Operation and maintenance method and device of equipment, nonvolatile storage medium and electronic equipment

By constructing a target graph and a multi-level attention framework, and combining equipment operation characteristics and multimodal data, the problem of low operation and maintenance efficiency in existing technologies is solved, and efficient anomaly root cause localization and fault diagnosis are achieved.

CN122120109APending Publication Date: 2026-05-29CHINA TELECOM CORP LTD

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
CHINA TELECOM CORP LTD
Filing Date
2026-02-11
Publication Date
2026-05-29

AI Technical Summary

Technical Problem

Existing technologies cannot comprehensively consider the operational data of different modes of various devices in the system, resulting in low operation and maintenance efficiency and an inability to accurately locate the root cause of abnormal areas and devices.

Method used

By constructing a target graph, nodes and devices are matched one-to-one. Node features include the device's operating characteristics and time and location information. Abnormal areas are identified using correlation indicators, and the causes of abnormal device failures are determined through multimodal operating data analysis. A multi-level attention framework is used for deep fusion and diagnosis.

Benefits of technology

It enables efficient and accurate location of the root cause of anomalies, improves operation and maintenance efficiency, and can comprehensively consider multimodal data for accurate diagnosis and fault analysis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122120109A_ABST
    Figure CN122120109A_ABST
Patent Text Reader

Abstract

The application discloses an operation and maintenance method and device of equipment, a nonvolatile storage medium and an electronic device. The method comprises the following steps: determining a target graph of a target system; determining an association degree index between a node and a neighbor node of the node according to a node feature of the node in the target graph, and determining an abnormal area in the target graph according to the association degree index; determining a target abnormal node according to a node feature of a node in the abnormal area, the target abnormal node being a node causing an abnormal state of the abnormal area; determining multi-modal operation data of an abnormal equipment corresponding to the target abnormal node within a second preset time period, and determining a fault cause of the abnormal equipment according to an association relationship between different modal operation data in the multi-modal operation data; and determining an operation and maintenance mode according to the fault cause. The application solves the technical problem of low operation and maintenance efficiency caused by the fact that different modal operation data of each equipment in a system are not comprehensively considered in the related art.
Need to check novelty before this filing date? Find Prior Art