Generating event output

Patent metadata

Field	Value
Publication number	US-12008995-B2
Application number	US-202217719563-A
Country	US
Kind code	B2
Filing date	Apr 13, 2022
Priority date	Jan 28, 2020
Publication date	Jun 11, 2024
Grant date	Jun 11, 2024

Abstract

A system is provided for determining subscription data when a user requests to receive an output in the future when an event occurs. The system may determine an output type based on the capabilities of the output device and a trigger type. The system may determine a trigger type based on the priority of the triggering event. The system may also determine how many times the subscription is to be executed. Using this information, the system creates the subscription so that the user may receive a notification or an announcement when an event occurs.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
receiving input data associated with a user profile;
processing the input data to determine to cause an output in response to an event at a future time;
determining sentiment data representing a sentiment corresponding to the event;
determining, using the sentiment data, first data representing the event;
determining a priority based on the sentiment data;
using the priority to determine at least one of a timing or output type for causing the output; and
associating the first data and the priority with the user profile.

2. The computer-implemented method of claim 1 , wherein the input data represents a natural language input and the method further comprises:
processing the input data to determine a command to cause the output when the event occurs.

3. The computer-implemented method of claim 1 , wherein the first data represents an action to be performed in response to the event and the method further comprises:
performing the action in response to occurrence of the event, wherein the action is performed based on the priority.

4. The computer-implemented method of claim 1 , wherein the input data comprises audio data representing an utterance and the method further comprises:
processing the audio data to determine the sentiment data.

5. The computer-implemented method of claim 1 , further comprising:
determining the sentiment data corresponds to excitement; and
in response to the sentiment data corresponding to excitement, determining that the priority is high.

6. The computer-implemented method of claim 1 , wherein the input data represents a natural language input and the method further comprises:
performing language processing on the input data to determine language processing data,
wherein determining the priority is further based at least in part on the language processing data.

7. The computer-implemented method of claim 1 , wherein the input data includes second data corresponding to past user interactions corresponding to the user profile and the method further comprises processing the second data to determine to cause the output.

8. The computer-implemented method of claim 1 , further comprising:
receiving event data indicating occurrence of the event;
determining an output device corresponding to the user profile, wherein the output device is outputting content; and
based at least on the priority, sending a command to the output device to interrupt output of the content to present the output corresponding to the event.

9. The computer-implemented method of claim 1 , further comprising:
receiving further input data representing user activity;
determining a second priority based on the user activity; and
associating the first data and the second priority with the user profile.

10. The computer-implemented method of claim 1 , wherein the output type includes at least one of text notification, text-to-speech notification, push notification, visual notification, or audio notification.

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 input data associated with a user profile;
process the input data to determine to cause an output in response to an event at a future time;
determine sentiment data representing a sentiment corresponding to the event;
determine, using the sentiment data, first data representing the event;
determine a priority based on the sentiment data;
use the priority to determine at least one of a timing or output type for causing the output; and
associate the first data and the priority with the user profile.

12. The system of claim 11 , wherein the input data represents a natural language input and wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
process the input data to determine a command to cause the output when the event occurs.

13. The system of claim 11 , wherein the first data represents an action to be performed in response to the event and wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
perform the action in response to occurrence of the event, wherein the action is performed based on the priority.

14. The system of claim 11 , wherein the input data comprises audio data representing an utterance and wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
process the audio data to determine the sentiment data.

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:
determine the sentiment data corresponds to excitement; and
in response to the sentiment data corresponding to excitement, determine that the priority is high.

16. The system of claim 11 , wherein the input data represents a natural language input and wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
perform language processing on the input data to determine language processing data,
wherein determination of the priority is further based at least in part on the language processing data.

17. The system of claim 11 , the input data corresponds to past user interactions corresponding to the user profile.

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:
receive event data indicating occurrence of the event;
determine an output device corresponding to the user profile, wherein the output device is outputting content; and
based at least on the priority, send a command to the output device to interrupt output of the content to present the output corresponding to the event.

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:
receive further input data representing user activity;
determine a second priority based on the user activity; and
associate the first data and the second priority with the user profile.

20. The system of claim 11 , wherein the output type includes at least one of text notification, text-to-speech notification, push notification, visual notification, or audio notification.

Assignees

• Amazon Tech Inc

Inventors

• Nadig Vinaya
• Babuji Ambika
• Li Zhuxuan
• Lu He
• Kassis Elad Refael

Classifications

• G10L15/146

  with insufficient amount of training data, e.g. state sharing, tying, deleted interpolation · CPC title

• G06F40/30

  Semantic analysis · CPC title

• G06F40/284

  Lexical analysis, e.g. tokenisation or collocates · CPC title

• G06F40/216

  using statistical methods · CPC title

• G06F3/167

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title