Online service anomaly detection method based on log semantic analysis

An anomaly detection and semantic analysis technology, applied in semantic analysis, natural language data processing, text database clustering/classification, etc., can solve problems such as difficult parameters, difficult representation, and complex models

Inactive Publication Date: 2021-01-05
HANGZHOU DIANZI UNIV
View PDF4 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method only treats the log as a single time series. In a large-scale cluster system that generates mutual cross logs, the model will be too complex, and the cross logs make it difficult to adjust the parameters and achieve better performance.

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
  • Online service anomaly detection method based on log semantic analysis
  • Online service anomaly detection method based on log semantic analysis
  • Online service anomaly detection method based on log semantic analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0106] The present invention will be further described below in conjunction with accompanying drawing, please refer to figure 1 ;

[0107] figure 1 It is the VCNN mechanism. As shown in the figure, the VCNN of the present invention can be divided into three layers. Since the structure of VCNN is similar to TextCNN, the two differ only in the convolutional and pooling layers. Therefore, the present invention only introduces the convolutional and pooling layers of the improved network structure.

[0108] Suppose the input matrix of the convolutional layer is x∈R n×k , where n represents the length of the input sentence and k represents the dimensionality of the word vector. In the direction of sentence length, x i represents the word vector of the i-th word, x i：j Represents the concatenation of word vectors from the i-th word (related to) to the j-th word. The input matrix x can be represented as a concatenation of n word vectors in k dimensions.

[0109] ...

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 an online service anomaly detection method based on log semantic analysis. According to the method, a TextCNN is improved, and a variable convolution and pooling convolution neural network is provided for log classification. The VCNN provided by the invention mainly considers the influence factors of the word embedding dimension. The multi-convolution and multi-pooling operation performed by the method is not only applied to sentence length, but also more applied to the word embedding dimension to extract rich semantic feature information so as to make up for the deficiency of semantic information in the word embedding dimension. In addition, the average pooling operation proposed in a pooling layer facilitates the storage of the important feature information of the extracted features. The core of the method is log classification based on log semantics and service completion strength and performance anomaly classification based on improved Bayesian. The methodis mainly suitable for detecting the online service exception, deduces the log cluster influencing the system performance by utilizing a log, and can support exception detection and search for the logrelated to the influence on the service performance.

Description

technical field [0001] The invention relates to a classification based on log semantics and service completion intensity, and then performing a correlation analysis on the classification result and the performance of online services to find out log source texts related to service exceptions. Background technique [0002] For large-scale software systems, especially cloud-based online service systems (such as Microsoft Azure, Amazon AWS, Google Cloud), high service quality is crucial. These systems serve hundreds of millions of users around the world, so small service issues can lead to huge revenue losses and dissatisfied users. [0003] Large software systems often generate logs to record system runtime information (such as status and events). Logs contain a lot of valuable information. Therefore, log anomaly detection is a key technology to help debug system failures and perform root cause analysis. However, as the types of logs generated by systems and applications bec...

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): G06F16/35G06F40/194G06F40/30G06K9/62G06N3/04
CPCG06F16/35G06F40/30G06F40/194G06N3/045G06F18/24155
Inventor 李冬青蒋从锋万健欧东阳闫龙川殷昱煜张纪林黄震赵子岩李妍
Owner HANGZHOU DIANZI 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