Granted Patent B2

US 12,562,164 · App. 18/229,898 · Granted Feb 24, 2026

Inventors: Rebecca Joy Lopdrup Miller (Seattle, WA); Liron Torres (Redmond, WA); Kadirvel Chockalingam Vanniarajan (Mercer Island, WA); Gonzalo Alvarez Barrio (Seattle, WA); Dick Clarence Hardt (Seattle, WA)

Assignee: Amazon Technologies, Inc.

G10L15/22G06F3/167H04W4/14

Abstract

Claims (76)

1 . A method comprising:

receiving audio data representing a user utterance captured at a voice-enabled device;

determining a voice signature of the audio data;

determining account data associated with the voice signature;

determining, based at least in part on the audio data, intent data representing a request to perform an action;

identifying a first application configured to process the intent data;

identifying a second application configured to process the intent data;

determining, by an association-management component implemented as computer-readable instructions stored in memory and executed by one or more processors, that the first application is associated with the account data;

determining, by the association-management component, that the second application is unassociated with the account data;

selecting the first application to process the intent data instead of the second application based at least in part on the determining, by the association-management component, that the first application is associated with the account data and the second application is unassociated with the account data; and

causing the action to be performed utilizing the first application.

2 . The method of claim 1 , further comprising:

storing data representing multiple voice signatures including the voice signature; and

parsing the multiple voice signatures to determine which of the multiple voice signatures is most similar to the voice signature of the audio data.

3 . The method of claim 1 , further comprising:

determining, based at least in part on the voice signature, that a user that provided the user utterance is a guest user with respect to the voice-enabled device; and

associating a guest user designation with the action.

4 . The method of claim 1 , further comprising:

determining that the account data is associated with a device of an environment in which the voice-enabled device is not situated;

determining that the intent data is for performing the action in association with the device; and

sending a command to perform the action to the device.

5 . The method of claim 1 , further comprising selecting the action from multiple actions based at least in part on selecting the first application to process the intent data.

6 . The method of claim 1 , wherein the action comprises a first action, and the method further comprises:

determining, using the first application, the first action is associated with the intent data;

determining, using the first application, a second action associated with the intent data, the second action differing from the first action; and

selecting the first action for performance instead of the second action based at least in part on historical usage data.

7 . The method of claim 1 , further comprising:

sending a command to the voice-enabled device, the command causing output of audio requesting confirmation of the account data;

receiving user input data indicating confirmation of the account data; and

wherein causing the action to be performed comprises causing the action to be performed based at least in part on the user input data indicating confirmation of the account data.

8 . The method of claim 1 , wherein determining that the first application is associated with the account data is based at least in part on the first application being selected for use with the voice-enabled device prior to receiving the audio data.

9 . The method of claim 1 , wherein:

the first application is associated with a first set of actions; and

the second application is associated with a second set of actions that differ at least in part from the first set of actions.

10 . The method of claim 1 , further comprising:

sending, to the first application, first data requesting the first application to determine the action to be performed and including an identifier of the account data; and

receiving, from the first application, second data representing a command to perform the action, the action based at least in part on the identifier of the account data.

11 . A system comprising:

one or more processors; and

non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:

receiving audio data representing a user utterance captured at a voice-enabled device;

determining a voice signature of the audio data;

determining account data associated with the voice signature;

determining, based at least in part on the audio data, intent data representing a request to perform an action;

identifying a first application configured to process the intent data;

identifying a second application configured to process the intent data;

determining, by an association-management component implemented as computer-readable instructions stored in memory and executed by one or more processors, that the first application is associated with the account data;

determining, by the association-management component, that the second application is unassociated with the account data;

selecting the first application to process the intent data instead of the second application based at least in part on the determining, by the association-management component, that the first application is associated with the account data and the second application is unassociated with the account data; and

causing the action to be performed utilizing the first application.

12 . The system of claim 11 , the operations further comprising:

storing data representing multiple voice signatures including the voice signature; and

parsing the multiple voice signatures to determine which of the multiple voice signatures is most similar to the voice signature of the audio data.

13 . The system of claim 11 , the operations further comprising:

determining, based at least in part on the voice signature, that a user that provided the user utterance is a guest user with respect to the voice-enabled device; and

associating a guest user designation with the action.

14 . The system of claim 11 , the operations further comprising:

determining that the account data is associated with a device of an environment in which the voice-enabled device is not situated;

determining that the intent data is for performing the action in association with the device; and

sending a command to perform the action to the device.

15 . The system of claim 11 , the operations further comprising selecting the action from multiple actions based at least in part on selecting the first application to process the intent data.

16 . The system of claim 11 , wherein the action comprises a first action, and the operations further comprise:

determining, using the first application, the first action is associated with the intent data;

determining, using the first application, a second action associated with the intent data, the second action differing from the first action; and

selecting the first action for performance instead of the second action based at least in part on historical usage data.

17 . The system of claim 11 , the operations further comprising:

sending a command to the voice-enabled device, the command causing output of audio requesting confirmation of the account data;

receiving user input data indicating confirmation of the account data; and

wherein causing the action to be performed comprises causing the action to be performed based at least in part on the user input data indicating confirmation of the account data.

18 . The system of claim 11 , wherein determining that the first application is associated with the account data is based at least in part on the first application being selected for use with the voice-enabled device prior to receiving the audio data.

19 . The system of claim 11 , wherein:

the first application is associated with a first set of actions; and

the second application is associated with a second set of actions that differ at least in part from the first set of actions.

20 . The system of claim 11 , the operations further comprising:

sending, to the first application, first data requesting the first application to determine the action to be performed and including an identifier of the account data; and

receiving, from the first application, second data representing a command to perform the action, the action based at least in part on the identifier of the account data.

Assignments (1)

Continuity (3)

References Cited (42)