TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED patent applications on July 25th, 2024
Patent Applications by TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED on July 25th, 2024
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED: 16 patent applications
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED has applied for patents in the areas of G06T7/00 (3), G06V10/44 (2), G06F3/0482 (2), G06V10/80 (2), G06V10/82 (2) G05D1/60 (1), G06F3/023 (1), G06F3/0482 (1), G06F3/0484 (1), G06F3/14 (1)
With keywords such as: target, image, information, feature, sample, voice, based, obtain, vector, and obtaining in patent application abstracts.
Patent Applications by TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
Inventor(s): Wanchao CHI of Shenzhen (CN) for tencent technology (shenzhen) company limited, Xinyang JIANG of Shenzhen (CN) for tencent technology (shenzhen) company limited, Yu ZHENG of Shenzhen (CN) for tencent technology (shenzhen) company limited, Yufeng ZHANG of Shenzhen (CN) for tencent technology (shenzhen) company limited, Lingzhu XIANG of Shenzhen (CN) for tencent technology (shenzhen) company limited
IPC Code(s): G05D1/60, B62D57/032, G05D109/12
CPC Code(s): G05D1/60
Abstract: the present disclosure discloses a motion control method and apparatus for a legged robot, a legged robot, a computer-readable storage medium, and a computer program product. the legged robot includes at least two foot-ends. the method includes: receiving a bound instruction for the legged robot in response to the foot-ends of the legged robot standing in unit regions that are independent from one another, the bound instruction being used for instructing the legged robot to bound to a target unit region from at least two unit regions in which the legged robot is currently located; and controlling the legged robot to bound to the target unit region in response to the bound instruction, a distance between any two foot-ends of the legged robot in the target unit region being less than a distance between two corresponding foot-ends before bounding.
Inventor(s): Xingzhong ZHUO of Shenzhen (CN) for tencent technology (shenzhen) company limited
IPC Code(s): G06F3/023, G06F3/04886
CPC Code(s): G06F3/023
Abstract: a keyboard input method and system, the method including obtaining inputted information of a current input keyboard, and determining a first type of the current input keyboard based on the inputted information, loading, based on the first type being inconsistent with a second type of a previous input keyboard used during a previously performed input operation, a system word vocabulary and a conversion algorithm model that correspond to the first type from a library, obtaining user entry information corresponding to the inputted information from a user lexicon that has been loaded, obtaining system entry information corresponding to the inputted information from the system word vocabulary, and determining a list of to-be-selected entries corresponding to the inputted information according to the user entry information, the system entry information, and the conversion algorithm model, and outputting the list of to-be-selected entries.
Inventor(s): Ruijie JIANG of Shenzhen (CN) for tencent technology (shenzhen) company limited, Guilin XIANG of Shenzhen (CN) for tencent technology (shenzhen) company limited
IPC Code(s): G06F3/0482, H04M1/72439
CPC Code(s): G06F3/0482
Abstract: in a method for acquiring a shared emotive image, a plurality of candidate contact identifiers is displayed. a user selection of a target contact identifier from the plurality of candidate contact identifiers is received. at least one emotive image corresponding to the target contact identifier is displayed. the at least one emotive image is shared by a target contact of the target contact identifier. a user selection of the shared emotive image from the at least one emotive image corresponding to the target contact identifier is received. an emotive image acquisition request is sent to the target contact corresponding to the target contact identifier. the emotive image acquisition request identifies the shared emotive image for which authorization is requested. the shared emotive image is added to an emotive image library based on the authorization to use the shared emotive image being received.
Inventor(s): Ying YE of Shenzhen (CN) for tencent technology (shenzhen) company limited, Yang LI of Shenzhen (CN) for tencent technology (shenzhen) company limited, Lijing YUAN of Shenzhen (CN) for tencent technology (shenzhen) company limited, Licheng ZHENG of Shenzhen (CN) for tencent technology (shenzhen) company limited, Rui WANG of Shenzhen (CN) for tencent technology (shenzhen) company limited, Jingyi ZHOU of Shenzhen (CN) for tencent technology (shenzhen) company limited, Jingjing LIU of Shenzhen (CN) for tencent technology (shenzhen) company limited, Ni SU of Shenzhen (CN) for tencent technology (shenzhen) company limited, Yuyang KUANG of Shenzhen (CN) for tencent technology (shenzhen) company limited
IPC Code(s): G06F3/0484, G06F3/04817, G06F40/186
CPC Code(s): G06F3/0484
Abstract: a media content creation method includes: displaying, by a terminal device, a main modality editing interface; generating, by the terminal device, main modality media content in response to an editing operation performed on the main modality editing interface; converting, by the terminal device, the main modality media content to target sub-modality media content in response to a modality conversion operation; and displaying, by the terminal device, the generated main modality media content and the target sub-modality media content.
Inventor(s): Shuai Lou of Shenzhen (CN) for tencent technology (shenzhen) company limited
IPC Code(s): G06F3/14
CPC Code(s): G06F3/14
Abstract: a resource rendering method/apparatus including obtaining, based on a resource rendering request for a target object in a geographical area, a node relationship graph corresponding to the geographical area, the node relationship graph comprising at least one node in a connection relationship, the at least one node corresponding to a terminal in the geographical area, and the at least one node comprising a rendering execution node shared by nodes in the geographical area, identifying, in the node relationship graph, a node path from the at least one node to the rendering execution node, transferring the resource rendering request to the rendering execution node according to the node path, the resource rendering request instructing the rendering execution node to render the target object by using a cloud to obtain a rendering resource, and receiving the rendering resource returned by the rendering execution node, and displaying the rendering resource.
Inventor(s): Xing YANG of Shenzhen (CN) for tencent technology (shenzhen) company limited, Honghui TAO of Shenzhen (CN) for tencent technology (shenzhen) company limited, Guohui ZHENG of Shenzhen (CN) for tencent technology (shenzhen) company limited
IPC Code(s): G06F16/958, H04N21/431
CPC Code(s): G06F16/972
Abstract: a local dynamic page generation method includes: receiving a service package name of target information delivered by an operation platform, the service package name being configured and generated according to configuration information of the target information; receiving an information display request transmitted by a terminal; acquiring attribute information of the terminal; parsing, when the attribute information of the terminal matches the target information, fields in the service package name in response to the information display request, to obtain the configuration information; and invoking a local dynamic component corresponding to the configuration information to load the target information to a local display region on a current page of the terminal, to generate a local dynamic page.
Inventor(s): Xingyu MA of Shenzhen (CN) for tencent technology (shenzhen) company limited, Shaogang HAO of Shenzhen (CN) for tencent technology (shenzhen) company limited, Shengyu ZHANG of Shenzhen (CN) for tencent technology (shenzhen) company limited
IPC Code(s): G06F30/392, G06F30/398
CPC Code(s): G06F30/392
Abstract: a chip layout screening method is performed by an electronic device, and belong to the field of integrated circuit technologies. the method includes: obtaining a plurality of target chip layouts and a chip layout encoder; extracting target layout features of the plurality of target chip layouts by using the chip layout encoder; performing clustering on the plurality of target chip layouts based on the target layout features to obtain a plurality of target clusters, wherein each target cluster comprises a group of target chip layouts; and identifying a key chip layout from a respective group of target chip layouts. the chip layout encoder focuses on extracting a layout feature that can distinguish between chip layout types. this helps improve accuracy of a clustering result when chip layouts are subsequently clustered based on the layout feature.
Inventor(s): Zhiyuan TANG of Shenzhen (CN) for tencent technology (shenzhen) company limited, Shen HUANG of Shenzhen (CN) for tencent technology (shenzhen) company limited, Shidong SHANG of Shenzhen (CN) for tencent technology (shenzhen) company limited
IPC Code(s): G06N3/08, G06N3/04
CPC Code(s): G06N3/08
Abstract: a recognition method includes inputting a media resource feature into a recognition model having n layers of attention modules, and processing the media resource feature by using the n layers of attention modules to obtain a representation vector. an ilayer of attention module is configured to determine an ilayer weight parameter and an iinput representation vector based on (i) a group of shared parameters and (ii) an igroup of non-shared parameters, and determine an ilayer of representation vector outputted by the ilayer of attention module. when i is less than n, the ilayer of representation vector determines an (i+1)group of non-shared parameters used by an (i+1)layer of attention module and at least two layers of attention modules among the n layers of attention modules share the group of shared parameters.
Inventor(s): Kuan TIAN of Shenzhen (CN) for tencent technology (shenzhen) company limited, Jun ZHANG of Shenzhen (CN) for tencent technology (shenzhen) company limited
IPC Code(s): G06T7/00, G06T7/11, G06T7/77, G06T7/90, G16H30/40
CPC Code(s): G06T7/0012
Abstract: this application discloses a physiological image processing method performed by a computer device. the method includes: obtaining a physiological image; determining position information of at least one mutated object in the physiological image based on a physiological image processing model; performing color channel decomposition on the physiological image to obtain staining information corresponding to the physiological image; and making statistics according to the position information and the staining information to obtain a staining counting result of the mutated objects. according to this application, by obtaining the staining counting result of the mutated objects according to the position information of the mutated objects and the staining information, the staining counting result of the mutated objects is quickly obtained.
Inventor(s): Xinghua JIANG of Shenzhen (CN) for tencent technology (shenzhen) company limited, Hao LIU of Shenzhen (CN) for tencent technology (shenzhen) company limited, Xin LI of Shenzhen (CN) for tencent technology (shenzhen) company limited, Deqiang JIANG of Shenzhen (CN) for tencent technology (shenzhen) company limited
IPC Code(s): G06V10/764, G06V10/26, G06V10/42, G06V10/44, G06V10/77, G06V10/80, G06V10/82
CPC Code(s): G06V10/764
Abstract: disclosed in this application is an image processing method and a related apparatus. the method includes performing vectorization on a to-be-processed image, to obtain an image representation vector; performing feature mapping on the image representation vector to obtain an image feature, including: performing, at a same network layer of a network block, global feature mapping on input content to obtain a global feature, and performing local feature mapping on the input content to obtain a local feature, the input content being obtained based on the image representation vector; performing feature fusion on the global feature and the local feature to obtain a fused feature; obtaining an image feature based on the fused feature; and performing category prediction by using a classification module in the image classification model based on the image feature, to obtain a classification result of the to-be-processed image.
Inventor(s): Guiliang GONG of Shenzhen (CN) for tencent technology (shenzhen) company limited, Gaoxiong Yi of Shenzhen (CN) for tencent technology (shenzhen) company limited
IPC Code(s): G06V10/80, G06T7/00, G06V10/44, G06V10/62, G06V10/771
CPC Code(s): G06V10/806
Abstract: a video quality assessment method and apparatus including playing an online video stream, obtaining a time-domain feature of a corresponding unit of duration based on video playback fluency detected within at least one unit of duration in a process of playing the online video stream, extracting video frames from the online video stream, separately extracting a spatial-domain feature from each extracted video frame, obtaining a time-domain feature vector based on the time-domain feature of the unit of duration, obtaining a spatial-domain feature vector based on a corresponding spatial-domain feature of each video frame, performing feature fusion processing on the spatial-domain feature vector and the time-domain feature vector to obtain a fusion feature vector, and determining a video quality assessment value of the online video stream based on the fusion feature vector.
Inventor(s): Zhongyi YANG of Shenzhen (CN) for tencent technology (shenzhen) company limited, Sen YANG of Shenzhen (CN) for tencent technology (shenzhen) company limited, Jinxi XIANG of Shenzhen (CN) for tencent technology (shenzhen) company limited, Jun ZHANG of Shenzhen (CN) for tencent technology (shenzhen) company limited, Xiao HAN of Shenzhen (CN) for tencent technology (shenzhen) company limited
IPC Code(s): G06V10/82, G06T7/00
CPC Code(s): G06V10/82
Abstract: a method for training an image recognition model is performed by a computer device. the method includes: obtaining a sample image and a corresponding sample label; obtaining a sample image patch bag of sample image patches corresponding to the sample image, the sample patch bag having a bag label corresponding to the sample label of the sample image; performing feature analysis on the sample patch bag and the sample image patches in the sample patch bag, respectively, by using an image recognition model; determining a relative entropy loss, a first cross entropy loss corresponding to the sample patch bag and a second cross entropy loss corresponding to the sample image patches based on corresponding bag feature analysis and patch analysis results, respectively; and training the image recognition model based on the relative entropy loss, the first cross entropy loss, and the second cross entropy loss.
Inventor(s): Tianchu YAO of Shenzhen (CN) for tencent technology (shenzhen) company limited, Xiaohui SUN of Shenzhen (CN) for tencent technology (shenzhen) company limited, Baoxun WANG of Shenzhen (CN) for tencent technology (shenzhen) company limited, Haolong LIANG of Shenzhen (CN) for tencent technology (shenzhen) company limited
IPC Code(s): G10L13/047, G10L15/02, G10L21/007
CPC Code(s): G10L13/047
Abstract: a method for training a voice conversion model includes acquiring a voice sample set that includes training voice samples corresponding to training object identifiers, a training voice sample corresponding to a piece of voice content, and at least one training voice sample being a synthesized voice sample; extracting voice features of the training voice samples to obtain initial voice features; fusing initial voice features that belong to different training object identifiers and have corresponding voice content matching each other to obtain target voice features; obtaining a voice feature set; and inputting a voice feature in the voice feature set into an initial voice conversion model to obtain predicted voice data, and adjusting a model parameter of the initial voice conversion model based on a difference between the predicted voice data and target voice data until a first convergence condition is met, to obtain a target voice conversion model.
Inventor(s): Chao HUA of Shenzhen (CN) for tencent technology (shenzhen) company limited, Fei HUANG of Shenzhen (CN) for tencent technology (shenzhen) company limited
IPC Code(s): G10L19/022, G10L19/00, G10L19/038, G10L19/04
CPC Code(s): G10L19/022
Abstract: an audio decoding method performed by a computer device includes obtaining encoding vectors of audio frames in an audio frame sequence, and performing, in response to a current audio frame in the audio frame sequence being to be decoded, up-sampling on an encoding vector of a historical audio frame to obtain an up-sampling feature value describing the historical audio frame. the historical audio frame includes one or more audio frames decoded before the current audio frame in the audio frame sequence. the method further includes performing, based on the up-sampling feature value, up-sampling on an encoding vector of the current audio frame to obtain decoded data of the current audio frame.
Inventor(s): Ziqiao MENG of Shenzhen (CN) for tencent technology (shenzhen) company limited, Peilin ZHAO of Shenzhen (CN) for tencent technology (shenzhen) company limited
IPC Code(s): G16C20/70, G16C20/10
CPC Code(s): G16C20/70
Abstract: embodiments of this application disclose a training method and an application method for a reaction product prediction model. the method includes constructing a positive sample reactant set and a negative sample reactant set through a first auxiliary network; determining a reaction predicted loss value; constructing a positive sample reaction group set and a negative sample reaction group set through a second auxiliary network; determining a reaction relationship predicted loss value; determining, through a third auxiliary network according to the sample reactant vector and the sample reaction product vector, an atom label and a predicted probability value of an atom in the sample reactant being present in a main product; determining an atom predicted loss value; and training the reaction product prediction model based on the reaction predicted loss value, the reaction relationship predicted loss value, and the atom predicted loss value, to obtain a target reaction product prediction model.
Inventor(s): Fen HE of Shenzhen (CN) for tencent technology (shenzhen) company limited, Yaxin YONG of Shenzhen (CN) for tencent technology (shenzhen) company limited
IPC Code(s): H04L9/40, G06F3/0482, H04L51/52
CPC Code(s): H04L63/104
Abstract: a privacy protection method performed by an electronic device includes displaying, in response to a configuration operation with respect to an information sharing permission for a social network, a configuration result of the information sharing permission, and displaying target information in response to a trigger operation for transmitting the target information, including displaying the target information in a first display mode in response to the configuration result representing that the target information is configured with the information sharing permission, and displaying the target information in a second display mode different from the first display mode in response to the configuration result representing that the target information is not configured with the information sharing permission.
TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED patent applications on July 25th, 2024
- TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
- G05D1/60
- B62D57/032
- G05D109/12
- CPC G05D1/60
- Tencent technology (shenzhen) company limited
- G06F3/023
- G06F3/04886
- CPC G06F3/023
- G06F3/0482
- H04M1/72439
- CPC G06F3/0482
- G06F3/0484
- G06F3/04817
- G06F40/186
- CPC G06F3/0484
- G06F3/14
- CPC G06F3/14
- G06F16/958
- H04N21/431
- CPC G06F16/972
- G06F30/392
- G06F30/398
- CPC G06F30/392
- G06N3/08
- G06N3/04
- CPC G06N3/08
- G06T7/00
- G06T7/11
- G06T7/77
- G06T7/90
- G16H30/40
- CPC G06T7/0012
- G06V10/764
- G06V10/26
- G06V10/42
- G06V10/44
- G06V10/77
- G06V10/80
- G06V10/82
- CPC G06V10/764
- G06V10/62
- G06V10/771
- CPC G06V10/806
- CPC G06V10/82
- G10L13/047
- G10L15/02
- G10L21/007
- CPC G10L13/047
- G10L19/022
- G10L19/00
- G10L19/038
- G10L19/04
- CPC G10L19/022
- G16C20/70
- G16C20/10
- CPC G16C20/70
- H04L9/40
- H04L51/52
- CPC H04L63/104
