Station library creation for a media service

Patent metadata

Field	Value
Publication number	US-12585692-B2
Application number	US-202318529501-A
Country	US
Kind code	B2
Filing date	Dec 5, 2023
Priority date	Dec 19, 2013
Publication date	Mar 24, 2026
Grant date	Mar 24, 2026

Abstract

A machine may form all or part of a network-based system configured to provide media service to one or more user devices. The machine may be configured to define a station library within a larger collection of media files. In particular, the machine may access metadata that describes a seed that forms the basis on which the station library is to be defined. The machine may determine a genre composition for the station library based on the metadata. The machine may generate a list of media files from the metadata based on a relevance of each media file to the station library. The machine may determine the relevance of each media file based on a similarity of the media file to the genre composition of the station library as well as a comparison of metadata describing the media file to the accessed metadata that describes the seed.

First claim

What is claimed is:

1 . A method comprising:
accessing collection metadata that describes media files included within a collection of media files; accessing seed metadata, the seed metadata being a basis on which a first subset of the collection of media files is to be defined; machine-generating, using a processor, a station set from the collection metadata based on the seed metadata, the machine-generated station set defining a station library by defining the first subset of the collection and referencing each media file in the first subset, wherein a boost value determined for each media file in the collection of media files augments a similarity score associated with the corresponding media file, wherein the boost value determined for each media file is based on at least one of (i) a relationship between an artist for the media file and a seed artist included in the collection metadata, or (ii) co-occurrences of the artist for the media file and the seed artist, wherein the corresponding media file is defined to be in the first subset of the collection based on the augmented similarity score; modifying the machine-generated station set based on a human-contributed input received from an editor device, the modified station set modifying the station library by defining a second subset of the collection and referencing each media file in the second subset; and configuring a media server to stream to a user device a media datastream that comprises media files selected from the second subset defined by the modified machine-generated station set, wherein the editor device comprises a first computer system, wherein the user device comprises a second computer system, wherein the user device is distinct from the editor device.

2 . The method of claim 1 , wherein:
the media files include audio files; and the configuring of the media server configures a network radio service that streams the audio files to the user device.

3 . The method of claim 1 , wherein:
the media files include video files; and the configuring of the media server configures a network video service that streams the video files to the user device.

4 . The method of claim 1 , wherein modifying the station library comprises removing one or more media files from the first subset.

5 . The method of claim 1 , wherein modifying the station library comprises adding one or more media files to the first subset.

6 . The method of claim 1 , wherein the collection metadata indicates for at least one media file a seasonality score of a given media file, the seasonality score indicating a level of correlation of the media file with an annual calendar date, and wherein machine-generating the station set comprises, based the seasonality score and a comparison of the annual calendar date with a present calendar date, controlling whether to include given media file in the first subset.

7 . A computing system comprising:
at least one processor comprising microcircuits; non-transitory machine-readable storage; instructions stored in the non-transitory machine-readable storage for causing the at least one processor to carry out operations including: accessing collection metadata that describes media files included within a collection of media files; accessing seed metadata, the seed metadata being a basis on which a first subset of the collection of media files is to be defined; machine-generating, using a processor, a station set from the collection metadata based on the seed metadata, the machine-generated station set defining a station library by defining the first subset of the collection and referencing each media file in the first subset, wherein a boost value determined for each media file in the collection of media files augments a similarity score associated with the corresponding media file, wherein the boost value determined for each media file is based on at least one of (i) a relationship between an artist for the media file and a seed artist included in the collection metadata, or (ii) co-occurrences of the artist for the media file and the seed artist, wherein the corresponding media file is defined to be in the first subset of the collection based on the augmented similarity score; modifying the machine-generated station set based on a human-contributed input received from an editor device, the modified station set modifying the station library by defining a second subset of the collection and referencing each media file in the second subset; and configuring a media server to stream to a user device a media datastream that comprises media files selected from the second subset defined by the modified machine-generated station set, wherein the editor device comprises a first computer system, wherein the user device comprises a second computer system, wherein the user device is distinct from the editor device.

8 . The computing system of claim 7 , wherein:
the media files include audio files; and the configuring of the media server configures a network radio service that streams the audio files to the user device.

9 . The computing system of claim 7 , wherein:
the media files include video files; and the configuring of the media server configures a network video service that streams the video files to the user device.

10 . The computing system of claim 7 , wherein modifying the station library comprises removing one or more media files from the first subset.

11 . The computing system of claim 7 , wherein modifying the station library comprises adding one or more media files to the first subset.

12 . The computing system of claim 7 , wherein the collection metadata indicates for at least one media file a seasonality score of a given media file, the seasonality score indicating a level of correlation of the media file with an annual calendar date, and wherein machine-generating the station set comprises, based the seasonality score and a comparison of the annual calendar date with a present calendar date, controlling whether to include given media file in the first subset.

13 . A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:
accessing collection metadata that describes media files included within a collection of media files; accessing seed metadata, the seed metadata being a basis on which a first subset of the collection of media files is to be defined; machine-generating a station set from the collection metadata based on the seed metadata, the machine-generated station set defining a station library by defining the first subset of the collection and referencing each media file in the first subset, wherein a boost value determined for each media file in the collection of media files augments a similarity score associated with the corresponding media file, wherein the boost value determined for each media file is based on at least one of (i) a relationship between an artist for the media file and a seed artist included in the collection metadata, or (ii) co-occurrences of the artist for the media file and the seed artist, wherein the corresponding media file is defined to be in the first subset of the collection based on the augmented similarity score; modifying the machine-generated station set based on a human-contributed input received from an editor device, the modified station set modifying the station library by defining a second subset of the collection and referencing each media file in the second subset; and configuring a media server to stream to a user device a media datastream that comprises media files sele

Assignees

• Gracenote Inc

Inventors

• Dimaria Peter C
• Silverman Andrew

Classifications

• H04L65/612

  for unicast · CPC title

• H04N21/854

  Content authoring · CPC title

• H04N21/84

  Generation or processing of descriptive data, e.g. content descriptors {(systems specially adapted for using meta-information in broadcast systems H04H60/73)} · CPC title

• H04N21/812

  involving advertisement data (advertising per se G06Q30/02) · CPC title

• H04N21/8113

  comprising music, e.g. song in MP3 format · CPC title