Patents Assigned to Tencent Technology (Shenzhen) Company Limited
-
Patent number: 11928893Abstract: An action recognition method includes: obtaining original feature submaps of each of temporal frames on a plurality of convolutional channels by using a multi-channel convolutional layer; calculating, by using each of the temporal frames as a target temporal frame, motion information weights of the target temporal frame on the convolutional channels according to original feature submaps of the target temporal frame and original feature submaps of a next temporal frame, and obtaining motion information feature maps of the target temporal frame on the convolutional channels according to the motion information weights; performing temporal convolution on the motion information feature maps of the target temporal frame to obtain temporal motion feature maps of the target temporal frame; and recognizing an action type of a moving object in image data of the target temporal frame according to the temporal motion feature maps of the target temporal frame on the convolutional channels.Type: GrantFiled: November 18, 2021Date of Patent: March 12, 2024Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Donghao Luo, Yabiao Wang, Chenyang Guo, Boyuan Deng, Chengjie Wang, Jilin Li, Feiyue Huang, Yongjian Wu
-
Patent number: 11930197Abstract: A video decoding method includes: obtaining target type information of a target video upon receiving a play instruction of the target video, the target type information indicating a type of the target video; obtaining specified type information of a plurality of decoders configured in a terminal, the specified type information of the decoders indicating types of videos of which decoding is supported by the decoders; and determining, from the plurality of decoders by comparing the specified type information of the plurality of decoders with the target type information, a target decoder that supports decoding of the target video. The target video is decoded by using the target decoder to play a decoded video.Type: GrantFiled: July 15, 2021Date of Patent: March 12, 2024Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventor: Cunai Han
-
Patent number: 11928765Abstract: Embodiments of this disclosure include an information processing method, an information processing apparatus, and non-transitory computer-readable storage medium. A first key frame that includes initial posture data corresponding to an initial posture of a target virtual character is obtained. Target posture data is determined by inputting the initial posture data and a target task to a policy network trained by reinforcement learning. An output of the policy network indicates the target posture data corresponding to a target posture. At least one force to be acted on at least one first joint of the target virtual character is determined according to the initial and the target posture data. A posture of the target virtual character is adjusted from the initial posture to the target posture by applying the at least one force on the at least one first joint to obtain a second key frame.Type: GrantFiled: March 4, 2022Date of Patent: March 12, 2024Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventor: Qunfen Lin
-
Patent number: 11928863Abstract: This application discloses a method for determining an implantation location of recommendation information performed at a computer device. The method includes: acquiring a target video; acquiring, according to a scene change status of the target video, a target video frame being used for location detection; performing image recognition on the target video frame to obtain masking information of the target video frame including a first region of an object of a target type in the target video frame; and determining an implantation location of recommendation information in the target video frame based on the first region. Image recognition processing is performed on the target video frame to obtain the masking information of the target video frame, so as to determine the implantation location in the target video frame on the basis of the first region corresponding to the object of the target type in the target video frame.Type: GrantFiled: July 19, 2021Date of Patent: March 12, 2024Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Hui Sheng, Dongbo Huang
-
Patent number: 11928816Abstract: An image processing method includes: obtaining DCE magnetic resonance images corresponding to a plurality of time points for a same detection target; determining average pixel grayscale values of images of a same lesion region in the DCE magnetic resonance images of the plurality of time points respectively; determining a time to peak according to the average pixel grayscale values corresponding to the plurality of time points; and generating a first-stage time-intensity image before the time to peak and a second-stage time-intensity image after the time to peak respectively according to the DCE magnetic resonance images and the time to peak. The first-stage time-intensity image and the second-stage time-intensity image are 3D images. A pixel grayscale value of each pixel in the first-stage time-intensity image and the second-stage time-intensity image represents a change rate of blood supply intensity and reflects a severity level of a lesion corresponding to the lesion region.Type: GrantFiled: July 22, 2021Date of Patent: March 12, 2024Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Liang Wang, Jun Zhang
-
Patent number: 11929090Abstract: A method for matching audio clips includes: obtaining a first feature sequence corresponding to a first audio clip and a second feature sequence corresponding to a second audio clip; constructing a distance matrix, elements in the distance matrix representing respective distances between first positions in the first feature sequence and second positions in the second feature sequence; calculating a first accumulation distance between a start position and a target position in the distance matrix, and calculating a second accumulation distance between an end position and the target position in the distance matrix; and calculating a minimum distance between the first feature sequence and the second feature sequence based on the first accumulation distance and the second accumulation distance, and determining a degree of matching between the first audio clip and the second audio clip according to the minimum distance.Type: GrantFiled: June 2, 2021Date of Patent: March 12, 2024Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Fang Chao Lin, Wei Biao Yun, Peng Zeng
-
Patent number: 11928485Abstract: A data transmission method includes: displaying a target message in a session interface; in response to a trigger operation on the target message, outputting a resource transmission interface including an object display region and an icon display region; and the object display region including an object identifier of at least one transmission object, and the icon display region including a message icon corresponding to the target message; moving the message icon from the icon display region to the object display region according to a moving operation on the message icon; and transmitting, in response to the message icon being moved to the object display region, the data resource to a target transmission object of the at least one transmission object in the object display region, the target transmission object being determined according to an ending position of a movement track of the message icon corresponding to the moving operation.Type: GrantFiled: October 12, 2022Date of Patent: March 12, 2024Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Zhiying Wu, Xuejun Sun, Jinhui Chen
-
Patent number: 11928800Abstract: An image coordinate system transformation method includes obtaining video images acquired by adjacent cameras, the adjacent cameras including a first camera and a second camera that have an overlapping photography region on a ground plane, recognizing N groups of key points of a target object on the ground plane from the video images acquired by the adjacent cameras, each group of key points including first key point extracted from a video image of the first camera and a second key point extracted from a video image of the second camera, the first key point and the second key point being the same feature point of the same target object appearing in the adjacent cameras at the same moment, and N being an integer greater than or equal to 3, and calculating a transformation relationship between image coordinate systems of the adjacent cameras according to the N groups of key points.Type: GrantFiled: July 12, 2021Date of Patent: March 12, 2024Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventor: Xiangqi Huang
-
Publication number: 20240080429Abstract: A video data processing method includes generating, based on a spliced texture map and depth map, an encoded video bitstream of a free-view video based on multiple images collected by an ith camera in a camera array. The method further includes obtaining boundary metadata information indicating a scene boundary of the free-view video, and adding the boundary metadata information to a file encapsulation data box, to obtain an extended data box. The method further includes performing encapsulation on the encoded video bitstream and the extended data box to obtain a video media file of the free-view video including the boundary metadata information. The method further includes delivering the video media file to a video client, enabling the video client to determine that the ith camera is a boundary camera, and to render video content in the scene boundary indicated by the boundary metadata information.Type: ApplicationFiled: November 14, 2023Publication date: March 7, 2024Applicant: Tencent Technology (Shenzhen) Company LimitedInventors: Ying HU, Shan LIU
-
Publication number: 20240080478Abstract: A point cloud encoding and decoding method including: obtaining encoding limit information that comprises a group quantity limit threshold; obtaining a transform coefficient sequence of point cloud points based on the encoding limit information, where the point cloud points are comprised in a point cloud group that has a quantity less than or equal to the group quantity limit threshold, and where the transform coefficient sequence is obtained by sorting transform coefficients of the point cloud points; and encoding the transform coefficient sequence to obtain a point cloud group bitstream that corresponds to the point cloud group.Type: ApplicationFiled: November 6, 2023Publication date: March 7, 2024Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Wenjie ZHU, Shai Cohen, Dor OZ, Alon Gabbay, Idan Yokev
-
Publication number: 20240080495Abstract: A processing method includes generating first training data through a kth updated video coding application, the first training data including a sample original video frame as a training label, and a first sample to-be-filtered reconstructed frame output from the kth updated video coding application and corresponding to the sample original video frame. The method further includes, based on the sample original video frame and the first sample to-be-filtered reconstructed frame, training a second filtering model in the kth updated video coding application to obtain the second filtering model in a training convergence state, and integrating the second filtering model in the training convergence state into the kth updated video coding application to obtain a (k+1)th updated video coding application.Type: ApplicationFiled: November 14, 2023Publication date: March 7, 2024Applicant: Tencent Technology (Shenzhen) Company LimitedInventor: Liqiang WANG
-
Publication number: 20240080487Abstract: In a method for processing media data, signaling description information of the media data is received. The media data includes N media frames of a plurality of qualities that are encapsulated into M tracks to obtain a media file corresponding to each of the M tracks. The media frames encapsulated into a same track of the M tracks have a same quality of the plurality of qualities. The signaling description information includes combination indication information that indicates the media files allowed for combination decoding in the M media files. At least two media files are obtained according to the combination indication information. The media files correspond to at least two tracks in the M tracks having the same quality. The combination decoding is performed on the obtained at least two media files.Type: ApplicationFiled: November 14, 2023Publication date: March 7, 2024Applicant: Tencent Technology (Shenzhen) Company LimitedInventor: Ying HU
-
Patent number: 11918901Abstract: A method and apparatus for configuring a virtual scene are provided. The method includes obtaining a target configuration information for a target scene element in the virtual scene based on an instruction by a first client indicating a candidate scene element; and instructing a second client to display the target scene element in the virtual scene based on the target configuration information, wherein a player activity in the virtual scene is only viewable via the first client and the player activity in the virtual scene is interactable via the second client.Type: GrantFiled: November 23, 2022Date of Patent: March 5, 2024Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventor: Dajia Sun
-
Patent number: 11922972Abstract: A video processing method is provided. In the method, a total video duration of a video and a played duration of the video are obtained in response to a video reverse playback instruction. The video reverse playback instruction indicates that the video is to be played in reverse order. A first reverse playback time point corresponding to the video is determined based on the total video duration and the played duration. Subdata from video data of the video is determined based on a time range indicated by the first reverse playback time point and a pre-loading time threshold. The subdata corresponds to the time range of the video. The subdata is pre-loaded to obtain pre-loaded video data. A first reverse playback video frame corresponding to the first reverse playback time point is obtained from the pre-loaded video data for playback in the reverse order.Type: GrantFiled: November 14, 2022Date of Patent: March 5, 2024Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Wei Zhang, Shuai Tang
-
Patent number: 11924255Abstract: This application discloses data transmission that includes: dividing to-be-transmitted content into a plurality of data units at a session layer; transmitting the data units to the target terminal device by using a first transmission channel as a responsible channel of the to-be-transmitted content; distributing, by the session layer in a case that the session layer switches the responsible channel of the to-be-transmitted content from the first transmission channel to a second transmission channel with a different transmission protocol, the data units to the second transmission channel; and transmitting the data units distributed by the session layer to the target terminal device through the second transmission channel. In data transmission in this application, the session layer controls switching of the channels and distribution of the data units, so that the transmission sequence is free from constraints of protocols and the degree of freedom in data transmission is increased.Type: GrantFiled: April 27, 2023Date of Patent: March 5, 2024Assignee: Tencent Technology (Shenzhen) Company LimitedInventors: Rui Han, Honghao Liu, Jianjun Xiao, Fucai Zhang, Nian Wen
-
Patent number: 11921746Abstract: This application discloses a data replication method and apparatus, a computer device, and a storage medium, and belongs to the field of database technologies. The method includes: adding, when a commitment operation of a transaction is detected, historical state data of the transaction to a data queue; adding at least one piece of historical state data in the data queue to a transmission buffer; and replicating, when a first preset condition is met, the at least one piece of historical state data in the transmission buffer to a cluster device. In this application, a node device does not need to convert an original historical state data format into a log format, and the cluster device does not need to parse a log into an original data format for storage, thereby avoiding a cumbersome log replay procedure, and improving the efficiency of the data replication process.Type: GrantFiled: May 25, 2021Date of Patent: March 5, 2024Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventor: Haixiang Li
-
Patent number: 11922969Abstract: A speech emotion detection system may obtain to-be-detected speech data. The system may generate speech frames based on framing processing and the to-be-detected speech data. The system may extract speech features corresponding to the speech frames to form a speech feature matrix corresponding to the to-be-detected speech data. The system may input the speech feature matrix to an emotion state probability detection model. The system may generate, based on the speech feature matrix and the emotion state probability detection model, an emotion state probability matrix corresponding to the to-be-detected speech data. The system may input the emotion state probability matrix and the speech feature matrix to an emotion state transition model. The system may generate an emotion state sequence based on the emotional state probability matrix, the speech feature matrix, and the emotional state transition model. The system may determine an emotion state based on the emotion state sequence.Type: GrantFiled: October 8, 2021Date of Patent: March 5, 2024Assignee: Tencent Technology (Shenzhen) Company LimitedInventor: Haibo Liu
-
Patent number: 11922654Abstract: A computer device, obtains a mammographic image of a unilateral breast. The mammographic image includes a cranial-caudal (CC)-position mammographic image and a mediolateral-oblique (MLO)-position mammographic image. The computer device invokes a breast detection model to perform a prediction of a condition of the unilateral breast according to the CC-position mammographic image and the MLO-position mammographic image. The device obtains a prediction result of the unilateral breast, and generates and outputs a detection report that includes the prediction result.Type: GrantFiled: July 2, 2021Date of Patent: March 5, 2024Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Kuan Tian, Cheng Jiang, Kezhou Yan, Rongbo Shen
-
Patent number: 11922574Abstract: A method for determining a plurality of layers of bounding boxes of an object includes determining a polyhedron capable of accommodating the object therein as a first-layer bounding box. The method also includes selecting one vertex from a plurality of vertices of the first-layer bounding box as a target vertex, and determining, by processing circuitry of a computing device, a support plane of the object. The support plane has a normal vector that has a specific direction corresponding to the target vertex and that is closest to the target vertex, the support plane being a plane passing through a point on a surface of the object such that the object is completely located on one side of the support plane. The method further includes cutting the first-layer bounding box based on at least the support plane to form a smaller bounding box, as a second-layer bounding box.Type: GrantFiled: July 29, 2021Date of Patent: March 5, 2024Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Yu Zheng, Zhengyou Zhang
-
Patent number: 11922906Abstract: A frame rate adjustment method, apparatus and device, a computer-readable storage medium and a computer program product. The method includes: acquiring running data of a client during running in a foreground when the client in the terminal device supports dynamic frame rate switching; determining a running scenario of the client based on the running data; determining a target running frame rate of the client based on the running scenario; and performing, by the client, image outputting according to the target running frame rate, and triggering an operating system of the terminal device to adjust a refresh rate of a screen according to the target running frame rate.Type: GrantFiled: September 28, 2022Date of Patent: March 5, 2024Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Shili Xu, Kai Hong, Haiyang Wu, Qitian Zhang, Zhuan Liu, Jingjing Chen