Method and device for assessing quality of experience (QoE) of TCP (Transmission Control Protocol) video stream service
A quality of experience and video streaming technology, applied to electrical components, transmission systems, etc., can solve the problems of real experience deviation, poor evaluation effect, and less consideration of users watching video experience, so as to improve accuracy and improve evaluation effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0051] Such as figure 1 As shown, Embodiment 1 of the present invention provides a method for evaluating the user experience quality of a TCP video streaming service, including the following steps:
[0052] S101. Monitor and record the user interaction behavior when the client watches the video to be evaluated, including pause, fast forward, rewind and selected resolution;
[0053] When the user watches the video through the client, the script written by JavaScript is used on the client, and through the API of HTML video events, the user can control the player on the browser, and can monitor and record the user's actions during the video watching process. interactive behavior.
[0054] S102. According to the network layer performance, application layer performance and the user interaction behavior when the client watches the video to be evaluated, obtain a plurality of performance quantification indicators representing the playback fluency, content attractiveness and picture ...
Embodiment 2
[0090] Such as figure 2 As shown, another TCP video stream service user quality of experience evaluation method provided by the embodiment of the present invention is a preferred solution of embodiment 1. The difference between embodiment 2 and embodiment 1 is that after step S101 is executed After that, and before performing step S102, the method also includes:
[0091] S105. Screen the user interaction behavior.
[0092] It is understandable that users may perform various interactive behaviors while watching videos, but some of them are not often done by users, the probability of occurrence is small, the impact weight is low, and the research value is not great; some user behaviors Usually occurs randomly, with uncertainty. Therefore, properly screening the user interaction behavior can further improve the accuracy of QoE evaluation of the TCP video service flow.
[0093] Similarly, if the user interaction behavior in the sample data obtained through the subjective evalu...
Embodiment 3
[0109] As a preferred solution of embodiment 1 or embodiment 2, the difference between embodiment 3 and embodiment 1 or embodiment 2 is that the BP neural network model adopted in this embodiment is obtained by using sample data training , the specific process of training the BP neural network model is as follows:
[0110] In step 1, a subjective evaluation experiment of user experience quality of users watching videos is carried out to obtain sample data.
[0111] In the experiment, the male and female ratio of the subjects was coordinated, and they came from different backgrounds. build as Figure 5 The HTTP video transmission system shown in Figure 5 Among them, 1 represents the server, 2 represents the router, and 3 represents the client for users to watch videos. On router 2, TC commands are used to control netem to simulate different network environments. The network parameters are set as shown in Table 1.
[0112] Table 1 Network parameters set in the subjective eva...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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