-
1.发明申请公开(公告)号：US20220114724A1
公开(公告)日：2022-04-14
申请号：US17423439
申请日：2020-08-17
Inventor： Yongming SHI , Qiong WU , Ge OU , Chun WANG
Abstract: An image processing model generation method includes: inputting at least one training sample lesion image into an initial image processing model, the initial image processing model including a classification layer and a marking layer; calling the classification layer; calling the marking layer; obtaining a loss value of the at least one training sample lesion image in the initial image processing model; determining whether the loss value is within a preset range; if not, updating parameters of the initial image processing model, an image processing model with updated parameters being used as an initial image processing model in next training; and repeating above steps until the to loss value is within the preset range.
-
公开(公告)号：US20240320428A1
公开(公告)日：2024-09-26
申请号：US18638457
申请日：2024-04-17
Applicant: BOE Technology Group Co., Ltd.
Inventor： Pengfei ZHANG , Chao JI , Boran JIANG , Ge OU , Chuqian ZHONG , Shuqi WEI
IPC: G06F40/279 , G06V30/19
CPC classification number: G06F40/279 , G06V30/1912 , G06V30/19127 , G06V30/1916
Abstract: Provided in the present disclosure are a text recognition method, and a model and an electronic device, which are applied to a mode in which primary classification is first performed from different dimensions, and secondary classification is then performed, such that the meaning of text is analyzed from different dimensions, thereby improving the accuracy of text recognition. The method includes: acquiring text to be recognized, and performing primary classification on the text to obtain a plurality of text features, wherein the primary classification is used for performing feature extraction on the text from different dimensions, and there are differences between features extracted from the different dimensions (100); splicing the plurality of text features, so as to obtain spliced features (101); and performing secondary classification on the spliced features to obtain a text category corresponding to the text, wherein the secondary classification is used for classifying the spliced features (102).
-
公开(公告)号：US20240303798A1
公开(公告)日：2024-09-12
申请号：US18263230
申请日：2021-11-30
Inventor： Chao JI , Yaoping WANG , Hongxiang SHEN , Ge OU , Boran JIANG , Shuqi WEI , Chuqian ZHONG , Pengfei ZHANG
IPC: G06T7/00
CPC classification number: G06T7/0004 , G06T2207/20021 , G06T2207/20081 , G06T2207/20084 , G06T2207/30121
Abstract: The present disclosure relates to an image recognition method and system for a display panel, a training method, and an electronic device and a non-volatile computer-readable storage medium. The image recognition method includes: acquiring an image of a display panel, wherein the image includes gate lines extending in a first direction and data lines extending in a second direction, the gate lines and the data lines intersecting to define a plurality of sub-pixel regions, and the image further includes a defect pattern; and recognizing the defect pattern in the image by using an image recognition model to obtain defect information, wherein the defect information includes at least one of a defect type or a defect position of the defect pattern, the image recognition model comprises a first attention model configured to learn a weight proportion of a feature of the defect pattern in the image.
-
4.发明申请公开(公告)号：US20220292805A1
公开(公告)日：2022-09-15
申请号：US17754158
申请日：2021-04-15
Applicant: BOE TECHNOLOGY GROUP CO., LTD. , PEKING UNIVERSITY
Inventor： Jie FENG , Yadong MU , Shuai WANG , Guiyu TIAN , Yiming BAI , Xiangye WEI , Ge OU , Qiong WU
IPC: G06V10/26 , G06V10/44 , G06V10/764 , G06V10/774 , G06N7/00
Abstract: An image processing method and apparatus, and a device and a computer-readable storage medium. The method comprises: acquiring an image data set, wherein the image data set includes an image and accompanying text related to an unknown category in the image (S101); and generating a probability and/or distribution of the unknown category by means of an unknown category acquisition model (S102); wherein the probability and/or distribution of the unknown category comprises the probability of each pixel in the image being from the unknown category, the probability of the unknown category being present in the image, and a partitioning probability after the image is subdivided into a plurality of areas. By means of the method, a large amount of human labor costs and time can be saved on.
-
公开(公告)号：US20250037443A1
公开(公告)日：2025-01-30
申请号：US18279857
申请日：2022-11-24
Inventor： Chao JI , Boran JIANG , Ge OU , Shuqi WEI , Pengfei ZHANG , Chuqian ZHONG
IPC: G06V10/80 , G06T5/60 , G06V10/77 , G06V10/774 , G06V10/82
Abstract: A model training method includes: acquiring a sample set including a plurality of sample groups; the sample group includes an original image sample and original text samples; performing mask processing on the original image sample and the original text samples to generate a mask image sample and mask text samples; using the mask image sample and the mask text samples to perform adversarial training on a generator and a discriminator to obtain a target model; the generator includes a feature extraction network and an output network, the feature extraction network is used to perform feature extraction after information fusion of an input image and an input text of the generator.
-
Patent Agency Ranking
公开(公告)号：US20240370928A1
公开(公告)日：2024-11-07
申请号：US18291561
申请日：2021-09-29
Inventor： Boran JIANG , Qiong WU , Shuqi WEI , Chao JI , Chuqian ZHONG , Ge OU
Abstract: Disclosed are an asset value evaluation method and apparatus, a model training method and apparatus, and a readable storage medium. The asset value evaluation method includes: acquiring input asset value query information for a user; when it is determined that there is historical asset interaction information of the user, determining an asset set obtained by means of making a query using the asset value query information, the asset set includes at least one asset; performing embedding representation on each asset, so as to determine an asset embedding vector of each asset, the asset embedding vector is obtained by means of training based on the relationship between each asset and an attribute, and the attribute is used for representing an inherent parameter of the asset; and inputting the asset embedding vector of each asset into a graph convolutional network model to obtain the value of each asset for the user.
-
公开(公告)号：US20240303507A1
公开(公告)日：2024-09-12
申请号：US18026327
申请日：2022-03-30
Inventor： Boran JIANG , Ge OU , Chao JI , Chuqian ZHONG , Shuqi WEI , Pengfei ZHANG
IPC: G06N5/02 , G06Q30/0601
CPC classification number: G06N5/02 , G06Q30/0631
Abstract: Provided are a method and device for recommending goods, a method and device for training a goods knowledge graph, and a method and device for training a model. The method for training a goods knowledge graph includes: constructing an initial goods knowledge graph based on a first type of triples and a second type of triples, where a format of the first type of triples is head entity-relation-tail entity, and a format of the second type of triples is entity-attribute-attribute value (S101); and training the initial goods knowledge graph based on a graph embedding model to obtain embedding vectors of entities in the trained goods knowledge graph (S102).
-
公开(公告)号：US20250054280A1
公开(公告)日：2025-02-13
申请号：US18280299
申请日：2022-09-30
Inventor： Chao JI , Ge OU , Chuqian ZHONG , Pengfei ZHANG , Boran JIANG , Shuqi WEI
IPC: G06V10/774 , G06F40/279 , G06V10/40
Abstract: The present disclosure provides a training method and apparatus for an image-text matching model, a device and a storage medium. The method includes: acquiring a positive sample and a negative sample; where the positive sample includes text and an image, the text in the positive sample is used to describe content of the image in the positive sample; the negative sample includes text and an image, the text in the negative sample describes content that is inconsistent with content of the image in the negative sample; training the image-text matching model by using the acquired positive sample and the acquired negative sample based on a manner of contrastive learning; where the image-text matching model is used to predict, for an input image and input text, whether the input text is used to describe content of the input image.
-
公开(公告)号：US20250007156A1
公开(公告)日：2025-01-02
申请号：US18264192
申请日：2022-09-22
Inventor： Zongmin LIU , Ge OU , Feng QU
IPC: H01Q3/36
Abstract: The present disclosure provides a tunable antenna control method and apparatus, and a tunable antenna system. The tunable antenna control method includes: acquiring a beam pointing angle of a tunable antenna, calculating a phase-configuration parameter according to the beam pointing angle through a parameter calculation model, where the parameter calculation model is an artificial intelligence model taking the beam pointing angle as an input and the phase-configuration parameter of a phase shifter as an output, and controlling the phase shifter of the tunable antenna to perform phase configuration according to the phase-configuration parameter outputted by the parameter calculation model.
-
10.发明公开公开(公告)号：US20240330658A1
公开(公告)日：2024-10-03
申请号：US18554730
申请日：2022-08-17
Inventor： Chuqian ZHONG , Boran JIANG , Ge OU , Chao JI , Shuqi WEI , Mengjun HOU
IPC: G06N3/0455 , G06N3/0499
CPC classification number: G06N3/0455 , G06N3/0499
Abstract: The present disclosure relates to a method for natural language processing, a method of training a natural language processing model, an electronic device, and a non-transitory computer-readable storage medium, and relates to the technical field of natural language processing. The method for natural language processing includes: acquiring text data; and processing the text data by using a natural language processing model to obtain output information, wherein the natural language processing model comprises a first attention model, the first attention model comprising a sequential coding matrix for adding, on the basis of the text data, sequential relation information between at least one word and other words in the text data.
-
-
-
-
-
-
-
-
-
Search Results
16
records
(took 0.017 seconds)
