Log parameter anomaly detection method based on word embedding

An anomaly detection and parameter technology, applied in the Internet field, can solve the problems of model redundancy and lack of actual deployment ability, and achieve the effect of accurate detection ability

Pending Publication Date: 2020-12-11
XI AN JIAOTONG UNIV
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is only for continuous type parameter variables, and the ...

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 parameter anomaly detection method based on word embedding
  • Log parameter anomaly detection method based on word embedding
  • Log parameter anomaly detection method based on word embedding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention is described in further detail below in conjunction with accompanying drawing:

[0023] Such as figure 1 As shown, it is a flow chart of the log parameter abnormality detection method based on word embedding of the present invention, and the detection method of the present invention includes the following steps:

[0024] Step 1. Regularized analysis of parameters:

[0025] The log is plain text, with one part fixed and another part variable. For example, given the logs of "Newswitch connected from 127.0.0.1:54000" and "New switch connected from 127.0.0.1:54112", the four words "New", "switch", "connected" and "from" Treated as constant parts because they are always constant, called log templates. The remaining parts are called variable parts, because they assume different states in different situations. The variable part can be abstracted as an asterisk in the constant part, that is, "New switch connected from*", each variable part can be calle...

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 discloses a log parameter anomaly detection method based on word embedding, and the method comprises the following steps: 1, analyzing all parameters in a log, and independently dividingdiscrete parameters in all the parameters; 2, converting the discrete parameters into continuous parameter word vectors; 3, training a parameter word vector by using a long-term and short-term memoryneural network model, and predicting the parameter word vector at a subsequent target moment by using the trained parameter word vector; 4, determining the association degree of the prediction parameter word vector and the target parameter word vector by using cosine similarity, calculating a loss value through the association degree, feeding back the loss value to the network, and updating and optimizing the model until convergence; and 5, acquiring a log to perform parameter anomaly detection, calculating cosine similarity between the prediction parameter and the target parameter, and if the cosine similarity is lower than a threshold value, determining that the log parameter is abnormal. The detection bottleneck caused by parameter dynamics and difference can be effectively solved, andthe overall accuracy of log detection is improved.

Description

technical field [0001] The invention belongs to the technical field of the Internet, and relates to a log parameter abnormality detection method based on word embedding. Background technique [0002] Logs are an important part of various computer systems. System logs can reflect the execution process and status of computer programs, and can also identify errors and exceptions that occur during the execution of systems and programs. Due to the importance of logs, log anomaly detection has always been a hot topic of research. Most of the current anomaly detection methods classify logs into fixed-format log templates. Through the timing information of log templates, data statistics, machine learning, Methods such as deep learning complete log anomaly detection. However, in various types of computer logs, in addition to fixed format and category log templates, there are also a large number of dynamic log parameters. Abnormalities in the program execution sequence can be identi...

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
IPC IPC(8): G06F40/205G06F40/242G06N3/04G06N3/08
CPCG06F40/205G06F40/242G06N3/049G06N3/08G06N3/045
Inventor 王换招王肖晨张鹏单丹枫
Owner XI AN JIAOTONG 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