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

Convolutional neural network based memory early warning method and server

A convolutional neural network and server-side technology, which is applied in the memory early warning method and server field based on convolutional neural network, to achieve good scalability

Inactive Publication Date: 2018-11-27
FUJIAN TQ DIGITAL
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method is often an early warning given when the server memory has obvious problems, that is, the traditional memory early warning scheme is not a real early warning

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
  • Convolutional neural network based memory early warning method and server
  • Convolutional neural network based memory early warning method and server
  • Convolutional neural network based memory early warning method and server

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] Please refer to figure 1 as well as figure 2 , Embodiment 1 of the present invention is:

[0069] A memory early warning method based on convolutional neural network, comprising steps:

[0070] S1. The server receives the memory occupancy information sent by the client, and generates image information data to be predicted according to the continuous memory occupancy information within the set time;

[0071] S2. Call the memory classification model to classify the image information data to be predicted, obtain the memory result corresponding to the image information data to be predicted, and return the memory result to the client. The memory classification model is a trained convolutional neural network model.

[0072] Among them, the image information data to be predicted is generated according to the continuous memory occupancy rate information within a set time period as follows:

[0073] Set the first time to 1 second and the second time to 10 seconds in advance,...

Embodiment 2

[0097] Please refer to figure 1 as well as figure 2 , the second embodiment of the present invention is:

[0098] A memory warning server 1 based on a convolutional neural network, including a memory 2, a processor 3, and a computer program stored in the memory 2 and operable on the processor 3, and the processor 3 implements the above-mentioned example 1 when executing the computer program in the steps.

[0099] In summary, the present invention provides a convolutional neural network-based memory early warning method and server, which can effectively extract image information formed by memory information by using convolutional neural network, thereby effectively predicting the obtained memory information Whether there is overflow or overflow risk, provide better technical support for the client, server, and operation and maintenance; at the same time, because the client only needs to be able to communicate with the server, so that the present invention can be used across pl...

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 convolutional neural network based memory early warning method and a server. The method includes: allowing a server to receive memory information sent by a client, and generating to-be-predicted picture information data; and calling a memory classification model to classify the to-be-predicted picture information data, obtaining a memory result corresponding to the to-be-predicted picture information data, and returning the memory result to the client, wherein the memory classification model is a trained convolutional neural network model. The invention can effectively extract the picture information formed by the memory information by using the convolutional neural network, can effectively predict whether the acquired memory information overflows or there is an overflow risk, and can provide a better technical support for the client, the server, and the operation and maintenance; and meanwhile, the invention can achieve cross-platform use and has good scalability. In other words, the invention provides a memory overflow early warning scheme that can achieve cross-platform use, has good scalability, and is more realistic and effective.

Description

technical field [0001] The invention relates to the fields of computer vision and deep learning, in particular to a convolutional neural network-based memory early warning method and a server. Background technique [0002] When the client device is running the application program, there will be insufficient memory space for it to use. In view of this phenomenon of memory overflow, various memory warning schemes have appeared in the prior art. One is to monitor the program through the monitoring program. Whether the system memory is about to reach the upper limit; the second is to monitor the system's own errors to determine whether there is memory overflow or potential memory problem risk. [0003] Application No. 201610903370.5 is a method and device for monitoring memory usage. By monitoring the memory usage of each application, the user is reminded when the warning value is exceeded, allowing them to choose how to clean up. However, this method is often an early warning ...

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): G06F9/50G06K9/62G06N3/04H04L12/24H04L12/26
CPCH04L41/0631H04L43/0876G06F9/5016G06N3/045G06F18/241
Inventor 刘德建苏威鹏林琛
Owner FUJIAN TQ DIGITAL
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