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

Predication method for user QoE (Quality of Experience) based on BP-Adaboost neural network

A quality of experience, neural network technology, applied in the prediction field of user experience quality, can solve the problem of low prediction accuracy, and achieve the effect of efficient prediction and efficient user experience quality

Pending Publication Date: 2017-08-22
NANJING UNIV OF POSTS & TELECOMM
View PDF5 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the above-mentioned deficiencies in the prior art, and proposes a method for predicting user quality of experience based on BP-Adaboost neural network. High problem, the method first extracts KPI data from the data collected by the IPTV set-top box, and extracts features, especially designed the user viewing rate as an important feature, and then based on the Adaboost framework, embeds the BP neural network into it, as a weak The classifier completes the training of the BP-Adaboost neural network model, and then predicts the KPI data of the unknown user experience quality

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
  • Predication method for user QoE (Quality of Experience) based on BP-Adaboost neural network
  • Predication method for user QoE (Quality of Experience) based on BP-Adaboost neural network
  • Predication method for user QoE (Quality of Experience) based on BP-Adaboost neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The invention will be described in further detail below in conjunction with the accompanying drawings.

[0038] Such as figure 1 Shown, the present invention provides a kind of prediction method based on the user experience quality of BP-Adaboost neural network, and this method comprises the steps:

[0039] Step 1: Data preprocessing to determine factors affecting user satisfaction.

[0040] (1-1) From the original records of key performance indicators (KPI) of video services collected by IPTV set-top boxes, KPI data with a fixed length of time are selected, and each KPI data contains 5 attributes: device transmission delay df, device packet loss rate lp, media loss rate lm, start time of user watching video start_time, end time of watching video end_time;

[0041] (1-2) Calculation of program viewing rate V r , its calculation formula is as follows:

[0042]

[0043]In the above formula, program_time is the total duration of the program, which can be obtained by...

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 prediction method for the user QoE based on the BP-Adaboost neural network, and solves the problem that a present IPTV video service is low in the user QoE predicting accuracy. The method comprises that KPI data is extracted from data collected by an IPTV set top box, features are extracted, the user watching rate is designed and serves as a significant feature, the BP neural network is embedded into the Adaboost framework to serve as a weak classifier, training of a BP-Adaboost neural network model is completed, and the KPI data in which the user QoE is unknown is predicted. Via the method, the user QoE can be predicted in a better way from the aspect of subjective feelings of users, and the designed new model training and predicting method can be used to predict the user QoE more accurately and efficiently.

Description

technical field [0001] The invention relates to the technical field of user experience quality analysis in video services, in particular to a method for predicting user experience quality based on a BP-Adaboost neural network. Background technique [0002] With the rise of cable 4K, mobile 2K, AR / VR and other services and the rapid development of communication and network technologies, the already popular video service has become even more popular, and the enthusiasm of the industry chain has been greatly ignited, including video service providers, Operators, Internet service providers, equipment manufacturers and other links are actively participating in the big video boom. In the era of big video, the booming video services on various networks emphasize not only the speed, bandwidth, and video quality, but also the user's feeling and experience. In the face of massive video services, users ultimately make judgments and choices based on their own experience. For video ser...

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): H04N17/00
CPCH04N17/004
Inventor 魏昕黄若尘高赟毛佳丽周亮
Owner NANJING UNIV OF POSTS & TELECOMM
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