Customized content delivery
View Patent ↗Imaging devices may capture images of a user premises. The images may be analyzed and processed by a television receiver to determine a scene associated with the user premises. Information indicative of the scene may be transmitted to a service provider system. A content item is received by the television receiver from the service provider system, where the content item is determined based on the information indicative of the scene. The television receiver outputs the content item for presentation to a user device.
1. A method for targeting content for output by a television receiver, the method comprising:
activating, by the television receiver, an imaging device disposed in a user premises, the activating comprising directing the imaging device to capture one or more images of an area of the user premises;
processing, by the television receiver, the one or more images to determine a scene associated with the user premises, wherein the scene is an activity performed in the user premises;
transmitting, by the television receiver, information indicative of the scene to a service provider system;
receiving, by the television receiver, a content item from the service provider system, the content item being determined based on an effectiveness score associated with the content item and the scene, wherein the effectiveness score is indicative of a relevancy of the content item to the information indicative of the scene; and
outputting, by the television receiver, the content item for presentation to a user device.
2. The method of claim 1 , wherein a machine-learning model executed by the television receiver performs a classification that indicates the scene based on one or more entities detected in the one or more images, an activity performed by one or more entities in the area of the user premises, or both.
3. The method of claim 1 , further comprising:
filtering, by the television receiver, the one or more images captured by the imaging device based on a set of user preferences, wherein the set of user preferences direct the filtering of the one or more images to be performed based on: a field of view of the imaging device, a portion of the area defined as off-limits for the imaging device, and/or specified times.
4. The method of claim 2 , wherein the machine-learning model is a neural network.
5. The method of claim 1 , wherein the content item is an advertisement and the user device is a television that is communicatively coupled with the television receiver, the advertisement being delivered in a time-slot that immediately succeeds a programming content being displayed on the television.
6. The method of claim 1 , wherein the content item received by the television receiver is further determined based on one or more entities detected in the one or more images captured by the imaging device.
7. The method of claim 1 , further comprising:
sending, by the television receiver, a message including the information indicative of the scene to the service provider system, wherein the service provider system accesses a repository storing a plurality of content items to identify the content item to be delivered to the television receiver.
8. The method of claim 1 , further comprising:
sending, by the service provider system, the content item to the television receiver, wherein the service provider system identifies the content item based on a metadata associated with the content item, wherein the metadata comprises the effectiveness score.
9. A television receiver for outputting content, the television receiver comprising:
a processor; and
a memory including instructions that, when executed by the processor, cause the television receiver to perform operations comprising:
activating an imaging device disposed in a user premises, the activating comprising directing the imaging device to capture one or more images of an area of the user premises;
processing the one or more images to determine a scene associated with the user premises, wherein the scene is an activity performed in the user premises;
transmitting information indicative of the scene to a service provider system;
receiving a content item from the service provider system, the content item being determined based on an effectiveness score associated with the content item and the scene, wherein the effectiveness score is indicative of a relevancy of the content item to information indicative of the scene; and
outputting the content item for presentation to a user device.
10. The television receiver of claim 9 , wherein a machine-learning model executed by the television receiver performs a classification that indicates the scene based on one or more entities detected in the one or more images, an activity performed by one or more entities in the area of the user premises, or both.
11. The television receiver of claim 9 , wherein the television receiver is further configured for:
filtering the one or more images captured by the imaging device based on a set of user preferences, wherein the set of user preferences direct the filtering of the one or more images to be performed based on: a field of view of the imaging device, a portion of the area defined as off-limits for the imaging device, and/or specified times.
12. The television receiver of claim 10 , wherein the machine-learning model is a neural network.
13. The television receiver of claim 9 , wherein the content item is an advertisement and the user device is a television that is communicatively coupled with the television receiver, the advertisement being delivered in a time-slot that immediately succeeds a programming content being displayed on the television.
14. The television receiver of claim 9 , wherein the content item received by the television receiver is further determined based on one or more entities detected in the one or more images captured by the imaging device.
15. The television receiver of claim 9 , wherein the television receiver is further configured for:
sending a message including information indicative of the scene to the service provider system, wherein the service provider system accesses a repository storing a plurality of content items to identify the content item to be delivered to the television receiver.
16. One or more non-transitory, machine-readable media having machine-readable instructions thereon which, when executed by a television receiver, causes the television receiver to perform operations comprising:
activating, by the television receiver, an imaging device disposed in a user premises, the activating comprising directing the imaging device to capture one or more images of an area of the user premises;
processing, by the television receiver, the one or more images to determine a scene associated with the user premises, wherein the scene is an activity performed in the user premises;
transmitting, by the television receiver, information indicative of the scene to a service provider system;
receiving, by the television receiver, a content item from the service provider system, the content item being determined based on an effectiveness score associated with the content item and the scene, wherein the effectiveness score is indicative of a relevancy of the content item to the information indicative of the scene; and
outputting, by the television receiver, the content item for presentation to a user device.
17. The one or more non-transitory, machine-readable media as recited in claim 16 , wherein a machine-learning model executed by the television receiver performs a classification that indicates the scene based on one or more entities detected in the one or more images, an activity performed by one or more entities in the area of the user premises, or both.
18. The one or more non-transitory, machine-readable media as recited in claim 16 , wherein the content item is an advertisement and the user device is a television that is communicatively coupled with the television receiver, the advertisement being delivered in a time-slot that immediately succeeds a programming content being displayed on the television.
19. The one or more non-transitory, machine-readable media as recited in claim 16 , wherein the content item received by the television receiver is further determined based on one or more entities detected in the one or more images captured by the imaging device.
20. The one or more non-transitory, machine-readable media as recited in claim 16 , wherein the television receiver is further configured for:
sending a message including the information indicative of the scene to the service provider system, wherein the service provider system accesses a repository storing a plurality of content items to identify the content item to be delivered to the television receiver.