Back to results
US 2014/0229828 A1Published application
Creating playlists
AssigneeGoogle Inc.
InventorsBrandon Bilinski, Owen Daniel Otto
Life of this patent
Estimating the term…
Abstract
A method for automatic selection of songs for consumption in a music library may include assigning a selection score for each of a plurality of songs in the music library based on at least one selection criteria. A first list of songs may be generated from the plurality of songs. The selection score for each of the songs in the first list may be higher than a determined threshold value. A similarity score may be generated for each of the songs in the first list. The similarity score for a corresponding song in the first list may be based on a first number of songs selected from the plurality of songs, and the first number of songs may be similar to the corresponding song. The songs in the first list may be ranked based on a highest similarity score.
Claims20
A method for automatic selection of songs for consumption in a music library, the method comprising:
- assigning a selection score for each of a plurality of songs in the music library based on at least one selection criteria selected from the group consisting of:
- most played, highest rated, recently purchased, recently uploaded, recently rated high by a user, recently rated high by friends of the user in the user's social network, most played within a time range, and popular among users in the same social graph or demographics;
- generating a first list of songs from the plurality of songs, after assigning the selection score for each of the plurality of songs in the music library, wherein the selection score for each of the songs in the first list is higher than a determined threshold value;
- generating a similarity score for each of the songs in the first list wherein the similarity score for a corresponding song in the first list is based on a first number of songs selected from the plurality of songs, and the first number of songs are similar to the corresponding song;
- ranking the songs in the first list based on a highest similarity score;
- and
- generating a second list of songs, from the plurality of songs for consumption by a user, using a top-ranked song from the first list of songs and an additional second number of songs selected from the plurality of songs, wherein the second number of songs are similar to the top-ranked song from the first list, and wherein the first number of songs and the second number of songs are integers greater than one.
4 more elements
A system for automatic selection of songs for consumption in a music library, the system comprising:
- at least one network device comprising a memory and at least one processor, the at least one processor operable to:
- assign a selection score for each of a plurality of songs in the music library based on at least one selection criteria selected from the group consisting of:
- most played, highest rated, recently purchased, recently uploaded, recently rated high by a user, recently rated high by friends of the user in the user's social network, most played within a time range, and popular among users in the same social graph or demographics;
- generate a first list of songs, after assigning a selection score for each of the plurality of songs in the music library, from the plurality of songs, wherein the selection score for each of the songs in the first list is higher than a determined threshold value;
- generate a similarity score for each of the songs in the first list, wherein the similarity score for a corresponding song in the first list is based on a first number of songs selected from the plurality of songs, and the first number of songs are similar to the corresponding song;
- rank the songs in the first list based on a highest similarity score;
- and
- generate a second list of songs from the plurality of songs for consumption by a user, using a top-ranked song from the first list of songs and an additional second number of songs selected from the plurality of songs, wherein the second number of songs are similar to the top-ranked song from the first list, and wherein the first number of songs and the second number of songs are integers greater than one.
5 more elements
A device comprising:
- a machine readable storage having stored thereon a computer program having at least one code section for automatic selection of songs for consumption in a music library, the at least one code section executable by a machine for causing the machine to perform a method comprising:
- assigning a selection score for each of a plurality of songs in the music library based on at least one selection criteria selected from the group consisting of:
- most played, highest rated, recently purchased, recently uploaded, recently rated high by a user, recently rated high by friends of the user in the user's social network, most played within a time range, and popular among users in the same social graph or demographics;
- generating a first list of songs from the plurality of songs, after assigning a selection score for each of the plurality of songs in the music library, wherein the selection score for each of the songs in the first list is higher than a determined threshold value;
- generating a similarity score for each of the songs in the first list wherein the similarity score for a corresponding song in the first list is based on a first number of songs selected from the plurality of songs, and the first number of songs are similar to the corresponding song;
- ranking the songs in the first list based on a highest similarity score;
- and
- generating a second list of songs from the plurality of songs for consumption by a user, using a top-ranked song from the first list of songs and an additional second number of songs selected from the plurality of songs, wherein the second number of songs are similar to the top-ranked song from the first list, and wherein the first number of songs and the second number of songs are integers greater than one.
5 more elements
Dependencies are inferred from the claim text.