Voice activated premises device enrollment in a security system

Patent metadata

Field	Value
Publication number	US-12354591-B2
Application number	US-202218088324-A
Country	US
Kind code	B2
Filing date	Dec 23, 2022
Priority date	Dec 23, 2022
Publication date	Jul 8, 2025
Grant date	Jul 8, 2025

Abstract

A control device in a premises security system is provided. The control device receives a voice command or a touch-based input to initiate an enrollment of a premises device in a premises security system and synthesizes a plurality of audio clips for playback on a speaker. Each audio clip requests respective premises device information. In response to playback of the audio clips, the control device receives a plurality of voice responses, maps each of the plurality of voice responses to a plurality of respective attributes of a premises device, determines a premises device configuration or a premises security system configuration based at least in part on the plurality of respective attributes, and enrolls the premises device in the premises security system based at least in part on the premises device configuration or the premises security system configuration.

First claim

What is claimed is:

1. A control device for a premises security system, the control device comprising:
processing circuitry configured to:
receive at least one of a voice command or a touch-based input to initiate an enrollment of a premises device in the premises security system;
synthesize a plurality of audio clips for playback on at least one speaker, each of the plurality of audio clips requesting respective premises device information;
in response to playback of the plurality of audio clips, receive a plurality of voice responses;
map each of the plurality of voice responses to a plurality of respective attributes of the premises device;
determine a premises device configuration for the premises device or a premises security system configuration based at least in part on the plurality of respective attributes, the determining of the premises device configuration or the premises security system configuration comprising at least determining a sensitivity threshold based at least in part on a first voice response of the plurality of voice responses by:
determining at least one modifier term of the first voice response; and
mapping the at least one modifier term to a corresponding sensitivity threshold; and

enroll the premises device in the premises security system based at least in part on the premises device configuration or the premises security system configuration.

2. The control device of claim 1 , wherein the plurality of respective attributes comprises at least one of:
a name of the premises device;
a location of the premises device;
a type of the premises device; or
an operating mode of the premises device.

3. The control device of claim 1 , wherein the processing circuitry is further configured to map each of the plurality of voice responses to the plurality of respective attributes by at least:
predicting a first attribute of the plurality of attributes based at least in part on a first voice response of the plurality of voice responses;
synthesizing an additional audio clip for playback on the at least one speaker, the additional audio clip reciting the predicted first attribute and requesting a confirmation from the user;
in response to playback of the additional audio clip, receiving an additional voice response indicating whether the predicted first attribute is accurate; and
the mapping of the first voice response to the first attribute is based at least in part on the predicted first attribute being accurate.

4. The control device of claim 3 , wherein the processing circuitry is further configured to:
predict the first attribute using a trained machine learning model; and
update the trained machine learning model based at least in part on the additional voice response indicating whether the predicted first attribute is accurate.

5. The control device of claim 1 , wherein the processing circuitry is further configured to:
synthesize an additional audio clip for playback on the at least one speaker, the additional audio clip reciting an additional instruction for the user to present one of a barcode and a quick response (QR) code associated with the premises device to an image sensor of the control device;
in response to playback of the additional audio clip, receive an image corresponding to the QR code or the barcode;
determine at least one additional attribute based at least in part on the QR code or the barcode; and
determine the premises device configuration for the premises device or the premises security system configuration further based at least in part on the at least one additional attribute.

6. The control device of claim 1 , wherein the processing circuitry is further configured to:
synthesize an additional audio clip for playback on the at least one speaker, the additional audio clip reciting an additional instruction for the user to place the premises device in a field of view of an image sensor of the control device;
in response to playback of the additional audio clip, receive an image corresponding to the premises device;
determine a classification of the premises device based at least in part on the image; and
determine the premises device configuration for the premises device or the premises security system configuration further based at least in part on the classification.

7. The control device of claim 1 , wherein the processing circuitry is further configured to authenticate the user prior to enrolling the premises device in the premises security system by at least:
identifying a passcode in at least one of the voice command or at least one of the plurality of voice responses; and
comparing the passcode to a reference passcode.

8. The control device of claim 1 , wherein the processing circuitry is further configured to authenticate the user prior to enrolling the premises device in the premises security system by at least:
identifying a voiceprint based at least in part on at least one of:
the voice command; or
at least one of the plurality of voice responses; and

comparing the voiceprint to a reference voiceprint.

9. The control device of claim 1 , wherein the processing circuitry is further configured to:
receive an additional voice command from the user to add an additional premises device to a premises security system;
determine a grouping of the premises devices and the additional premises device based at least in part on at least one of the plurality of voice responses; and
determine the premises device configuration for the premises device or the premises security system configuration further based at least in part on the grouping.

10. A method implemented by a control device in a premises security system, the method comprising:
receiving at least one of a voice command or a touch-based input to initiate an enrollment of a premises device in the premises security system;
synthesizing a plurality of audio clips for playback on at least one speaker, each of the plurality of audio clips requesting respective premises device information;
in response to playback of the plurality of audio clips, receiving a plurality of voice responses;
mapping each of the plurality of voice responses to a plurality of respective attributes of the premises device;
determining a premises device configuration for the premises device or a premises security system configuration based at least in part on the plurality of respective attributes, the determining of the premises device configuration or the premises security system configuration comprising at least determining a sensitivity threshold based on at least in part on a first voice response of the plurality of voice responses by:
determining at least one modifier term of the first voice response; and
mapping the at least one modifier term to a corresponding sensitivity threshold; and

enrolling the premises device in the premises security system based at least in part on the premises device configuration or the premises security system configuration.

11. The method of claim 10 , wherein the plurality of respective attributes comprises at least one of:
a name of the premises device;
a location of the premises device;
a type of the premises device; or
an operating mode of the premises device.

12. The method of claim 10 , wherein mapping each of the plurality of voice responses to the plurality of respective attributes comprises at least:
predicting a first attribute of the plurality of attributes based at least in part on a first voice response of the plurality of voice responses;
synthesizing an additional audio clip for playback on the at least one speaker, the additional audio clip reciting the predicted first attribute an

Assignees

• The Adt Security Corp

Inventors

• Else Steven
• Patel Jatin

Classifications

• G10L15/22

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

• G06F21/32 Primary

  using biometric data, e.g. fingerprints, iris scans or voiceprints · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G06F3/167

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

• G10L13/027 Primary

  Concept to speech synthesisers; Generation of natural phrases from machine-based concepts (generation of parameters for speech synthesis out of text G10L13/08) · CPC title