International Business Machines Corporation

China Academy of Telecommunications Technology

Samsung Electronics Co., Ltd.

Tsinghua University

Beijing Baidu Netcom Science and Technology Co., Ltd.

Datang Mobile Communications Equipment Co., Ltd.

China Petroleum Chemical Corporation

Beijing Zitiao Network Technology Co., Ltd.

Lemon Inc.

Research Institute of Petroleum Processing, Sinopec

Wanhua Chemical Group Co., Ltd.

Wanhua Chemical (Ningbo) Co., Ltd.

Beijing Nmc Co., Ltd.

Wanhua Chemical (Beijing) Co., Ltd.

Yi Zhao

Jiayi Fang

Bo Yang

Li Li

Yan Li

Yuan Feng

Xiaohui Yang

Wei Xue

Ling Shao

Rui Xiong Tian

Zhi Liang

Fangli Xu

Yu Yang

Feng Li

Jing Liang

Tao Liu

Ke Xu

Li Li Zhao

Jiamin Liu

Hai Shan Wu

Zhe Xiang

Meifang Jing

Hai Bo Lin

Huiyang Wang

Jiajia Wang

Yue Wang

Yali Zhao

Rui Zhao

Qing Fa Wang

Wei Lu

Li Liu

Wen Jie Wang

Yonghua Lin

Ravinder Kumar Sabhikhi

Ranran Zhang

Haibo Lin

Haijun Zhou

Hao Ni

Huan Hao Zou

Pu Zhu

Shoufeng Wang

Bing Bing Du

Huan He

Jia Jia Wen

Zhu Han

Yu Zhang

Wei Li

Xiaodong Yang

Haitao Li

Han Zhou

Lin Li

Bo Wu

Jun Long

Guoqing Li

Qi Yu

Lin Lin

Jing Zhu

Haiyang Quan

Kai Zheng

Yu Ding

Ju Wei Shi

Jun Hong Zhao

Zhigang Wang

Liang Lu

Xiaoyu Li

Kuan Feng

Seho Kim

Yudong Yang

Guangyu Sun

Zhuo Gao

Chen Shen

Li Chen

Chanjuan Wei

Qi Tan

Wei Shang

Xin Hui Li

Qinghua Duan

Junfeng Liu

Jin Ling

Zhichun Shen

Qixin Huang

Chaoping Ji

Peng Wei

Zhiqiang Wu

Zhichao Su

Sheng Lei

Min Mao

Ziwei Li

Ronghui Zhang

Xinhua Li

Junyi Yu

Hai Yong Zhang

Shuo Su

Hui Ling

Xiaoguang Zhao

Zhixue Wang

Liang Lv

Jiangbo Guo

Shang Liu

Yupu Liu

A clustering-based adaptive robust collaborative learning method includes: local models uploaded by a plurality of collaborative terminals and at least part of training data of the plurality of the collaborative terminals for training the local models are obtained, a trusted global model is trained based on the at least part of the training data; by taking trusted global model parameters as a trust guidance, a clustering operation is performed on each parameter dimension of the local models based on a predetermined optimal clustering algorithm respectively; and weights of the trusted local model parameters are determined based on similarities between the trusted global model parameters and the trusted local model parameters, to update the trusted global model parameters.

Clustering-based adaptive robust collaborative learning method and apparatus

Display screen or portion thereof with a graphical user interface

An example embodiment may provide a method to be performed by a base station and/or a network node, and relevant devices. The method may include: acquiring channel related information of a target user equipment (UE); acquiring a modulation and coding scheme (MCS) determined based on MCS related information, the MCS related information being acquired by an artificial intelligence (AI) network based on the channel related information; and, transmitting the determined MCS to the target UE, the target UE comprising an edge UE, the number of MCS change value of the edge UE being greater than the number of MCS change value of a center UE. The steps in this scheme can be implemented by a trained artificial intelligence method. The corresponding MCS related information may be acquired by an AI network based on the channel related information of the target UE, and the MCS of the target UE may then be determined by using the acquired MCS related information. Since the MCS related information acquired by the AI network can accurately reflect the channel state of the target UE, the determined MCS is more accurate, and the user throughput is thus improved.

Network node such as base station for handling modulation and coding scheme (MCS) related information and method therefor

A method, an apparatus, device, and a computer-readable storage medium for processing information are provided. The method is used in a first network device, and includes receiving information related to a second network device, determining a first resource configuration corresponding to a coverage classification related to the second network device based on the information, and transmitting the first resource configuration to the second network device. The method may obtain the first resource configuration through making prediction and calculation analysis based on the information, which may achieve dynamic configurations of different coverage classifications, save energy consumption, and improve system capacity and performance at the same time.

Information processing method, apparatus, device and computer readable storage medium

A method and an apparatus for actively defending against backdoor attacks under an edge computing scenario. The method includes: generating an initial optional operation set based on optional operations configured to enhance a model generalization ability, and constructing a configuration parameter set for each operation in the set; selecting a first subset with a curve between configuration parameters and model accuracies of the operation presenting a monotonically decreasing concave function characteristic; selecting a second subset with a curve of the operation between configuration parameters and probabilities that a model is successfully attacked by the backdoor attack presenting a monotonically decreasing convex function characteristic; constructing a mutation characteristic set for each operation in an intersection of the first and second subsets; and for each operation in the intersection, determining a final parameter setting value of the operation based on the mutation characteristic set, to actively defend against possible backdoor attacks.

Method and apparatus for actively defending against backdoor attacks under edge computing scenario

The present disclosure discloses a method and apparatus for testing a stress based on a cloud service, and relates to the field of cloud computing technology, and further to the field of cloud operation and maintenance technology. A particular implementation comprises: acquiring, based on first stress test information of a business system in a cloud service, a number of expected stress test nodes corresponding to the business system; creating edge computing nodes, a number of the edge computing nodes being identical to the number of the expected stress test nodes; and performing a stress test on the business system by using the edge computing nodes, to acquire second stress test information of the business system.

Method and apparatus for testing stress based on cloud service

A method for controlling a beam in a cell, includes obtaining traffic distribution data of a plurality of beam areas included in the cell, obtaining a total number of a plurality of beams for a beam area among the plurality of the beam areas, based on the obtained traffic distribution data, and obtaining a beam width of one among the plurality of beams for the beam area, based on the obtained total number of the plurality of beams. The method further includes obtaining, from a candidate beam set, candidate beams for the beam area, based on the obtained total number of the plurality of beams and the obtained beam width of the one among the plurality of beams, and obtaining, from the obtained candidate beams, multiple beams for the beam area, based on a distance between the obtained candidate beams and the beam area.

Method and apparatus for controlling beam adaptively in wireless communication system

Embodiments of the present disclosure provide a BWP allocation method, apparatus, electronic device, and a computer-readable storage medium, and relate to the field of communication technologies. The method includes: acquiring service-related information of at least one base station; determining configuration information of the bandwidth part (BWP) of the at least one base station based on the service-related information of the at least one base station; and configuring the BWP of the at least one base station based on the configuration information. The BWP allocation method may meet requirements of different services and different user capabilities, improve a network throughput, and reduce energy consumption.

BWP allocation method, apparatus, electronic device and computer readable storage medium

A method performed by a terminal in a wireless communication system, including receiving, from a base station, a physical downlink control channel (PDCCH); predicting aggregation level information including information about an aggregation level of a control channel element (CCE) in which the PDCCH is received based on an aggregation level prediction model; determining a detection order for detecting the PDCCH based on the aggregation level information; and etecting the PDCCH based on the determined detection order.

Method and apparatus for detecting physical downlink control channel based on predicted information

Embodiments of the present disclosure provide a method and a device for cross-domain strong logically isolation and secure access control in the Internet of Things (IoT). The method includes the following. When one IoT gateway receives the identity authentication request, the IoT gateway sends the identity authentication request to all IoT gateways in the domain excluding that IoT gateway. When all IoT gateways in the domain receive the identity authentication request, all IoT gateways verify separately whether the identity authentication request is legal. After a certain IoT gateway obtains the identity authentication result, a distributed consensus procedure is initiated. The IoT gateways in the domain reach a consensus on the identity authentication result through a distributed consensus mechanism, and the identity authentication result is written and stored to a block of a blockchain.

Method and device for cross-domain strong logical isolation and secure access control in the internet of things

An apparatus for beam configuration in a wireless communication system, including a transceiver; and at least one processor connected with the transceiver and configured to: form at least one beam cluster from beams of a base station; determine a configuration of the at least one beam cluster; and configure the beams in the at least one beam cluster according to the determined configuration

Method and apparatus for beam configuration in wireless communication system

Embodiments for efficient machine and deep learning hyperparameter tuning in a distributed computing system. Runtime metrics of each training iteration are collected to identify candidate jobs to merge during an execution phase. The candidate jobs are grouped into job groups, and the job groups containing the candidate jobs are merged together subsequent to each iteration boundary for execution during the execution phase.

Job merging for machine and deep learning hyperparameter tuning

The present disclosure provides an unsupervised exception access detection method and apparatus based on one-hot encoding mechanism. The method includes: encoding each test URL sample by using one-hot encoding mechanism, to obtain a high-dimensional vector; inputting the high-dimensional vector into a pre-built deep autoencoder network for compression and dimension reduction processing, to obtain a two-dimensional vector; performing visualization operation on the two-dimensional vectors by using a two-dimensional coordinate system, to obtain visualized test URL samples; performing a cluster analysis on all visualized test URL samples by using a K-means algorithm, to divide the test URL sample set into a first type and a second type of URL sets; comparing sample sizes of the first type and second type of URL sets, determining the URL set with a larger sample size as a normal URL set, and determining the URL set with a smaller sample size as an abnormal URL set.

Unsupervised exception access detection method and apparatus based on one-hot encoding mechanism

Disclosed in the present invention are a method and an apparatus for determining resource occupation state. The method comprises: a first node receiving SA information sent by at least one second node, the SA information being used for indicating resource occupation state of the second node; at each state maintenance moment, the first node determining, according to the service transmission cycle of the first node itself and the SA information, the resource occupation state within the state maintenance cycle which has a length of the service transmission cycle of the first node The solutions provided in the embodiments of the present invention can effectively support the sensing of the resource occupation state in various service transmission cycles, and reduce the complexity of resource occupation state maintenance and resource selection.

Method and apparatus for determining resource occupation state

A method and device for resource reservation are provided. The resource reservation method includes: receiving scheduling assignment information transmitted by first UE, where the scheduling assignment information includes information about time-frequency resource that the first UE needs to reserve; determining the quantity of reservations for the time-frequency resource by the first UE according to the scheduling assignment information; if new scheduling assignment information about the time-frequency resource transmitted by the first UE has been received before the quantity of reservations becomes invalid, re-determining reservation information for the time-frequency resource according to the new scheduling assignment information; and if no new scheduling assignment information about the time-frequency resource transmitted by the first UE has been received before the quantity of reservations becomes invalid, taking the time-frequency resource as an idle resource.

Method and device for resource reservation

Growing community of inventors

Beijing, China

Yi Zhao