Configurable output data formats

Patent metadata

Field	Value
Publication number	US-12190885-B2
Application number	US-202318369291-A
Country	US
Kind code	B2
Filing date	Sep 18, 2023
Priority date	Jun 1, 2017
Publication date	Jan 7, 2025
Grant date	Jan 7, 2025

Abstract

Configurable core domains of a speech processing system are described. A core domain output data format for a given command is originally configured with default content portions. When a user indicates additional content should be output for the command, the speech processing system creates a new output data format for the core domain. The new output data format is user specific and includes both default content portions as well as user preferred content portions.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
receiving input data representing a natural language command;
performing natural language processing using the input data to determine first data corresponding to a default content source;
determining that output responsive to the natural language command is to include first content corresponding to a default content source;
identifying a profile associated with the input data;
determining that the profile is associated with an additional content source;
determining, based at least in part on the profile being associated with the additional content source, that the output is to additionally include second content corresponding to the additional content source;
receiving second data responsive to the natural language command, the second data corresponding to the additional content source; and
based at least in part on the first data and the second data, causing the output to include at least the first content of the default content source and the second content of the additional content source.

2. The computer-implemented method of claim 1 , wherein the additional content source is configured to provide output data in response to a natural language input.

3. The computer-implemented method of claim 1 , further comprising:
determining a category of the natural language command,
wherein determining that the output is to additionally include the second content of the additional content source is based at least in part on the category.

4. The computer-implemented method of claim 1 , further comprising:
the default content source is associated with a first domain of a natural language processing system; and
the additional content source is associated with a second domain of the natural language processing system.

5. The computer-implemented method of claim 1 , wherein:
the first data comprises first text data; and
the second data comprises second text data.

6. The computer-implemented method of claim 1 , further comprising:
sending, to the additional content source, context data corresponding to the profile.

7. The computer-implemented method of claim 1 , further comprising:
determining a geographic location corresponding to the natural language command; and
determining the additional content source based at least in part on the geographic location.

8. The computer-implemented method of claim 1 , wherein performing natural language processing using the input data to determine first data corresponding to a default content source is based at least in part on the profile.

9. The computer-implemented method of claim 1 , further comprising:
generating an output data format including a first slot to be populated with content from the default content source and a second slot to be populated with content from the additional content source; and
configuring output data corresponding to the output data format, the output data including the first data in the first slot and the second data in the second slot,
wherein causing the output uses the output data.

10. The computer-implemented method of claim 1 , further comprising:
performing speech synthesis using the first data and the second data to determine audio data,
wherein causing the output uses the audio data.

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 representing a natural language command;
perform natural language processing using the input data to determine first data corresponding to a default content source;
determine that output responsive to the natural language command is to include first content corresponding to a default content source;
identify a profile associated with the input data;
determine that the profile is associated with an additional content source;
determine, based at least in part on the profile being associated with the additional content source, that the output is to additionally include second content corresponding to the additional content source;
receive second data responsive to the natural language command, the second data corresponding to the additional content source; and
based at least in part on the first data and the second data, cause the output to include at least the first content of the default content source and the second content of the additional content source.

12. The system of claim 11 , wherein the additional content source is configured to provide output data in response to a natural language input.

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 category of the natural language command,
wherein the instructions that cause the system to determine that the output is to additionally include the second content of the additional content source are based at least in part on the category.

14. The system of claim 11 , wherein:
the default content source is associated with a first domain of a natural language processing system; and
the additional content source is associated with a second domain of the natural language processing system.

15. The system of claim 11 , wherein:
the first data comprises first text data; and
the second data comprises second text 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:
send, to the additional content source, context data corresponding to the profile.

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 a geographic location corresponding to the natural language command; and
determine the additional content source based at least in part on the geographic location.

18. The system of claim 11 , wherein the instructions that cause the system to perform natural language processing using the input data to determine first data corresponding to a default content source are based at least in part on the profile.

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:
generate an output data format including a first slot to be populated with content from the default content source and a second slot to be populated with content from the additional content source; and
configure output data corresponding to the output data format, the output data including the first data in the first slot and the second data in the second slot,
wherein the instructions that cause the system to cause the output use the output data.

20. 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:
perform speech synthesis using the first data and the second data to determine audio data,
wherein the instructions that cause the system to cause the output use the audio data.

Assignees

• Amazon Tech Inc

Inventors

• Mutagi Rohan
• Wu Felix
• Shen Rongzhou
• Agrawal Neelam Satish
• Gavini Vibhunandan
• Carballude Gonzalez Pablo

Classifications

• G10L15/00

  Speech recognition (G10L17/00 takes precedence) · CPC title

• G06F16/00

  Information retrieval; Database structures therefor; File system structures therefor · CPC title

• G10L13/00

  Speech synthesis; Text to speech systems · CPC title

• G06F3/167 Primary

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

• G10L2015/223

  Execution procedure of a spoken command · CPC title