Generating event output

Patent metadata

Field	Value
Publication number	US-11322150-B2
Application number	US-202016775247-A
Country	US
Kind code	B2
Filing date	Jan 28, 2020
Priority date	Jan 28, 2020
Publication date	May 3, 2022
Grant date	May 3, 2022

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:
during a first time period:
receiving, from a device, audio data corresponding to an utterance, the audio data associated with a user profile;
processing the audio data to determine intent data indicating a request to receive an output when a future event occurs;
determining trigger data representing the event;
determining, using at least the audio data, sentiment data representing a sentiment of the utterance;
determining priority data corresponding to the event and based at least in part on the sentiment data, the priority data indicating a high priority; and
storing the trigger data and the priority data;

during a second time period subsequent to the first time period:
receiving event data indicating occurrence of the event;
determining, using the trigger data, that the event data triggers an output with respect to the user profile;
determining, using the priority data, to output an announcement of the event occurring;
determining that the device is capable of outputting synthesized speech;
determining output text data representing the announcement;
processing, using text-to-speech (TTS) processing, the output text data to determine output audio data; and
sending the output audio data to the device.

2. The computer-implemented method of claim 1 , further comprising:
during the first time period:
processing the audio data using automatic speech recognition (ASR) to determine input text data;
processing the input text data using natural language understanding (NLU) to determine first frequency data indicating an intent to receive the output a number of times when the event occurs; and
storing the first frequency data;

during the second time period:
determining, using the first frequency data and the number of times the event has occurred, second frequency data indicating a remaining number of times the output is to be generated; and
associating the second frequency data with the trigger data.

3. The computer-implemented method of claim 1 , further comprising:
during a third time period:
receiving, from a second device, second audio data corresponding to a second utterance, the second audio data associated with the user profile;
processing the second audio data to determine second intent data indicating a second request to receive an output when a second event occurs;
determining, using NLU, second trigger data representing the second event;
determining second priority data corresponding to the second trigger data, the second priority data indicating a high priority; and
storing the second trigger data and the second priority data;

during a fourth time period subsequent to the third time period:
receiving second event data;
determining, using the second trigger data, that the second event data triggers an output with respect to the user profile;
determining that the second device is not capable of outputting synthesized speech;
determining, using the second priority data, to output a push notification to the second device and a third device associated with the user profile, the push notification representing an indication of the second event occurring;
generating notification data representing the push notification; and
sending the notification data to the second device and the third device.

4. A computer-implemented method comprising:
receiving input data representing an utterance, the input data associated with a user profile;
processing the input data to determine intent data indicating a request to receive an output when an event occurs;
determining, using the input data, trigger data representing the event;
determining, using at least the input data, sentiment data representing a sentiment of the utterance;
determining a priority corresponding to the trigger data based at least in part on the sentiment data; and
associating the trigger data and the priority with the user profile.

5. The computer-implemented method of claim 4 , further comprising:
determining a category corresponding to the event;
determining first priority data corresponding to the event;
determining second priority data represented in the input data; and
determining the priority using the first priority data and the second priority data.

6. The computer-implemented method of claim 4 , further comprising:
determining that the priority is high;
determining, using the priority, that the output is an announcement;
determining that an output capability of an output device includes an ability to output synthesized speech;
generating output data representing confirmation that an announcement will be generated when the event occurs;
processing, using text-to-speech (TTS) processing, the output data to determine output audio data; and
sending the output audio data to the output device.

7. The computer-implemented method of claim 4 , further comprising:
determining that the priority is high;
determining that a first output device is incapable of outputting synthesized speech;
determining, using the priority, to output a push notification to the first output device and a second output device;
generating output data representing confirmation that a notification will be generated when the event occurs; and
sending the output data to the first output device.

8. The computer-implemented method of claim 4 , further comprising:
determining a trigger type associated with the trigger data, the trigger type indicating a time when the event will occur;
associating the trigger type and the time with the trigger data;
generating output data representing confirmation that a reminder of the event occurring will generated;
processing, using TTS processing, the output data to determine output audio data; and
sending the output audio data to a device.

9. The computer-implemented method of claim 4 , further comprising:
determining that the priority is low;
determining, using the priority, that the output is a push notification;
generating output data representing confirmation that a notification will be generated when the event occurs; and
sending the output data to a device.

10. The computer-implemented method of claim 4 , further comprising:
receiving audio data corresponding to the input data;
processing the audio data using automatic speech recognition (ASR) to determine input text data;
processing the input text data using natural language understanding (NLU) to determine frequency data indicating an intent to receive the output one time; and
associating the frequency data with the trigger data;

during a time period subsequent to receiving the audio data:
receiving event data;
determining, using the trigger data, that the event data triggers an output with respect to the user profile;
determining, using the priority, output data;
sending the output data to a device; and
determining to delete the trigger data based on the frequency data.

11. The computer-implemented method of claim 4 , further comprising:
receiving audio data corresponding to the input data;
processing the audio data using automatic speech recognition (ASR) to determine input text data;
processing the input text data using natural language understanding (NLU) to determine first frequency data indicating a number of times to generate the output; and
associating the first frequency data with the trigger data;

during a time period subsequent to receiving the audio data:
receiving event data;
determining, using the trigger data, that the event data triggers a first output with respect to the user profile;
determining second frequen

Assignees

• Amazon Tech Inc

Inventors

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

Classifications

• G10L15/18 Primary

  using natural language modelling · 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