Method and system for identification of distributed broadcast content

• US 9,864,800 B2
• Filed: 03/30/2015
• Issued: 01/09/2018
• Est. Priority Date: 10/03/2006
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Shazam Entertainment Limited (Apple Inc.)
• Inventors: Wang, Avery Li-Chun, Wong, Chee, Symons, Jonathan
• Primary Examiner(s): Talukder, Md
• Application Number:
  US14/672,881
• Publication Number:
  US 20150205865A1
• Time in Patent Office: 1,016 Days
• Field of Search: 4554142
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content
• CPC Class Codes: H04H 2201/30 characterised by the use of a return channel, e.g. for collecting users' opinions, for returning broadcast space/time information or for requesting data
• CPC Class Codes: H04H 60/37 for identifying segments of broadcast information, e.g. scenes or extracting programme ID
• CPC Class Codes: H04H 60/40 for identifying broadcast time
• CPC Class Codes: H04H 60/42 for identifying broadcast areas
• CPC Class Codes: H04H 60/58 of audio determination or detection of speech characteristics in general G10L25/00; speech recognition in general G10L15/00
• CPC Class Codes: H04H 60/74 using programme related information, e.g. title, composer or interpreter
• CPC Class Codes: H04N 21/44 Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs

Abstract

A method and system of performing high-throughput identifications of broadcast content is provided. A device can send a content identification query, which includes a sample of content being broadcast, to a server to request an identity of the content. The server will perform a computational identification of the content, return the result to the device, and store the result. For all subsequently received content identification queries requesting an identity of content being broadcast from the same source and in a time during which the content is still being broadcast from the source, the server will send the stored content identification in response to the subsequent queries. If a subsequent content identification query does not request the identity of content being broadcast from the same source or is not received during the time that the content is still being broadcast, the server will perform a computational identification of a content sample.

Claims

1. A method of identifying an audio content sample and determining a broadcast station source for a broadcast, including:

monitoring a plurality of broadcast stations and identifying broadcast audio content from the broadcast stations as the broadcast audio content is received;

caching to memory fingerprints of the identified broadcast audio content from the plurality of broadcast stations;

receiving a sampled audio content;

matching fingerprints of the sampled audio content against;

the cache of fingerprints from the identified broadcast audio content; and

a database of audio content;

identifying the sampled audio content and, when the sampled audio content originates from a broadcast, a broadcast station source that was sampled;

receiving a location from a portable device; and

using at least the location and the identified sampled audio content to target the portable device for advertising or offers,

wherein if the matching of the fingerprints of the sampled audio content against the cache succeeds, bypassing matching against the database.

2. The method of claim 1, wherein the sampled audio content is received from the portable device.

3. The method of claim 1, wherein the sampled audio content is received from the portable device and further including:

using the location to validate an identity of the broadcast station source.

4. The method of claim 1,

wherein the sampled audio content is received from the portable device and further including:

using at least the location and the identified broadcast station source to target the portable device for advertising or offers.

5. The method of claim 1, wherein:

the identified sampled audio content is an advertisement; and

further including using at least the identified sampled audio content and the identified broadcast station source to target the portable device for advertising or offers.

6. The method of claim 1, wherein receiving the sampled audio content includes receiving fingerprints from the portable device.

7. The method of claim 1, further including creating fingerprints from the received sampled audio content.

8. The method of claim 1, further including sending at least some data regarding the identified sampled audio content to the portable device.

9. A method of identifying an audio content sample from a real time broadcast, including:

monitoring a plurality of broadcast stations and identifying broadcast audio content from the broadcast stations as the broadcast audio content is received;

wherein monitoring at least one broadcast station of the plurality of broadcast stations relies on a web-based feed that is delayed from an over-the-air feed from the same broadcast station;

caching fingerprints of the identified broadcast audio content from the plurality of broadcast stations;

receiving sampled audio content from a portable device;

receiving a location from the portable device;

matching the fingerprints of the sampled audio against the cache of fingerprints;

identifying the sampled audio content by matching fingerprints of the sampled audio content against a database of audio broadcast content;

wherein if the matching of the fingerprints of the sampled audio content against the cache succeeds, bypassing matching against the database;

wherein matching the fingerprints of the sampled audio content against the database of audio broadcast content is limited by a delay bound; and

combining the location and the identified sampled audio content to identify a broadcast station source which the portable device sampled.

10. The method of claim 9, wherein:

the identified sampled audio content is an advertisement;

further including using at least the identified sampled audio content and the identified broadcast station source to target the portable device for advertising or offers.

11. The method of claim 9, further including:

generating and saving playlists of the broadcast audio content from the broadcast stations monitored; and

sending the portable device at least a recent portion of the playlist that identifies a plurality of items broadcast by the identified broadcast station source.

12. A method of identifying an audio content sample that originates from an actual broadcast, including:

monitoring a plurality of broadcast stations, fingerprinting and saving the fingerprints of broadcast audio content in a database of broadcast content as the broadcast audio content is received;

identifying at least some of the broadcast audio content from the broadcast stations against a database of pre-indexed audio content and caching fingerprints of the identified broadcast audio content as the identified broadcast audio content is received;

receiving sampled audio content from a portable device;

matching the fingerprints of the sampled audio content against;

the cache of fingerprints for the identified broadcast audio content;

the database of broadcast content; and

the database of pre-indexed audio content; and

identifying a broadcast station source of the sampled audio content that originates from an actual broadcast and, when the sampled audio content can be found in the database of pre-indexed audio content, identifying the sampled audio content.

13. The method of claim 12, further including:

receiving a location from the portable device; and

using the location to validate an identity of the broadcast station source.

14. The method of claim 12, further including:

receiving a location from the portable device; and

using at least the location and the identified sampled audio content to target the portable device for advertising or offers.

15. The method of claim 12, wherein:

the monitoring of at least one broadcast station relies on a web-based feed that is delayed from an over-the-air feed from the same broadcast station; and

matching the fingerprints of the audio content sample against the cache is limited by a delay bound.

16. The method of claim 12, further including:

generating and saving playlists of the broadcast audio content from the broadcast stations monitored; and

sending the portable device at least a recent portion of the playlist that identifies a plurality of recent items broadcast by the identified broadcast station source.

17. A method of identifying an audio content sample and determining a broadcast station, comprising:

monitoring a plurality of broadcast stations and automatically identifying broadcast audio content from the broadcast stations as the broadcast audio content is received;

wherein monitoring at least one broadcast station of the plurality of broadcast stations relies on a web-based feed that is delayed from an over-the-air feed from the same broadcast station;

caching to memory fingerprints of the identified broadcast audio content from the plurality of broadcast stations;

receiving a sampled audio content;

matching fingerprints of the sampled audio content against;

the cache of fingerprints from the identified broadcast audio content; and

a database of audio content;

wherein matching the fingerprints of the sampled audio content against the database of broadcast audio content is limited by a delay bound; and

identifying the sampled audio content and, when the sampled audio content originates from a broadcast, a broadcast station source that was sampled,

wherein if the matching of the fingerprints of the sampled audio content against the cache succeeds, bypassing matching against the database.

18. The method of claim 17, further including:

receiving a location from the portable device; and

using the location to validate an identity of the broadcast station source.

19. The method of claim 17, further including:

generating and saving playlists of the broadcast audio content from the broadcast stations monitored; and

sending the portable device at least a recent portion of the playlist that identifies a plurality of recent items broadcast by the identified broadcast station source.

20. A method of identifying an audio content sample and determining a broadcast station source for a broadcast, including:

monitoring a plurality of broadcast stations and automatically identifying broadcast audio content from the broadcast stations as it is received;

caching to memory fingerprints of the identified broadcast audio content from the plurality of broadcast stations;

receiving a sampled audio content from a portable device;

matching fingerprints of the sampled audio content against;

the cache of fingerprints from the identified broadcast audio content;

and a database of audio content; and

identifying the sampled audio content and, when the sampled audio content originates from a broadcast, a broadcast station source that was sampled;

generating and saving playlists of the broadcast audio content from the broadcast stations monitored; and

sending the portable device at least a recent portion of the playlist that identifies a plurality of recent items broadcast by the identified broadcast station source,

wherein if the matching of the fingerprints of the sampled audio content against the cache succeeds, bypassing matching against the database.

21. The method of claim 20, wherein the sampled audio content is received from a portable device and further including:

receiving a location from the portable device; and

using the location to validate an identity of the broadcast station source.

22. A method of identifying an audio content sample and determining a broadcast station source for a broadcast, including:

monitoring a plurality of broadcast stations and automatically identifying broadcast audio content from the broadcast stations as it is received;

caching to memory fingerprints of the identified broadcast audio content from the plurality of broadcast stations;

receiving a sampled audio content;

matching fingerprints of the sampled audio content against the database of broadcast audio content and a database of audio content; and

identifying the sampled audio content and, when the sampled audio content originates from a broadcast, a broadcast station source that was sampled,

wherein if the matching of the fingerprints of the sampled audio content against the database of broadcast audio content succeeds, bypassing matching against the database of audio content.

23. The method of claim 22, further including:

receiving a location from a portable device; and

using the location to validate an identity of the broadcast station source.

24. A method of identifying an audio content sample from a real time broadcast, including:

monitoring a plurality of broadcast stations and identifying broadcast audio content from the broadcast stations as the broadcast audio content is received;

caching fingerprints of the identified broadcast audio content from the plurality of broadcast stations;

receiving sampled audio content from a portable device;

receiving a location from the portable device;

matching the fingerprints of the sampled audio against the cache of fingerprints;

identifying the sampled audio content by matching fingerprints of the sampled audio content against a database of audio content; and

wherein if the matching of the fingerprints of the sampled audio content against the cache succeeds, bypassing matching against the database;

combining the location and the identified sample audio content to identify a broadcast station source which the portable device sampled; and

using at least the identified broadcast station source to target the portable device for advertising or offers.

25. The method of claim 24, wherein:

the identified sampled audio content is an advertisement;

further including using at least the identified sampled audio content and the identified broadcast station source to target the portable device for advertising or offers.

26. The method of claim 24, further including:

generating and saving playlists of the broadcast audio content from the broadcast stations monitored; and

sending the portable device at least a recent portion of the playlist that identifies a plurality of items broadcast by the identified broadcast station source.