Granted Patent B2

US 12,380,186 · App. 18/214,368 · Granted Aug 5, 2025

Inventors: Dinesh Kumar Agrawal (McKinney, TX); Gilbert M. Gatchalian (Union, NJ); Steven Greene (Scarsdale, NY); Richard Scot (Huntersville, NC); Sanjay Lohar (Charlotte, NC); Benjamin F. Tweel (Romeoville, IL); James Siekman (Charlotte, NC); Erik Dahl (Newark, DE); Vijaya L. Vemireddy (Plano, TX)

Assignee: Bank of America Corporation

G06F21/316G06F2221/2133

Abstract

Claims (48)

1. A computing platform, comprising:

one or more processors;

a communication interface communicatively coupled to the one or more processors; and

memory storing computer-readable instructions that, when executed by the one or more processors, cause the computing platform to:

receive, via the communication interface, from a computing device of a user, identity information associated with the user, wherein the identity information includes cadence patterns associated with the user;

store, in a database, the identity information associated with the user;

receive, via the communication interface, an input from the computing device of the user;

determine an input pattern of the received input, wherein the input pattern of the user includes cadence patterns associated with the received input;

compare, using a machine learning model, the input pattern of the received input to one or more input patterns corresponding to a human and one or more input patterns corresponding to a machine;

further compare a background noise portion of the received input to background noise associated with a human user and a non-human user stored in the database;

based on these comparisons, determine whether the user is a human user or a non-human user;

responsive to determining that the user is a non-human user, transmit, to the computing device of the user, a request to the user to provide increased authentication credentials, wherein the increased authentication credentials include authentication credentials different from standard authentication credentials; and

responsive to determining that the user is a human user, verify an identity of the user by comparing the input pattern of the received input to the identity information stored in the database.

2. The computing platform of claim 1 , wherein determining whether the user is a human user or a non-human user includes identifying deviations of the input pattern of the received input from the one or more input patterns corresponding to a human by a predetermined threshold.

3. The computing platform of claim 1 , responsive to the input pattern of the received input matching the one or more input patterns corresponding to a human, validating the user as a human user.

4. The computing platform of claim 1 , wherein the computing device of the user includes a telephone.

5. The computing platform of claim 1 , wherein determining the input pattern of the received input includes identifying an input speed associated with the received input.

6. The computing platform of claim 1 , wherein the cadence patterns include cadence of one or more of: voice input, key input, mouse input, or handwriting input.

7. The computing platform of claim 1 , wherein determining whether the user is a human user or a non-human user includes performing a callback to the computing device of the user using a pre-registered phone number associated with the user.

8. The computing platform of claim 1 , wherein transmitting the request to the user to provide increased authentication credentials includes prompting the user to answer a series of increasingly detailed questions to confirm user identity.

9. A method, comprising:

at a computing platform comprising at least one processor, a communication interface, and memory:

receiving, by the at least one processor, via the communication interface, from a computing device of a user, identity information associated with the user, wherein the identity information includes cadence patterns associated with the user;

storing, by the at least one processor, in a database, the identity information associated with the user; receiving, by the at least one processor, via the communication interface, an input from the computing device of the user;

determining, by the at least one processor, an input pattern of the received input, wherein the input pattern of the user includes cadence patterns associated with the received input;

comparing, by the at least one processor, using a machine learning model, the input pattern of the received input to one or more input patterns corresponding to a human and one or more input patterns corresponding to a machine;

further comparing a background noise portion of the received input to background noise associated with a human user and a non-human user stored in the database;

based on these comparisons, determining, by the at least one processor, whether the user is a human user or a non-human user;

responsive to determining that the user is a non-human user, transmitting, by the at least one processor, to the computing device of the user, a request to the user to provide increased authentication credentials, wherein the increased authentication credentials include authentication credentials different from standard authentication credentials; and

responsive to determining that the user is a human user, verifying, by the at least one processor, an identity of the user by comparing the input pattern of the received input to the identity information stored in the database.

10. The method of claim 9 , wherein determining whether the user is a human user or a non-human user includes identifying, by the at least one processor, deviations of the input pattern of the received input from the one or more input patterns corresponding to a human by a predetermined threshold.

11. The method of claim 9 , further comprising: responsive to the input pattern of the received input matching the one or more input patterns corresponding to a human, validating, by the at least one processor, the user as a human user.

12. The method of claim 9 , wherein the computing device of the user includes a telephone.

13. The method of claim 9 , wherein determining the input pattern of the received input includes identifying, by the at least one processor, an input speed associated with the received input.

14. The method of claim 9 , wherein the cadence patterns include cadence of one or more of: voice input, key input, mouse input, or handwriting input.

15. The method of claim 9 , wherein determining whether the user is a human user or a non-human user includes performing, by the at least one processor, a callback to the computing device of the user using a pre-registered phone number associated with the user.

16. The method of claim 9 , wherein transmitting the request to the user to provide increased authentication credentials includes prompting, by the at least one processor, the user to answer a series of increasingly detailed questions to confirm user identity.

17. One or more non-transitory computer-readable media storing instructions that, when executed by a computing platform comprising at least one processor, memory, and a communication interface, cause the computing platform to:

receive, via the communication interface, from a computing device of a user, identity information associated with the user, wherein the identity information includes cadence patterns associated with the user;

store, in a database, the identity information associated with the user;

receive, via the communication interface, an input from the computing device of the user;

determine an input pattern of the received input, wherein the input pattern of the user includes cadence patterns associated with the received input;

compare, using a machine learning model, the input pattern of the received input to one or more input patterns corresponding to a human and one or more input patterns corresponding to a machine;

further compare a background noise portion of the received input to background noise associated with a human user and a non-human user stored in the database;

based on these comparisons, determine whether the user is a human user or a non-human user;

responsive to determining that the user is a non-human user, transmit, to the computing device of the user, a request to the user to provide increased authentication credentials, wherein the increased authentication credentials include authentication credentials different from standard authentication credentials; and

responsive to determining that the user is a human user, verify an identity of the user by comparing the input pattern of the received input to the identity information stored in the database.

18. The one or more non-transitory computer-readable media of claim 17 , wherein the cadence patterns include cadence of one or more of: voice input, key input, mouse input, or handwriting input.

Assignments (1)

Continuity (1)

References Cited (36)