Adapting search query processing according to locally detected video content consumption
A process adapts user-initiated search queries. The process executes at a client device with a microphone. The process downloads audio fingerprints from a remote server for a plurality of video programs, and downloads information that correlates the audio fingerprint to the video programs. The audio fingerprints are preselected according to relevancy criteria, including stored user preferences and prior search queries by the user. The audio fingerprints and correlating information are stored locally. The process detects ambient sound using the microphone and computes one or more sample audio fingerprints from the detected ambient sound. The process matches a sample audio fingerprint to a locally stored audio fingerprint and uses the correlating information to identify a first video program corresponding to the matched sample audio fingerprint. The process then receives user input to initiate a search query. The process provides auto-complete suggestions for the search query based on the first video program.
1. A method for identifying audio fingerprints, the method comprising:
receiving, at a client device, a plurality of audio fingerprints that correspond to a plurality of media content items based on scheduled broadcast times;
storing the plurality of audio fingerprints in a memory of the client device;
detecting ambient sound using an audio input device of the client device;
generating an audio fingerprint from the detected ambient sound;
comparing, at the client device, the audio fingerprint generated from the detected ambient sound to the plurality of audio fingerprints stored in the memory of the client device; and
determining whether to transmit a received input to initiate a query to a server, wherein determining whether to transmit the received input to initiate a query to the server is based on whether the comparing indicates that the audio fingerprint matches one of the plurality of audio fingerprints stored in the memory of the client device.
2. The method of claim 1 , further comprising downloading the plurality of audio fingerprints from a remote server for the plurality of media content items and information that correlates each respective downloaded audio fingerprint to a respective media content item.
3. The method of claim 2 , wherein the downloaded audio fingerprints are preselected by the remote server according to a set of relevancy criteria including stored preferences of a user and prior search queries by the user.
4. The method of claim 2 , further comprising:
computing sample audio fingerprints from the detected ambient sound; and
matching one of the sample audio fingerprints to a first audio fingerprint of the plurality of audio fingerprints and using the correlating information to identify a first media content item corresponding to the matched sample audio fingerprint.
5. The method of claim 4 , further comprising presenting the user with information related to the first media content item.
6. The method of claim 5 , wherein the information related to the first media content item includes auto-complete suggestions for the query.
7. The method of claim 1 , further comprising discarding one or more of the plurality of audio fingerprints from the memory upon reaching a predetermined time.
8. A client device comprising:
an audio input device;
a memory; and
a hardware processor coupled to the memory that is programmed to:
receive a plurality of audio fingerprints that correspond to a plurality of media content items based on scheduled broadcast times;
store the plurality of audio fingerprints in the memory;
detect ambient sound using the audio input device;
generate an audio fingerprint from the detected ambient sound;
compare the audio fingerprint generated from the detected ambient sound to the plurality of audio fingerprints stored in the memory; and
determine whether to transmit a received input to initiate a query to a server based on whether the comparing indicates that the audio fingerprint matches one of the plurality of audio fingerprints stored in the memory.
9. The client device of claim 8 , wherein the hardware processor is further programmed to download the plurality of audio fingerprints from a remote server for the plurality of media content items and information that correlates each respective downloaded audio fingerprint to a respective media content item.
10. The client device of claim 9 , wherein the downloaded audio fingerprints are preselected by the remote server according to a set of relevancy criteria including stored preferences of a user and prior search queries by the user.
11. The client device of claim 9 , wherein the hardware processor is further programmed to:
compute sample audio fingerprints from the detected ambient sound; and
match one of the sample audio fingerprints to a first audio fingerprint of the plurality of audio fingerprints and using the correlating information to identify a first media content item corresponding to the matched sample audio fingerprint.
12. The client device of claim 11 , wherein the hardware processor is further programmed to present the user with information related to the first media content item.
13. The client device of claim 12 , wherein the information related to the first media content item includes auto-complete suggestions for the query.
14. The client device of claim 8 , wherein the hardware processor is further programmed to discard one or more of the plurality of audio fingerprints from the memory upon reaching a predetermined time.
15. A non-transitory computer-readable medium containing computer executable instructions that, when executed by a processor, cause the processor to perform a method for identifying audio fingerprints, the method comprising:
receiving, at a client device, a plurality of audio fingerprints that correspond to a plurality of media content items based on scheduled broadcast times;
storing the plurality of audio fingerprints in a memory of the client device;
detecting ambient sound using an audio input device of the client device;
generating an audio fingerprint from the detected ambient sound;
comparing, at the client device, the audio fingerprint generated from the detected ambient sound to the plurality of audio fingerprints stored in the memory of the client device; and
determining whether to transmit a received input to initiate a query to a server, wherein determining whether to transmit the received input to initiate a query to the server is based on whether the comparing indicates that the audio fingerprint matches one of the plurality of audio fingerprints stored in the memory of the client device.
16. The non-transitory computer-readable medium of claim 15 , wherein the method further comprises downloading the plurality of audio fingerprints from a remote server for the plurality of media content items and information that correlates each respective downloaded audio fingerprint to a respective media content item.
17. The non-transitory computer-readable medium of claim 16 , wherein the downloaded audio fingerprints are preselected by the remote server according to a set of relevancy criteria including stored preferences of a user and prior search queries by the user.
18. The non-transitory computer-readable medium of claim 16 , wherein the method further comprises:
computing sample audio fingerprints from the detected ambient sound; and
matching one of the sample audio fingerprints to a first audio fingerprint of the plurality of audio fingerprints and using the correlating information to identify a first media content item corresponding to the matched sample audio fingerprint.
19. The non-transitory computer-readable medium of claim 18 , wherein the method further comprises presenting the user with information related to the first media content item.
20. The non-transitory computer-readable medium of claim 19 , wherein the information related to the first media content item includes auto-complete suggestions for the query.
21. The non-transitory computer-readable medium of claim 15 , wherein the method further comprises discarding one or more of the plurality of audio fingerprints from the memory upon reaching a predetermined time.