A song recommendation method and device
A recommendation method and song technology, applied in the communication field, can solve problems such as slow song recommendation speed, achieve the effect of increasing the recommendation speed and improving the user experience
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0028] refer to figure 1 , a flow chart of a method for recommending songs provided by an embodiment of the present invention is given.
[0029] Step 101, acquiring information about songs sung by a user in history.
[0030] The method of this embodiment can be applied to a scene where a user sings a song. For example, in the song ordering system of Karaoke (Karaoke Television, KTV), the user logs into the song ordering system through a social software account, and then performs a song ordering operation, and the songs that the user has sung will be saved under the user's account. Or, when the user uses the singing software to sing songs, he will first log in to his own account, and the singing software will also save the songs that the user has sung. The songs that the user has sung are the user's historical singing songs. The information of the song includes information such as the artist who sang the song, the album to which the song belongs, and the label of the song. ...
Embodiment 2
[0042] On the basis of the above embodiments, this embodiment further discusses the song recommendation method.
[0043] refer to image 3 , a flow chart of another song recommendation method provided by an embodiment of the present invention is given:
[0044] Step 301, constructing a graph database.
[0045] Before using the graph database for song recommendation, the graph database can be constructed according to the following steps.
[0046] Step 3011, making statistics on the preferences of each user in the user group for each node, and generating a preference vector for each node.
[0047] In practical applications, according to the user's behavior data, the preferences of each user in the user group for each node can be counted, and then the preference vector of each node can be generated. Among them, the user's behavior data may include the relevant data of each user's singing history, attention, collection, and comment on the song in the user group. Therefore, the be...
Embodiment 3
[0078] On the basis of the above embodiments, this embodiment also provides a song recommendation device.
[0079] refer to Figure 4 A structural block diagram of a song recommendation device provided in an embodiment of the present invention is provided, which may specifically include the following modules:
[0080] History obtaining module 41, is used for obtaining the information of user's history singing song;
[0081] The node to be checked determining module 42 is used to determine the node to be checked corresponding to the song sung in the history in the pre-built graph database;
[0082] The candidate node determination module 43 is used to determine the node at the other end connected to the node to be checked as a candidate node according to the graph database;
[0083] The recommended song determination module 44 is used to determine the song corresponding to at least one node in the candidate node except the node to be checked as the song to be recommended;
...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


