Method and device for music recommendation based on video information

Abstract

The invention provides a music recommendation method and device based on film and television information. The music recommendation method comprises: a coordinate system based on pre acquired music labels is established, wherein the coordinate system comprises: at least a coordinate axis, a label located on the coordinate axis and a label scale values. A musical category point is formed in the candidate music mapped in the coordinate system forms. A video class point is formed in the video information which the user has watched in the preset time period mapped into the coordinate system. The corresponding music of music category points meeting preset conditions of the distance between musical category point and the video class point is determined as the music to be recommended to users. The quantitative mapping of music information and film and television information is achieved. The film and television information the user watched permeats into the music recommendation, thereby improving the accuracy and the user experience of the music recommendation.

Description

technical field [0001] The invention relates to big data recommendation technology, in particular to a music recommendation method and device based on video information. Background technique [0002] With the continuous development of communication technologies, more and more users start to use terminal devices to play music. How the terminal device predicts the music that the user likes, and then, recommends music to the user is becoming more and more important. [0003] At present, the terminal device obtains the information of the music that the user has listened to, predicts that the music that is similar to the information of the music that has been listened to is the music that the user likes, and then recommends the music to the user. [0004] However, in the above method, since the playing time of the music is relatively short, the user may have listened to a certain music for some accidental reason, and the music does not represent the user's real interest. Theref...

AI Technical Summary

Problems solved by technology

[0004] However, in the above method, due to the short playing time of the music, the user may have listened to a certain music for some accidental reason, and the music does not represent the user's real interest

Therefore, the information of the listened music obtained by the terminal device cannot reflect the real interest of the user, and the music recommended to the user based on the information of the listened music may not be the music that the user wants to listen to.

To sum up, the accuracy rate of the music recommendation method in the prior art is low, and the user experience is poor

Images