IP Library › Granted Patent US 12,236,957
Granted Patent B1
US 12,236,957 · App. 17/901,269 · Granted Feb 25, 2025

Authenticating a user profile with devices

Inventors: Lizhen Peng (Seattle, WA); Alok Upadhyay (Seattle, WA); Jason Cline (Bellevue, WA); Ankur Gandhe (Bothell, WA)
Assignee: Amazon Technologies, Inc.
G10L17/12G06N20/00G10L17/02G10L17/18G10L17/24H04L67/54
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,236,957
App. No.
17/901,269
Granted
Feb 25, 2025
Kind
B1
Abstract

Systems and methods for presence ground truth approximation and utilization are disclosed. For example, a system detects the presence of a predefined subject, such as a person associated with a given user profile, and/or determines that authentication criteria for performing an action in association with the user profile has been satisfied. A period of time to associate data is determined, and data of one or more data types is labeled as being associated with the speaker identification event. That data may be formatted and input into one or more models to train those models to more accurately detect presence and/or determine whether authentication of a user profile should succeed.

Claims (76)

1. A method comprising:

receiving a request to authenticate a user profile based at least in part on first data received at a first device, the first data having a first data type;

determining a second device associated with the first device;

receiving second data from the second device, the second data:

including sensor data generated by one or more sensors in an environment of the second device, the one or more sensors configured to detect environmental changes within the environment;

indicating an event determined by the second device, the event being an environmental change predefined as being associated with profile authentication; and

having a second data type that differs from the first data type;

receiving third data from a third device, the third data indicating detection of the event at the third device;

determining a device type of the third device;

requesting authentication of the user profile at the third device based at least in part on the device type of the third device that detected the event;

associating the event with the user profile; and

determining to authenticate the user profile based at least in part on the sensor data and receiving an indication of the authentication from the third device.

2. The method of claim 1 , wherein:

the event further includes a predefined device communicating with the second device over a short range communication protocol; and

the second data further indicates devices communicating with the second device over the short range communication protocol.

3. The method of claim 1 , further comprising:

receiving audio data representing a user utterance while the user profile is authenticated;

determining an action to be performed in response to the user utterance utilizing data from the user profile based at least in part on the user profile being authenticated; and

causing the action to be performed while the user profile is authenticated.

4. The method of claim 1 , wherein:

the event further includes a predefined device mode of the second device; and

the second data further indicates that a device mode transition has occurred with respect to the second device.

5. The method of claim 1 , wherein:

the event further includes a predefined device state of the third device associated with the second device; and

the second data further indicates that a device state transition of the third device has been detected by the second device.

6. The method of claim 1 , further comprising:

receiving request data for utilizing an application;

determining that the request data is received from a device on which the user profile is authenticated based at least in part on determining to authenticate the user profile; and

enabling use of the application on the device.

7. The method of claim 1 , wherein:

the first data corresponds to speaker identification processing results indicating detection of speech from a user associated with the user profile;

the second data corresponds to audio data representing user speech; and

the event further includes a predefined wake word being detected in the user speech.

8. The method of claim 1 , wherein

determining to authenticate the user profile is based at least in part on the third device having the device type.

9. The method of claim 1 , wherein the environmental change includes detecting presence of a signal from an authentication device within the environment.

10. The method of claim 1 , wherein the sensor data includes audio data associated with an authentication device within the environment.

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 a request to authenticate a user profile based at least in part on first data received at a first device, the first data having a first data type;

determining a second device associated with the first device;

receiving second data from the second device, the second data:

including sensor data generated by one or more sensors in an environment of the second device, the one or more sensors configured to detect environmental changes within the environment;

indicating an event determined by the second device, the event being an environmental change predefined as being associated with profile authentication; and

having a second data type and differs from the first data type;

receiving third data from a third device, the third data indicating detection of the event at the third device;

determining a device type of the third device;

requesting authentication of the user profile at the third device based at least in part on the device type of the third device that detected the event;

associating the event with the user profile; and

determining to authenticate the user profile based at least in part on the sensor data and receiving an indication of the authentication from the third device.

12. The system of claim 11 , wherein:

the event further includes a predefined device communicating with the second device over a short range communication protocol; and

the second data further indicates devices communicating with the second device over the short range communication protocol.

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

receiving audio data representing a user utterance while the user profile is authenticated;

determining an action to be performed responsive to the user utterance utilizing data from the user profile based at least in part on the user profile being authenticated; and

causing the action to be performed while the user profile is authenticated.

14. The system of claim 11 , wherein:

the event further includes a predefined device mode of the second device; and

the second data further indicates that a device mode transition has occurred with respect to the second device.

15. The system of claim 11 , wherein:

the event further includes a predefined device mode of the third device associated with the second device; and

the second data further indicates that a device mode transition of the third device has been detected by the second device.

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

receiving request data for utilizing an application;

determining that the request data is received from a device on which the user profile is authenticated based at least in part on determining to authenticate the user profile; and

enabling use of the application on the device.

17. The system of claim 11 , wherein:

the first data corresponds to speaker identification processing results indicating detection of speech from a user associated with the user profile;

the second data corresponds to audio data representing user speech; and

the event further includes a predefined wake word being detected in the user speech.

18. The system of claim 11 ,

wherein determining to authenticate the user profile is based at least in part on the third device having the device type.

19. The system of claim 11 , wherein the environmental change includes detecting presence of a signal from an authentication device within the environment.

20. The system of claim 11 , wherein the sensor data includes audio data associated with an authentication device within the environment.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 1, 2022
From: PENG, LIZHEN; UPADHYAY, ALOK; CLINE, JASON; GANDHE, ANKUR
To: AMAZON TECHNOLOGIES, INC.
Reel/Frame 060967/0266 →
Continuity (1)
Continuation 16712613 · Dec 12, 2019
References Cited (38)
US 9350717B1 · Siddiqui · 2016 [cited by examiner]
US 9491033B1 · Soyannwo et al. · 2016 [cited by applicant]
US 9781106B1 · Vitus · 2017 [cited by examiner]
US 9876788B1 · Ziraknejad et al. · 2018 [cited by applicant]
US 10027662B1 · Mutagi et al. · 2018 [cited by applicant]
US 10051600B1 · Zhong et al. · 2018 [cited by applicant]
US 10063542B1 · Kao · 2018 [cited by examiner]
US 10498721B1 · Pham · 2019 [cited by examiner]
US 10591969B2 · Agrawal · 2020 [cited by examiner]
US 10902001B1 · Rengasamy et al. · 2021 [cited by applicant]
US 10909983B1 · Peng et al. · 2021 [cited by applicant]
US 11328323B2 · Miller · 2022 [cited by examiner]
US 11437043B1 · Peng · 2022 [cited by examiner]
US 20060120281A1 · Schmidt et al. · 2006 [cited by applicant]
US 20070178882A1 · Teunissen · 2007 [cited by examiner]
US 20090168977A1 · Galvin · 2009 [cited by applicant]
US 20140330560A1 · Venkatesha et al. · 2014 [cited by applicant]
US 20150142438A1 · Dai · 2015 [cited by examiner]
US 20160057139A1 · McDonough · 2016 [cited by examiner]
US 20160094529A1 · Mityagin · 2016 [cited by examiner]
US 20160125879A1 · Lovitt · 2016 [cited by applicant]
US 20160165381A1 · Kapoor et al. · 2016 [cited by applicant]
US 20170134944A1 · Christian · 2017 [cited by examiner]
US 20180190290A1 · Campbell et al. · 2018 [cited by applicant]
US 20180234411A1 · Masiero · 2018 [cited by examiner]
US 20190219976A1 · Giorgi et al. · 2019 [cited by applicant]
US 20190303553A1 · Choiniere · 2019 [cited by examiner]
US 20190325892A1 · Chenier et al. · 2019 [cited by applicant]
US 20190333522A1 · Lesso · 2019 [cited by examiner]
US 20200106776A1 · Ito · 2020 [cited by examiner]
US 20200137046A1 · Sharma · 2020 [cited by examiner]
US 20200258502A1 · Mitchell et al. · 2020 [cited by applicant]
US 20200349966A1 · Konzelmann et al. · 2020 [cited by applicant]
US 20210073362A1 · Alameh · 2021 [cited by examiner]
US 20210136066A1 · Llamas Virgen · 2021 [cited by examiner]
US 20210160335A1 · Bellet et al. · 2021 [cited by applicant]
Office Action for U.S. Appl. No. 16/712,613, mailed Jan. 31, 2022, Peng, “Presence Ground Truth Approximation and Utilization”, 17 pages. [cited by applicant]
Office Action for U.S. Appl. No. 16/712,613, mailed on Oct. 4, 2021, Peng, “Presence Ground Truth Approximation and Utilization”, 33 pages. [cited by applicant]