Methods and systems for providing context-based recommendations

• US 10,380,208 B1
• Filed: 12/28/2015
• Issued: 08/13/2019
• Est. Priority Date: 12/28/2015
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Brahmbhatt, Kintan Dilipkumar, Durham, Brandon Scott, Hanson, Kristine Anne, Lee Thorp, Charles Frederick, Pal, Rickesh, Thetford, Ted William
• Primary Examiner(s): Trujillo, James
• Assistant Examiner(s): Shechtman, Cheryl M
• Application Number:
  US14/981,273
• Time in Patent Office: 1,324 Days
• Field of Search: None
• CPC Class Codes: G06F 16/635 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/735 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 2015/221 Announcement of recognition results
• CPC Class Codes: G10L 25/51 for comparison or discrimination

Abstract

Described herein are online services provided to users based on the current context information of the users. In particular, a user may interact with an interactive device to stream media content from a remote service provider. The user may provide commands to the interactive device using a voice command. The interactive device may transmit requests based on such user command. In order for the service providers to provide customized services, the interactive device can be configured to capture additional contextual data indicative of an environment of the user such as ambient sound and provide such contextual data to the service provider. The service provider can utilize such contextual data to generate content recommendations suitable to the current context of the request or command or user.

Claims

1. A computer-implemented method, comprising:

storing, at a service provider computing system, profile information for a user that includes at least user preferences, the user preferences indicating preferred types of media content to be played with respect to particular activities;

receiving, from a voice-activated device, a voice command requesting media content to be played by the voice-activated device;

receiving an ambient sound captured by the voice-activated device, the ambient sound being associated with the voice command;

determining, based on the voice command, the user from which the voice command was received;

determining a context of the voice command based at least in part on the ambient sound, the context indicating an activity in which the user is engaged;

determining, by accessing the profile information for the user, recommended media content based at least in part on the determined context and based on the user preferences with respect to the determined activity; and

providing the recommended media content to the voice-activated device to be presented by the voice-activated device.

2. The computer-implemented method of claim 1, wherein determining the context is further based on a time when the voice command is received or a location of the voice-activated device.

3. The computer-implemented method of claim 1, wherein the context is indicative of a time, a location, or an event.

4. The computer-implemented method of claim 1, wherein determining the context of the voice command comprises:

processing the ambient sound to extract an audio feature;

comparing the extracted audio feature with predetermined audio features associated with known contexts; and

determining the context from the known contexts based at least in part on the comparison.

5. A computer-implemented method, comprising:

storing profile information for a user that includes at least user preferences indicating at least one preferred type of media content to be played with respect to at least one respective activity;

receiving a request for media content from a device;

determining, based on the request, the user from which the request was received;

determining a context of the request based at least in part on contextual data indicative of an environment of the device when the request was generated, the context indicating an activity in which the user is engaged;

generating, by accessing the profile information for the user, recommended media content based at least in part on the determined context and based on the user preferences with respect to the determined activity; and

providing the recommended media content to the device to be played by the device.

6. The computer-implemented method of claim 5, wherein the request is generated in response to a voice command.

7. The computer-implemented method of claim 5, wherein the contextual data includes an ambient sound.

8. The computer-implemented method of claim 5, wherein determining the context of the request or command comprises:

processing the contextual data to extract a feature;

comparing the extracted feature of the contextual data with predetermined features associated with known contexts; and

determining the context from the known contexts based at least in part on the comparison.

9. The computer-implemented method of claim 5, wherein the contextual data includes non-audio data.

10. The computer-implemented method of claim 9, wherein the non-audio data is indicative of a time or a location of the device.

11. The computer-implemented method of claim 5, further comprising:

generating a profile associated with the context and the user, the profile comprising one or more features extracted from the contextual data; and

associating the context with the recommended media content and the user.

12. The computer-implemented method of claim 11, further comprising:

receiving a second request for media content from the user via the device, the second request comprising second contextual data;

determining that the second contextual data matches the profile; and

providing the recommended media content associated with the context to the device in response to the second request.

13. A computer system, comprising:

a memory that stores computer-executable instructions; and

a processor configured to access the memory and execute the computer-executable instructions to implement a method comprising;

storing profile information that includes at least user preferences, the user preferences indicating preferred types of media content to be played with respect to particular activities for each of a plurality of users;

receiving a request for media content from a device;

determining, based on the request, a user of the plurality of users from which the request was received;

determining a context of the request based at least in part on contextual data indicative of an environment of the device when the request was generated and an activity in which the user is engaged;

generating, by accessing the profile information for the user, recommended media content based at least in part on an ambient sound indicative of an environment of the device and based on preferences of the user with respect to the activity; and

providing the recommended media content to the device to be played by the device.

14. The computer system of claim 13, wherein the request comprises a voice command.

15. The computer system of claim 13, wherein the contextual data includes at least one of ambient sound, lighting data, or temperature data.

16. The computer system of claim 15, wherein determining the context of the request comprises:

processing the contextual data to extract a feature;

comparing the extracted feature of the contextual data with predetermined features associated with known contexts; and

determining the context from the known contexts based at least in part on the comparison.

17. The computer system of claim 13, wherein the contextual data is indicative of one or more people near the device.

18. The computer system of claim 13, wherein the contextual data is captured by the device.

19. The computer system of claim 13, wherein the method further comprising:

generating a profile associated with the context and the user, the profile comprising one or more features extracted from the contextual data; and

associating the profile with the recommended media content and the user.

20. The computer system of claim 19, wherein the method further comprising:

receiving a second request for media content from the user via the device, the second request comprising second contextual data;

determining that the second contextual data matches the profile; and

providing the recommended media content associated with the context to the device in response to the second request.