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

Video service experience quality identification method based on encrypted traffic data

A technology of traffic data and quality of experience, which is applied in the field of identification of video service experience quality, can solve problems such as difficult automatic collection of data and difficult application of solutions, and achieve the effect of overcoming time-consuming and high cost

Inactive Publication Date: 2019-06-18
ZHEJIANG UNIV
View PDF4 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] (1) It is difficult to automatically collect data with QoE level labels
[0013] (2) Features often require expert design and screening
[0014] Due to the above problems, this solution is difficult to apply

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
  • Video service experience quality identification method based on encrypted traffic data
  • Video service experience quality identification method based on encrypted traffic data
  • Video service experience quality identification method based on encrypted traffic data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] The following describes the present invention in further detail with reference to the accompanying drawings and specific embodiments, and the purpose and effects of the present invention will become more apparent.

[0067] figure 1 The flow chart of the method of the present invention is given. The QoE level identification of video playback under encrypted video traffic is divided into three steps in the present invention, that is, first collect encrypted traffic network video playback data and construct a training set. Then use the constructed training set to train the neural network classification model. After the classification model training is completed, the classification model can be used to generate the QoE level of video playback for the new encrypted traffic network video playback data.

[0068] Such as figure 1 As shown, in step 101, the collection of video playback data refers to a set of dedicated network video service quality data collection system suitable f...

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 video service experience quality identification method based on encrypted traffic data. The method comprises the following steps: acquiring an encrypted traffic file and corresponding event information when a video is played; processing the event information to determine the QoE level of the playing;preprocessing the encrypted traffic file to obtain TCP stream data; constructing an end-to-end deep learning model by taking the QoE grade as a label and the TCP stream data as a feature; The model can identify the QoE level of video playing according to the encrypted traffic file. According to the video QoE level identification method provided by the invention, the video QoE level can be accurately identified, and a fully automatic scheme is provided.

Description

Technical field [0001] The invention relates to the field of multi-sensor collection and traffic classification, and in particular to a method for identifying the quality of experience (QoE) of video services based on encrypted traffic data. Background technique [0002] The video service experience quality level identification technology refers to the technology for identifying the user's service experience after watching the video. Using this technology, network service providers can dynamically adjust network parameters to improve bandwidth utilization. [0003] Video QoE evaluation is mainly obtained through subjective evaluation or objective evaluation. Subjective evaluation is time-consuming and costly, and cannot cover all network conditions and user viewing habits. Therefore, more and more video service providers use objective evaluation to overcome the shortcomings of subjective evaluation. However, objective evaluation needs to establish an objective video experience qu...

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): H04N17/00G06N3/08
Inventor 陈锐杜歆
Owner ZHEJIANG 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