AI-based congestion control algorithm, device and equipment and medium

A congestion control and algorithm technology, applied in the computer field, can solve problems such as difficulty in ensuring the experience of all users

Active Publication Date: 2021-02-02
FUJIAN STAR NET WISDOM TECH CO LTD
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Most of the existing congestion control algorithms use a set of relatively fixed rules to apply to all users, and refer to fewer network characteristics, but the network conditions of different users are often different, so relatively fixed congestion control algorithms are difficult to ensure that all users have a better good experience

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
  • AI-based congestion control algorithm, device and equipment and medium
  • AI-based congestion control algorithm, device and equipment and medium
  • AI-based congestion control algorithm, device and equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0150] Such as image 3 As shown, the present embodiment provides that the present invention provides an AI-based congestion control algorithm, including: network state feature extractor, audio and video state feature extractor, feature processor, reward calculator and AI code rate estimator;

[0151] The network state feature extractor: used to extract characteristic attribute values ​​reflecting the network state;

[0152] Described audio-video state feature extractor: be used for extracting the feature attribute value that embodies audio-video state;

[0153] The feature processor: according to the input feature value, obtain information corresponding to at least one dimension of the feature value through calculation, the information is used to expand the dimension of the feature value, and the information and the input feature value together form a state feature space; For example, when the feature value is the packet loss rate, more dimensional information such as varian...

Embodiment 2

[0189] Such as Figure 4 As shown, the second aspect is provided in the present embodiment, and the present invention provides an AI-based congestion control device, including: a network state feature extractor, an audio and video state feature extractor, a feature processor, a reward calculator, and AI code rate estimator;

[0190] The network state feature extractor: used to extract characteristic attribute values ​​reflecting the network state;

[0191] Described audio-video state feature extractor: be used for extracting the feature attribute value that embodies audio-video state;

[0192] The feature processor: according to the input feature value, obtain information corresponding to at least one dimension of the feature value through calculation, the information is used to expand the dimension of the feature value, and the information and the input feature value together form a state feature space; For example, when the feature value is the packet loss rate, more dimen...

Embodiment 3

[0229] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the computer program, any implementation manner in Embodiment 1 can be implemented.

[0230] Since the electronic device introduced in this embodiment is the device used to implement the method in Embodiment 1 of this application, based on the method described in Embodiment 1 of this application, those skilled in the art can understand the electronic device of this embodiment. Specific implementation methods and various variations thereof, so how the electronic device implements the method in the embodiment of the present application will not be described in detail here. As long as those skilled in the art implement the equipment adopted by the method in the embodiment of the application, they all belong to the intended protection scope of the application.

[0231] Based on the same inventi...

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 provides an AI-based congestion control algorithm, device and equipment and a medium, and the method comprises the steps that a network state feature extractor extracts a network state according to a state feature space of a feature processor, and obtains a feature attribute value of the network state through calculation; an audio and video state feature extractor extracts feature attribute values of the audio and video states and calculates a reward value through a reward calculator; an AI code rate estimator calculates a code rate estimated value through the reward value and the characteristic attribute value of the network state; and a receiving end or a sending end performs adjustment according to the code rate estimation value, so the network characteristic data of multiple dimensions can be effectively utilized, the current bandwidth value can be predicted more accurately, and a timely and effective congestion control effect is realized.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to an AI-based congestion control algorithm, device, device and medium. Background technique [0002] Congestion control is a research hotspot in the field of video conferencing. Network congestion will lead to increased delay and packet loss rate, resulting in increased audio and video delay and even freezes, affecting user experience. Congestion control is an important means of video conference quality assurance, which can reduce network delay and relieve network congestion. There are many current congestion control schemes, such as GCC congestion control algorithm, Sendside-BWE algorithm, etc. [0003] Most of the existing congestion control algorithms use a set of relatively fixed rules to apply to all users, and refer to fewer network characteristics, but the network conditions of different users are often different, so relatively fixed congestion control algorithms ...

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): H04L12/811H04L12/853H04L29/06H04L12/26H04N7/15G06F17/11H04L47/2416
CPCH04L47/2416H04L47/38H04L43/0829H04N7/15G06F17/11H04L65/70H04L65/65
Inventor 陈荣观刘硕陈玉龙王颖戴立陈
Owner FUJIAN STAR NET WISDOM TECH 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