Unlock instant, AI-driven research and patent intelligence for your innovation.

An Encrypted Video QoE Evaluation Method Based on Network Flow Feature Construction Learning

An evaluation method and network flow technology, applied in machine learning, data exchange network, digital transmission system, etc., can solve the problems of video frame HAS segmentation time length parameter acquisition, evaluation method is not comprehensive enough, etc., to achieve high accuracy effect

Active Publication Date: 2020-03-31
UNIV OF SCI & TECH OF CHINA
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the parameters of video frame, bit rate and HAS segment duration cannot be obtained through DPI technology in encrypted scenarios, so the existing evaluation methods for mobile video service KQI are still not comprehensive enough

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
  • An Encrypted Video QoE Evaluation Method Based on Network Flow Feature Construction Learning
  • An Encrypted Video QoE Evaluation Method Based on Network Flow Feature Construction Learning
  • An Encrypted Video QoE Evaluation Method Based on Network Flow Feature Construction Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] This embodiment is an encrypted video QoE evaluation method based on TCP protocol and network flow characteristic construction learning. figure 1 A schematic block diagram of the process flow of the encrypted video QoE evaluation method based on TCP protocol-based network flow feature construction learning in Embodiment 1 is given. First extract the experimental data set D4 required for analysis from the data collection platform data set D3, then perform TCP flow feature extraction D5, and finally realize the QoE evaluation based on network quality D6.

[0029] The data acquisition platform is mainly composed of the terminal APP D1 and the data acquisition LAN D2. The data set D3 is the HAS video data set based on the TCP protocol collected by the terminal APPD1 through the data acquisition LAN D2 to access the content provider D7 while watching the video, including terminal information. , video information, user operation behavior, QoE parameters, MOS score and QoS par...

Embodiment 2

[0058] Embodiment 2 of the present invention is a UDP protocol-based encrypted video QoE evaluation method based on network flow feature construction learning. Figure 5 A schematic flow chart of the network quality-based QoE evaluation method for the HAS video stream service based on the UDP protocol in Embodiment 2 is given. The QoE evaluation method of the HAS video stream service based on the UDP protocol is the same as the process in Embodiment 1. The data collection platform is composed of the terminal APPF1, the data collection local area network F2 and the content provider F7, and the data based on the UDP protocol is obtained through the data collection local area network F2. Based on the set F3, first extract the experimental data set F4 required for analysis, and then perform UDP data flow feature extraction F5 from the downlink rate F9, and finally realize the QoE evaluation F6 based on network quality by modeling the MOS score F10 model. Experimental dataset F4 in...

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 encrypted video QoE evaluation method based on network flow feature construction learning, characterized in that network data flow features irrelevant to data contents are extracted from QoS parameters through the analysis of data flow features of an HAS video service, and on this basis, a mapping model of 'the network data flow features-video KQI-user MOS' is trained and established by using a machine learning method, and the evaluation of the encrypted video QoE can be directly implemented in a data collection platform. Since the required features in a modeling process of the scheme of the invention are derived from the QoS parameters of the video service acquired by the data collection platform, the established mapping model does not depend on the video contents, so that the modeling method based on network data flows can be widely applicable to each encrypted and unencrypted mobile HAS video service based on TCP and UDP protocols.

Description

technical field [0001] The invention belongs to the technical field of mobile communication networks, and in particular relates to a QoE evaluation method suitable for encrypted video stream services based on network data stream characteristics. Background technique [0002] According to the 2016 "Cisco visual networking index: Global mobile datatraffic forecast update, 2016-2021 white paper" statistical forecast by Cisco, the traffic generated by mobile video services will account for more than 75% of mobile traffic by 2021. Therefore, operators need to ensure the quality of experience (Quality of Experience, QoE) of users of mobile video services to provide better network services, and how to effectively obtain and evaluate the QoE of video services in their networks is an urgent problem to be solved. Video service QoE refers to the subjective experience of users on the videos they watch. At present, the five-point subjective mean opinion score (Mean Opinion Score, MOS) p...

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 Patents(China)
IPC IPC(8): H04L12/26G06N20/00
CPCH04L43/08H04L43/50
Inventor 唐爽秦晓卫
Owner UNIV OF SCI & TECH OF CHINA