Abstract: An object detection method and apparatus include obtaining a point cloud of a scene that includes location information of points. The point cloud is mapped to a 3D voxel representation. A convolution operation is performed on the feature information of the 3D voxel to obtain a convolution feature set and initial positioning information of a candidate object region is determined based on the convolution feature set. A target point is located in the candidate object region in the point cloud is determined and the initial positioning information of the candidate object region is adjusted based on the location information and target convolution feature information of the target point. Positioning information of a target object region is obtained to improve object detection accuracy.
Type:
Grant
Filed:
May 27, 2021
Date of Patent:
February 27, 2024
Assignee:
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
Inventors:
Yi Lun Chen, Shu Liu, Xiao Yong Shen, Yu Wing Tai, Jia Ya Jia
Abstract: An audio acquisition device positioning method is provided. In the method, a first image that includes an audio acquisition device is obtained. The audio acquisition device in the first image is identified. First coordinate data of the identified audio acquisition device in the first image is obtained. First displacement data is determined according to the first coordinate data and historical coordinate data of the audio acquisition device. First coordinates of the audio acquisition device are determined according to the first displacement data.
Type:
Grant
Filed:
July 15, 2021
Date of Patent:
February 27, 2024
Assignee:
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
Abstract: An artificial intelligence (AI) parameter configuration method for a racing AI model performed by an AI parameter configuration device is provided. A first parameter set including m sets of AI parameters is obtained. Each of the m sets of AI parameters is used by the racing AI model to travel on a track. The racing AI model is controlled to undergo an adaptation degree test according to each of the m sets of AI parameters to obtain m adaptation degrees. The m adaptation degrees are positively correlated with travel distances of the racing AI model on the track according to the m sets of AI parameters. A second parameter set is generated according to the first parameter set in a case that all the m adaptation degrees are less than an adaptation degree threshold. In a case that a target adaptation degree in the m adaptation degrees is greater than the adaptation degree threshold, an AI parameter corresponding to the target adaptation degree is configured as a target AI parameter.
Type:
Grant
Filed:
June 11, 2020
Date of Patent:
February 27, 2024
Assignee:
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
Abstract: An animation display method is provided. In the method, a first display area is displayed on a game setting interface of a game application. The first display area is configured to display a first operation flow in the game application. A first picture is displayed in the first display area when the first display area is not selected. The first picture is at least one display picture in the first operation flow. A first animation is played in the first display area when the first display area is selected. The first animation plays at least one group of display pictures in the first operation flow.
Type:
Grant
Filed:
October 20, 2021
Date of Patent:
February 27, 2024
Assignee:
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
Abstract: The present disclosure includes a method for processing distributed data. In the method, the distributed data of a first main body is obtained. The distributed data has a transfer identifier. The distributed data is transferred, in response to a second main body different from the first main body, to a management address based on the transfer identifier when the distributed data meets a first condition. The first condition is that the distributed data includes abnormal information. The distributed data transferred to the management address freezes transfer of the distributed data by the first main body.
Type:
Grant
Filed:
June 1, 2021
Date of Patent:
February 27, 2024
Assignee:
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
Inventors:
Maocai Li, Zongyou Wang, Hu Lan, Yifang Shi
Abstract: A virtual-environment-based object construction method is disclosed for a computer device. The method includes displaying an environment interface corresponding to a virtual environment, receiving a three-dimensional (3D) model input operation, the 3D model input operation being used for inputting a target 3D model of a target object, receiving a position input operation, the position input operation being used for determining a display position of the target object in the virtual environment, and displaying the target object at the display position according to the 3D model input operation and the position input operation, the target object being obtained by filling with voxel blocks within a contour range of the target 3D model.
Type:
Grant
Filed:
May 28, 2021
Date of Patent:
February 27, 2024
Assignee:
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
Abstract: A computing device transmits, to a second node, first consensus voting information for a target block. The device receives, from the second node, second consensus voting information for the target block. The device determines a consensus result for the target block according to the first and second consensus voting information. In accordance with a determination that the consensus result is a consensus success result, the device activates an accounting duration window. The device performs accounting processing on the target block in the predetermined time duration of the accounting duration window. The device receives, from the second node, a first accounting completion message for the target block transmitted by the second node in the accounting duration window. In accordance with a determination that accounting processing on the target block is completed in the accounting duration window, the device transmits a second accounting completion message to the second node.
Type:
Grant
Filed:
April 26, 2022
Date of Patent:
February 27, 2024
Assignee:
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
Abstract: An image processing method includes obtaining a sample image, a category label of the sample image, and a label value of the category label. The method further includes calling a preset image processing model to perform segmentation processing on the sample image to obtain at least two sub-regions. The method further includes calling the preset image processing model to perform category prediction on the sample image to obtain a predicted value of the category label. The method further includes updating a network parameter of the preset image processing model according to center coordinates of the sub-regions, the label value of the category label, and the predicted value of the category label. The method further includes performing iterative training on the preset image processing model according to the updated network parameter, to obtain a target image processing model.
Type:
Grant
Filed:
August 27, 2021
Date of Patent:
February 27, 2024
Assignee:
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
Abstract: A data storage method is provided at a computer system, including: obtaining first data and second data of a target object, the first data and the second data being data of different dimensions for measuring any aspect of the target object from generation to existence; storing the first data and the second data of the target object in the first node; receiving audit information of the first node for indicating the first data and the second data stored in the first node; verifying the audit information based on target audit information of at least one target node that transacts with the first node; broadcasting a verification success notification in the data storage system in a case that the verification succeeds; and determining that a consensus on the audit information is reached in a case that the received verification success notification meets a consensus success condition.
Type:
Grant
Filed:
August 12, 2020
Date of Patent:
February 27, 2024
Assignee:
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
Abstract: A method for adjusting the position of a virtual button includes: presenting a button adjustment interface of a virtual scene including a target virtual button; controlling, in response to a movement operation for the target virtual button, the target virtual button to move in the button adjustment interface, to adjust a presentation position of the target virtual button in the virtual scene, wherein at least two presentation forms of the target virtual button are in the virtual scene; and presenting prompt information in response to the target virtual button being moved to a boundary area in the button adjustment interface, the prompt information being used for prompting that the target virtual button is displayed abnormally in the virtual scene when the target virtual button is in a target presentation form of the at least two presentation forms.
Type:
Application
Filed:
October 24, 2023
Publication date:
February 22, 2024
Applicant:
Tencent Technology (Shenzhen) Company Limited
Abstract: A real-time voice recognition method and a real-time voice recognition model training method are provided. The model training method includes: obtaining an audio feature sequence of sample voice data, the audio feature sequence comprising audio features of a plurality of audio frames of the sample voice data; inputting the audio feature sequence to an encoder of the real-time voice recognition model; chunking the audio feature sequence into a plurality of chunks by the encoder according to a mask matrix; encoding each of the chunks to obtain a hidden layer feature sequence of the sample voice data; decoding the hidden layer feature sequence by a decoder of the real-time voice recognition model to obtain a predicted recognition result for the sample voice data; and training the real-time voice recognition model based on the predicted recognition result and a real recognition result of the sample voice data.
Type:
Application
Filed:
October 26, 2023
Publication date:
February 22, 2024
Applicant:
Tencent Technology (Shenzhen) Company Limited
Abstract: A data processing method, apparatus, device, and medium are provided. The method may include obtaining a set of edges marked as usable for cutting from a two-dimensional mesh model, searching the set of edges to obtain a cut path set, calculating, for each candidate cut path in the cut path set, a path length, and calculating a structural evaluation value corresponding to the candidate cut path.
Type:
Application
Filed:
November 2, 2023
Publication date:
February 22, 2024
Applicant:
Tencent Technology (Shenzhen) Company Limited
Abstract: A loop filtering method, a video coding and decoding method and apparatus, a medium, and an electronic device that can obtain block classification information of a luma component in a video image frame in a case that adaptive loop filtering is performed (S710), use the block the block classification information to determine block classification information of a chroma component in the video image frame in a case that cross-component adaptive loop filtering is performed (S720); and select a corresponding filter coefficient to perform cross-component adaptive loop filtering on the chroma component according to the block classification information of the chroma component.
Type:
Application
Filed:
October 31, 2023
Publication date:
February 22, 2024
Applicant:
Tencent Technology (Shenzhen) Company Limited
Abstract: Disclosed are a reconfigurable optical add-drop multiplexer, and an optical signal processing method. The reconfigurable optical add-drop multiplexer includes: at least one optical cross-connect device and at least two optical signal processing devices. Each optical signal processing device includes a wavelength-selective switch and a filter. The wavelength-selective switch is configured to perform wavelength-based allocation on inputted dense wavelength division multiplexing optical signals and input the dense wavelength division multiplexing optical signals into the filter. The filter is configured to separate optical signals outputted by the wavelength-selective switch into single-channel optical signals, and multiplex a plurality of single-channel optical signals outputted by the optical cross-connect device and input the multiplexed single-channel optical signals into the wavelength-selective switch.
Type:
Grant
Filed:
May 17, 2021
Date of Patent:
February 20, 2024
Assignee:
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
Inventors:
Minggang Chen, Fangchao Li, Yu Wang, Xiang Li
Abstract: Embodiments of this application disclose an image description generation method performed at a computing device. The method includes: obtaining a target image; generating a first global feature vector and a first label vector set of the target image; generating a first multi-mode feature vector of the target image through a matching model, the matching model being a model obtained through training according to a training image and reference image description information of the training image; and applying the first multi-mode feature vector, the first global feature vector, and the first label vector set to a computing model, to obtain the target image description information, the computing model being a model obtained through training according to image description information of the training image and the reference image description information.
Type:
Grant
Filed:
January 31, 2022
Date of Patent:
February 20, 2024
Assignee:
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
Abstract: This application provides a method for training a pose recognition model performed at a computer device. The method includes: inputting a sample image labeled with human body key points into a feature map model included in a pose recognition model, to output a feature map of the sample image; inputting the feature map into a two-dimensional (2D) model included in the pose recognition model, to output 2D key point parameters used for representing a 2D human body pose; input a target human body feature map cropped from the feature map and the 2D key point parameter into a three-dimensional (3D) model included in the pose recognition model, to output 3D pose parameters used for representing a 3D human body pose; constructing a target loss function based on the 2D key point parameters and the 3D pose parameters; and updating the pose recognition model based on the target loss function.
Type:
Grant
Filed:
May 25, 2021
Date of Patent:
February 20, 2024
Assignee:
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
Inventors:
Jingmin Luo, Xiaolong Zhu, Yitong Wang, Xing Ji
Abstract: A computer device obtains a plurality of medical images. The device generates a texture image based on image data of a region of interest in the medical images. The device extracts a local feature from the texture image using a first network model. The device extracts a global feature from the medical images using a second network model. The device fuses the extracted local feature and the extracted global feature to form a fused feature. The device performs image classification based on the fused feature.
Type:
Grant
Filed:
August 9, 2021
Date of Patent:
February 20, 2024
Assignee:
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
Abstract: The present disclosure provides an image processing method and apparatus, and an electronic device, and relates to the field of artificial intelligence (AI). The method includes: obtaining an input image and extracting region features of image regions in the input image to obtain a first image feature; processing pixels in the first image feature according to a predetermined rule, and determining a second image feature according to the processed pixels; and determining, based on the second image feature and at least one word vector that is determined for the input image, word vectors corresponding to the region features of the image regions in the first image feature at different moments, predicting positions of the word vectors in a text description, and forming the text description corresponding to the input image according to the word vectors and the positions.
Type:
Grant
Filed:
November 2, 2021
Date of Patent:
February 20, 2024
Assignee:
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
Inventors:
Lei Ke, Wenjie Pei, Ruiyu Li, Xiaoyong Shen, Yuwing Tai, Jiaya Jia
Abstract: This application relates to a file loading method performed at an electronic device, and a non-transitory computer-readable storage medium thereof. The method including: receiving, in response to a user operation, an instruction for loading a target file; determining an associated feature of at least one piece of resource information in the target file; determining a type of the resource information according to the associated feature of the resource information; and loading the resource information by using a loading algorithm corresponding to the type of the resource information.
Type:
Grant
Filed:
May 19, 2021
Date of Patent:
February 20, 2024
Assignee:
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
Abstract: Embodiments of this disclosure disclose a virtual item control method and apparatus, a terminal, and a non-transitory storage medium, and belong to the field of computer technologies. The method includes: displaying a plurality of item icons after a press operation on a throw button is detected; controlling, in response to the press operation moving to the target item icon and a duration reaches a target duration, a virtual object to hold a target virtual item corresponding to the target item icon; controlling, in response to a movement of the press operation, the virtual object to aim at a target position; and controlling, in response to a release of the press operation, the virtual object to throw the target virtual item to the target position.
Type:
Grant
Filed:
November 24, 2021
Date of Patent:
February 20, 2024
Assignee:
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
Inventors:
Shengyu Wu, Cong Tian, Meng Qiu, Jingjing He, Dancheng Zou, Boyi Liu, Weijian Cui, Yi Li