Multi-user authentication on a device

Patent metadata

Field	Value
Publication number	US-11721326-B2
Application number	US-202217584866-A
Country	US
Kind code	B2
Filing date	Jan 26, 2022
Priority date	Apr 20, 2017
Publication date	Aug 8, 2023
Grant date	Aug 8, 2023

Abstract

In some implementations, processor(s) can receive an utterance from a speaker, and determine whether the speaker is a known user of a user device or not a known user of the user device. The user device can be shared by a plurality of known users. Further, the processor(s) can determine whether the utterance corresponds to a personal request or non-personal request. Moreover, and in response to determining that the speaker is not a known user of the user device and in response to determining that the utterance corresponds to a non-personal request, the processor(s) can cause a response to the utterance to be provided for presentation to the speaker at the user device response to the utterance, or can cause an action to be performed by the user device responsive to the utterance.

First claim

What is claimed is:

1. A method implemented by one or more processors comprising:
receiving an utterance from a speaker at a user device;
determining whether the speaker is a known user of the user device or not a known user of the user device that is shared by a plurality of known users;
determining whether the utterance corresponds to a personal request or non-personal request; and
in response to determining that the speaker is not a known user of the user device and in response to determining that the utterance corresponds to a non-personal request:
causing a response to the utterance to be provided for presentation to the speaker at the user device responsive to the utterance, or
causing an action to be performed by the user device responsive to the utterance.

2. The method of claim 1 , further comprising:
in response to determining that the speaker is not a known user of the user device and in response to determining that the utterance corresponds to a personal request:
causing a no access message to be provided for presentation to the speaker at the user device responsive to the utterance that indicates:
the response to the utterance cannot be provided for presentation to the speaker at the user device responsive to the utterance, or
the action cannot be performed by the user device responsive to the utterance.

3. The method of claim 2 , further comprising:
in response to determining that the speaker is a known user of the user device:
causing a personalized response to the utterance to be provided for presentation to the speaker at the user device responsive to the utterance, the personalized response to the utterance being personalized based on an identity of the speaker, or
causing a personalized action to be performed by the user device responsive to the utterance, the personalized action to be performed being personalized based on an identity of the speaker.

4. The method of claim 1 , wherein determining whether the speaker is a known user of the user device or not a known user of the user device comprises:
classifying, locally at the user device, and based on authentication tokens that correspond to the plurality of known users of the user device, the speaker of the utterance as a known user of the user device or not a known user of a user device based on speaker identification features of the utterance.

5. The method of claim 1 , wherein determining whether the speaker is a known user of the user device or not a known user of the user device comprises:
generating a query that includes at least authentication tokens that correspond to the plurality of known users of the user device and a representation of the utterance;
transmitting the query to a remote server; and
receiving, from the remote server, an indication of whether the speaker is a known user of the user device or not a known user of the user device.

6. The method of claim 1 , wherein determining whether the utterance corresponds to a personal request or non-personal request comprises:
determining whether personal information of one or more of the plurality of known users of the user device is needed to cause the response to be provided or to cause the action to be performed; and
determining that the utterance is a non-personal request in response to determining the personal information of one or more of the plurality of known users of the user device is not needed to cause the response to be provided or to cause the action to be performed.

7. The method of claim 1 , wherein determining whether the utterance corresponds to a personal request or non-personal request comprises:
generating a query that includes at least a representation of the utterance;
transmitting the query to a remote server; and
receiving, from the remote server, an indication of whether the utterance corresponds to a personal request or non-personal request.

8. The method of claim 1 , wherein determining whether the utterance corresponds to a personal request or non-personal request is in response to determining that the speaker is not a known user of the user device.

9. The method of claim 1 , wherein a personal request is dependent on personal information of one or more of the plurality of known users of the user device, and wherein a non-personal request is not dependent on the personal information of any of the plurality of known users of the user device.

10. A user device comprising:
at least one processor; and
memory storing instructions that, when executed, cause the at least one processor to:
receive an utterance from a speaker;
determine whether the speaker is a known user of the user device or not a known user of the user device, the user device being shared by a plurality of known users;
determine whether the utterance corresponds to a personal request or non-personal request; and
in response to determining that the speaker is not a known user of the user device and in response to determining that the utterance corresponds to a non-personal request:
cause a response to the utterance to be provided for presentation to the speaker at the user device responsive to the utterance, or
cause an action to be performed by the user device responsive to the utterance.

11. The user device of claim 10 , wherein the instructions further cause the at least one processor to:
in response to determining that the speaker is not a known user of the user device and in response to determining that the utterance corresponds to a personal request:
cause a no access message to be provided for presentation to the speaker at the user device responsive to the utterance that indicates:
the response to the utterance cannot be provided for presentation to the speaker at the user device responsive to the utterance, or
the action cannot be performed by the user device responsive to the utterance.

12. The user device of claim 11 , wherein the instructions further cause the at least one processor to:
in response to determining that the speaker is a known user of the user device:
cause a personalized response to the utterance to be provided for presentation to the speaker at the user device responsive to the utterance, the personalized response to the utterance being personalized based on an identity of the speaker, or
cause a personalized action to be performed by the user device responsive to the utterance, the personalized action to be performed being personalized based on an identity of the speaker.

13. The user device of claim 10 , wherein the instructions to determine whether the speaker is a known user of the user device or not a known user of the user device comprise instructions to:
classify, locally at the user device, and based on authentication tokens that correspond to the plurality of known users of the user device, the speaker of the utterance as a known user of the user device or not a known user of a user device based on speaker identification features of the utterance.

14. The user device of claim 10 , wherein the instructions to determine whether the speaker is a known user of the user device or not a known user of the user device comprise instructions to:
generate a query that includes at least authentication tokens that correspond to the plurality of known users of the user device and a representation of the utterance;
transmit the query to a remote server; and
receive, from the remote server, an indication of whether the speaker is a known user of the user device or not a known user of the user device.

15. The user device of claim 10 , wherein the instructions to determine whether the utterance corresponds t

Assignees

• Google Llc

Inventors

• Oktem Meltem
• Joglekar Taral Pradeep
• Heryandi Fnu
• Chao Pu-Sen
• Lopez Moreno Ignacio
• Rajadhyaksha Salil
• Gruenstein Alexander H
• Melendo Casado Diego

Classifications

• G06F3/167 Primary

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

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G06F21/32

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

• G10L15/08 Primary

  Speech classification or search · CPC title

• G06F16/636

  by using biological or physiological data · CPC title