Granted Patent B2

US 12,499,885 · App. 17/693,171 · Granted Dec 16, 2025

Inventors: Harrison Holmes Jones (Seattle, WA); Jonathan Alan Leblang (Menlo Park, CA)

Assignee: Amazon Technologies, Inc.

G10L15/22G10L13/00G10L15/02G10L15/30H04L67/51G10L2015/223H04L67/10

Abstract

Claims (68)

1 . A system, comprising:

one or more computing devices in a service provider environment comprising one or more services implementing voice input analysis and device management, wherein the one or more computing devices are configured to:

receive, over one or more one networks, voice input from a voice-capturing device, wherein the voice input includes a voiced configuration assignment indicating configuration of a configuration parameter representing an authorized device user of the voice-capturing device;

perform the voice input analysis for the voice input, wherein the voice input analysis for the voice input determines a value for the configuration parameter, representing an authorized device user of the voice-capturing device, based on a representation of the voiced configuration assignment in the voice input; and

store, using the device management, an association between the voice-capturing device and the determined value for the configuration parameter representing an authorized device user of the voice-capturing device, wherein the determined value affects one or more actions taken by the service provider environment responsive to further voice input from the voice-capturing device.

2 . The system of claim 1 , wherein the value for the configuration parameter representing an authorized device user comprises an identifier of a particular authorized device user.

3 . The system of claim 1 , wherein the one or more computing devices are configured to:

determine a set of authorized values for the configuration parameter representing an authorized device user; and

verify that the value for the configuration parameter representing an authorized device user is in the set of authorized values.

4 . The system of claim 1 , wherein the voice-capturing device is associated with an audio output component, and wherein the one or more computing devices are configured to:

send, over the one or more networks, voice output to the voice-capturing device, wherein the voice output represents a request for disambiguation of a user-supplied value for the configuration parameter representing an authorized device user; and

cause the voice output to be played via the audio output component.

5 . The system of claim 1 , wherein the voice-capturing device is associated with an audio output component, and wherein the one or more computing devices are configured to:

receive, over the one or more networks, additional voice input from the voice-capturing device;

perform the voice input analysis for the additional voice input, wherein the voice input analysis for the additional voice input determines that the additional voice input represents a request seeking information descriptive of the voice-capturing device;

generate voice output responsive to the additional voice input, wherein the voice output is sent over the one or more networks to the voice-capturing device, and wherein the voice output represents a recitation of the value for the configuration parameter representing an authorized device user; and

cause the voice output to be played via the audio output component.

6 . The system of claim 1 , wherein the voice-capturing device is associated with an audio output component, and wherein the one or more computing devices are configured to:

receive, over the one or more networks, initial voice input from the voice-capturing device;

perform the voice input analysis for the initial voice input, wherein the voice input analysis for the initial voice input determines that the initial voice input represents a request for a function associated with the configuration parameter representing an authorized device user;

generate voice output responsive to the initial voice input, wherein the voice output is sent over the one or more networks to the voice-capturing device, and wherein the voice output represents a request for the value for the configuration parameter representing an authorized device user; and

cause the voice output to be played via the audio output component.

7 . The system of claim 1 , wherein the one or more computing devices are configured to:

invoke an additional service in the service provider environment based at least in part on the further voice input, wherein the additional service performs the one or more actions based at least in part on the value for the configuration parameter representing an authorized device user.

8 . A method, comprising:

receiving voice input from a voice-capturing device, wherein the voice input is received over one or more networks at one or more computing devices in a service provider environment comprising one or more services implementing voice input analysis and device management, and wherein the voice input includes a voiced configuration assignment indicating configuration of a configuration parameter representing an authorized device user of the voice-capturing device, and;

performing the voice input analysis for the voice input, wherein the voice input analysis for the voice input determines a value for the configuration parameter, representing an authorized device user of the voice-capturing device, based on a representation of the voiced configuration assignment in the voice input; and

storing, using the device management, an association between the voice-capturing device and the determined value for the configuration parameter representing an authorized device user of the voice-capturing device, wherein the determined value affects one or more actions taken by the service provider environment responsive to further voice input from the voice-capturing device.

9 . The method of claim 8 , wherein the value for the configuration parameter representing an authorized device user comprises an identifier of a particular authorized device user.

10 . The method of claim 8 , comprising:

determining a set of authorized values for the configuration parameter representing an authorized device user; and

verifying that the value for the configuration parameter representing an authorized device user is in the set of authorized values.

11 . The method of claim 8 , wherein the voice-capturing device is associated with an audio output component, and wherein the method comprises:

sending, over the one or more networks, voice output to the voice-capturing device, wherein the voice output represents a request for disambiguation of a user-supplied value for the configuration parameter representing an authorized device user; and

causing the voice output to be played via the audio output component.

12 . The method of claim 8 , wherein the voice-capturing device is associated with an audio output component, and wherein the method comprises:

receiving, over the one or more networks, additional voice input from the voice-capturing device;

performing the voice input analysis for the additional voice input, wherein the voice input analysis for the additional voice input determines that the additional voice input represents a request seeking information descriptive of the voice-capturing device;

generating voice output responsive to the additional voice input, wherein the voice output is sent over the one or more networks to the voice-capturing device, and wherein the voice output represents a recitation of the value for the configuration parameter representing an authorized device user; and

causing the voice output to be played via the audio output component.

13 . The method of claim 8 , wherein the voice-capturing device is associated with an audio output component, and wherein the method comprises:

receiving, over the one or more networks, initial voice input from the voice-capturing device;

performing the voice input analysis for the initial voice input, wherein the voice input analysis for the initial voice input determines that the initial voice input represents a request for a function associated with the configuration parameter representing an authorized device user;

generating voice output responsive to the initial voice input, wherein the voice output is sent over the one or more networks to the voice-capturing device, and wherein the voice output represents a request for the value for the configuration parameter representing an authorized device user; and

causing the voice output to be played via the audio output component.

14 . The method of claim 8 , comprising:

invoking an additional service in the service provider environment based at least in part on the further voice input, wherein the additional service performs the one or more actions based at least in part on the value for the configuration parameter representing an authorized device user.

15 . One or more non-transitory computer-readable media storing program instructions that, when executed on or across one or more processors, cause the one or more processors to:

receive voice input from a voice-capturing device, wherein the voice input is received over one or more networks at one or more computing devices in a service provider environment comprising one or more services implementing voice input analysis and device management, and wherein the voice input includes a voiced configuration assignment indicating configuration of a configuration parameter representing an authorized device user of the voice-capturing device, and;

perform the voice input analysis for the voice input, wherein the voice input analysis for the voice input determines a value for the configuration parameter, representing an authorized device user of the voice-capturing device, based on a representation of the voiced configuration assignment in the voice input; and

store, using the device management, an association between the voice-capturing device and the determined value for the parameter representing the user, wherein the determined value affects one or more actions taken by the service provider environment responsive to further voice input from the voice-capturing device.

16 . The one or more non-transitory computer-readable media of claim 15 , wherein the value for the configuration parameter representing an authorized device user comprises an identifier of a particular authorized device user.

17 . The one or more non-transitory computer-readable media of claim 15 , wherein the program instructions cause the one or more processors to:

determine a set of authorized values for the configuration parameter representing an authorized device user; and

verify that the value for the configuration parameter representing an authorized device user is in the set of authorized values.

18 . The one or more non-transitory computer-readable media of claim 15 , wherein the voice-capturing device is associated with an audio output component, and wherein the program instructions cause the one or more processors to:

send, over the one or more networks, voice output to the voice-capturing device, wherein the voice output represents a request for disambiguation of a user-supplied value for the configuration parameter representing an authorized device user; and

cause the voice output to be played via the audio output component.

19 . The one or more non-transitory computer-readable media of claim 15 , wherein the voice-capturing device is associated with an audio output component, and wherein the program instructions cause the one or more processors to:

receive, over the one or more networks, additional voice input from the voice-capturing device;

perform the voice input analysis for the additional voice input, wherein the voice input analysis for the additional voice input determines that the additional voice input represents a request seeking information descriptive of the voice-capturing device;

generate voice output responsive to the additional voice input, wherein the voice output is sent over the one or more networks to the voice-capturing device, and wherein the voice output represents a recitation of the value for the configuration parameter representing an authorized device user; and

cause the voice output to be played via the audio output component.

20 . The one or more non-transitory computer-readable media of claim 15 , wherein the voice-capturing device is associated with an audio output component, and wherein the program instructions cause the one or more processors to:

receive, over the one or more networks, initial voice input from the voice-capturing device;

perform the voice input analysis for the initial voice input, wherein the voice input analysis for the initial voice input determines that the initial voice input represents a request for a function associated with the configuration parameter representing an authorized device user;

generate voice output responsive to the initial voice input, wherein the voice output is sent over the one or more networks to the voice-capturing device, and wherein the voice output represents a request for the value for the configuration parameter representing an authorized device user; and

cause the voice output to be played via the audio output component.

Continuity (2)

References Cited (107)