Resource management method, device and storage medium

A technology for resource management and resource occupancy rate, applied in the fields of resource management methods, devices and storage media, can solve problems such as equipment stuck and poor resource management efficiency, and achieve the effect of improving efficiency

Pending Publication Date: 2020-07-24
TENCENT MUSIC ENTERTAINMENT TECH SHENZHEN CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the prior art, since the neural network model will occupy the central processing unit (CPU) resources of the smart device when running, especially when the neural network models in multiple different types of projects are used at the same time, the central processing unit resources are concentrated A large amount of consumption causes equipment freezes, which makes resource management less efficient

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
  • Resource management method, device and storage medium
  • Resource management method, device and storage medium
  • Resource management method, device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] In this embodiment, description will be made from the perspective of a resource management device. Specifically, the resource management device may be integrated in a network device equipped with a storage unit and equipped with a microprocessor and has computing capabilities. The network device may be a terminal or a server. , the following will take the terminal as an example for description.

[0046] A method for resource management, comprising: obtaining the corresponding processes of a plurality of neural network models; determining a corresponding number of target processes according to the resource occupancy rate indicated by the processes of each neural network model; determining the running time distribution information of the target processes; The distribution information sets a different start time for each target process.

[0047] see figure 1 , figure 1 It is a schematic flowchart of the resource management method provided by the embodiment of the present...

Embodiment 2

[0070] According to the method described in Embodiment 1, an example will be given below for further detailed description.

[0071] In this embodiment, it will be described that the resource management device is specifically integrated into a server.

[0072] see figure 2 , figure 2 Another schematic flowchart of the resource management method provided by the embodiment of the present application.

[0073] The method flow may include:

[0074] In step 201, the server acquires CPU resource usage, memory usage, and hard disk usage.

[0075] In some embodiments, the server will pre-acquire CPU information, total memory information and hard disk total information, the CPU information includes model and total resource resources, and store the CPU information, memory total information and hard disk total information in In the local database, the overall device performance of the server can be evaluated through the CPU information, total memory information, and total hard disk ...

Embodiment 3

[0095] In order to facilitate better implementation of the resource management method provided by the embodiment of the present application, the embodiment of the present application further provides a device based on the foregoing resource management method. The meanings of the nouns are the same as those in the resource management method above, and for specific implementation details, please refer to the description in the method embodiments.

[0096] see image 3 , image 3 It is a schematic structural diagram of a resource management device provided in the embodiment of the present application, wherein the resource management device may include an acquisition unit 301, a process determination unit 302, a distribution determination unit 303, a setting unit 304, and the like.

[0097] The acquiring unit 301 is configured to acquire processes corresponding to multiple neural network models.

[0098] Among them, when multiple projects need to be started at the same time, mul...

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

Embodiments of the invention disclose a resource management method, a device and a storage medium. The method comprises the steps of obtaining processes corresponding to multiple neural network models; determining a corresponding number of target processes according to the resource occupancy rate indicated by the process of each neural network model; determining running time distribution information of the target process; and setting different starting time for each target process based on the running time distribution information. Therefore, when a plurality of neural network models are integrated in the equipment; according to the embodiment of the invention, the appropriate number of target processes are obtained according to the resource occupancy rate of the process corresponding to each neural network model, the running time distribution information of the target processes is determined, different starting time is set for each target process, excessive consumption of resources caused by conflicts among multiple target processes is staggered, and the resource management efficiency is greatly improved.

Description

technical field [0001] The present application relates to the field of computer technology, and in particular to a resource management method, device and storage medium. Background technique [0002] As neural network-related technologies become more and more mature, the neural network model formed by this technology can be applied to various types of projects, such as recommendation projects, music genre classification projects, and sentiment analysis projects. In order to facilitate users to use smart devices, Many different types of items are integrated in smart devices. [0003] In the prior art, since the neural network model will occupy the central processing unit (CPU) resources of the smart device when running, especially when the neural network models in multiple different types of projects are used at the same time, the central processing unit resources are concentrated A large amount of consumption causes device freezes, making resource management inefficient. ...

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): G06F9/48G06N3/04
CPCG06F9/4887G06N3/045Y02D10/00
Inventor 杨伟明
Owner TENCENT MUSIC ENTERTAINMENT TECH SHENZHEN CO LTD
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