Content generation framework

Patent metadata

Field	Value
Publication number	US-11580182-B2
Application number	US-202017099295-A
Country	US
Kind code	B2
Filing date	Nov 16, 2020
Priority date	Sep 22, 2017
Publication date	Feb 14, 2023
Grant date	Feb 14, 2023

Abstract

Techniques for performing outputting additional content associated with but nonresponsive to an input command are described. A system receives input data from a device. The system determines an intent representing the input data and receives first output data responsive to the input data. The system determines, based on context data, that additional content associated with the first output data but nonresponsive to the input data should be output. The system receives second output data associated with but nonresponsive to the input data thereafter. The system then presents first content corresponding to the first output data and second content corresponding to the second output data.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
receiving, from a device, input data corresponding to a first command;
determining first output data responsive to the first command;
determining usage history data associated with the device;
based at least in part on the usage history data, determining additional content is to be output, wherein the additional content is nonresponsive to the first command;
determining second output data corresponding to first additional content;
causing the device to present a first output corresponding to the first output data; and
causing the device to present a second output corresponding to the second output data.

2. The computer-implemented method of claim 1 , further comprising:
determining a first application available with respect to the device,
wherein the first additional content corresponds to the first application.

3. The computer-implemented method of claim 1 , further comprising:
determining a first offer available with respect to the device,
wherein the first additional content corresponds to the first offer.

4. The computer-implemented method of claim 1 , further comprising:
determining a content type corresponding to the usage history data,
wherein the first additional content corresponds to the content type.

5. The computer-implemented method of claim 1 , further comprising:
determining a current time,
wherein the device is caused to present the first additional content based at least in part on the current time.

6. The computer-implemented method of claim 1 , further comprising:
identifying profile data associated with the input data; and
determining at least a portion of the profile data indicating a maximum number of times additional content is to be output over a period of time,
wherein the device is caused to present the first additional content based at least in part on the at least a portion of the profile data.

7. The computer-implemented method of claim 1 , further comprising:
determining a type of the first command,
wherein the device is caused to present the first additional content based at least in part on the type of the first command.

8. The computer-implemented method of claim 1 , further comprising:
determining an entity indicated in the first command,
wherein the device is caused to present the first additional content based at least in part on the entity.

9. The computer-implemented method of claim 1 , further comprising:
determining intent data representing the first command,
wherein the first output data is based at least in part on the intent data.

10. The computer-implemented method of claim 1 , further comprising:
determining the usage history data indicates a pattern whereby second input data, corresponding to the first additional content, has been received following output of content responsive to the first command,
wherein the device is caused to present the first additional content based at least in part on the usage history data including the pattern.

11. A system comprising:
at least one processor; and
at least one memory comprising instructions that, when executed by the at least one processor, cause the system to:
receive, from a device, input data corresponding to a first command;
determine first output data responsive to the first command;
receive context data corresponding to the first command;
based at least in part on the context data, determine additional content is to be output, wherein the additional content is related to the first output data and is nonresponsive to the first command;
determine second output data corresponding to first additional content;
cause output of first content corresponding to the first output data; and
cause output of the first additional content.

12. The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
receive second input data comprising feedback responsive to the first additional content; and
configuring a component based at least in part on the feedback.

13. The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine a content type corresponding to the first output data,
wherein the first additional content corresponds to the content type.

14. The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine a first application available with respect to the device,
wherein the first additional content corresponds to the first application.

15. The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
identify profile data associated with the input data,
wherein the second output data is based at least in part on the profile data.

16. The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine a type of the first command,
wherein output of the first additional content is based at least in part on the type of the first command.

17. The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine an entity indicated in the first command,
wherein output of the first additional content is based at least in part on the entity.

18. The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine intent data representing the first command,
wherein the first output data is based at least in part on the intent data.

19. The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine usage history data associated with the device,
wherein output of the first additional content is based at least in part on the usage history data.

20. The system of claim 19 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine the usage history data indicates a pattern whereby second input data, corresponding to the first additional content, has been received following output of content responsive to the first command,
wherein output of the first additional content is based at least in part on the usage history data including the pattern.

Assignees

• Amazon Tech Inc

Inventors

• Mutagi Rohan
• Shen Rongzhou
• Gavini Vibhunandan
• Malik Hassan Haider

Classifications

• G06F16/3329

  Natural language query formulation · CPC title

• G06F40/205

  Parsing · CPC title

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G06F40/30

  Semantic analysis · CPC title

• G10L2015/227

  of the speaker; Human-factor methodology · CPC title