Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

SaaS software fault diagnosis method and device based on convolutional neural network

A convolutional neural network and software fault technology, applied in the computer field, can solve problems such as low accuracy of fault diagnosis methods, and achieve the effect of avoiding the intervention of human subjective factors, ensuring accuracy, and ensuring speed

Active Publication Date: 2020-05-26
WUHAN UNIV
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] In view of this, the present invention provides a SaaS software fault diagnosis method and device based on convolutional neural network to solve or at least partially solve the technical problem of low accuracy in the fault diagnosis method 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
  • SaaS software fault diagnosis method and device based on convolutional neural network
  • SaaS software fault diagnosis method and device based on convolutional neural network
  • SaaS software fault diagnosis method and device based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] This embodiment provides a SaaS software fault diagnosis method based on convolutional neural network, please refer to figure 1 , the method includes:

[0068] S1: Filter the log data generated by the system.

[0069] Specifically, considering the time dimension, when a performance failure node fails to be resolved within a specific period of time, it will frequently report the same log information. Considering the space dimension, the scheduling node sends a request to the node with performance failure. Since the scheduling node fails to process it in time, the scheduling node will send the request to other nodes, and other nodes will also report the same log information. Therefore, it is necessary to remove the same log information in the performance log, so as to improve diagnosis efficiency. The present invention judges whether they are redundant according to whether the performance log has the same severity level, performance failure component and performance fai...

Embodiment 2

[0164]This embodiment provides a SaaS software fault diagnosis device based on convolutional neural network, please refer to Figure 4 , the device consists of:

[0165] A filtering module 201, configured to filter log data generated by the system;

[0166] Labeling module 202, used for classifying and labeling the filtered log data;

[0167] A denoising module 203, configured to perform denoising processing on the log data after classification and labeling;

[0168] The vectorization module 204 is used to vectorize the denoised log data by using the Skip-Gram method, and construct a two-dimensional topology structure for the vectorized log data into two dimensions: a word vector dimension and a word dimension The two-dimensional vector data of ;

[0169] The training module 205 is used to use the constructed two-dimensional vector data as training data to train the pre-built convolutional neural network model to obtain a trained performance fault diagnosis model;

[0170]...

Embodiment 3

[0173] See Figure 5 , based on the same inventive concept, the present application also provides a computer-readable storage medium 300, on which a computer program 311 is stored, and when the program is executed, the method as described in the first embodiment is implemented.

[0174] Since the computer-readable storage medium introduced in the third embodiment of the present invention is a computer device used to implement a SaaS software fault diagnosis method based on a convolutional neural network in the first embodiment of the present invention, it is based on the introduction in the first embodiment of the present invention Those skilled in the art can understand the specific structure and deformation of the computer-readable storage medium, so details will not be repeated here. All computer-readable storage media used in the method in Embodiment 1 of the present invention fall within the scope of protection intended by the present invention.

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 an SaaS software fault diagnosis method based on a convolutional neural network. The method comprises the following steps: firstly, filtering log data generated by a system; then, subjecting the filtered log data to category classification and labeling; carrying out denoising processing on the log data subjected to category division and labeling; secondly, vectorizing the denoised log data by adopting a Skip-Gram method, and constructing a two-dimensional topological structure for the vectorized log data to form two-dimensional vector data of two dimensions, namely a word vector dimension and a word dimension; training a pre-constructed convolutional neural network model by taking the constructed two-dimensional vector data as training data to obtain a trained performance fault diagnosis model; and finally, diagnosing the log data of the unknown type by utilizing the trained performance fault diagnosis model to obtain the fault type of the log data. According tothe invention, the diagnosis accuracy and diagnosis efficiency of log data of unknown types are improved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a SaaS software fault diagnosis method and device based on a convolutional neural network. Background technique [0002] Software as a Service (SaaS) is an increasingly popular paradigm for delivering applications on the cloud because it eliminates the upfront investment in software products, infrastructure, and expensive maintenance costs. SaaS is the delivery of software functionality over the Internet from a single application instance shared by all users. SaaS software solutions are accessible through a web browser, requiring no software and hardware to install or maintain. They also replace the upfront licensing fees and lengthy implementation cycles of traditional installed applications with a "pay-as-you-go," subscription-based service relationship. Additionally, pricing can be tiered based on the required features and amount of data storage. The service provi...

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): G06F11/36G06F40/279G06N3/04
CPCG06F11/3608G06F11/366G06N3/045
Inventor 应时帕提古丽·阿不力孜段晓宇成海龙原万里
Owner WUHAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com