-
1.发明公开公开(公告)号：US20240356767A1
公开(公告)日：2024-10-24
申请号：US18035488
申请日：2022-04-29
Inventor： Lirong XU , Hongxiang SHEN , Xiao CHU , Xiying ZHANG , Mingyuan MA
CPC classification number: H04L9/50 , H04L9/3218 , H04L9/3247
Abstract: A data storage method, a data storage apparatus, an electronic device, and a non-transitory computer-readable storage medium. The method is applied to a node device deployed with a blockchain node, wherein the blockchain node belongs to a user blockchain network and an object blockchain network, the user blockchain network is used to store evaluation data generated by evaluation behavior of a target user on at least one object, and the object blockchain network is used to store evaluation data generated by at least one user performing evaluation behavior on the target object, the method includes: obtaining target evaluation data on a target object, the target evaluation data being generated by the target user performing target evaluation behavior on the target object; storing the target evaluation data separately to the user blockchain network and the object blockchain network through the blockchain node.
-
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.
-
公开(公告)号：US20220300262A1
公开(公告)日：2022-09-22
申请号：US17575983
申请日：2022-01-14
Applicant: BOE Technology Group Co., Ltd.
Inventor： Zhenyan ZHAO , Hongxiang SHEN
IPC: G06F8/41
Abstract: Embodiments of the present application provide a method for constructing, running and implementing a cross-platform application, a terminal, a server, a system, and a non-transitory computer-readable storage medium. The method includes: obtaining a project template of the cross-platform application and information about a microprogram component corresponding to the project template of the cross-platform application, in response to an operation of selecting the project template of the cross-platform application by a user on a first platform, where the project template of the cross-platform application comprises a Flutter component based on a domain-specific language, and the Flutter component is configured to parse the microprogram component and load an interface of the microprogram component; and constructing an application on the first platform and generating an application package, based on the project template of the cross-platform application and the information about the microprogram component.
-
公开(公告)号：US20240370668A1
公开(公告)日：2024-11-07
申请号：US18031511
申请日：2022-03-08
Inventor： Boran JIANG , Chao JI , Hongxiang SHEN , Zhenzhong ZHANG , Ge OU , Chuqian ZHONG , Shuqi WEI , Pengfei ZHANG
IPC: G06F40/58
Abstract: The present disclosure relates to a method for training a natural language processing model, including: obtaining a sample text of natural language; determining one or more triples in the sample text, wherein each of the triples comprises two entities in the sample text and a relation between the two entities; processing the sample text based on the triples to obtain one or more knowledge fusion vectors; and training a natural language processing model by inputting the knowledge fusion vectors into the natural language processing model to obtain a target model.
-
5.发明公开公开(公告)号：US20240362259A1
公开(公告)日：2024-10-31
申请号：US18291902
申请日：2021-09-18
Inventor： Ge OU , Boran JIANG , Chao JI , Shuqi WEI , Hongxiang SHEN
IPC: G06F16/335
CPC classification number: G06F16/335
Abstract: Provided in the present disclosure are a text recommendation method and apparatus, a model training method and apparatus, and a readable storage medium. The text recommendation method includes: acquiring text retrieval information from a user; when it is determined that there is historical text retrieval information for the user, determining text information of each text in a text set retrieved by using the text retrieval information; performing embedded representation on the text information of each text based on a self-attention model, and determining a text embedding vector of each text; inputting the text embedding vector of each text into a trained graph convolutional network model, to obtain the probability of interaction between the user and each text in the text set; and screening out, from the text set, target text which meets a preset interaction probability, and recommending the target text to the user.
-
Patent Agency Ranking
公开(公告)号：US20240320858A1
公开(公告)日：2024-09-26
申请号：US18272360
申请日：2021-10-15
Inventor： Chao JI , Hongxiang SHEN , Ge OU , Boran JIANG , Shuqi WEI
CPC classification number: G06T7/75 , G06T7/11 , G06T9/00 , G06T2207/20021 , G06T2207/20081
Abstract: The present disclosure relates to a meter recognition method, which includes: determining embedded features of pixels in a target image of a meter, and encoding position information of the pixels to obtain encoded position features; inputting superimposed features obtained by superimposing the encoded position features and the embedded features into an encoder of a target model; wherein an input of the target model includes the labels, and an output of the target model includes coordinates of key points in a sample image of the meter. According to the present disclosure, the image of the meter can be processed by the trained target model, the coordinates of key points in the target image of the meter are outputted. It can reduce manual operations and improve efficiency, and on the other hand, it can avoid possible misoperations during manual operations, which is beneficial for improving accuracy.
-
公开(公告)号：US20240419438A1
公开(公告)日：2024-12-19
申请号：US17916258
申请日：2021-03-30
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Zhenyan ZHAO , Zhe ZHANG , Naifu WU , Chu CHU , Yu SHI , Hongxiang SHEN
IPC: G06F8/71
Abstract: A program data package generation method, the method includes: obtaining configuration information of a target application program, the configuration information including an identifier of a platform to which the target application program is applicable; obtaining data package(s) of target component(s) in the target application program according to the configuration information, each target component being adapted to the platform; and calling a preset automated construction script, and generating a data package of the target application program according to the configuration information and the data package of the target component.
-
8.发明公开公开(公告)号：US20240083442A1
公开(公告)日：2024-03-14
申请号：US18274493
申请日：2021-10-21
Inventor： Junjie ZHAO , Hongxiang SHEN
IPC: B60W40/09 , B60W30/182 , B60W50/08 , B60W60/00 , H04L9/00
CPC classification number: B60W40/09 , B60W30/182 , B60W50/082 , B60W60/005 , H04L9/50 , B60W2540/043 , B60W2556/10 , H04L2209/84
Abstract: A data storage method, an apparatus, an electronic device, and a computer-readable storage medium. The method includes: detecting a mode switching behavior performed by an operator of a vehicle, the mode switching behavior being used to trigger switching a driving mode of the vehicle between a manual driving mode and an automatic driving mode; acquiring first data corresponding to the mode switching behavior, the first data including a vehicle identification of the vehicle, switching trigger information corresponding to the mode switching behavior and time information corresponding to the mode switching behavior; storing the first data to a blockchain network.
-
9.发明公开公开(公告)号：US20240054489A1
公开(公告)日：2024-02-15
申请号：US18278380
申请日：2021-10-27
Inventor： Junjie ZHAO , Hongxiang SHEN
CPC classification number: G06Q20/401 , G08G1/04 , G06Q20/389
Abstract: The present disclosure relates to traffic information processing methods, including: receiving transaction information sent by a first vehicle, the transaction information carrying violation information of the target vehicle detected by the first vehicle; the smart contract being used to determine second vehicles to verify the transaction information, and sending the violation information to the second vehicles such that the second vehicles generate verification results based on the violation information; determining whether the target vehicle has violated traffic rules based on the verification results; if determining that the target vehicle has violated traffic rules, storing the violation information in the blockchain network.
-
公开(公告)号：US20250069326A1
公开(公告)日：2025-02-27
申请号：US18576357
申请日：2022-12-23
Applicant: BOE Technology Group Co., Ltd.
Inventor： Zhe ZHANG , Naichuan CHEN , Danfeng ZHU , Hongxiang SHEN
Abstract: Provided is a method for rendering an image. The method includes: acquiring a plurality of pieces of raw point cloud data by scanning an object with a scanning device, wherein any one piece of raw point cloud data is configured to describe a data acquisition point on the object; determining at least one piece of boundary line data based on the plurality of pieces of raw point cloud data, wherein any one piece of boundary line data is configured to describe a contour boundary on the object; and determining an object image based on the plurality of pieces of raw point cloud data and the at least one piece of boundary line data, and rendering the object image.
-
-
-
-
-
-
-
-
-
Search Results
13
records
(took 0.02 seconds)
