Granted Patent B1

US 10,867,021 · App. 16/549,619 · Granted Dec 15, 2020

Inventors: John Shelton (San Antonio, TX); Michael Wayne Lester (Fair Oaks Ranch, TX); Debra Randall Casillas (Helotes, TX); Sudarshan Rangarajan (San Antonio, TX); Maland Keith Mortensen (San Antonio, TX)

Assignee: United Services Automobile Association (USAA)

G06F21/32G10L17/24H04L63/0861H04L63/105

Abstract

Claims (50)

1. A computer-implemented method of authenticating a user interacting with an interactive voice response system, comprising:

receiving biometric information of the user, the received biometric information comprising a spoken request from the user to perform a first activity from among a plurality of activities;

generating a voice sample of the user based on the spoken request;

verifying an identity of the user based on the received biometric information and the voice sample of the user, wherein said verifying the identity of the user comprises:

determining that the identity of the user was previously compromised, and

responsive to the determination that the identity of the user was previously compromised, modifying a value of a confidence metric associated with the verification relative to a value of the confidence metric prior to the verification, modifying an access level required by the user for the first activity, and maintaining an access level required by the user for a second activity from among the plurality of activities;

determining an access level of the user based on the modified confidence metric; and

performing the first activity when the access level based on the modified confidence metric of the user meets or exceeds the modified access level required by the user for the first activity.

2. The method of claim 1 , wherein the voice sample of the user is generated further based on spoken information different than the spoken request, and wherein the spoken information that is different than the spoken request comprises a spoken identifier of an account associated with the user.

3. The method of claim 1 , wherein said verifying the identity of the user comprises performing a statistical analysis of the voice sample of the user.

4. The method of claim 1 , wherein the confidence metric corresponds to an averaging of interactions with the interactive voice response system.

5. The method of claim 1 , wherein the received biometric information further comprises at least one non-voice biometric factor.

6. The method of claim 5 , wherein the at least one non-voice biometric factor comprises information regarding an eye movement of the user.

7. The method of claim 6 , further comprising:

prompting the user to look at a display element presented on a display device associated with the user, and

determining the eye movement of the user in response to the prompt of the user to look at the display element.

8. One or more non-transitory computer-readable media including one or more sequences of instructions which, when executed by one or more processors, causes:

receiving biometric information of a user, the received biometric information comprising a spoken request from the user to perform a first activity from among a plurality of activities;

generating a voice sample of the user based on the spoken request;

verifying an identity of the user based on the received biometric information and the voice sample of the user, wherein said verifying the identity of the user comprises:

determining that the identity of the user was previously compromised, and

responsive to the determination that the identity of the user was previously compromised, modifying a value of a confidence metric associated with said verifying relative to a value of the confidence metric prior to said verifying, modifying an access level required by the user for the first activity, and maintaining access level required by the user for a second activity from among the plurality of activities;

determining an access level of the user based on the modified confidence metric; and

performing the first activity when the access level based on the modified confidence metric of the user meets or exceeds the modified access level required by the user for the first activity.

9. The one or more non-transitory computer-readable media of claim 8 , wherein the voice sample of the user is generated further based on spoken information different than the spoken request, and wherein the spoken information that is different than the spoken request comprises a spoken identifier of an account associated with the user.

10. The one or more non-transitory computer-readable media of claim 8 , wherein said verifying the identity of the user comprises performing a statistical analysis of the voice sample of the user.

11. The one or more non-transitory computer-readable media of claim 8 , wherein the confidence metric corresponds to an averaging of interactions with an interactive voice response system.

12. The one or more non-transitory computer-readable media of claim 8 , wherein the received biometric information further comprises at least one non-voice biometric factor.

13. The one or more non-transitory computer-readable media of claim 12 , wherein the at least one non-voice biometric factor comprises information regarding an eye movement of the user.

14. The one or more non-transitory computer-readable media of claim 13 , further comprising:

prompting the user to look at a display element presented on a display device associated with the user, and

determining the eye movement of the user in response to the prompt of the user to look at the display element.

15. A system comprising:

one or more processors;

one or more non-transitory computer-readable media including one or more sequences of instructions which, when executed by the one or more processors, causes:

receiving biometric information of a user, the received biometric information comprising a spoken request from the user to perform a first activity from among a plurality of activities;

generating a voice sample of the user based on the spoken request;

verifying an identity of the user based on the received biometric information and the voice sample of the user, wherein said verifying the identity of the user comprises:

determining that the identity of the user was previously compromised, and

responsive to the determination that the identity of the user was previously compromised, modifying a value of a confidence metric associated with said verifying relative to a value of the confidence metric prior to said verifying, modifying an access level required by the user for the first activity, and maintaining an access level required by the user for a second activity from among the plurality of activities;

determining an access level of the user based on the modified confidence metric; and

performing the first activity when the access level based on the modified confidence metric of the user meets or exceeds the modified access level required by the user for the first activity.

16. The system of claim 15 , wherein the voice sample of the user is generated further based on spoken information different than the spoken request, and wherein the spoken information that is different than the spoken request comprises a spoken identifier of an account associated with the user.

17. The system of claim 15 , wherein said verifying the identity of the user comprises performing a statistical analysis of the voice sample of the user.

18. The system of claim 15 , wherein the confidence metric corresponds to an averaging of interactions with an interactive voice response system.

19. The system of claim 15 , wherein the received biometric information further comprises at least one non-voice biometric factor.

20. The system of claim 19 , wherein the at least one non-voice biometric factor comprises information regarding an eye movement of the user.

21. The system of claim 20 , further comprising:

prompting the user to look at a display element presented on a display device associated with the user, and

determining the eye movement of the user in response to the prompt of the user to look at the display element.

Assignments (1)

Continuity (3)

Cited By (13)

US 12,206,763 US 12,212,959 US 12,284,512 US 12,335,399 US 12,341,790 US 12,388,817 US 12,395,353 US 12,425,230 US 12,438,731 US 12,443,700 US 12,445,305 US 12,499,201 US 12,538,123