with a visible attribute, and the second training set includes a second sub-sample image with an invisible attribute; performing self-supervised training on a to-be-trained encoder by taking the second training set as a tag of the first training set, to obtain a target encoder.

公开(公告)号：US20230134615A1

公开(公告)日：2023-05-04

申请号：US18146839

申请日：2022-12-27

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Qunyi XIE ,  Dongdong ZHANG ,  Xiameng QIN ,  Mengyi EN ,  Yangliu XU ,  Yi CHEN ,  Ju HUANG ,  Kun YAO

IPC: G06F9/48 ,  G06F40/205 ,  G06F9/50

Abstract: A method of processing a task, an electronic device, and a storage medium are provided, which relate to a field of artificial intelligence, in particular to fields of deep learning and computer vision, and may be applied to OCR optical character recognition and other scenarios. The method includes: parsing labeled data to be processed according to a task type identification, to obtain task labeled data, a tag information of the task labeled data is matched with the task type identification, and the task labeled data includes first task labeled data and second task labeled data; training a model using the first task labeled data, to obtain candidate models, the model is determined according to the task type identification; and determining a target model from the candidate models according to a performance evaluation result obtained by performing performance evaluation on the plurality of candidate models using the second task labeled data.

公开(公告)号：US20220415071A1

公开(公告)日：2022-12-29

申请号：US17899712

申请日：2022-08-31

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Chengquan ZHANG ,  Pengyuan LV ,  Shanshan LIU ,  Meina QIAO ,  Yangliu XU ,  Liang WU ,  Jingtuo LIU ,  Junyu HAN ,  Errui DING ,  Jingdong WANG

IPC: G06V30/19 ,  G06V30/18 ,  G06T9/00 ,  G06V30/262 ,  G06N20/00

Abstract: The present disclosure provides a training method of a text recognition model, a text recognition method, and an apparatus, relating to the technical field of artificial intelligence, and specifically, to the technical field of deep learning and computer vision, which can be applied in scenarios such as optional character recognition, etc. The specific implementation solution is: performing mask prediction on visual features of an acquired sample image, to obtain a predicted visual feature; performing mask prediction on semantic features of acquired sample text, to obtain a predicted semantic feature, where the sample image includes text; determining a first loss value of the text of the sample image according to the predicted visual feature; determining a second loss value of the sample text according to the predicted semantic feature; training, according to the first loss value and the second loss value, to obtain the text recognition model.