Song recommendation method and device, server and storage medium

Abstract

The embodiment of the invention discloses a song recommendation method and device, a server and a storage medium, and the method comprises: enabling received retrieval information to be matched with emotion words in an emotion text database, obtaining emotion words matched with the retrieval information, and determining the emotion words matched with the retrieval information as emotion keywords;obtaining at least one emotion label of each song in a to-be-selected song set, the to-be-selected song set comprising at least one song; determining a corresponding emotion category of the emotion keyword in the to-be-selected song set, and determining at least one emotion label belonging to the emotion category in the to-be-selected song set as at least one emotion label matched with the emotionkeyword, determining at least one song corresponding to the at least one emotion label as an initial song set, and screening out a recommended song set from the initial song set based on song attributes. By adopting the method, the song listening experience of the user can be improved, and the manual operation cost of the song library is reduced.

Description

technical field [0001] The present application relates to the field of music recommendation systems, in particular to a song recommendation method and device, a server, and a storage medium. Background technique [0002] At present, in the process of listening to songs, users often select the songs they want to listen to by searching for the song name, singer name, album name, etc. in text. This method is effective for accurate matching. However, due to the Name, singer name, and album name information do not include the emotional type of the song content. If the user wants to accurately and quickly obtain songs with a specific emotional type, the user's needs cannot be met in the above situation. Therefore, how to accurately push songs of the emotional type that the user is interested in according to the input information of the user is a problem that needs to be solved. Contents of the invention [0003] The embodiments of the present application provide a song recommen...

AI Technical Summary

Problems solved by technology

[0002] At present, in the process of listening to songs, users often select the songs they want to listen to by searching for the song name, singer name, album name, etc. in text. This method is effective for accurate matching. However, due to the Name, artist name, and album name information do not include the emotional type of the song content. If the user wants to accurately and quickly obtain songs with a specific emotional type, the user's needs cannot be met in the above situation.

Images