Audiovisual content curation system
AssigneeGracenote, Inc.
InventorsPeter C. DiMaria, Andrew Silverman
Life of this patent
Estimating the term…
Abstract
Systems and methods are provided for filtering at least one media content catalog based on criteria for a station library to generate a first list of candidate tracks for the station library, combining a similarity score and a popularity score for each track of the first list of candidate tracks to generate a total score for each track of the first list of candidate tracks, generating a list of top ranked tracks for the first genre, and returning the list of top ranked tracks of the first genre as part of the station library.
Claims20
A tangible, non-transitory machine-readable medium having stored thereon instructions that, when executed, cause one or more processors to perform a set of operations comprising:
- generating a similarity score for a plurality of tracks in a list of candidate tracks, wherein generating the similarity scores comprises determining, for each track in the plurality of tracks, correlation values between a first criteria and a second criteria of the plurality of tracks in the list of candidate tracks;
- determining popularity scores for each for each track in the plurality of tracks;
- generating a total score for each track of the plurality of tracks, wherein generating a total score comprises combining, for each track of the plurality of tracks, the similarity score and the popularity score associated with each track;
- and
- generating a list of top ranked tracks, wherein generating the list of top ranked tracks is based on the total score for each track in the plurality of tracks.
A computer-implemented method comprising:
- generating a similarity score for a plurality of tracks in a list of candidate tracks, wherein generating the similarity scores comprises determining, for each track in the plurality of tracks, correlation values between a first criteria and a second criteria of the plurality of tracks in the list of candidate tracks;
- determining popularity scores for each for each track in the plurality of tracks;
- generating a total score for each track of the plurality of tracks, wherein generating a total score comprises combining, for each track of the plurality of tracks, the similarity score and the popularity score associated with each track;
- and
- generating a list of top ranked tracks, wherein generating the list of top ranked tracks is based on the total score for each track in the plurality of tracks.
A computing device comprising:
- one or more processors;
- and
- a tangible, non-transitory machine-readable medium having stored thereon instructions that, when executed, cause the one or more processors to perform a set of operations comprising:
- generating a similarity score for a plurality of tracks in a list of candidate tracks, wherein generating the similarity scores comprises determining, for each track in the plurality of tracks, correlation values between a first criteria and a second criteria of the plurality of tracks in the list of candidate tracks;
- determining popularity scores for each for each track in the plurality of tracks;
- generating a total score for each track of the plurality of tracks, wherein generating a total score comprises combining, for each track of the plurality of tracks, the similarity score and the popularity score associated with each track;
- and
- generating a list of top ranked tracks, wherein generating the list of top ranked tracks is based on the total score for each track in the plurality of tracks.
Dependencies are inferred from the claim text.