Video recommendation method and device

Abstract

The present invention discloses a video recommendation method and a device, and belongs to the technical field of network video playing technology. The method comprises the steps of acquiring video data with a video type tag; acquiring the interest feature of a user; matching the similarity for the interest feature of the user with the video type tag of the video data; and pushing a video data list with the matching similarity thereof reaching a set value to the user. According to the technical scheme of the invention, the video data with the video type tag for representing the video type and the interest feature of the user are acquired. After that, the video type tag of the video data and the interest feature of the user are subjected to similarity matching. Finally, the video data list with the matching similarity thereof reaching the set value is pushed to the user. In this way, the video personalized recommendation is realized, so that the user can efficiently find a interested video. The user experience is improved, and the viscosity of the user to a video website is enhanced. Meanwhile, the brand value of the website is improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of network video playback, and in particular, to a video recommendation method and device. Background technique [0002] With the development of network technology, watching videos online is more and more favored by users. Various multimedia applications are constantly emerging, the Internet and TV programs are becoming more and more abundant, and the number of videos is increasing rapidly. It has become difficult to manually filter the required information from the massive videos. Users have no time and cannot browse the massive video content. With too much information, it is difficult to find the content you are really interested in, the information contained in the video cannot be effectively accessed and utilized, and it is also difficult for content providers to accurately push high-quality content to interested target users. How to enable users to quickly access interesting video...

AI Technical Summary

Problems solved by technology

[0003] In the process of realizing the present invention, the inventor found that there are at least the following problems in the prior art: video websites are facing the problem of information overload, such as YouTube currently has billions of video entries, and nearly 1,500 minutes of video are blocked every minute. upload, and professional video sites such as Sohu also have nearly hundreds of thousands of high-quality videos, and it is difficult for users to find the content they are really interested in; at the same time, it is also very important to improve users' viewing and staying time, so efficient personalized video The recommendation method is considered to be an effective way to solve these problems. The problem with the current existing technology is that the recommendation cannot be personalized. Each user browses the same video website and sees the same information, and the user cannot quickly find himself. Interesting video content, low efficiency, poor user experience, low user stickiness to video sites, resulting in low brand value of video sites, etc.

Images