Server cluster operation and maintenance method based on multi-source heterogeneous data fusion and dynamic knowledge graph

By using multi-source heterogeneous data fusion and dynamic knowledge graphs, the data silos and root cause localization problems in server cluster operation and maintenance are solved, enabling efficient fault detection and handling, and improving the system's adaptability and accuracy.

CN121705077AActive Publication Date: 2026-03-20金品计算机科技(天津)有限公司 +1
5 Cites 9 Cited by

Patent Information

Application Number
CN202610218892.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-02-24
Publication Date
2026-03-20
Estimated Expiration
2046-02-24

AI Technical Summary

Technical Problem

Existing server cluster operations and maintenance suffer from issues such as multimodal data barriers, alarm storms, lack of adaptability in static models, and lack of closed-loop feedback in handling, making it difficult to achieve unified fusion of multi-source heterogeneous data and dynamic fault root cause localization.

Method used

We adopt a method based on multi-source heterogeneous data fusion and dynamic knowledge graph, analyze multimodal feature sequences through unsupervised deep learning models, construct dynamic health baselines, use graph neural network algorithms to analyze fault propagation probabilities, and combine incremental learning mechanisms to achieve intelligent operation and maintenance.

Benefits of technology

It improves the accuracy of fault detection, clearly locates the root cause, suppresses alarm storms, and enhances system adaptability through a feedback closed-loop mechanism.

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

Abstract

The invention provides a server cluster operation and maintenance method based on multi-source heterogeneous data fusion and a dynamic knowledge graph, and the method comprises the following steps: collecting a performance index, a log text and topological structure data of a server cluster, splicing the performance data and the log data based on a unified time window, and generating a multi-modal feature sequence; and analyzing the sequence by using an unsupervised deep learning model, constructing a dynamic health baseline, and generating a health degree portrait through the deviation with real-time data. When an exception is detected, mapping an exception event into a dynamic topological graph constructed based on a topological structure; analyzing a fault propagation probability between nodes by using a graph neural network algorithm, positioning a root cause node, and generating a disposal strategy to execute disposal operation; and collecting the processed recovery data as a feedback signal, and updating the deep learning model by using incremental learning. The method has the beneficial effects that the fault discovery accuracy is improved, the alarm storm is effectively inhibited, the root cause is directly positioned, and the model self-iteration adaptability is higher.
Need to check novelty before this filing date? Find Prior Art