A method and apparatus for identifying a faulty network element

By employing a baseline learning algorithm to calculate dynamic baselines and dynamic alarm thresholds in VoLTE networks, and combining node-level correlation information to automatically identify faulty network elements, the problem of insufficient timeliness and accuracy in fault identification in VoLTE networks is solved, achieving rapid and accurate fault delimitation.

CN116112963BActive Publication Date: 2026-06-26CHINA MOBILE GRP GUANGDONG CO LTD +1
View PDF 3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CHINA MOBILE GRP GUANGDONG CO LTD
Filing Date
2021-11-11
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

The timeliness and accuracy of fault element identification in existing VoLTE networks are insufficient. Relying on manual methods makes it difficult to quickly and timely delineate faults, and manual judgment is easily influenced by experience, leading to errors in judgment.

Method used

The baseline learning algorithm is used to calculate the dynamic baseline and dynamic alarm threshold in real time. Faulty network elements are automatically identified through real-time indicator monitoring and node-dimensional correlation information. Multi-dimensional judgment is made using big data intelligent analysis.

Benefits of technology

It enables real-time and accurate delimitation of faulty network elements, improves the timeliness and accuracy of fault identification, avoids human judgment errors, and adapts to fluctuations and adjustments in network indicators.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116112963B_ABST
    Figure CN116112963B_ABST
Patent Text Reader

Abstract

The application provides a fault network element identification method and device, electronic equipment and computer program product, and relates to the technical field of data processing. The method comprises: extracting real-time index values of key network indexes; using a preset baseline learning algorithm to calculate a dynamic baseline according to the real-time index values; determining a dynamic alarm threshold line of the key network indexes according to a preset deviation tolerance and the dynamic baseline; and when an alarm event is triggered, identifying a fault network element according to node dimension association information. The application can automatically and in real time monitor network element index conditions, automatically adapt to fluctuations and adjustments of network indexes through a dynamic baseline and a dynamic threshold value, and identify a fault network element through node dimension association information, thereby avoiding human judgment errors and effectively improving the timeliness and accuracy of fault identification.
Need to check novelty before this filing date? Find Prior Art