IP Library Granted Patent US 12,339,987
Granted Patent B2
US 12,339,987 · App. 18/307,635 · Granted Jun 24, 2025

Automated machine learning access rights engine

Inventors: Alejandro J. Carao (Atlanta, GA); Robert William Childress (Peoria, AZ); Donnell Douglas (Charlotte, NC); Jaisimha L. Gyanmote (Buffalo Grove, IL); Jonathan Wayne Ingram (Covington, WA); Gokarna KC (Concord, NC); Naresh Kumar Koppuravuri (Hyderabad, IN); Suki Ramasamy (Chennai, IN); Tara R. Ross (Norwalk, IA); Vijay Talupula (YSR Kadapa District, IN)
Assignee: Wells Fargo Bank, N.A.
G06F21/6218
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,339,987
App. No.
18/307,635
Granted
Jun 24, 2025
Kind
B2
Abstract

A method may include accessing digital characteristics associated with a user identifier, the digital characteristics including a task identifier assigned to the user identifier; encoding the digital characteristics into components of an input vector, the components of the input vector corresponding to inputs of a machine learning model; inputting the input vector into the machine learning model; executing the machine learning model; subsequent to the executing, accessing an output of the machine learning model, the output corresponding to a cluster identifier associated with a plurality of user identifiers with similar digital characteristics; and automatically transmitting a request to change a resource access right for the user identifier based on access rights associated with the cluster identifier.

Claims (92)

1. A method comprising:

accessing digital characteristics associated with a user identifier, the digital characteristics including a task identifier assigned to the user identifier;

encoding the digital characteristics into components of an input vector, the components of the input vector corresponding to inputs of a machine learning model;

inputting the input vector into the machine learning model;

executing the machine learning model;

subsequent to the executing, accessing an output of the machine learning model, the output corresponding to a cluster identifier associated with a plurality of user identifiers with similar digital characteristics;

determining a difference between current access rights of the user identifier and the access rights associated with the cluster identifier, the difference indicating the user identifier is not authorized to access to a resource that is authorized with respect to the cluster identifier; and

automatically transmitting a request to change a resource access right for the user identifier based on access rights associated with the cluster identifier, wherein automatically transmitting includes:

generating a change access right electronic message that includes:

an identification of the resource;

the user identifier; and

a link to approve the request;

transmitting the change access right electronic message to a user authorized to approve the request;

generating a change access right electronic message application programming interface (API) call, the API call including parameters of:

the identification of the resource;

the user identifier; and

a request to authorize the user identifier to access the resource; and

transmitting the API call.

2. The method of claim 1 , further comprising:

receiving an indication of an update access rights trigger event;

in response to receiving the indication, accessing second digital characteristics associated with the user identifier;

encoding the second digital characteristics into components of a second input vector,

inputting the second input vector into the machine learning model;

executing the machine learning model;

subsequent to the executing, accessing a second output of the machine learning model, the second output corresponding to a second cluster identifier associated with a plurality of user identifiers with similar digital characteristics; and

automatically transmitting a second request to change a second resource access right for the user identifier based on access rights associated with the second cluster identifier.

3. The method of claim 2 , wherein the update access rights trigger event is the user identifier being added to an email distribution list.

4. The method of claim 2 , wherein the digital characteristics include a role of the user identifier, and wherein the update access rights trigger event is a change in role.

5. The method of claim 2 , wherein the update access rights trigger event is a change in location of a meeting in an event associated with the user identifier.

6. The method of claim 5 , wherein automatically transmitting the second request to change the second resource access right for the user identifier based on access rights associated with the second cluster identifier includes transmitting a request for physical access to a building.

7. A non-transitory computer-readable medium comprising instructions, which when executed by a processing unit, configure the processing unit to perform operations comprising:

accessing digital characteristics associated with a user identifier, the digital characteristics including a task identifier assigned to the user identifier;

encoding the digital characteristics into components of an input vector, the components of the input vector corresponding to inputs of a machine learning model;

inputting the input vector into the machine learning model;

executing the machine learning model;

subsequent to the executing, accessing an output of the machine learning model, the output corresponding to a cluster identifier associated with a plurality of user identifiers with similar digital characteristics;

determining a difference between current access rights of the user identifier and the access rights associated with the cluster identifier, the difference indicating the user identifier is not authorized to access to a resource that is authorized with respect to the cluster identifier; and

automatically transmitting a request to change a resource access right for the user identifier based on access rights associated with the cluster identifier, wherein automatically transmitting includes:

generating a change access right electronic message that includes:

an identification of the resource;

the user identifier; and

a link to approve the request;

transmitting the change access right electronic message to a user authorized to approve the request;

generating a change access right electronic message application programming interface (API) call, the API call including parameters of:

the identification of the resource;

the user identifier; and

a request to authorize the user identifier to access the resource; and

transmitting the API call.

8. The non-transitory computer-readable medium of claim 7 , wherein the instructions, which when executed by the processing unit, further configure the processing unit to perform operations comprising:

receiving an indication of an update access rights trigger event;

in response to receiving the indication, accessing second digital characteristics associated with the user identifier;

encoding the second digital characteristics into components of a second input vector,

inputting the second input vector into the machine learning model;

executing the machine learning model;

subsequent to the executing, accessing a second output of the machine learning model, the second output corresponding to a second cluster identifier associated with a plurality of user identifiers with similar digital characteristics; and

automatically transmitting a second request to change a second resource access right for the user identifier based on access rights associated with the second cluster identifier.

9. The non-transitory computer-readable medium of claim 8 , wherein the update access rights trigger event is the user identifier being added to an email distribution list.

10. The non-transitory computer-readable medium of claim 8 , wherein the digital characteristics include a role of the user identifier, and wherein the update access rights trigger event is a change in role.

11. The non-transitory computer-readable medium claim 8 , wherein the update access rights trigger event is a change in location of a meeting in an event associated with the user identifier.

12. The non-transitory computer-readable medium of claim 11 , wherein automatically transmitting the second request to change the second resource access right for the user identifier based on access rights associated with the second cluster identifier includes transmitting a request for physical access to a building.

13. A system comprising:

a hardware processing unit; and

a storage device comprising instructions, which when executed at the processing unit, configure the processing unit to perform operations comprising:

accessing digital characteristics associated with a user identifier, the digital characteristics including a task identifier assigned to the user identifier;

encoding the digital characteristics into components of an input vector, the components of the input vector corresponding to inputs of a machine learning model;

inputting the input vector into the machine learning model;

executing the machine learning model;

subsequent to the executing, accessing an output of the machine learning model, the output corresponding to a cluster identifier associated with a plurality of user identifiers with similar digital characteristics;

determining a difference between current access rights of the user identifier and the access rights associated with the cluster identifier, the difference indicating the user identifier is not authorized to access to a resource that is authorized with respect to the cluster identifier; and

automatically transmitting a request to change a resource access right for the user identifier based on access rights associated with the cluster identifier, wherein automatically transmitting includes:

generating a change access right electronic message that includes:

an identification of the resource;

the user identifier; and

a link to approve the request;

transmitting the change access right electronic message to a user authorized to approve the request;

generating a change access right electronic message application programming interface (API) call, the API call including parameters of:

the identification of the resource;

the user identifier; and

a request to authorize the user identifier to access the resource; and

transmitting the API call.

14. The system of claim 13 , wherein the instructions, which when executed by the processing unit, further configure the processing unit to perform operations comprising:

receiving an indication of an update access rights trigger event;

in response to receiving the indication, accessing second digital characteristics associated with the user identifier;

encoding the second digital characteristics into components of a second input vector,

inputting the second input vector into the machine learning model;

executing the machine learning model;

subsequent to the executing, accessing a second output of the machine learning model, the second output corresponding to a second cluster identifier associated with a plurality of user identifiers with similar digital characteristics; and

automatically transmitting a second request to change a second resource access right for the user identifier based on access rights associated with the second cluster identifier.

15. The system of claim 14 , wherein the update access rights trigger event is the user identifier being added to an email distribution list.

16. The system of claim 14 , wherein the digital characteristics include a role of the user identifier, and wherein the update access rights trigger event is a change in role.

17. The system of claim 14 , wherein the update access rights trigger event is a change in location of a meeting in an event associated with the user identifier.

18. The method of claim 17 , wherein automatically transmitting the second request to change the second resource access right for the user identifier based on access rights associated with the second cluster identifier includes transmitting a request for physical access to a building.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 24, 2023
From: CARAO, ALEJANDRO J; CHILDRESS, ROBERT WILLIAM; DOUGLAS, DONNELL; GYANMOTE, JAISIMHA L; INGRAM, JONATHAN W; KC, GOKARNA; KOPPURAVURI, NARESH KUMAR; RAMASAMY, SUKI; ROSS, TARA R; TALUPULA, VIJAY
To: WELLS FARGO BANK, N.A.
Reel/Frame 064699/0557 →
Continuity (1)
Related Publication 20240362352A1 · Oct 31, 2024
References Cited (24)
US 10482268B1 · Osborne et al. · 2019 [cited by applicant]
US 11010488B2 · Roden et al. · 2021 [cited by applicant]
US 11115421B2 · Nevatia et al. · 2021 [cited by applicant]
US 11120150B2 · Ravizza et al. · 2021 [cited by applicant]
US 11210418B2 · Stockert et al. · 2021 [cited by applicant]
US 11316864B2 · Asher et al. · 2022 [cited by applicant]
US 11394719B2 · Vegulla et al. · 2022 [cited by applicant]
US 11457015B2 · Carnahan et al. · 2022 [cited by applicant]
US 20200137150A1 · Chatley · 2020 [cited by examiner]
US 20200287904A1 · Asher · 2020 [cited by examiner]
US 20200358784A1 · Khaund · 2020 [cited by applicant]
US 20210027181A1 · Roden et al. · 2021 [cited by applicant]
US 20210160244A1 · Carnahan · 2021 [cited by examiner]
US 20210216893A1 · Roden et al. · 2021 [cited by applicant]
US 20210303360A1 · Rishabh et al. · 2021 [cited by applicant]
US 20210383008A1 · Manasse et al. · 2021 [cited by applicant]
US 20220255796A1 · Smith · 2022 [cited by examiner]
KR 20220046870 · 2022 [cited by applicant]
WO 2022112346 · 2022 [cited by applicant]
“Overview of Role Recommendations”, [Online]. Retrieved from the Internet: https: cloud.google.com policy-intelligence docs role-recommendations-overview, 20 pgs. [cited by applicant]
Frehn, Jacob, “Leveraging Machine Learning for Behavior Based Access Control”, [Online]. Retrieved from the Internet: https: www.portnox.com blog network-access-control leveraging-machine-learning-for-bbac , (Jun. 14, 2… [cited by applicant]
Jones, Isa, “How Machine Learning Is Changing Access Monitoring”, [Online]. Retrieved from the Internet: https: www.healthcareinfosecurity.com blogs how-machine-learning-changing-access-monitoring-p-3243?highlight=true,… [cited by applicant]
McDougald, Damon, “Rbac, you're about to get even better”, [Online]. Retrieved from the Internet: https: www.accenture.com us-en blogs security role-based-access-control, (Nov. 4, 2021), 2 pgs. [cited by applicant]
Thiago, Ferraz, “AI and Machine Learning Applied to Identity and Access Management”, [Online]. Retrieved from the Internet: https: www.linkedin.com pulse ai-machine-learning-aplicados-gest%C3%A30-de-identidades-e-thiago… [cited by applicant]