Method and electronic device for authenticating user by using voice command

Patent metadata

Field	Value
Publication number	US-11960582-B2
Application number	US-201815733390-A
Country	US
Kind code	B2
Filing date	Dec 10, 2018
Priority date	Jan 17, 2018
Publication date	Apr 16, 2024
Grant date	Apr 16, 2024

Abstract

Various embodiments of the present invention relate to a method and an electronic device for authenticating a user by using a voice command. Here, the electronic device may comprise a memory, an input apparatus, and a processor, wherein the processor is configured to: receive a voice command from the input apparatus; acquire user identification information and voice print information from the voice command; search reference voice print information of each of multiple users stored in the memory, for reference voice print information corresponding to the acquired user identification information; and perform authentication on the basis of the acquired voice print information and the reference voice print information. Other embodiments are also possible.

First claim

The invention claimed is:

1. An electronic device comprising:
a memory;
an input device; and
a processor,
wherein the processor is configured to:
receive a voice command of a first user from the input device;
acquire an identifier indicating the first user and voice print information of the first user from the received voice command;
search a first reference voice print information including the identifier of the first user from among a plurality of pieces of reference voice print information stored in the memory, wherein the plurality of pieces of reference voice information include identifiers of a plurality of users including the first user, and are generated by the first user;
perform authentication on the basis of a comparison between the acquired voice print information and the first reference voice print information;
based on the authentication failing, retrieve second reference voice print information from among the plurality of pieces of reference voice print information, wherein the second reference voice print information includes another identifier indicating a second user and is generated by the first user; and
perform authentication of the first user based on a comparison between the acquired voice print information and the second reference voice print information,
wherein the second reference voice print information is acquired from a previous voice command of the first user received in a state of successful authentication and stored in the memory.

2. The electronic device of claim 1 , further comprising at least one of a display device and a sound output device,
wherein the processor is configured to:
determine a matching ratio by comparing the acquired voice print information with the first reference voice print information or the second reference voice print information;
when the matching ratio correspond to a first designated range, determine that authentication succeeds, and
refine the reference voice print information about each of the plurality of users on the basis of the voice print information acquired from the received voice command.

3. The electronic device of claim 2 , wherein, when the matching ratio corresponds to a second designated range, the electronic device is configured to output an additional speech request message through at least one of the display device and the sound output device.

4. The electronic device of claim 3 , wherein the additional speech request message comprises guide information regarding an additional speech.

5. The electronic device of claim 3 , wherein the processor is configured to:
when the matching ratio corresponds to a third designated ratio, search voice print information of another user regarding the acquired user identification information; and
identify a user speaking the voice command on the basis of the acquired voice print information and the voice print information of another user.

6. The electronic device of claim 5 , wherein, when the matching ratio corresponds to the third designated range, the processor is configured to output a message comprising at least one of a user authentication failure and information indicating the identified user.

7. The electronic device of claim 1 , wherein, when a length of the received voice command is shorter than a designated length, the processor is configured to output an additional speech request message through at least one of a display device and a sound output device, and
wherein the additional speech request message comprises guide information regarding an additional speech.

8. The electronic device of claim 1 , further comprising at least one of a display device and a sound output device,
wherein the processor is configured to:
determine whether there exists the user identification information in the received voice command;
when there does not exist the user identification information in the received voice command, output an additional speech request message regarding a voice command comprising the user identification information through at least one of the display device and the sound output device; and
in response to the additional speech request message regarding the voice command, receive a voice command comprising the user identification information through the input device.

9. The electronic device of claim 1 , wherein the processor is configured to determine whether the voice command received from the input device requires authentication, on the basis of whether the received voice command corresponds to at least one of a voice command requesting execution of a new service, a voice command comprising a pre-designated text, a voice command related to a service requiring security, a voice command requiring connection with an account of a specific user, or a voice command comprising an identification word.

10. The electronic device of claim 1 , wherein the processor is configured to:
detect a user authentication information registration event;
acquire user account information;
acquire user identification information and reference voice print information from a voice command for the user authentication information registration; and
store the user identification information and the reference voice print information acquired from the voice command for the user authentication information registration in the memory as authentication information regarding the user account information.

11. The electronic device of claim 10 , wherein the processor is configured to detect the user authentication information registration event on the basis of at least one of detection of an unregistered identification word, detection of an unregistered user, detection of a voice command to request registration, a request from an external electronic device, a user input through the input device, and a user input through a display device.

12. An operating method of an electronic device, the method comprising:
receiving a voice command of a first user through an input device;
acquiring an identifier indicating the first user and voice print information of the first user from the received voice command;
searching a first reference voice print information including the identifier of the first user from among a plurality of pieces of reference voice print information stored in a memory, wherein the plurality of pieces of reference voice information include identifiers of a plurality of users including the first user, and are generated by the first user; a plurality of users; and
performing authentication on the basis of a comparison between the acquired voice print information and the first reference voice print information;
based on the authentication failing, retrieving second reference voice print information from among the plurality of pieces of reference voice print information, wherein the second reference voice print information includes another identifier indicating a second user and is generated by the first user; and
performing authentication of the first user based on a comparison between the acquired voice print information and the second reference voice print information,
wherein the second reference voice print information is acquired from a previous voice command of the first user received in a state of successful authentication and stored in the memory.

13. The method of claim 12 , wherein performing the first authentication or a second authentication comprises:
determining a matching ratio by comparing the acquired voice print information with the first reference voice print information or the second reference voice print information;
when the matching ratio correspond to a first designated range, determining that

Assignees

• Samsung Electronics Co Ltd

Inventors

• Lee Boram
• Lee Woohyoung
• Chun Taeksoo
• Kim Sunah
• Kim Yongho
• Cho Kyoungsun
• Joo Gahyun

Classifications

• G06F21/32 Primary

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

• G06F21/45

  Structures or tools for the administration of authentication · CPC title

• G06V40/50

  Maintenance of biometric data or enrolment thereof · CPC title

• G10L15/04

  Segmentation; Word boundary detection · CPC title

• G10L15/22

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