Natural language processing using context

Patent metadata

Field	Value
Publication number	US-12080282-B2
Application number	US-202217848901-A
Country	US
Kind code	B2
Filing date	Jun 24, 2022
Priority date	Mar 23, 2020
Publication date	Sep 3, 2024
Grant date	Sep 3, 2024

Abstract

This disclosure proposes systems and methods for processing natural language inputs using data associated with multiple language recognition contexts (LRC). A system using multiple LRCs can receive input data from a device, identify a first identifier associated with the device, and further identify second identifiers associated with the first identifier and representing candidate users of the device. The system can access language processing data used for natural language processing for the LRCs corresponding to each of the first and second identifiers, and process the input data using the language processing data at one or more stages of automatic speech recognition, natural language understanding, entity resolution, and/or command execution. User recognition can reduce the number of candidate users, and thus the amount of data used to process the input data. Dynamic arbitration can select from between competing hypotheses representing the first identifier and a second identifier, respectively.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
receiving, by a language processing component from a first device, input data corresponding to a natural language input;
receiving, from a second device, first context data corresponding to the input data, the first context data representing a device identifier corresponding to the second device;
processing the first context data to determine a first identifier corresponding to a first possible user of the first device; and
performing, by the language processing component based on to the first identifier, first language processing on the input data to generate output data.

2. The computer-implemented method of claim 1 , further comprising:
determining a first automatic speech recognition (ASR) configuration corresponding to the first identifier,
wherein performing the first language processing comprises using the first ASR configuration.

3. The computer-implemented method of claim 1 , further comprising:
determining a first natural language understanding (NLU) configuration corresponding to the first identifier,
wherein performing the first language processing comprises using the first NLU configuration.

4. The computer-implemented method of claim 1 , further comprising:
determining first entity data corresponding to the first identifier,
wherein performing the first language processing comprises using the first entity data.

5. The computer-implemented method of claim 1 , further comprising:
determining, based at least in part on the first context data, that the first possible user is proximate to the first device.

6. The computer-implemented method of claim 1 , wherein performing the first language processing comprising:
determining a first hypothesis corresponding to the natural language input;
determining a second hypothesis corresponding to the natural language input; and
based at least in part on the first identifier, selecting the first hypothesis.

7. The computer-implemented method of claim 1 , wherein the second device comprises a wearable device and receiving the first context data comprises receiving a signal corresponding to the wearable device.

8. The computer-implemented method of claim 1 , further comprising:
receiving second context data corresponding to the input data;
determining, based on the second context data, a second identifier corresponding to a second possible user of the first device; and
based at least in part on the input data, determining the first possible user more likely provided the natural language input than the second possible user.

9. The computer-implemented method of claim 1 , further comprising:
determining, based at least in part on the first context data, that the first device detects only a single user proximate to the first device.

10. The computer-implemented method of claim 1 , wherein the input data is audio data corresponding to an utterance and wherein the method comprising:
processing the audio data to determine a voice identifier corresponding to the input data; and
determining that the voice identifier corresponds to a second identifier different from the first identifier, wherein performing the first language processing is additionally based on the second identifier.

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, by at least one language processing component corresponding to a first device, input data corresponding to a natural language input;
receive, from a second device, first context data corresponding to the input data, the first context data representing a device identifier corresponding to the second device;
processing the first context data to determine a first identifier corresponding to a first possible user of the first device; and
perform, by the at least one language processing component based on to the first identifier, first language processing on the input data to generate output data.

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:
determine a first automatic speech recognition (ASR) configuration corresponding to the first identifier,
wherein the instructions that cause the system to perform the first language processing comprise instructions that, when executed by the at least one processor, cause the system to use the first ASR configuration.

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 first natural language understanding (NLU) configuration corresponding to the first identifier,
wherein the instructions that cause the system to perform the first language processing comprise instructions that, when executed by the at least one processor, cause the system to use the first NLU configuration.

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 first entity data corresponding to the first identifier,
wherein the instructions that cause the system to perform the first language processing comprise instructions that, when executed by the at least one processor, cause the system to use the first entity 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, based at least in part on the first context data, that the first possible user is proximate to the first device.

16. The system of claim 11 , wherein the instructions that cause the system to perform the first language processing comprise instructions that, when executed by the at least one processor, cause the system to:
determine a first hypothesis corresponding to the natural language input;
determine a second hypothesis corresponding to the natural language input; and
based at least in part on the first identifier, select the first hypothesis.

17. The system of claim 11 , wherein the second device comprises a wearable device and the instructions that cause the system to receive the first context data comprise instructions that, when executed by the at least one processor, cause the system to receive a signal corresponding to the wearable device.

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 second context data corresponding to the input data;
determine, based on the second context data, a second identifier corresponding to a second possible user of the first device; and
based at least in part on the input data, determine the first possible user more likely provided the natural language input than the second possible user.

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, based at least in part on the first context data, that the first device detects only a single user proximate to the first device.

20. The system of claim 11 , wherein the input data is audio data corresponding to an utterance and the at least one memory further comprises instructions that

Assignees

• Amazon Tech Inc

Inventors

• Teng Da
• Evans Adrian
• Narayanan Naresh

Classifications

• G10L17/22

  Interactive procedures; Man-machine interfaces · CPC title

• G10L2015/227

  of the speaker; Human-factor methodology · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10L2015/228

  of application context · CPC title

• G10L15/22

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