Systems and methods for high fidelity multi-modal out-of-band biometric authentication with human cross-checking

Patent metadata

Field	Value
Publication number	US-10628571-B2
Application number	US-201916262015-A
Country	US
Kind code	B2
Filing date	Jan 30, 2019
Priority date	May 8, 2013
Publication date	Apr 21, 2020
Grant date	Apr 21, 2020

Abstract

Systems and methods for high fidelity multi-modal out-of-band biometric authentication with cross-checking are disclosed. According to one embodiment, a method for integrated biometric authentication may include (1) receiving, from a user, biometric data; (2) at least one computer processor performing machine-based biometric matching on the biometric data; (3) the at least one computer processor determining that human identity confirmation is necessary; (4) the at least one computer processor processing the biometric data; (5) the at least one computer processor identifying at least one contact for human identity confirmation; (6) the at least one computer processor sending at least a portion of the processed biometric data for the user to the at least one contact; (7) receiving, from the at least one contact, human confirmation information; and (8) the at least one computer processor authenticating the user based on the machine-based biometric matching and the human confirmation information.

First claim

We claim:

1. A method for integrated authentication, comprising:
in an information processing apparatus comprising at least one computer processor:
receiving, from a user, identifying data;
performing machine-based identity matching on the identifying data;
based on the machine-based matching, determining that human confirmation of the user's identity is necessary;
accessing a connectivity graph stored in memory to identify at least one contact having a connection with the user in the connectivity graph;
identifying a connection and a connectivity score between the identified contact and the user;
returning the connectivity score for the identified connection;
sending at least a portion of the identifying data for the user to the contact based on the connectivity score;
receiving, from the at least one contact, human identity confirmation information; and
the at least one computer processor authenticating the user based on both the machine-based matching and the human identity confirmation information;

wherein the connectivity graph is generated by:
receiving, from a database, a plurality of contacts for the user;
identifying a connection between the user and each of the plurality of contacts;
identifying a connectivity score for each connection;
generating a connectivity graph for the user, wherein each contact is represented as a node in the connectivity graph, and the connections are represented by edges between the nodes, and the edges are associated with their connectivity scores; and
storing the connectivity graph in the memory.

2. The method of claim 1 , wherein the connectivity score is based on at least one of a relationship between the user and the contact, a length of a relationship between the user and the contact, a date of the last in-person interaction between the user and the contact, and a location of the user and the contact.

3. The method of claim 1 , wherein each node is associated with a verification history profile, wherein the verification history profile identifies how successful the contact associated with the node is at identifying humans or spoof attempts.

4. The method of claim 1 , wherein the connection comprises a relationship type.

5. The method of claim 1 , wherein the relationship type comprises at least one of teammates, shared office, shared floor, shared building, family, friend, and no relationship.

6. The method of claim 1 , wherein the database comprises a human resources database identifying business connections with at least some of the contacts.

7. The method of claim 1 , wherein the database comprises a social media database identifying social connections with at least some of the contacts.

8. The method of claim 1 , wherein the connection is unidirectional, and the connectivity score is associated with the direction of the connection.

9. The method of claim 1 , wherein the connection is bidirectional, and each direction is associated with a different connectivity score.

10. The method of claim 1 , further comprising;
updating a verification history profile for the contact based on a result of the machine-based matching.

11. A method for integrated biometric authentication, comprising:
in an information processing apparatus comprising at least one computer processor:
receiving, from a user, biometric data;
performing machine-based biometric matching on the biometric data;
based on the machine-based biometric matching, determining that human confirmation of the user's identity is necessary;
accessing a connectivity graph stored in memory to identify at least one contact having a connection with the user in the connectivity graph;
identifying a connection and a connectivity score between the identified contact and the user;
returning the connectivity score for the identified connection;
sending at least a portion of the biometric data for the user to the contact based on the at least a portion of the biometric data for the user;
receiving, from the at least one contact, human identity confirmation information; and
authenticating the user based on both the machine-based biometric matching and the human identity confirmation information;

wherein the connectivity graph is generated by:
receiving, from a database, a plurality of contacts for the user;
identifying a connection between the user and each of the plurality of contacts;
identifying a connectivity score for each connection; and
generating the connectivity graph for the user, wherein each contact is represented as a node in the connectivity graph, and the connections are represented by edges between the nodes, and the edges are associated with their connectivity scores.

12. The method of claim 11 , further comprising:
weighting the human identity confirmation information based on the connectivity score.

13. The method of claim 11 , wherein the connectivity score is based on at least one of a relationship between the user and the contact, a length of a relationship between the user and the contact, a date of the last in-person interaction between the user and the contact, and a location of the user and the contact.

14. The method of claim 12 , wherein each node is associated with a biometric verification history profile, wherein the biometric verification history profile identifies how successful the contact associated with the node is at identifying humans or spoof attempts.

15. The method of claim 11 , wherein the connection comprises a relationship type, wherein the relationship type comprises at least one of teammates, shared office, shared floor, shared building, family, friend, and no relationship.

16. The method of claim 11 , wherein the database comprises a human resources database identifying business connections with at least some of the contacts.

17. The method of claim 11 , wherein the database comprises a social media database identifying social connections with at least some of the contacts.

18. The method of claim 11 , wherein the step of determining that human confirmation of the user's identity is necessary comprises:
determining a reliability of at least one algorithm in comparing the biometric data to a stored biometric profile of the user; and
initiating human confirmation of the user's identity in response to the reliability of at least one algorithm being below a predetermined threshold.

19. The method of claim 11 , further comprising:
updating a biometric verification history profile for the contact based on a result of the machine-based biometric matching.

Assignees

• Jpmorgan Chase Bank Na

Inventors

• Kursun Eren
• Fernandez Gene
• Berson Alex
• Goodman Brian

Classifications

• G06F21/32 Primary

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

• G06Q30/00

  Commerce · CPC title