Huawei Technologies Co., Limited

Shenzhen Yinwang Intelligent Technologies Co., Ltd.

Kang Cheng

Jian Tong Li

Liang Zhang

Jianfeng Wang

Xin Xiao

Jian Li

Bo Xie

Yinliang Hu

Min Hu

Lv Ding

Xingfen Wu

Jiyu Pan

Wenxiao Yu

Zemin Zhu

Fei Zhong

Zengjun Huang

Xiaoping Ma

Jiajia Wang

A battery charging progress prediction method and apparatus are provided. One example method includes: receiving a request message from a first terminal or a second terminal, where the request message includes a battery model of a battery of the first terminal and a first state of charge (SOC); determining charging progress information of the battery of the first terminal based on the request message; and sending a response message to the first terminal or the second terminal, where the response message includes the charging progress information.

Battery charging process prediction method and apparatus

A method includes obtaining a first memory log, where the first memory log includes log information of a plurality of garbage collections, and log information of each garbage collection includes a garbage collection time, and includes at least one of a downtime, memory usage after garbage collection, and memory usage before garbage collection, obtaining, based on log information in a first detection time window, first statistical information corresponding to the first detection time window, and determining, based on the first statistical information corresponding to the first detection time window, an anomaly degree corresponding to the log information in the first detection time window.

Memory anomaly detection method and device

A fault root cause analysis method and apparatus are provided. The method includes: obtaining a first alarm event set, where the first alarm event set includes a plurality of alarm events; for a first alarm event in the first alarm event set, extracting a feature vector of the first alarm event, where a part of or all features of the feature vector are used to represent a relationship between the first alarm event and another alarm event in the first alarm event set; and determining, based on the feature vector of the first alarm event, whether the first alarm event is a root cause alarm event. In this application, whether the first alarm event is the root cause alarm event is determined based on a feature vector of the relationship between the first alarm event and the another alarm event, and the accuracy of fault root cause identification is improved.

Fault root cause analysis method and apparatus

A method for obtaining a standard configuration template of a network device and a computing device includes obtaining configuration commands of a plurality of network devices, erating a command template set including a plurality of different command templates, generating a correlation matrix based on the command template set, clustering the plurality of network devices based on the correlation matrix to obtain at least two categories of network devices, dividing the correlation matrix into a plurality of submatrixes based on a clustering result, performing singular value decomposition on each submatrix to obtain a non-zero singular value, and using, as a standard configuration template of a corresponding category, a command template in the command template set that makes a contribution greater than a threshold to the non-zero singular value.

Method for obtaining standard configuration template of network device, and computing device

Growing community of inventors

Nanjing, China

Kang Cheng