Video heat prediction method based on deep belief networks and system thereof

Abstract

The invention provides a video heat prediction method based on deep belief networks. The method comprises following steps: selecting input variables according to video features; normalizing and quantifying influence factors, thus preprocessing training data; determining a single-layer restricted Boltzmann machine reconstitution dimension according to the selected input variable and feature reconstruction errors; forming the deep belief networks by multi-layer stacked restricted Boltzmann machines and a BP (Back Propagation) neural network; adjusting the deep belief networks through a global learning algorithm, thus obtaining an optimum video prediction model; placing to-be-tested video test data in the optimum video prediction model for heat prediction analysis and watching quantity prediction analysis. The invention also provides a video heat prediction system based on the deep belief networks. According to the method and the system of the invention, an online video prediction model based on the deep belief networks is provided; the deep neural network is applied in the online video prediction field; and the prediction accuracy and reliability can be improved.

Description

technical field [0001] The invention relates to the technical field of the Internet, in particular to a video popularity prediction method and system based on a deep belief network. Background technique [0002] Video-on-demand volume prediction plays an important role in the field of Internet data mining. Videos with high volume of on-demand videos (especially movies and TV dramas) can increase the volume of advertisements. Predicting the volume of video-on-demand in advance has a wide range of advertising business expansion. application. [0003] At present, the forecasting of video-on-demand resources generally adopts the prediction method based on historical on-demand data or artificial methods. The prediction method based on historical on-demand data needs to be predicted after the video is broadcast for a period of time, and cannot be predicted before the video goes online. For the forecasting of on-demand volume, the prediction based on artificial methods relies heav...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the object of the present invention is to provide a video popularity prediction method and system based on a deep belief network, aiming at solving the problem of low accuracy and reliability of video popularity prediction in the prior art

Images