Association of content identifier of audio-visual data with additional data through capture infrastructure
A method of a capture infrastructure includes determining a content identifier by applying a first automatic content recognition algorithm to fingerprint data of an audio-visual data rendered on a networked media device, and associating the content identifier with additional data derived from information other than the fingerprint data.
1. A method of a capture infrastructure comprising: dividing an audio-visual data rendered on a networked media device into a series of scenes, said networked media device comprising a sandbox reachable service; applying an automatic content recognition algorithm to a first scene of the series of scenes to determine a content identifier; associating an advertisement data with the determined content identifier; identifying a correlation pattern between the first scene and a second scene of the series of scenes; associating the advertisement data to the second scene of the series of scenes; and identifying targeted content to be targeted to a client device associated with the networked media device, said client device supporting sandboxed application execution.
2. The method of claim 1 , further comprising associating, with the content identifier, an audio identifier determined from fingerprint data of audio data received by the capture infrastructure for a same content identified by the content identifier.
3. The method of claim 2 , comprising the audio identifier identifying a piece of music in the same content.
4. The method of claim 2 , comprising the audio identifier identifying a person speaking in the same content.
5. The method of claim 1 , further comprising associating, with the content identifier, a text identifier determined by applying an optical character recognition algorithm to data received by the capture infrastructure for a same content identified by the content identifier and by comparing recognized text to entries in a master database, wherein the text identifier identifies at least one of: a brand, a product, a person, and a location shown in the same content.
6. The method of claim 5 , comprising the additional data text identifier being a logo name determined by comparing the entries in the master database with a logo data of the audio-visual data identified using a logo detection algorithm.
7. The method of claim 1 , comprising the association of the advertisement data with the content identifier being based on a correlation between a metadata of the advertisement data provided by a content provider and the content identifier.
8. The method of claim 1 , further comprising at least one of: automatically dividing the audio-visual data into the series of scenes based on a semantic grouping of actions in the audio-visual data: analyzing the audio-visual data in advance of a broadcast to determine content identifiers associated with each commercial in the audio-visual data such that advertisements are pre-inserted into the audio-visual data prior to the broadcast; and applying a time-order algorithm to automatically match the advertisement data to the audio-visual data when the correlation pattern is identified.
9. The method of claim 1 , further comprising causing rendering of the identified targeted content in the sandboxed application executing within the client device.
10. A capture infrastructure, comprising: a memory; and a processor communicatively coupled to the memory, the processor configured to execute instructions to: divide an audio-visual data rendered on a networked media device into a series of scenes, said networked media device comprising a sandbox reachable service, apply an automatic content recognition algorithm to a first scene of the series of scenes to determine a content identifier, associate an advertisement data with the determined content identifier, identify a correlation pattern between the first scene and a second scene of the series of scenes, associate the advertisement data to the second scene of the series of scenes, and identifying targeted content to be targeted to a client device associated with the networked media device, said client device supporting sandboxed application execution.
11. The capture infrastructure of claim 10 , wherein the processor is further configured to execute instructions to associate, with the content identifier, an audio identifier determined from fingerprint data of audio data received by the capture infrastructure for a same content identified by the content identifier.
12. The capture infrastructure of claim 11 , wherein the audio identifier identifies a piece of music in the same content.
13. The capture infrastructure of claim 11 , wherein the audio identifier identifies a person speaking in the same content.
14. The capture infrastructure of claim 10 , wherein the processor is further configured to execute instructions to associate, with the content identifier, a text identifier determined by applying an optical character recognition algorithm to data received by the capture infrastructure for a same content identified by the content identifier and by comparing recognized text to entries in a master database, wherein the text identifier identifies at least one of: a brand, a product, a person, and a location shown in the same content.
15. The capture infrastructure of claim 14 , wherein the text identifier is a logo name determined by comparing the entries in the master database with a logo data of the audio-visual data identified using a logo detection algorithm.
16. The capture infrastructure of claim 10 , wherein the processor is configured to execute instructions to associate the advertisement data with the content identifier based on a correlation between a metadata of the advertisement data provided by a content provider and the content identifier.
17. The capture infrastructure of claim 10 , wherein the processor is further configured to execute instructions to at least one of: automatically divide the audio-visual data into the series of scenes based on a semantic grouping of actions in the audio-visual data, analyze the audio-visual data in advance of a broadcast to determine content identifiers associated with each commercial in the audio-visual data such that advertisements are pre-inserted into the audio-visual data prior to the broadcast, and apply a time-order algorithm to automatically match the advertisement data to the audio-visual data when the correlation pattern is identified.