Granted Patent B2

US 12,315,510 · App. 18/777,134 · Granted May 27, 2025

Inventors: Haris Ramic (San Francisco, CA); Vikram Aggarwal (Palo Alto, CA); Moises Morgenstern Gali (San Francisco, CA); Brandon Stuut (Palo Alto, CA)

Assignee: GOOGLE LLC

G10L15/22G06F9/44505G06F9/44536G06F9/452G10L15/1822G10L15/30G10L2015/088G10L2015/223

Abstract

Claims (72)

1. A method implemented by one or more processors of a computing device, the method comprising:

receiving, via one or more microphones of the computing device, an input audio signal that includes: (i) a first portion capturing a given trigger word or phrase, and (ii) a second portion capturing a request;

determining, based on processing the first portion of the input audio signal that includes the given trigger word or phrase, a given digital assistant application, from among a plurality of digital assistant applications that are accessible by the computing device, that is associated with the given trigger word or phrase,

wherein the plurality of digital assistant applications that are accessible by the computing device include at least a first digital assistant application and a second digital assistant application,

determining, based on processing the second portion of the input audio signal that includes the request, an action to be performed responsive to the request;

generating, based on the action to be performed responsive to the request, an action data structure including instructions that, when executed, cause the action to be performed responsive to the request;

in response to determining that the given trigger word or phrase is a first trigger word or phrase that is associated with the first digital assistant application:

causing the first digital assistant application to perform the action to satisfy the request, wherein causing the first digital assistant application to perform the action to satisfy the request comprises causing the first digital assistant application to:

receive the action data structure via a first application programming interface (API) associated with the first digital assistant application; and

execute the instructions, included in the action data structure, to cause the action to be performed responsive to the request; and

in response to determining that the given trigger word or phrase is a second trigger word or phrase that is associated with the second digital assistant application:

causing the second digital assistant application to perform the action to satisfy the request, wherein causing the second digital assistant application to perform the action to satisfy the request comprises causing the second digital assistant application to:

receive the action data structure via a second API associated with the second digital assistant application; and

execute the instructions, included in the action data structure, to cause the action to be performed responsive to the request.

2. The method of claim 1 , wherein the plurality of digital assistant applications that are accessible by the computing device further include a third digital assistant application.

3. The method of claim 2 , further comprising:

in response to determining that the given trigger word or phrase is a third trigger word or phrase that is associated with the third digital assistant application:

causing the third digital assistant application to perform the action to satisfy the request.

4. The method of claim 1 , wherein an indication of the given digital assistant application is stored in association with the given trigger word or phrase in one or more databases that are accessible to the computing device.

5. The method of claim 1 , wherein determining the given digital assistant application that is associated with the given trigger word or phrase and based on processing the first portion of the input audio signal that includes the given trigger word or phrase comprises:

parsing, using a natural language processor component of the computing device, the first portion of the input audio signal to identify the given trigger word or phrase; and

determining, based on parsing the input audio signal to identify the given trigger word or phrase, that the given trigger word or phrase is associated with the given digital assistant application.

6. The method of claim 5 , wherein determining the action to be performed responsive to the request and based on processing the second portion of the input audio signal that includes the request comprises:

parsing, using the natural language processor component of the computing device, the second portion of the input audio signal to identify the request; and

determining, based on parsing the input audio signal to identify the request, the action to be performed responsive to the request.

7. The method of claim 1 , wherein the computing device is a standalone computing device.

8. A system comprising:

at least one processor; and

memory storing instructions that, when executed, cause the at least one processor to be operable to:

receive, via one or more microphones of a computing device, an input audio signal that includes: (i) a first portion capturing a given trigger word or phrase, and (ii) a second portion capturing a request;

determine, based on processing the first portion of the input audio signal that includes the given trigger word or phrase, a given digital assistant application, from among a plurality of digital assistant applications that are accessible by the computing device, that is associated with the given trigger word or phrase,

wherein the plurality of digital assistant applications that are accessible by the computing device include at least a first digital assistant application and a second digital assistant application,

determine, based on processing the second portion of the input audio signal that includes the request, an action to be performed responsive to the request;

generate, based on the action to be performed responsive to the request, an action data structure including instructions that, when executed, cause the action to be performed responsive to the request;

in response to determining that the given trigger word or phrase is a first trigger word or phrase that is associated with the first digital assistant application:

cause the first digital assistant application to perform the action to satisfy the request, wherein the instructions to cause the first digital assistant application to perform the action to satisfy the request comprise instructions to cause the first digital assistant application to:

receive the action data structure via a first application programming interface (API) associated with the first digital assistant application; and

execute the instructions, included in the action data structure, to cause the action to be performed responsive to the request; and

in response to determining that the given trigger word or phrase is a second trigger word or phrase that is associated with the second digital assistant application:

cause the second digital assistant application to perform the action to satisfy the request, wherein the instructions to cause the second digital assistant application to perform the action to satisfy the request comprise instructions to cause the second digital assistant application to:

receive the action data structure via a second API associated with the second digital assistant application; and

execute the instructions, included in the action data structure, to cause the action to be performed responsive to the request.

9. The system of claim 8 , wherein the plurality of digital assistant applications that are accessible by the computing device further include a third digital assistant application.

10. The system of claim 9 , wherein the instructions are further operable to:

in response to determining that the given trigger word or phrase is a third trigger word or phrase that is associated with the third digital assistant application:

cause the third digital assistant application to perform the action to satisfy the request.

11. The system of claim 8 , wherein an indication of the given digital assistant application is stored in association with the given trigger word or phrase in one or more databases that are accessible to the computing device.

12. The system of claim 8 , wherein the instructions to determine the given digital assistant application that is associated with the given trigger word or phrase and based on processing the first portion of the input audio signal that includes the given trigger word or phrase comprise instructions to:

parse, using a natural language processor component of the computing device, the first portion of the input audio signal to identify the given trigger word or phrase; and

determine, based on parsing the input audio signal to identify the given trigger word or phrase, that the given trigger word or phrase is associated with the given digital assistant application.

13. The system of claim 12 , wherein the instructions to determine the action to be performed responsive to the request and based on processing the second portion of the input audio signal that includes the request comprise instructions to:

parse, using the natural language processor component of the computing device, the second portion of the input audio signal to identify the request; and

determine, based on parsing the input audio signal to identify the request, the action to be performed responsive to the request.

14. The system of claim 8 , wherein the computing device is a standalone computing device.

15. A non-transitory computer-readable storage medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform operations, the operations comprising:

receiving, via one or more microphones of a computing device, an input audio signal that includes: (i) a first portion capturing a given trigger word or phrase, and (ii) a second portion capturing a request;

determining, based on processing the first portion of the input audio signal that includes the given trigger word or phrase, a given digital assistant application, from among a plurality of digital assistant applications that are accessible by the computing device, that is associated with the given trigger word or phrase,

wherein the plurality of digital assistant applications that are accessible by the computing device include at least a first digital assistant application and a second digital assistant application,

determining, based on processing the second portion of the input audio signal that includes the request, an action to be performed responsive to the request;

generating, based on the action to be performed responsive to the request, an action data structure including instructions that, when executed, cause the action to be performed responsive to the request;

in response to determining that the given trigger word or phrase is a first trigger word or phrase that is associated with the first digital assistant application:

causing the first digital assistant application to perform the action to satisfy the request, wherein causing the first digital assistant application to perform the action to satisfy the request comprises causing the second digital assistant application to:

receive the action data structure via a first application programming interface (API) associated with the first digital assistant application; and

execute the instructions, included in the action data structure, to cause the action to be performed responsive to the request; and

in response to determining that the given trigger word or phrase is a second trigger word or phrase that is associated with the second digital assistant application:

causing the second digital assistant application to perform the action to satisfy the request, wherein causing the second digital assistant application to perform the action to satisfy the request comprises causing the first digital assistant application to:

receive the action data structure via a second API associated with the second digital assistant application; and

execute the instructions, included in the action data structure, to cause the action to be performed responsive to the request.

16. The non-transitory computer-readable storage medium of claim 15 , wherein the plurality of digital assistant applications that are accessible by the computing device further include a third digital assistant application.

17. The non-transitory computer-readable storage medium of claim 16 , the operations further comprising:

in response to determining that the given trigger word or phrase is a third trigger word or phrase that is associated with the third digital assistant application:

causing the third digital assistant application to perform the action to satisfy the request.

Assignments (1)

Continuity (4)

References Cited (110)