Log mode extraction and matching method

An extraction method and log technology, applied in neural learning methods, biological neural network models, instruments, etc., can solve the problems of low efficiency of log pattern extraction and matching, and unreliable results, so as to improve the efficiency of log pattern extraction and improve reliability , Improve the efficiency of log pattern matching

Pending Publication Date: 2020-03-13
TONGJI UNIV
View PDF8 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a log pattern extraction and matching method based on a deep twin neural network in order to overcome the defects of low log pattern extraction and matching efficiency and unreliable results in the prior art

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
  • Log mode extraction and matching method
  • Log mode extraction and matching method
  • Log mode extraction and matching method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0036] This embodiment provides a log pattern extraction and matching method, such as figure 1 shown, including the following steps:

[0037] Step S1: Cleaning the historical log data to obtain the cleaned historical log data;

[0038] Step S2: Preprocessing the cleaned historical log data to obtain the preprocessed historical log data;

[0039] Step S3: Obtain historical word vectors based on the preprocessed historical log data;

[0040] Step S4: Input the historical word vector into the Siamese LSTM network to extract the log pattern;

[0041] The matching of the log pattern is based on the log pattern obtained by the log pattern extraction method and the twin LSTM network, and the log pattern matching of the log data to be matched is performed.

[0042] in particular:

[0043] 1) Extract log mode

[0044] Such as image 3 As shown, for the historical log data of all components that appear in the system, first scan them one by one, perform simple data cleaning, and th...

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 invention relates to a log mode extraction and matching method, which comprises the following steps of S1, cleaning historical log data to obtain cleaned historical log data; S2, preprocessing thecleaned historical log data to obtain preprocessed historical log data; S3, obtaining a historical word vector based on the preprocessed historical log data; S4, inputting the historical word vectorsinto a twin LSTM network, and extracting a log mode; and S5, based on the to-be-matched log data, the log mode and the twin LSTM network, performing log mode matching of the to-be-matched log data. Compared with the prior art, the data volume of log analysis is reduced, the log pattern extraction efficiency is improved, the log pattern matching efficiency is improved, and the reliability of a logpattern extraction result and the reliability of a log pattern matching result are effectively improved.

Description

technical field [0001] The invention relates to the field of data mining, in particular to a log pattern extraction and matching method. Background technique [0002] Nowadays, the scale and complexity of information systems are increasing significantly. The challenges faced by system operation and maintenance are becoming increasingly severe, and the required labor and material costs are constantly increasing. In severe cases, they may even exceed the construction cost of the system itself. The operation and maintenance of the system is mainly through continuous monitoring and analysis of system logs, performance counters and application resource usage patterns, assessing system health and determining performance changes. It mainly relies on various types of running status record data generated by the system. The common ones are performance index record data generated regularly by performance counters, such as KPI data, and system logs generated in real time, such as event ...

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): G06F16/18G06F16/35G06F40/289G06N3/04G06N3/08
CPCG06F16/1815G06F16/35G06N3/08G06N3/044
Inventor 杨恺谢雨霞
Owner TONGJI UNIV
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