Relative and dynamic multifactor authentication

• US 10,303,869 B1
• Filed: 04/17/2015
• Issued: 05/28/2019
• Est. Priority Date: 04/17/2015
• Status: Active Grant

• Current Assignee: Wells Fargo Bank NA (Wells Fargo & Company)
• Original Assignee: Wells Fargo Bank NA (Wells Fargo & Company)
• Inventors: Duke, Michael T, Eidam, Kourtney, Clausen, Christopher P., Suen, Darrell L., Kao, Melody
• Primary Examiner(s): Nguyen, Trong H
• Assistant Examiner(s): Lin, Amie C.
• Application Number:
  US14/689,606
• Time in Patent Office: 1,502 Days
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 21/34 involving the use of external additional devices, e.g. dongles or smart cards
• CPC Class Codes: G06F 21/36 by graphic or iconic representation

Abstract

Provided is relative multifactor authentication for interactions between users and one or more entities. Relative multifactor authentication includes monitoring a set of attributes associated with a user during an interaction between the user and the entity. The set of attributes include at least two of a behavioral attribute, a health attribute, a geospatial attribute, and a device attribute. Relative multifactor authentication also include comparing respective parameters of attributes of the set of attributes with expected parameters and determining an authentication status based on the comparison and weighted values assigned to respective attributes of the set of attributes. The user is selectively authenticated to begin to continue the interaction based on the authentication status.

Claims

1. A system, comprising:

at least one hardware processor that executes the following computer executable components stored in a memory;

an observation component that monitors a set of attributes associated with a user during an interaction between the user and an entity;

an evaluation component that compares respective parameters of attributes of the set of attributes obtained continuously during the interaction with expected parameters;

an analysis component that determines an authentication status of the user based on the comparison and weighted values dynamically assigned to respective attributes of the set of attributes based on a type of the interaction and an observed condition of the user during the interaction;

a context component configured to determine context through cognitive and semantic analytic analysis and populate a context weighting database with context situations, ratings, and potential associations; and

an authentication component that selectively authenticates the user as a function of the authentication status and based on a determination that a sum of the weighted values is within a threshold range of values, dynamically provides an incentive to the user upon completing an authentication condition associated with the interaction, wherein the function is based at least in part on an authentication nominal variance, said authentication nominal variance computed continually from a multifactor combination of the weighted values, and the authentication nominal variance is context weighted.

2. The system of claim 1, wherein the set of attributes comprise a behavioral pattern attribute and a health attribute.

3. The system of claim 1, wherein the analysis component sets the authentication status to verified when the authentication nominal variance is within a threshold range.

4. The system of claim 1, wherein the analysis component sets the authentication status to unverified when the authentication nominal variance is outside a threshold range.

5. The system of claim 1, further comprising an assessment module that prompts the user for additional information or instructs the user to take an additional action based on the sum of the weighted values being outside a range of the authentication nominal variance.

6. The system of claim 1, wherein the weighted values are selected based on a type of interaction between the user and the entity, a parameter associated with an interaction, a condition associated with the user, or combinations thereof.

7. The system of claim 1, further comprising an impact module that determines influences that respective attributes or respective categories of attributes have on the authentication nominal variance.

8. The system of claim 1, wherein the set of attributes are captured by respective external devices associated with the user and communicated to the observation component.

9. The system of claim 8, wherein an external device of the respective external devices is a wearable device that monitors biological data, health data, or both biological data and health data.

10. The system of claim 8, wherein an external device of the respective external devices is a carrying device that monitors device data.

11. The system of claim 8, wherein an external device of the respective external device is a traveling device that monitors geospatial data.

12. A method, comprising:

comparing, by a system comprising at least one hardware processor, a set of parameters obtained at substantially the same time as an interaction between a user and an entity with historical parameters, wherein parameters of the set of parameters are obtained continuously during the interaction;

determining, by a context component of the system, context through cognitive and semantic analytic analysis and populating a context weighting database with context situations, ratings, and potential associations;

dynamically applying, by the system, respective weighted values to the parameters of the set of parameters as a function of a type of the interaction and an observed condition of the user during the interaction, wherein the function is based at least in part on an authentication nominal variance, said authentication nominal variance computed continually from a multifactor combination of the weighted values, and the authentication nominal variance is context weighted; and

based on a determination that a sum of the weighted values is within a threshold range of values, verifying an identity of the user, continuing the interaction and dynamically providing an incentive to the user upon completing an authentication condition associated with the interaction; and

based on a determination that the sum of the weighted values is outside the threshold range of values, temporarily suspending the interaction, and requesting additional authentication criteria from the user.

13. The method of claim 12, wherein the comparing comprises receiving a first parameter related to a health attribute and a second parameter related to a behavioral attribute.

14. The method of claim 12, wherein the comparing comprises receiving a first parameter related to a health attribute, a second parameter related to a geospatial attribute, and a third parameter related to a device attribute.

15. The method of claim 12, wherein the comparing comprises accessing one or more historical parameters obtained during a previous verified encounter with the user.

16. The method of claim 12, further comprising dynamically rewarding the user based on approval of a determined level of authentication.

17. The method of claim 12, wherein the applying comprises using a rule-based pattern to selectively alter the weighted values based on an interaction condition, a user condition, a current context, or combinations thereof.

18. A computer-readable storage device storing executable instructions that, in response to execution, cause a system comprising at least one hardware processor to perform operations, comprising:

monitoring a set of attributes associated with a user during an interaction between the user and an entity, wherein the set of attributes comprise at least two of a behavioral attribute, a health attribute, a geospatial attribute, and a device attribute;

determining context through cognitive and semantic analytic analysis and populating a context weighting database with context situations, ratings, and potential associations;

comparing respective parameters of attributes of the set of attributes obtained continuously during the interaction with expected parameters;

determining an authentication status based on the comparison and weighted values dynamically assigned to respective attributes of the set of attributes based on a type of the interaction and an observed condition of the user during the interaction, wherein the determining of the authentication status is based at least in part on an authentication nominal variance, said authentication nominal variance computed continually from a multifactor combination of the weighted values, and the authentication nominal variance is context weighted;

selectively authenticating the user based on the authentication status and based on a determination that a sum of the weighted values is within a threshold range of values; and

dynamically providing an incentive to the user upon completing an authentication condition associated with the interaction.

19. The computer-readable storage device of claim 18, the operations further comprise changing an assignment of respective weighted values based on at least one of an interaction type, an interaction parameter, and a user parameter.

20. The computer-readable storage device of claim 18, the operations further comprise establishing the weighted values based on a rule-based parameter.