A video playback evaluation method and device

Abstract

The embodiment of the present invention provides a video playback evaluation method and device. The method includes: obtaining the level value of the clarity level factor of the played video and the value of the target playback factor; from the corresponding relationship between each level value and the evaluation function, determine The target evaluation function corresponding to the obtained grade value; based on the target evaluation function and the value of the target playback factor, the evaluation result of the played video is obtained. Through this technical solution, the definition level factor is added as a non-quality of service feature in the evaluation process, and the service quality feature of the playback interaction factor and / or playback experience factor is also included. Based on the non-service quality feature and service quality feature, compared with the existing There are technical assessments that are more comprehensive. The sharpness level factor is correlated with the playback interaction factor and the playback experience factor, and there is no correlation between the playback interaction factor and the playback experience factor, which controls the increase in the number of cross features, and then controls the increase in evaluation complexity.

Description

technical field [0001] The present invention relates to the field of multimedia technology, in particular to a method and device for video playback evaluation. Background technique [0002] Browsing videos on video sites has become a daily routine, and many video sites provide users with more choices. For each video network, how to attract and retain users has become a key issue. Among them, user experience is an important factor for user retention. Only by improving user experience can there be a chance to retain more users. [0003] In order to improve the user experience, it is necessary to understand the viewing experience of the user in the process of watching the video, that is, QoE (QualityOf Experience, Quality of Experience), and then make targeted improvements. At present, there are mainly two ways to evaluate the user experience. The first way is to display the playback evaluation for the user after each video is played, and the user can fill it in according to ...

AI Technical Summary

Problems solved by technology

[0004] However, the inventor found in the process of implementing the present invention that the prior art has at least the following problems: For the second method, only the impact of service quality features is reflected in the evaluation process, while the impact of non-service quality features is lacking. make the assessment less comprehensive

However, if non-service quality features are added, cross features need to be added in the evaluation process due to the correlation between each feature, and the increase of cross features will increase the complexity of evaluation

For example, if the quality of service features include A and B, then add non-quality of service feature C, and there is correlation among A, B, and C, then in addition to evaluating A, B, and C, it is also necessary to evaluate the cross feature A* B, B*C and C*A are evaluated, which greatly increases the complexity of the evaluation

Images