Abnormal node detection method and device based on log, equipment and medium

A technology of anomaly detection and node detection, applied in the direction of response error generation, etc., can solve problems such as inaccurate status, achieve the effects of improving accuracy, realizing distributed processing, and improving efficiency

Active Publication Date: 2022-07-15
国家超级计算天津中心
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, calculating the state of a system purely based on the number of logs is inaccurate

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Abnormal node detection method and device based on log, equipment and medium
  • Abnormal node detection method and device based on log, equipment and medium
  • Abnormal node detection method and device based on log, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] In order to more clearly understand the above objects, features and advantages of the present disclosure, the solutions of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments may be combined with each other under the condition of no conflict.

[0023] Many specific details are set forth in the following description to facilitate a full understanding of the present disclosure, but the present disclosure can also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only a part of the embodiments of the present disclosure, and Not all examples.

[0024] In computing systems such as supercomputers, the structure is complex, the scale is large, and the components are tightly coupled. Therefore, it is an urgent problem to be able to detect the abnormality of the computing system in time and improve the rel...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The embodiment of the invention relates to a log-based abnormal node detection method and device, equipment and a medium, and the method comprises the steps: obtaining a first log event, inputting the first log event into a pre-trained log processing model, and obtaining at least one second prediction event; wherein the second prediction event is a log event obtained by performing causal relationship speculation on the first log event according to a log processing model; determining an anomaly detection result of the child node based on the second log event and at least one second prediction event; wherein the second log event is a log event generated after the first log event. According to the embodiment of the invention, the anomaly detection result of the child node can be determined in time based on the causal relationship, the anomaly detection efficiency and accuracy of the child node are improved, and then the average fault-free duration and reliability of the child node are improved.

Description

technical field [0001] The present disclosure relates to the technical field of artificial intelligence, and in particular, to a log-based abnormal node detection method, device, device and medium. Background technique [0002] In the system log of computing systems such as supercomputers, important events that occur in the system at each moment are recorded, and the state of the system can be understood through reasonable and effective analysis of the system log. However, the scale of computing systems such as supercomputers is relatively large and the software architecture is relatively complex, which significantly increases the number of logs. [0003] In the related art, a log counter is used to count the number of logs generated by the computing system, and whether the state of the computing system is abnormal is determined based on the number of logs. However, the state of a computing system based solely on the number of logs is not accurate. SUMMARY OF THE INVENTIO...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F11/07
CPCG06F11/0766G06F11/079
Inventor 李宇奇徐斌张健谭昕雨冯景华
Owner 国家超级计算天津中心
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap