Automatic generation of online media stations customized to individual users

Abstract

An online media station can be automatically generated based on a user's media preference data. Media preference data can include a user's media item purchase history. The media preference data is analyzed and media preference clusters are generated from the analyzed media preference data. Generated media preference clusters are ranked based on a predetermined set of ranking rules. The top ranked media preference clusters are selected dependent upon the user's number of slots available for customized media stations. One or more media station seeds are selected from each media preference cluster selected based on a set of predetermined selection rules. An algorithmic media station is automatically generated from the one or more media station seeds and provided to an electronic device of the user.

We claim: 
     
         1 . A computer-implemented method for automatically generating a customized media station on an electronic device comprising:
 analyzing a user's media preference data;   generating media preference clusters from the analyzed media preference data;   ranking the generated media preference clusters based on a set of predetermined ranking rules;   selecting the top ranked media preference clusters dependent upon the user's number of slots available for customized media stations;   selecting one or more media station seeds from each media preference cluster selected based on a set of predetermined selection rules;   generating an algorithmic media station customized to the user from the one or more media station seeds from each media preference cluster selected; and   providing the generated algorithmic media station customized to the user to the electronic device of the user.   
     
     
         2 . The method of  claim 1 , wherein the set of predetermined ranking rules dictate ranking the generated media preference clusters based on at least one of a number of media items contained in the media preference clusters, a most recent play time of the media items in the media preference clusters, and user ratings assigned to media items in the media preference clusters. 
     
     
         3 . The method of  claim 1 , wherein the set of predetermined selection rules dictate selecting media station seeds based on at least one of a determined number of media items authored by a common artist that are within the media preference clusters, a minimum threshold value of times an artist must appear within the media preference clusters, and top artists in the media preference clusters. 
     
     
         4 . The method of  claim 1 , wherein the media preference data comprises a user's media item purchase history. 
     
     
         5 . The method of  claim 1 , wherein analyzing the user's media preference data further comprises:
 inferring, from demographic and geographic location of the user, a musical preference of the user.   
     
     
         6 . The method of  claim 1 , wherein the selecting one or more media station seeds further comprises:
 determining that a first artist included in at least one of the selected media preference clusters is a heat seeker; and   selecting the first artist as one of the one or more media station seeds.   
     
     
         7 . The method of  claim 1 , further comprising:
 providing a preexisting editorial station to the electronic device of a user, wherein one or more of the media station seeds selected is an artist of the editorial station.   
     
     
         8 . The method of  claim 1 , wherein the predetermined selection rules dictate selection of the one or more media station seeds based on a determined popularity of the one or more media station seeds. 
     
     
         9 . An automatic media station generation system comprising:
 a processor; and   a computer-readable storage medium having stored therein instructions which, when executed by the processor, cause the processor to perform operations comprising:   analyze a user's media preference data;   generate media preference clusters from the analyzed media preference data;   rank the generated media preference clusters based on a set of predetermined ranking rules;   select the top ranked media preference clusters dependent upon the user's number of slots available for customized media stations;   select one or more media station seeds from each media preference cluster selected based on a set of predetermined selection rules;   generate an algorithmic media station customized to the user from the one or more media station seeds from each media preference cluster selected; and   provide the generated algorithmic media station customized to the user to the electronic device of the user.   
     
     
         10 . The system of  claim 9 , wherein the set of predetermined ranking rules dictate ranking the generated media preference clusters based on at least one of a number of media items contained in the media preference clusters, a most recent play time of the media items in the media preference clusters, and user ratings assigned to media items in the media preference clusters. 
     
     
         11 . The system of  claim 9 , wherein the set of predetermined selection rules dictate selecting media station seeds based on at least one of a determined number of media items authored by a common artist that are within the media preference clusters, a minimum threshold value of times an artist must appear within the media preference clusters, and top artists in the media clusters. 
     
     
         12 . The system of  claim 9 , wherein the media preference data comprises a user's media item purchase history. 
     
     
         13 . The system of  claim 9 , wherein analyzing the user's media preference data further comprises:
 inferring, from demographic and geographic location of the user, a musical preference of the user.   
     
     
         14 . The system of  claim 9 , wherein the instructions further cause the processor to:
 determine that a first artist included in at least one of the selected media preference clusters is a heat seeker; and   select the first artist as one of the one or more media station seeds.   
     
     
         15 . The system of  claim 9 , wherein the instructions further cause the processor to:
 provide a preexisting editorial station to the electronic device of a user wherein one or more of the media station seeds selected is an artist of the editorial station.   
     
     
         16 . The system of  claim 9 , wherein the predetermined selection rules dictate selection of the one or more media station seeds based on a determined popularity of the one or more media station seeds. 
     
     
         17 . A non-transitory computer-readable storage medium having stored therein instructions which, when executed by a processor, cause the processor to perform operations comprising:
 analyzing a user's media preference data;   generating media preference clusters from the analyzed media preference data;   ranking the generated media preference clusters based on a set of predetermined ranking rules;   selecting the top ranked media preference clusters dependent upon the user's number of slots available for customized media stations;   selecting one or more media station seeds from each media preference cluster selected based on a set of predetermined selection rules;   generating an algorithmic media station customized to the user from the one or more media station seeds from each media preference cluster selected; and   providing the generated algorithmic media station customized to the user to the electronic device of the user.   
     
     
         18 . The non-transitory computer-readable storage medium of  claim 17 , wherein the set of predetermined ranking rules dictate ranking the generated media preference clusters based on at least one of a number of media items contained in the media preference clusters, a most recent play time of the media items in the media preference clusters, and user ratings assigned to media items in the media preference clusters. 
     
     
         19 . The non-transitory computer-readable storage medium of  claim 17 , wherein the set of predetermined selection rules comprises selecting media station seeds based on at least one of a determined number of media items authored by a common artist that are within the media preference clusters, a minimum threshold value of the number of times an artist must appear within the media preference clusters, and top artists in the media clusters. 
     
     
         20 . The non-transitory computer-readable storage medium of  claim 17 , wherein the media preference data comprises a user's media item purchase history. 
     
     
         21 . The non-transitory computer-readable storage medium of  claim 17 , wherein analyzing the user's media preference data further comprises:
 inferring, from demographic and geographic location of the user, a musical preference of the user.   
     
     
         22 . The non-transitory computer-readable storage medium of  claim 17 , wherein the instructions further cause the computing device to:
 determine that a first artist included in at least one of the selected media preference clusters is a heat seeker; and   select the first artist as one of the one or more media station seeds.   
     
     
         23 . The non-transitory computer-readable storage medium of  claim 17 , wherein the instructions further cause the computing device to:
 provide a preexisting editorial station to the electronic device of a user wherein one or more of the media station seeds selected is an artist of the editorial station.   
     
     
         24 . The non-transitory computer-readable storage medium of  claim 17 , wherein the predetermined selection rules dictate selection of the one or more media station seeds based on a determined popularity of the one or more media station seeds.