On-line video recommendation method and video portal service system

Abstract

The invention provides an on-line video recommendation method and a video portal service system. The on-line video recommendation method comprises the following steps that: a user terminal transmits an on-demand request to a video portal server; the video portal server dynamically calculates the weight of each video classification according to the past historic record; and the video portal server performs video recommendation according to the weight of the classification. The video portal service system comprises a terminal and user manager, a resource manager, a strategy database, a media grading database and a user database, wherein the resource manager is used for performing storage management and evaluation on video resources; the strategy database is used for storing video recommendation strategies; the media grading database is used for storing grading data of a video; the user database is used for storing historic watching record of a user; and the strategy database recommends a video to the user according to a preset video recommendation strategy. In an on-line video recommendation technique provided by the invention, an algorithm is not static but dynamic; data in the system can perform dynamic autoregulation and perfection along with the increase of visitor volume; and viscosity of the user is improved through excellent user experience.

Description

technical field [0001] The invention belongs to the field of network video applications, and relates to an online video recommendation method and a video portal service system. Background technique [0002] In a conventional online video application, when a user selects a video to play online, the website can actively recommend similar video files associated with it to the user. The advantage of this is to improve user experience, provide users with more personalized services, and increase user stickiness. [0003] On the other hand, through in-depth mining and analysis of user preferences, behavior habits and other data, it can also lay the foundation for other more Internet value-added services, such as micropayment, advertising, etc. After all, mastering users in the network is quite beneficial s position. [0004] The application of related video recommendation has just emerged, and the current implementation technology is relatively rough. The simplest implementation ...

AI Technical Summary

Problems solved by technology

[0005] This technique is too simplistic. When a user clicks on a video, it does not necessarily mean that he is only interested in this type of video. In addition, the user's data should also have a process of self-enhancement, self-improvement, and self-evolution, which cannot be achieved today. In this way, after using it for a year, it still recommends the same video, even duplicate videos

Images