Video resource popularity prediction method

Abstract

The invention discloses a video resource popularity prediction method. The video resource popularity prediction method comprises the steps of counting ratings data of group users in a certain region, obtaining ratings type data and interactive behavior data of the group users and calculating the resource popularity of the data by utilizing the ratings type data; traversing the ratings type data and the interactive behavior data by utilizing an LDA model of a coupling user behavior so as to generate corresponding dirichlet distribution respectively, deducing a full probability of each behavior mode through a chain rule and getting an expected value of each dirichlet distribution so as to obtain a behavior mode matrix; regarding the resource popularity of the counted data and the behavior mode matrix as an input of a neural network by combining with a neural network model, training to generate a prediction model and further predicting the video resource popularity in future. The method comprehensively considers influence from the ratings interactive content data and interactive behavior data of users to the prediction of the resource popularity, researches the relationship between the two types of data and the popularity, and improves the prediction accuracy of the resource popularity.

Description

technical field [0001] The invention relates to the technical fields of data mining and machine learning, and in particular designs a method for predicting the popularity of video resources. Background technique [0002] Video on demand is a video playback technology that transmits and plays corresponding service content based on the dynamic needs of users to watch. Users have the initiative over the data flow in terms of viewing content selection and viewing methods, and whether they can respond to user viewing behavior needs in a timely manner is closely related to the efficiency of resource scheduling. In the resource scheduling process, the popularity of resource information is an important reference standard for scheduling algorithms. [0003] In the following, we will introduce the relevant research work from user behavior analysis and resource popularity prediction respectively. [0004] In the existing research on user behavior analysis, the definition of user beha...

AI Technical Summary

Problems solved by technology

From the perspective of the above scheme, the existing research does not jointly analyze the prediction of popularity and user interaction behavior, so that the prediction research of popularity lacks the data support from the perspective of user behavior, and the accuracy of popularity prediction cannot be reliably guaranteed

Images