Patents Assigned to TENCENT TECHNOLOGY (SHENZHEN)
  • Patent number: 12266363
    Abstract: The present disclosure provides methods, devices, apparatus, and storage medium for performing speech-to-text conversion. The method includes: displaying, by a first device, a first user interface, the first user interface being a display screen of a virtual environment that provides a virtual activity place for a first virtual role controlled by a first user account; displaying, by a second device, a second user interface, the second user interface being a display screen of a virtual environment that provides a virtual activity place for a second virtual role controlled by a second user account; in response to a speech input operation by the first user account performed on the first device, displaying, by the first device, a chat message in a first language, and displaying, by the second device, the chat message in a second language.
    Type: Grant
    Filed: October 13, 2021
    Date of Patent: April 1, 2025
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Peicheng Liu, Xiaohao Liu, Yancan Wang, Dong Ding, Kai Tang, Shan Lin
  • Patent number: 12266114
    Abstract: An image processing method and apparatus, a device, and a storage medium. The image processing method includes: performing preliminary segmentation recognition on a raw image by using a first segmentation model to obtain a candidate foreground image region and a candidate background image region of the raw image; recombining the candidate foreground image region, the candidate background image region, and the raw image to obtain a recombined image, pixels in the recombined image being in a one-to-one correspondence with pixels in the raw image; and performing region segmentation recognition on the recombined image by using a second segmentation model to obtain a target foreground image region and a target background image region of the raw image.
    Type: Grant
    Filed: August 15, 2022
    Date of Patent: April 1, 2025
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Rui Zhang, Pei Cheng, Gang Yu, Bin Fu
  • Patent number: 12266173
    Abstract: The disclosure provides an image recognition method and apparatus. The image recognition method may include obtaining a first frame image of which a frame type is known, and a second frame image and a third frame image of which frame types are unknown from an image frame sequence. The method may further include predicting a pixel sequence of the second frame image according to the first frame image and the third frame image. The method may further include calculating a pixel error according to a second pixel sequence of the second frame image and the predicted pixel sequence. The second pixel sequence includes pixel values of the pixels in the second frame image. The method may further include recognizing a frame type of the second frame image or the third frame image according to the pixel error.
    Type: Grant
    Filed: March 30, 2022
    Date of Patent: April 1, 2025
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventor: Fasheng Chen
  • Patent number: 12266045
    Abstract: This application discloses an image rendering method and apparatus, an electronic device, and a storage medium, and belongs to the field of image processing technologies. The method includes: acquiring a lightmap of a target three-dimensional model in response to a light rendering instruction; acquiring a seam edge of the target three-dimensional model; determining, in the lightmap, a target pixel corresponding to the seam edge; and updating an initial pixel value of the target pixel in the lightmap to obtain a repaired lightmap. In this application, the seam edge of the target three-dimensional model is automatically identified, and the pixel value of the target pixel is automatically updated, so that automatic recognition and automatic repair of a seam problem can be completed by one click, thereby avoiding a waste of labor resources for troubleshooting and repairing the seam problem, reducing image rendering time, and improving image rendering efficiency.
    Type: Grant
    Filed: August 19, 2022
    Date of Patent: April 1, 2025
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Shun Cao, Huabing Xu, Yuanheng Li, Nan Wei, Xiaochun Cui, Congbing Li
  • Patent number: 12260623
    Abstract: Embodiments of this application disclose a method and apparatus for training an image region segmentation model, and an image region segmentation method and apparatus. The method includes acquiring a sample image set, and each image of the sample image set having first annotation information; generating graph structure data corresponding to a sample image in the sample image set, the graph structure data comprising multiple nodes, and each node comprising at least one pixel in the sample image; determining second annotation information of each node according to the graph structure data and the first annotation information corresponding to the sample image by using a graph convolutional network model, a granularity of the second annotation information being smaller than a granularity of the first annotation information, the graph convolutional network model being a part of an image segmentation model; and training the image segmentation model according to the second annotation information.
    Type: Grant
    Filed: March 29, 2022
    Date of Patent: March 25, 2025
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Jun Zhang, Kuan Tian, Kezhou Yan, Jianhua Yao, Xiao Han
  • Patent number: 12260615
    Abstract: An image attack detection method includes: acquiring an image-to-be-detected, and performing global classification recognition based on the image-to-be-detected to obtain a global classification recognition result; performing local image extraction randomly based on the image-to-be-detected to obtain a target number of local images, the target number being obtained by calculation according to a defensive rate of a reference image corresponding to the image-to-be-detected; performing local classification recognition based on the target number of local images respectively to obtain respective local classification recognition results, and fusing the respective local classification recognition results to obtain a target classification recognition result; and detecting a similarity between the target classification recognition result and the global recognition result, and determining the image-to-be-detected as an attack image when the target classification recognition result and the global classification recognit
    Type: Grant
    Filed: November 30, 2022
    Date of Patent: March 25, 2025
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Bo Li, Jianghe Xu, Shuang Wu, Shouhong Ding, Jilin Li
  • Patent number: 12260226
    Abstract: A method for starting an application, performed by a terminal, includes: displaying an application startup management interface, the application startup management interface including at least one startup control of at least one application, each application corresponding to one startup control; obtaining a first trigger signal, the first trigger signal being a signal generated upon detecting a trigger operation on a startup control of a target application; obtaining an application video stream when a terminal has not finished downloading a client of the target application, the application video stream being a video stream formed by application screens generated during running of a first client, the first client being a client of the target application run on a server; and displaying a first application interface of the target application according to the application video stream. The server may be a cloud server.
    Type: Grant
    Filed: July 1, 2021
    Date of Patent: March 25, 2025
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Haijun Wu, Wanze Xiong, Zhiming Yang
  • Patent number: 12262000
    Abstract: This application discloses a data transmission method performed by a computer device. It is detected that the ith forward reference frame is lost, during video decoding, when the (i+T+1)th forward reference frame is decoded, since a video frame in a first reference frame combination of the (i+T+1)th forward reference frame is located before the (i+T+1)th forward reference frame with an interval of T forward reference frames from the (i+T+1)th forward reference frame, T being a positive integer, so that before the (i+T+1)th forward reference frame is decoded, there is more time for retransmitting the ith forward reference frame, improving a possibility of completing retransmission of the ith forward reference frame during decoding of the (i+T+1)th forward reference frame, thereby reducing a possible waiting time for decoding the (i+T+1)th forward reference frame.
    Type: Grant
    Filed: April 7, 2023
    Date of Patent: March 25, 2025
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventor: Junling Mao
  • Patent number: 12262376
    Abstract: Embodiments of this application disclose a transmission processing method and apparatus, a device, and a storage medium. The method is applied to a first device, and includes: receiving a pre-scheduling message that is transmitted by a second device through a first channel; reading, from the pre-scheduling message, a pre-scheduling moment and a pre-scheduling band that are used for pre-scheduling transmission between the first device and the second device; and transmitting, before the pre-scheduling moment is reached, indication information to the second device by using any band other than the pre-scheduling band, the indication information being used for indicating cancellation of the pre-scheduling transmission.
    Type: Grant
    Filed: April 29, 2024
    Date of Patent: March 25, 2025
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Yunbo Han, Yiyong Zha, Binhui Ning, Gang Wu, Xing Meng
  • Patent number: 12260521
    Abstract: An image processing method is performed by an electronic device, the method including: obtaining, according to a quantity of pixels whose color feature values fall within color feature intervals in an original image, a first histogram corresponding to the original image; obtaining, according to a quantity of pixels whose color feature values fall within the color feature intervals in an upsampled image of the original image, a second histogram corresponding to the upsampled image; respectively determining, according to the first histogram and the second histogram, target color feature intervals matching the color feature intervals in the second histogram; and processing, according to the target color feature intervals matching the color feature intervals in the second histogram, the color feature values of the pixels falling within the color feature intervals in the upsampled image, to obtain a target image.
    Type: Grant
    Filed: January 11, 2022
    Date of Patent: March 25, 2025
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventor: Zhicheng Li
  • Patent number: 12254121
    Abstract: A data processing method includes: acquiring a first intersection set, acquiring a second intersection set, calculating an intersection between the first intersection set and the second intersection set to obtain an intersection result set that includes an intersecting portion of the first intersection data and the second intersection data, and obfuscating the intersection result set to obtain an obfuscation set that includes obfuscated data based on data in the second intersection set and an intersection data set based on the intersection result set.
    Type: Grant
    Filed: November 30, 2022
    Date of Patent: March 18, 2025
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LTD
    Inventors: Fangcheng Fu, Jie Jiang, Junwei Pan, Chen Hou, Huanran Xue, Yong Cheng, Yuhong Liu, Peng Chen, Yangyu Tao
  • Patent number: 12251635
    Abstract: This application relates to a method for controlling a virtual character performed by a computer device, the method including: displaying at least a portion of a target virtual character in a virtual scene, the target virtual character being bound with basic bones and deformed bones; triggering the character action of the target virtual character in the virtual scene; when the character action comprises a character movement, controlling the target virtual character to implement the character movement in the virtual scene through a movement of a basic bone associated with the character movement; and when the character action comprises a local character deformation, controlling the target virtual character to implement the local character deformation in the virtual scene through a deformation of a deformed bone associated with the local character deformation.
    Type: Grant
    Filed: August 8, 2022
    Date of Patent: March 18, 2025
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventor: Chang Guo
  • Patent number: 12251628
    Abstract: This application discloses an object display method and apparatus, and a storage medium. The method includes: obtaining, by using a client of a game application, first target movement information of a first member object participating in a current game event, the first member object being different from a target object, the target object being an object controlled by the client of the game application in the current game event, and the first target movement information comprising at least a moving direction of the first member object; and displaying, in the client of the game application, a first movement direction marker of the first member object according to the moving direction of the first member object on a minimap corresponding to the current game event.
    Type: Grant
    Filed: June 7, 2022
    Date of Patent: March 18, 2025
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventor: Yiran Wang
  • Patent number: 12256072
    Abstract: A video decoding method includes performing entropy decoding processing on a code block of a video image frame of a video image frame sequence, to obtain a quantization coefficient block of residual data corresponding to the code block; collecting statistics of quantization coefficients in a target region in the quantization coefficient block, to obtain a quantization coefficient statistical value; selecting a transform matrix combination corresponding to the quantization coefficient statistical value; and performing inverse transform processing on an inverse quantization result of the quantization coefficient block based on the selected transform matrix combination, to obtain reconstructed residual data, the reconstructed residual data being used for video image reconstruction.
    Type: Grant
    Filed: September 8, 2022
    Date of Patent: March 18, 2025
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Liqiang Wang, Xiaozhong Xu, Shan Liu
  • Patent number: 12252136
    Abstract: Embodiments of the disclosure provide a warning method and an apparatus for a driving risk, a computing device and a storage medium. In an embodiment, driving behavior data of a driver in a first time period is obtained, and a correspondence between a quantity of occurrences of preset driving behaviors of one or more drivers and a quantity of an actual occurrence of preset scenarios to the one or more drivers while driving is obtained. Based on a quantity of actual occurrences of the preset driving behaviors of the driver, indicated in the driving behavior data of the driver, and the correspondence, it is predicted a target quantity of times the driver is predicted to encounter one or more preset scenarios in the first time period, and warning information is generated based on the target quantity of times.
    Type: Grant
    Filed: October 18, 2022
    Date of Patent: March 18, 2025
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventor: Chen Hou
  • Patent number: 12254580
    Abstract: An identity information presentation method and apparatus, a terminal, a server, and a storage medium are provided, which relate to the field of augmented reality technologies. The method includes: acquiring an image by using the camera, the acquired image including a character; displaying the image acquired by the camera based on an augmented reality social mode, in which augmented reality social information is provided for a currently logged-in account; and presenting, based on a geographical location of the character, first identity information around the character in an augmented reality manner, the first identity information indicating a social identity of the character.
    Type: Grant
    Filed: October 21, 2022
    Date of Patent: March 18, 2025
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventor: Rui Han
  • Patent number: 12246257
    Abstract: This application discloses an object control method performed at a terminal device. The method includes: determining a target angle between a facing direction of a target object controlled by a user of the terminal device and a moving direction of the target object during execution of a target action in a racing game; when the target angle reaches a trigger threshold, increasing an energy value corresponding to a target virtual key by a first target value to obtain an accumulated energy value; and adjusting a key state of the target virtual key from a non-touch-enabled state to a touch-enabled state according to the accumulated energy value.
    Type: Grant
    Filed: November 29, 2023
    Date of Patent: March 11, 2025
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventor: Xiongfei Huang
  • Patent number: 12248511
    Abstract: This application provides a video retrieval method performed by a computer device. The method includes: performing feature extraction on an image feature of a query video to obtain a first quantization feature, obtaining a second candidate video with a high category similarity to the query video based on the first quantization feature, and finally taking a second candidate video with a high content similarity to the query video as a target video. The quantization control parameters are adjusted according to the texture feature loss value corresponding to each training sample to cause the target quantization processing sub-model to learn the ranking ability of the target texture feature sub-model, to ensure that the ranking effect of two sub-models tend to be consistent, and an end-to-end model architecture enables the target quantization processing sub-model to obtain the corresponding quantization feature based on the image feature.
    Type: Grant
    Filed: April 19, 2023
    Date of Patent: March 11, 2025
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventor: Hui Guo
  • Patent number: 12250277
    Abstract: Embodiments of this application provide a method for making recommendations to a user and an apparatus, a computing device, and a storage medium. The method includes obtaining user attribute information, reading attribute information, reading history information, and candidate items; performing intra-group information fusion on the reading attribute information according to preset groupings to obtain reading feature information; obtaining a reading history weight according to the reading history information; obtaining history feature information according to the reading history weight and the reading history information; obtaining user feature information according to the user attribute information, the reading feature information, and the history feature information; and selecting a recommendation item from the candidate items according to the user feature information.
    Type: Grant
    Filed: May 24, 2021
    Date of Patent: March 11, 2025
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Zhijie Qiu, Jun Rao, Yi Liu, Zhou Su, Shukai Liu, Zhenlong Sun, Qi Liu, Liangdong Wang, Tiantian Shang, Mingfei Liang, Lei Chen, Bo Zhang, Leyu Lin
  • Patent number: 12248478
    Abstract: A method for federated data query includes: using, by a first electronic device, a joint query statement corresponding to a federated data query to obtain at least one operator containing a joint query operator; transforming the joint query operator to a first joint security operator; determining first data for intersection on the first electronic device by executing the first joint security operator, receiving second data for intersection from a second electronic device involved in the federated data query, and performing joint computing on the first data for intersection and the second data for intersection in a form of a ciphertext to obtain a joint data table; and determining a federated data query result corresponding to the at least one operator based on the joint data table.
    Type: Grant
    Filed: June 15, 2023
    Date of Patent: March 11, 2025
    Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
    Inventors: Xiaoliang Fan, Jie Jiang, Yong Cheng, Chen Hou, Yuhong Liu, Peng Chen, Yangyu Tao