Huawei Technologies Co., Limited

Tencent Technology (Shenzhen) Company Limited

Shenzhen Royole Technologies Co., Ltd.

Hytera Communications Corporation Limited

Honor Device Co., Ltd.

Nanjing University of Science and Technology

Zte Corporation

Tcl China Star Optoelectronics Technology Co., Ltd.

Peking University

The Hong Kong Polytechnic University

Yulong Computer Telecommunication Scientific (Shenzhen) Co., Ltd.

Shenzhen Dahui Home Furnishings Co., Ltd.

Shenzhen Zhihe Shanhai Technology Co., Ltd.

Tencent Technology Company Limited

Liang Zhang

Lixia Xue

Jing Liu

Hao Sun

Chao Jiang

Yan Xu

Yu Wang

Zhe Liu

Tianran Zhou

Xinyu Hu

Cong Zhao

Bangshi Yin

Hui Yang

Junwei Wang

Hui Li

Songling Yang

Jun Wu

Li Xue

Xinyuan Xia

Rui Guo

Bin Yan

Yun Chen

Xingwei Zhang

He Li

Jie Shi

Chao Li

Yuming Xie

Jue Wang

Rui Yang

Fei Huang

Yali Wang

Jian Mg Cheng

Meng Wang

Yan Wang

Zihong Liu

Chen Dong

Yuanlong Jiang

Chen Wang

Fei Zhang

Hewen Zheng

Ling Liu

Rui Xu

Yi Long

Dong Ma

Yang Yu

Songya Chen

Jiuliang Gao

Xiaohan Chen

Yixin Chen

Jian Cheng

Haonan Ye

Yanfang Zhang

Xiaoyun Si

Yuping Zhao

Kangle Xue

Qian Chen

Dewei Bao

Ji Wang

Ridong Xu

Chao Zuo

Shijie Feng

Chia Han Siong Samuel

Xiaomeng Chen

Jinxin Li

Jia Liu

Peichen Xu

Xinrong Hu

Wei Jin

Jiasong Sun

Haining Huang

Yingzhe Zhang

Yusong Chi

Jinwei Xia

Hongyu Wang

Min Yi

Zhuobiao He

Weilian Jiang

Zhenghua Luo

Xin Lv

Xiaoyan Wang

Zhanchao Liu

Kai Liu

Jianjun Zhou

Mingjun Chen

Zhenhang Sun

Zhongyu Wang

Huiying Xu

Jianhong Luo

Chao Han

Dan Ni

Lizhong Jin

Yuan Wei

Wenjun Luo

Jianqiang Guo

Weiqing Kong

Tao Feng

Xiulan Liu

Feifei Sui

A method, an apparatus, and a computing device for constructing a prediction model, and a storage medium are disclosed, and relate to the field of artificial intelligence technologies. The method includes: obtaining, based on a target dataset of a target prediction scenario and/or scenario information of the target prediction scenario, model search space corresponding to the target prediction scenario; performing model training based on the target dataset and models and hyperparameters that are included in the model search space, to obtain trained prediction models; and obtaining, based on evaluation results of the trained prediction models, a prediction model corresponding to the target prediction scenario. Efficiency of constructing the prediction model can be improved.

Method, apparatus, and computing device for constructing prediction model, and storage medium

A packet transmission method and device are disclosed. A first pseudo wire (PW) is established between a first node and a second node. The first node obtains a first service packet, and performs SRv6 encapsulation on the first service packet to obtain a second service packet. The second service packet includes the first service packet and information about the first PW. The first node sends the second service packet to the second node through the first PW. After receiving the second service packet, the second node performs SRv6 decapsulation on the second service packet to obtain the first service packet. An ingress PE device can perform SRv6 encapsulation on a PW service, and encapsulate PW description information and a to-be-transmitted service packet into an actually sent service packet, and an egress PE device performs SRv6 decapsulation on the service packet received through the PW to obtain the to-be-transmitted service packet.

Pseudo wire packet transmission method and related device

This application discloses a method and for dividing geographical regions performed by a computing device. The method includes: obtaining N groups of the place names, their corresponding latitudes and longitudes; converting the N groups of the place names, their corresponding latitudes and the longitudes into a first dataset; encoding latitudes and longitudes in the first dataset into a second dataset, each pair of latitude and longitude corresponding to a respective geographical region associated with a region number in the second dataset; converting the second dataset into a third dataset, the third dataset including M groups of the region numbers, each group of region numbers representing central point latitudes and central point longitudes in the geographical regions represented by the group of region numbers; and dividing the geographical regions represented by the M groups of region numbers into P regions according to the third dataset.

Method and apparatus for dividing region, storage medium, and electronic device

A device identification method, apparatus, and system are provided. A management device or a collection device first determines a network traffic feature of a to-be-identified device based on a first dataset. The first dataset includes a plurality of pieces of first data, and each piece of first data includes a data amount of a data packet that is of the to-be-identified device and that is collected within one first periodicity. Then, the management device or the collection device determines a device type of the to-be-identified device based on a device identification model and the network traffic feature of the to-be-identified device.

Device identification method, apparatus, and system

A method for improving a paging response speed of a user equipment (UE), includes: camping, by the UE on a first cell of a first network, the UE being in an RRC connected state; when a first preset condition is met, sending, by an access network device, a first message to the UE, the first message being used to indicate the UE to enter an RRC inactive state; recording, by the access network device, that the UE is in an RRC inactive state; and in response to the first message that is received, entering, by the UE, the RRC inactive state; and when a second preset condition is met, camping, by the UE, on a second cell of the first network, where the UE is in an RRC inactive state, and the first cell and the second cell are the same or different.

Method for increasing paging response speed of terminal and terminal

Tent

A protection switching method provides a manner of transferring a protection switching message on an SRv6 data plane. In this manner, a first node can switch, after a fault occurs on an end-to-end transmission path of forward service traffic of the first node, a transmission path of the forward service traffic of the first node to another end-to-end transmission path, and send the forward service traffic through the transmission path after switching. In this manner, the first node only needs to store information about the another transmission path, and an intermediate node does not need to maintain a large amount of path state information and path configuration information.

Method and apparatus for performing protection switching in segment routing SR network

A network device inputs first network status information of the network device in a first time period to an ECN inference model, to obtain an inference result that is output by the ECN inference model based on the first network status information. Then, the network device sends an ECN parameter sample to an analysis device that manages the network device, where the ECN parameter sample includes the first network status information and a target ECN configuration parameter corresponding to the first network status information, and the target ECN configuration parameter is obtained based on the inference result. The network device receives an updated ECN inference model sent by the analysis device.

Congestion control method, apparatus, and system, and computer storage medium

In certain embodiments, a forwarding device receives at least one service flow. The forwarding device obtains service information of the at least one service flow, where the service information of the service flow includes identification information of a network object to which the service flow belongs and M key performance indicators KPIs of the service flow. M is an integer greater than 0, and the network object includes one or more devices. The forwarding device sends detection information to a first device, where the detection information includes the service information of the at least one service flow or a feature set obtained based on the service information of the at least one service flow. The detection information is used to detect whether the network object is in a faulty state.

Fault detection method, apparatus, and system

This application provides a data collection method and a device. A data collection device determines, based on a threshold corresponding to a target indicator, a collection interval for to-be-collected data of the target indicator from a plurality of available collection intervals; and the data collection device collects the data of the target indicator based on the collection interval.

Data collection method and device

A data stream classification model updating method is disclosed. Determining, based on packet information of a current data stream and a behavior classification model, a first data stream class corresponding to the current data stream; determining, based on a target correspondence and a common feature of the current data stream, a second data stream class corresponding to the current data stream, where the target correspondence is a correspondence between a plurality of common features and a plurality of data stream classes; and if the first data stream class is different from the second data stream class, obtaining correction data corresponding to the current data stream, where the correction data includes the packet information of the current data stream and the second data stream class, and the correction data is used as a training sample to update the behavior classification model.

Data stream classification model updating method and related device

A forwarding device receives at least one service flow; the forwarding device obtains service information of the at least one service flow, where the service information of the service flow includes identification information of a network object to which the service flow belongs and M key performance indicators KPIs of the service flow, M is an integer greater than 0, and the network object includes one or more devices; and the forwarding device sends training information to a first device, where the training information includes the service information of the at least one service flow or a feature set obtained based on the service information of the at least one service flow, the training information is used to train a fault detection model, and the fault detection model is used to detect whether the network object is in a faulty state.

Fault detection model training method, apparatus, and system

Embodiments of this application provide a circuit board assembly and an electronic device. The circuit board assembly includes at least a frame plate, circuit boards, support bodies, and solder joints. The frame plate includes a frame body and first pads provided on the frame body. The circuit boards each are provided on one side of the frame plate. The circuit board includes a board body and second pads provided on the board body. The support bodies are provided between the frame plate and the circuit boards. The support bodies each include a first support portion and a second support portion. The first support portion is connected to the frame body. The second support portion is connected to the board body. Solder joints are provided between the first pads and the second pads. The solder joints connect the first pads to the second pads.

Circuit board assembly and electronic device

A method for collecting bit error information is provided. According to the method, a head node may encapsulate indication information into an IPv6 extension header of an IPv6 measurement request packet. The indication information indicates at least one intermediate node on a transmission path of the IPv6 measurement request packet to record bit error information into the IPv6 extension header. According to the application, the bit error information of the intermediate node on the transmission path can be collected.

Method and apparatus for collecting bit error information

A liquid crystal display (LCD) includes several transparent material layers and several non-transparent material layers that are disposed in a stacked mode. The LCD also has a local transparent region, and no non-transparent material is applied to the several non-transparent material layers in the local transparent region. This forms a transparent channel in the local transparent region along a stacking direction. An optical component is completely or partially disposed in the transparent channel of the LCD display. The optical component may be a camera, an ambient light sensor, an optical fingerprint sensor, or another component disposed under the display by using the local transparent region on the LCD display.

Liquid crystal display comprising a light channel formed through a stack including at least a color film layer, a thin-film-transistor layer, and a backlight and electronic device having the same

Growing community of inventors

Shenzhen, China

Liang Zhang