Huawei Technologies Co., Limited

Shenzhen Yinwang Intelligent Technologies Co., Ltd.

Tencent Technology (shenzhen) Company Limited

Boe Technology Group Co., Ltd.

China University of Petroleum

Shenzhen Xumi Yuntu Space Technology Co., Ltd.

Pla General Hospital of China

Zheng Zhou

Chunshan Xiong

Mingchao Li

Dong Chen

Min Xu

Jing Wang

Mingzeng Dai

Bo Lin

Hongping Zhang

Hui Ni

Jie Ma

Sha Ma

Yanmei Yang

Lei Wan

Bin Xu

Tao N Zhang

Rui Zhao

Li Zhou

Tao Zhang

Xing Ji

Yitong Wang

Hang Liu

Yongqiang Gao

Le Yan

Yi Tong Wang

Cuili Ge

Haiyang Sun

Shuai Wang

Qianghua Zhu

Xiaolong Zhu

Jingwang Ma

Yi Cheng Zhang

Rui Li

Yuan Lin

Jinlin Zhang

Min Luo

Xijun Xue

Bo Qiao

Ruizhi Xu

Liang Zhu

Fan Jia

Fan Chen

Shengyi He

Chunyu Ren

Zhengfu Ning

Hang Feng

Wenjun Yu

Nenghao Jin

Suixin Hu

Fanhao Meng

Xiaoguang Tian

Yao Duan

Tingting Jia

Youbai Chen

Lejun Xing

Yutong Zhang

Haizhong Zhang

A data processing method, apparatus, chip system, and medium are provided. The method may be applied to the field of autonomous driving or intelligent driving. The method includes: obtaining first abstract data from first raw data by using a first recognition algorithm, where the first abstract data includes attribute description data of a first target; receiving first feedback data, where the first feedback data includes attribute description data of a second target; and optimizing the first recognition algorithm based on the first feedback data, where the first raw data is measurement data of a scenario, and the first target and the second target are targets in the scenario.

Data processing method and apparatus, chip system, and medium

This disclosure relates to a communication method and an apparatus, applied to an internet of vehicles, for example, V2X, LTE-V, and V2V. An in-vehicle apparatus triggers an on-board function for a first vehicle. The first vehicle carries the in-vehicle apparatus. The in-vehicle apparatus checks whether the first vehicle is allowed to use the on-board function on a first road. When the first vehicle is on the first road, the in-vehicle apparatus enables or disables the on-board function based on a check result. In the embodiments of this disclosure, whether to enable a corresponding on-board function may be controlled, so that the on-board function is enabled without depending on a human requirement. In this way, the corresponding on-board function may be controlled to be applied to an appropriate road, to reduce a vehicle accident risk, and a danger to social security.

Communication method and apparatus for enabling an on-board function for a vehicle

A communication method and an apparatus are provided, to improve transmission resource utilization. The communication method and the apparatus relate to the field of automatic driving or smart driving technologies. The method includes: obtaining first data and second data; and sending the first data to a second apparatus based on a first period, and sending the second data to the second apparatus based on a second period, where the first period is a sending period of the first data, the second period is a sending period of the second data, and the first period and the second period are different.

Communication method and apparatus

A traffic indication information determining method includes: obtaining n pieces of first traffic indication information from n sensors, where the first traffic indication information is used to indicate traffic indication information of a traffic command target, the traffic indication information is used to provide a road traffic rule for a vehicle, and n is an integer greater than or equal to 1; and determining second traffic indication information based on the n pieces of first traffic indication information. In the method, the n pieces of first traffic indication information of the traffic command target are obtained based on the n sensors, and then the second traffic indication information used when the vehicle actually travels is determined based on the n pieces of first traffic indication information.

Traffic indication information determining method and apparatus

A method and apparatus for determining content of adsorbed gas in a deep shale, and a server, wherein experimental tests are combined with molecular dynamics models. Firstly, tests are performed on a core sample of a target area at various temperatures in a first-class pressure environment with low pressure to obtain shale gas adsorption data of the core sample; next, a first shale molecule dynamics model of the core sample is established, and a fitting adjustment is performed on the first shale molecule dynamics model using the shale gas adsorption data to obtain a second shale molecule dynamics model. Further, the second shale molecular dynamics model is used to obtain, by analogue simulation, shale gas adsorption data of the core sample corresponding to the various temperatures in a second-class pressure environment with high pressure, so as to obtain an accurate and comprehensive adsorption characteristic curve in a full pressure range.

Method and apparatus for determining content of adsorbed gas in deep shale, and server

An autonomous driving method, an autonomous driving apparatus, a computer-readable storage medium, and a computer program product are provided. The method includes: receiving first driving-related information of a first road section ahead of a road on which a first vehicle currently drives and information about a parking waiting area that are sent by a network side device, where the parking waiting area is used to park the first vehicle before the first vehicle drives into the first road section (S); then determining, based on the first driving-related information, that the first road section does not meet an autonomous driving condition requirement of the first vehicle (S); finally, controlling the first vehicle to drive into the parking waiting area (S).

Autonomous driving method and apparatus

A data processing method applied to a data processing apparatus is disclosed. The data processing apparatus includes a central processor and a sensor processor set, and the sensor processor set includes at least one sensor processor. The data processing method comprises obtaining status information of at least one sensor processor in a sensor processor set; determining task switching information based on status information of the at least one sensor processor and/or status information of the central processor, and processing the data processing task switched from the first sensor processor to the central processor, and/or processing, the data processing task switched from the central processor to the second sensor processor. The task switching information indicates to switch a data processing task of a first sensor processor to the central processor, or switch a data processing task of the central processor to a second sensor processor, and the first sensor processor and the second sensor processor each is a sensor processor in the sensor processor set.

Data processing method and corresponding apparatus based on status information of processors

An electronic device obtains an image that includes a face. The device performs feature extraction on the image, to obtain facial expression information corresponding to the face and facial feature information corresponding to the facial expression, wherein the facial feature information indicates an extent of the facial expression. The device determines facial emotion information according to the facial expression information. The device also determines facial feature expression information according to a target feature value corresponding to the facial emotion and the facial feature information. This expression recognition techniques disclosed herein can implement multi-task learning and reduce an amount of data required for model training, and can obtain both an emotion recognition result and a local expression recognition result, thereby improving efficiency and real-time performance of expression recognition and improving user experience.

Expression recognition method and related apparatus

An indoor design scheme acquisition method and apparatus, a computer device and a storage medium are provided. The method includes: acquiring basic information of a target room, the basic information at least including house structure information; controlling a layout of articles in the target room based on the basic information of the target room to generate at least one design scheme of the target room, the design scheme including the house structure information and article placement information; acquiring scores of the design schemes based on the house structure information and the article placement information; and determining the design scheme meeting a preset requirement as a target design scheme based on the scores of the design schemes. The method can adapt to design requirements of different scenarios and different house structures, and the design scheme meeting a preset requirement is determined by scoring all the design schemes.

Indoor design scheme acquisition method and apparatus, computer device and storage medium

Embodiments of this application disclose a request processing method and a corresponding entity, to control a data notification and signaling that is used for triggering paging, thereby avoiding overload of a network element in a core network. The request processing method includes: determining, by an AMF, a first control plane function entity for a terminal device; determining, by the AMF, that the terminal device enters an idle state; obtaining, by the AMF, a first reachability service invocation request from the first control plane function entity; and rejecting, by the AMF, the first reachability service invocation request when the AMF determines, based on the first reachability service invocation request, that a reachability service invocation limitation condition is satisfied.

Request processing method and corresponding entity

This application discloses a method for training a gaze tracking model, including: obtaining a training sample set; processing the eye sample images in the training sample set by using an initial gaze tracking model to obtain a predicted gaze vector of each eye sample image; determining a model loss according to a cosine distance between the predicted gaze vector and the labeled gaze vector for each eye sample image; and iteratively adjusting one or more reference parameters of the initial gaze tracking model until the model loss meets a convergence condition, to obtain a target gaze tracking model. According to the solution provided in this application, a gaze tracking procedure is simplified, a difference between a predicted value and a labeled value can be better represented by using the cosine distance as a model loss to train a model, to improve prediction accuracy of the gaze tracking model.

Method and apparatus for training gaze tracking model, and method and apparatus for gaze tracking

A face key point detection method includes determining, according to an image containing a face, a multi-channel feature map of the image; converting the multi-channel feature map into a predetermined channel quantity of target feature maps; performing a convolution operation on each target feature map in the predetermined channel quantity of target feature maps by using a convolution kernel corresponding to each target feature map; generating a feature vector corresponding to the image based on a result of the convolution operation on each target feature map; and determining key point coordinates of the face on the image according to the feature vector.

Face key point detection method and apparatus, storage medium, and electronic device

The present disclosure provides a pixel driving circuit, an array substrate and a display panel. The pixel driving circuit of the present disclosure includes a switch transistor and N redundant switch transistors, the switch transistor and the N redundant switch transistors are connected in series, a second electrode of an Nredundant switch transistor is coupled to a first electrode of the switch transistor, and a second electrode of the switch transistor is coupled to a display electrode.

Pixel driving circuit, array substrate and display panel

The present disclosure relates to mobile edge computing (MEC) information obtaining methods and apparatus. One example method performed by a first network element includes receiving target reference information from a second network element, and sending, to the second network element, information about a MEC platform corresponding to the target reference information. The target reference information comprises target capability information.

MEC information obtaining method and apparatus

A policy transmission method, a policy control function (PCF) network element, and a computer storage medium, where the method includes: obtaining, by a PCF network element, a connection management state of a terminal apparatus, where the connection management state includes a connected mode or an idle mode; and sending, by the PCF network element, policy rule information to the terminal apparatus when the connection management state of the terminal apparatus is the connected mode.

Policy transmission method, policy control function (PCF) network element, and computer storage medium

Growing community of inventors

Beijing, China

Zheng Zhou