Video playing recommendation system and method based on video big data

Abstract

The invention discloses a video playing recommendation system based on video big data, which relates to the technical field of big data and comprises a video recommendation module, a video preprocessing module, a video analysis module and a video release management module. The video recommendation module is used for acquiring feature information of videos browsed by users, processing the feature information and recommending videos to other users; the video preprocessing module is used for acquiring and processing a long video to form at least two short videos; the video analyzing and processing module is used for calculating a popularity difference value according to the information, acquiring the popularity difference value and processing the long video to obtain at least two updated short videos; the video release management module is used for processing the at least two updated short videos so as to increase the frequency of browsing the short videos by the user; according to the invention, the interest degree and watching times of the user on the video can be improved; and meanwhile, according to the set short video, the interest degree of other feature users on the short video can be increased.

Description

technical field [0001] The invention relates to the technical field of big data, in particular to a video playback recommendation system and method based on video big data. Background technique [0002] With the advancement of information in the age of science and technology, more and more users choose to quickly understand relevant knowledge information through videos; users basically choose to understand or read relevant knowledge through fragmented time, but because short videos can only get part of the information, It is not possible to understand the demonstration process and extension information of knowledge; but the above problems can be solved through long videos; because the content of long videos is too long, it also limits the viewing threshold and viewing time of viewers, so long videos often discourage many users. Therefore, the shortcomings of long videos and short videos are opposite to each other. In order to solve the problem that long videos are too long a...

AI Technical Summary

Problems solved by technology

[0003] 1. When cutting a long video into a short video, it is usually cut according to multi-dimensional parameters to obtain a short video; however, the cut short video is usually directly distributed to the video playback platform, regardless of the popularity of the cut short video. It will not arouse the interest of users, which will lead to the low number of viewers of the cut short videos;

[0004] 2. According to the user's memory curve, although the short video will not be forgotten immediately after watching, the memory of watching the short video will always be lost, and it cannot strengthen the user's memory to watch the short video and achieve the recommendation effect of the short video, etc. Wait;

Images