USER-SPECIFIC MEDIA PLAYLISTS
A media recommendation system may provide seed media items to a user from a plurality of media items and receive a selection of a seed media item from the user. Distances between a vector representation of the seed media item and a plurality of vector representations of the plurality of media items are determined. The distances are determined as a dot product of the vector representation of the seed media item and each of the representations of the plurality of media items. A pool of media items for playback to the user is automatically generated from the plurality of media items based on the distances.
1 . (canceled)
2 . A method comprising:
providing, by one or more processors and to a user, representations of a plurality of seed media items from among a plurality of media items available for playback within a computerized media recommendation;
receiving, by the one or more processors, a selection of a representation of a seed media item from among the representations;
determining, by the one or more processors, distances between a vector and each vector in a plurality of vectors, wherein the distances are determined as a dot product of the vector and each vector in the plurality of vectors, and wherein the vector is a representation of the seed media item, and each vector in the plurality of vectors is a representation of respective media items of the plurality of media items; and
automatically generating, by the one or more processors, a pool of media items from the plurality of media items for playback to the user based at least in part on the distances.
3 . The method of claim 2 , further comprising:
receiving, by the one or more processors, a feedback signal for a media item of the pool of media items; and
modifying, by the one or more processors and based on the feedback signal, contents of the pool of media items.
4 . The method of claim 3 , wherein the pool of media items is a first pool, the modified pool of media items is a second pool, and the second pool comprises one or more of:
at least one media item not included in the first pool; and
a re-sorting of the media items in the first pool.
5 . The method of claim 2 , wherein the plurality of seed media items is one of: trending media items, emerging media items, recently played media items, selected media items, liked media items, and recommended media items.
6 . The method of claim 2 , wherein the plurality of seed media items is based at least in part on a user profile of the user, wherein the user profile includes media items previously consumed by the user.
7 . The method of claim 2 , further comprising sorting the media items in the pool of media items based at least in part on the distances.
8 . The method of claim 2 , further comprising sorting the media items in the pool of media items based at least in part on a number of times that the user has consumed a specific media item in the pool of media items.
9 . A system comprising:
one or more processors; and
one or more computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
providing, by the one or more processors and to a user, representations of a plurality of seed media items from among a plurality of media items available for playback within a computerized media recommendation;
receiving, by the one or more processors, a selection of a representation of a seed media item from among the representations;
determining, by the one or more processors, distances between a vector and each vector in a plurality of vectors, wherein the distances are determined as a dot product of the vector and each vector in the plurality of vectors, and wherein the vector is a representation of the seed media item, and each vector in the plurality of vectors is a representation of respective media items of the plurality of media items; and
automatically generating, by the one or more processors, a pool of media items from the plurality of media items for playback to the user based at least in part on the distances.
10 . The system of claim 9 , the operations further comprising:
receiving, by the one or more processors, a feedback signal for a media item of the pool of media items; and
modifying, by the one or more processors and based on the feedback signal, contents of the pool of media items.
11 . The system of claim 10 , wherein the pool of media items is a first pool, the modified pool of media items is a second pool, and the second pool comprises one or more of:
at least one media item not included in the first pool; and
a re-sorting of the media items in the first pool.
12 . The system of claim 9 , wherein the plurality of seed media items is items is one of: trending media items, emerging media items, recently played media items, selected media items, liked media items, and recommended media items.
13 . The system of claim 9 , wherein the plurality of seed media items is based at least in part on a user profile of the user, wherein the user profile includes media items previously consumed by the user.
14 . The system of claim 9 , the operations further comprising sorting the media items in the pool of media items based at least in part on the distances.
15 . The system of claim 9 , further comprising sorting the media items in the pool of media items based at least in part on a number of times that the user has consumed a specific media item in the pool of media items.
16 . One or more non-transitory computer-readable media storing instructions that, when executed, cause one or more processors to perform operations comprising:
providing, by a processor and to a user, representations of a plurality of seed media items from among a plurality of media items available for playback within a computerized media recommendation;
receiving, by the processor, a selection of a representation of a seed media item from among the representations;
determining, by the one or more processors, distances between a vector and each vector in a plurality of vectors, wherein the distances are determined as a dot product of the vector and each vector in the plurality of vectors, and wherein the vector is a representation of the seed media item, and each vector in the plurality of vectors is a representation of respective media items of the plurality of media items; and
automatically generating, by the one or more processors, a pool of media items from the plurality of media items for playback to the user based at least in part on the distances.
17 . The one or more non-transitory computer-readable media of claim 16 , the operations further comprising:
receiving, by the processor, a feedback signal for a media item of the pool of media items; and
modifying, by the processor and based on the feedback signal, contents of the pool of media items.
18 . The one or more non-transitory computer-readable media of claim 17 , wherein the pool of media items is a first pool, and the modified pool of media items is a second pool, and the second pool comprises one or more of:
at least one media item not included in the first pool; and
a re-sorting of the media items in the first pool.
19 . The one or more non-transitory computer-readable media of claim 16 , wherein the plurality of seed media items is one of: trending media items, emerging media items, recently played media items, selected media items, liked media items, and recommended media items.
20 . The one or more non-transitory computer-readable media of claim 16 , wherein the plurality of seed media items is based at least in part on a user profile of the user, wherein the user profile includes media items previously consumed by the user.
21 . The one or more non-transitory computer-readable media of claim 16 , the operations further comprising sorting the media items in the pool of media items based at least in part on the distances.