Fault root cause positioning method, device, equipment, medium and product

By combining multimodal data fusion and anomaly detection networks with causal dependency graphs, the problem of single-modal data diagnosis failure is solved, enabling efficient root cause localization of distributed system failures and adapting to fault diagnosis in complex microservice architectures.

CN121705069APending Publication Date: 2026-03-20CHINA MOBILE INFORMATION TECHNOLOGY CO LTD +1
0 Cites 3 Cited by

Patent Information

Application Number
CN202511857800.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-10
Publication Date
2026-03-20

AI Technical Summary

Technical Problem

Existing fault diagnosis solutions are mainly based on single-modal data, which cannot capture or completely miss some abnormal information caused by faults, resulting in diagnosis failure. In particular, the difficulty of fault diagnosis increases in distributed and microservice architectures, and it is difficult to locate faults in real time.

Method used

Multimodal data fusion technology is used to acquire structured time-series monitoring data and unstructured operation logs. A fusion feature vector is generated by multimodal feature fusion, and anomaly detection and root cause analysis are performed using a multimodal anomaly discrimination network. Finally, the root cause of the fault is located by combining causal dependency graphs and knowledge bases.

Benefits of technology

It enables comprehensive anomaly detection of multimodal data in distributed systems, can discover more granular root causes of failures, improves the accuracy and efficiency of fault diagnosis, and adapts to complex microservice architecture changes.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a fault root cause positioning method and device, equipment, a medium and a product, and relates to the technical field of IT, the method comprises the steps that cluster multi-modal data collected by a data collection agent is acquired, and the multi-modal data comprises structured time sequence monitoring data and unstructured operation logs; performing multi-modal feature fusion on the time sequence monitoring data and the running log to obtain a fusion feature vector representing the current state of the cluster; according to the fusion feature vector, performing anomaly detection on the cluster to obtain a detection result, the detection result including an anomaly score and an anomaly category; and under the condition that the anomaly score is greater than a first threshold value, performing fault root cause analysis according to the anomaly category, the time sequence monitoring data related to the anomaly category and the fusion feature vector to obtain an analysis result. Therefore, the problem that abnormity diagnosis based on single-mode data is likely to fail is solved.
Need to check novelty before this filing date? Find Prior Art