MUSIC RECOMMENDATION METHOD AND APPARATUS

• US 20120136814A1
• Filed: 04/18/2011
• Published: 05/31/2012
• Est. Priority Date: 11/30/2010
• Status: Active Grant

• Current Assignee: Beijing Ruixin Online System Technology Co., Ltd.
• Original Assignee: Beijing Ruixin Online System Technology Co., Ltd.
• Inventors: WANG, Paul
• Granted Patent: US 8,442,925 B2
• Time in Patent Office: Days
• US Class Current: 706/12
• CPC Class Codes: G06F 16/60 of audio data
• CPC Class Codes: G06F 16/65 Clustering; Classification

Abstract

A music recommendation method may include obtaining the music belongingness function of music, which is the set of granularity of music in different dimensions, wherein the dimension is the classification of music and the granularity is the classification of the dimension; obtaining the user belongingness function of a user, which is the set of granularity indicating likes of user in different dimensions; calculating a granularity correlation function by using the music belongingness function and the user belongingness function; calculating the value of the probability function indicating likes of user for music by using the granularity correlation function and a dimension weighting coefficient; and recommending the music to the user when the value of the probability function indicating likes of user for music is greater than a preset threshold. An apparatus applying to the method comprises corresponding modules.

Claims

1. A music recommendation method for use with a music recommendation apparatus, the method comprising:

obtaining the music belongingness function of music, the music belongingness function of music being is the set of granularity of music in different dimensions, wherein the dimension is the classification of music and the granularity is the classification of the dimension, and the expression of the music belongingness function is A(music, P_k)={p_kj|j=1,2, . . . , n}, k=1,2, . . . m, wherein P_k is the dimension, P_kj is the granularity, m is the number of the dimensions and n is the number of the granularities in a dimension;

obtaining the user belongingness function of a user, the user belongingness function of a user being is the set of granularity indicating likes of user in different dimensions, and the expression of the user belongingness function is A(user, P_k)={p_ki|i=1,2 . . . , n}, k=1,2, . . . m, wherein P_k is the dimension, p_ki is the granularity, m is the number of the dimensions and n is the number of the granularities in a dimension;

calculating a granularity correlation function by using the music belongingness function and the user belongingness function, and the expression of the granularity correlation function is

2. The music recommendation method according to claim 1, wherein the obtaining the music belongingness function of music comprises obtaining the music belongingness function of music by one of the following ways:

receiving manual input and performing program identification performing program identification.

3. The music recommendation method according to claim 1, wherein at least one user belongingness function is assigned to the user.

4. The music recommendation method according to claim 1, wherein the obtaining the user belongingness function of a user comprises obtaining the user belongingness function of a user by one of the following ways:

receiving user input and analyzing user behavior.

5. The music recommendation method according to claim 4, wherein obtaining the user belongingness function by analyzing the user behavior comprises:

getting the behavior function indicating likes of user for music according to the behavior that a user takes to music, and the expression of the behavior function indicating likes of user for music is

6. A music recommendation apparatus comprising:

a music belongingness function obtaining unit for obtaining a music belongingness function, the music belongingness function being the set of granularity of music in different dimensions, wherein the dimension is the classification of music and the granularity is the classification of the dimension, and the expression of the music belongingness function is A(music, P_k)={p_kj|j=1,2, . . . , n}, k=1,2, . . . m, wherein P_k is the dimension, p_kj is the granularity, m is the number of the dimensions and n is the number of the granularities in a dimension;

a user belongingness function obtaining unit for obtaining a user belongingness function, the user belongingness function being the set of granularity indicating likes of user in different dimensions, and the expression of the user belongingness function is A(user, P_k)={p_ki|i=1,2 . . . , n}, k=1,2, . . . m, wherein P_k is the dimension, p_ki is the granularity, m is the number of the dimensions and n is the number of the granularities in the dimension;

a granularity correlation function calculating unit for calculating a granularity correlation function by using the music belongingness function and the user belongingness function, and the expression of the granularity correlation function is

7. The music recommendation apparatus according to claim 6, wherein the music belongingness function obtaining unit obtains the music belongingness function of music by one of the following ways:

receiving manual input and performing program identification.

8. The music recommendation apparatus according to claim 6, wherein at least one user belongingness function is assigned to the user.

9. The music recommendation apparatus according to claim 6, wherein the user belongingness function obtaining unit obtains the user belongingness function of a user by one of the following ways:

receiving user input and analyzing user behavior.

10. The music recommendation apparatus according to claim 9, wherein the user belongingness function obtaining unit comprises:

a behavior function calculating module for getting the behavior function indicating likes of user for music according to the behavior that a user takes to music, and the expression of the behavior function indicating likes of user for music is

11-14. -14. (canceled)