IP Library › Granted Patent US 12,657,591
Granted Patent B2
US 12,657,591 · App. 18/373,837 · Granted Jun 16, 2026

Automated billpay based on cross-provider performance information

Inventors: Jim Carlough (San Francisco, CA); Srinivas R. Doki (San Francisco, CA); Debashis Ghosh (Charlotte, NC); Richard Claude Robert Trent (Newton, NC); Jane Turpin (San Francisco, CA)
Assignee: Wells Fargo Bank, N.A.
G06Q20/4016H04L67/535
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 12,657,591
App. No.
18/373,837
Granted
Jun 16, 2026
Kind
B2
Abstract

Systems, methods, and computer-readable storage media for performance indicator operations. One method includes identifying, by one or more processing circuits, user activity data and one or more performance indicators of a user. The method further includes modeling, by the one or more processing circuits, the user activity data and the one or performance indicators to generate a user data structure. The method further includes determining, by the one or more processing circuits, the user data structure causing an update in the one or more performance indicators. The method further includes configuring an actionable activity corresponding to the at least one future activity of the user, wherein the actionable activity is below a user threshold. The method further includes generating and presenting, by the one or more processing circuits, a graphical user interface (GUI) including actionable elements and at least one message associated with the actionable activity.

Claims (95)

1 . A method, comprising:

identifying, by one or more processing circuits, user activity data and one or more performance indicators of a user, wherein user activity data comprises financial activity associated with the user and where a performance indicator is a metric indicative of a creditworthiness of the user;

modeling, by the one or more processing circuits, the user activity data and the one or more performance indicators using one or more machine learning models, wherein the one or more machine learning models are selected based on a type of the user activity data, a type of the one or more performance indicators, and a type of modeling to be performed;

identifying, using the modeled user activity data and the one or more performance indicators, a pattern in the user activity data;

generating, by the one or more processing circuits, using the modeled user activity data, the one or more performance indicators, and the identified pattern, a user data structure, wherein the user data structure is a representation of one or more relationships between two or more of the modeled user activity data, the one or more performance indicators, or the identified pattern;

predicting, by the one or more processing circuits, using the generated user data structure, at least one future activity of the user;

determining, by the one or more processing circuits, the user data structure comprises at least one previous activity of the user that impacts the one or more performance indicators;

determining, by the one or more processing circuits, an actionable activity to be performed based on the at least one previous activity, wherein the actionable activity is performed by a financial institution associated with the user for the user;

configuring, by the one or more processing circuits, the actionable activity to be executed based on the at least one future activity of the user;

generating and presenting, by the one or more processing circuits, a graphical user interface (GUI) comprising at least one actionable element and at least one message associated with the actionable activity; and

executing, by the one or more processing circuits, the actionable activity responsive to a selection of the at least one actionable element by the user.

2 . The method of claim 1 , further comprising:

identifying, by the one or more processing circuits, a plurality of resource allocation authorizations associated with at least two provider computing systems, wherein each of the plurality of resource allocation authorizations correspond to at least one authorization parameter to utilize one or more resources of each of the at least two provider computing systems; and

determining, by the one or more processing circuits, a bundled resource authorization to offer to the user in the GUI, wherein the bundled resource authorization comprises generating one or more new authorization parameters based on the at least one authorization parameter of each of the at least two provider computing systems.

3 . The method of claim 2 , further comprising:

determining, by the one or more processing circuits, one or more authorization parameters common to each other across the plurality of resource allocation authorizations;

determining, by the one or more processing circuits, one or more authorization parameters conflicting with each other across the plurality of resource allocation authorizations; and

modeling, by the one or more processing circuits, the one or more authorization parameters common to each other and the one or more authorization parameters conflicting with each other to generate the one or more new authorization parameters, wherein modeling comprises combining the one or more authorization parameters common to each other and resolving the one or more authorization parameters conflicting with each other based on a set of predefined rules or user-defined preferences.

4 . The method of claim 3 , wherein the one or more processing circuits consolidate the plurality of resource allocation authorizations into the bundled resource authorization that provides a positive impact on the one or more performance indicators by increasing the creditworthiness of the user, and wherein the bundled resource authorization comprises an estimated elimination period for satisfying one or more obligations associated with the plurality of resource allocation authorizations.

5 . The method of claim 1 , further comprising:

monitoring, by the one or more processing circuits, the user activity data and the one or more performance indicators based on continuously receiving new information from a user device of the user and one or more data sources;

determining, by the one or more processing circuits, at least one of:

a discrepancy in the at least one of the user activity data or the one or more performance indicators based on the at least one previous activity of the user;

a violation associated with the actionable activity based on a comparison between the at least one of the user activity data or the one or more performance indicators and an action to take to increase the one or more performance indicators of the user, wherein the comparison identifies an activity counter to the action;

remediating, by the one or more processing circuits, the discrepancy or violation based on at least one of:

presenting, by the one or more processing circuits, an alert on the GUI comprising remediation instructions for the user; and

establishing, by the one or more processing circuits via an application programming interface (API), a communication session with an external system associated with the activity counter to the action and either (1) updating the external system to remove the activity counter to the action or (2) initiating an exchange between an account of the user and the external system.

6 . The method of claim 1 , further comprising:

determining, by the one or more processing circuits, one or more characteristics of the user data structure that cause the impact to the one or more performance indicators;

generating, by the one or more processing circuits, a plan associated with at least one different characteristic to cause an increase to the one or more performance indicators; and

in response to the user performing the at least one different characteristic, providing and presenting a reward in the GUI, wherein the reward enables another feature of the GUI.

7 . The method of claim 1 , further comprising:

determining, by the one or more processing circuits, the at least one previous activity is a fraudulent activity within the user activity data;

automatically removing, by the one or more processing circuits, the fraudulent activity from the user activity data; and

remodeling, by the one or more processing circuits, the user activity data and the one or more performance indicators to generate an updated user data structure.

8 . The method of claim 1 , wherein the at least one future activity of the user is associated with a statement settlement action, the method further comprising:

determining, by the one or more processing circuits, the statement settlement action will cause a negative account balance associated with an account of the user;

updating, by the one or more processing circuits, an automatic exchange associated with the statement settlement action to cause a non-negative account balance associated with the account of the user; and

configuring, by the one or more processing circuits, a different statement settlement action to satisfy the difference between the non-negative account balance and the negative account balance.

9 . The method of claim 1 , wherein the at least one future activity comprises a future exchange event associated with the user, wherein the future exchange event causes a change in the user data structure, and wherein in response to a selection of the at least one actionable element, the future exchange event is automated based on configuring an automatic exchange between an account of the user and an external system.

10 . A system, comprising:

a processing circuit comprising memory and one or more processors, the processing circuit configured to:

identify user activity data and one or more performance indicators of a user, wherein the user activity data comprises financial activity associated with the user and where a performance indicator is a metric indicative of a creditworthiness of the user;

model the user activity data and the one or more performance indicators using one or more machine learning models, wherein the one or more machine learning models are selected based on a type of the user activity data, a type of the one or more performance indicators, and a type of modeling to be performed;

identify, using the modeled user activity data and the one or more performance indicators, a pattern in the user activity data;

generate, using the modeled user activity data, the one or more performance indicators, and the identified pattern, a user data structure, wherein the user data structure is a representation of one or more relationships between two or more of the modeled user activity data, the one or more performance indicators, or the identified pattern;

predict, using the generated user data structure, at least one future activity of the user;

determine the user data structure comprises at least one previous activity of the user that impacts the one or more performance indicators;

determine an actionable activity to be performed based on the at least one previous activity, wherein the actionable activity is performed by a financial institution associated with the user for the user;

configure the actionable activity to be executed based on the at least one future activity of the user;

generate and present a graphical user interface (GUI) comprising at least one actionable element and at least one message associated with the actionable activity; and

execute the actionable activity responsive to a selection of the at least one actionable element by the user.

11 . The system of claim 10 , wherein the memory and the one or more processors are further configured to:

identify a plurality of resource allocation authorizations associated with at least two provider computing systems, wherein each of the plurality of resource allocation authorizations correspond to at least one authorization parameter to utilize one or more resources of each of the at least two provider computing systems; and

determine a bundled resource authorization to offer the user in the GUI, wherein the bundled resource authorization comprises generating one or more new authorization parameters based on the at least one authorization parameter of each of the at least two provider computing systems.

12 . The system of claim 11 , wherein the processing circuit is 12 . Further configured to:

determine one or more authorization parameters common to each other across the plurality of resource allocation authorizations;

determine one or more authorization parameters conflicting with each other across the plurality of resource allocation authorizations; and

model the one or more authorization parameters common to each other and the one or more authorization parameters conflicting with each other to generate the one or more new authorization parameters, wherein modeling comprises combining the one or more authorization parameters common to each other and resolving the one or more authorization parameters conflicting with each other based on a set of predefined rules or user-defined preferences.

13 . The system of claim 12 , wherein the processing circuit is further configured to consolidate the plurality of resource allocation authorizations into the bundled resource authorization that provides a positive impact on the one or more performance indicators by increasing the creditworthiness of the user, and wherein the bundled resource authorization comprises an estimated elimination period for satisfying one or more obligations associated with the plurality of resource allocation authorizations.

14 . The system of claim 10 , wherein the processing circuit is further configured to:

monitor the user activity data and the one or more performance indicators based on continuously receiving new information from a user device of the user and one or more data sources;

determine at least one of:

a discrepancy in the at least one of the user activity data or the one or more performance indicators based on the at least one previous activity of the user;

a violation associated with the actionable activity based on a comparison between the at least one of the user activity data or the one or more performance indicators and an action to take to increase the one or more performance indicators of the user, wherein the comparison identifies an activity counter to the action; and

remediate the discrepancy or violation based on at least one of:

present an alert on the GUI comprising remediation instructions for the user;

establish, via an application programming interface (API), a communication session with an external system associated with the activity counter to the action and either (1) updating the external system to remove the activity counter to the action or (2) initiating an exchange between an account of the user and the external system.

15 . The system of claim 10 , wherein the processing circuit is further configured to:

determine one or more characteristics of the user data structure that cause the impact to the one or more performance indicators;

generate a plan associated with at least one different characteristic to cause an increase to the one or more performance indicators; and

in response to the user performing the at least one different characteristic, provide and present a reward in the GUI, wherein the reward enables another feature of the GUI.

16 . The system of claim 10 , wherein the processing circuit is further configured to:

determine the at least one previous activity is a fraudulent activity within the user activity data;

automatically remove the fraudulent activity from the user activity data; and

remodel the user activity data and the one or more performance indicators to generate an updated user data structure.

17 . The system of claim 10 , wherein the at least one future activity of the user is associated with a statement settlement action, and wherein the processing circuit is further configured to:

determine the statement settlement action will cause a negative account balance associated with an account of the user;

update an automatic exchange associated with the statement settlement action to cause a non-negative account balance associated with the account of the user; and

configure a different statement settlement action to satisfy the difference between the non-negative account balance and the negative account balance.

18 . The system of claim 10 , wherein the at least one future activity comprises a future exchange event associated with the user, wherein the future exchange event causes a change in the user data structure, and wherein in response to a selection of the at least one actionable element, the future exchange event is automated based on configuring an automatic exchange between an account of the user and an external system.

19 . A non-transitory computer-readable storage medium (CRM) having instructions stored thereon that, when executed by at least one processing circuit, cause the at least one processing circuit to perform operations comprising:

identifying user activity data and one or more performance indicators of a user, wherein the user activity data comprises financial activity associated with the user and where a performance indicator is a metric indicative of a creditworthiness of a user;

modeling the user activity data and the one or more performance indicators using one or more machine learning models, wherein the one or more machine learning models are selected based on a type of the user activity data, a type of the one or more performance indicators, and a type of modeling to be performed;

identifying, using the modeled user activity data and the one or more performance indicators, a pattern in the user activity data;

generating, using the modeled user activity data, the one or more performance indicators, and the identified pattern, a user data structure, wherein the user data structure is a representation of one or more relationships between two or more of the modeled user activity data, the one or more performance indicators, or the identified pattern;

predicting, using the generated user data structure, at least one future activity of the user;

determining the user data structure comprises at least one previous activity of the user that impacts the one or more performance indicators;

determining an actionable activity to be performed based on the at least one previous activity, wherein the actionable activity is performed by a financial institution associated with the user for the user;

configuring the actionable activity to be executed based on the at least one future activity of the user;

generating and presenting a graphical user interface (GUI) comprising at least one actionable element and at least one message associated with the actionable activity; and

executing the actionable activity responsive to a selection of the at least one actionable element by the user.

20 . The CRM of claim 19 , wherein the operations further comprise:

identifying a plurality of resource allocation authorizations associated with at least two provider computing systems, wherein each of the plurality of resource allocation authorizations correspond to at least one authorization parameter to utilize one or more resources of each of the at least two provider computing systems; and

determining a bundled resource authorization to offer to the user in the GUI, wherein the bundled resource authorization comprises generating one or more new authorization parameters based on the at least one authorization parameter of each of the at least two provider computing systems.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 31, 2025
From: DOKI, SRINIVAS R.; GHOSH, DEBASHIS; TRENT, RICHARD CLAUDE ROBERT; TURPIN, JANE; CARLOUGH, JIM
To: WELLS FARGO BANK, N.A.
Reel/Frame 070680/0148 →
Continuity (1)
Related Publication 20250104072A1 · Mar 27, 2025
References Cited (19)
US 9443268B1 · Kapczynski et al. · 2016 [cited by applicant]
US 9710852B1 · Olson et al. · 2017 [cited by applicant]
US 11544713B1 · Hansen · 2023 [cited by examiner]
US 12002055B1 · Miller · 2024 [cited by examiner]
US 20090228307A1 · Sorbe · 2009 [cited by examiner]
US 20100094791A1 · Miltonberger · 2010 [cited by examiner]
US 20120116951A1 · Chung et al. · 2012 [cited by applicant]
US 20140258083A1 · Achanta et al. · 2014 [cited by applicant]
US 20150026027A1 · Priess · 2015 [cited by examiner]
US 20170004501A1 · Ledford · 2017 [cited by examiner]
US 20180005230A1 · Zovi · 2018 [cited by examiner]
US 20200257608A1 · Fradkin · 2020 [cited by examiner]
US 20200273040A1 · Novick · 2020 [cited by examiner]
US 20200304592A1 · Park · 2020 [cited by examiner]
US 20200364785A1 · Olson et al. · 2020 [cited by applicant]
US 20210279819A1 · Maheshwari · 2021 [cited by applicant]
US 20220129871A1 · Rodgers · 2022 [cited by examiner]
WO WO2017189114A1 · 2017 [cited by examiner]
Kiley: “Financial Conditions and Economic Activity: Insights from Machine Learning”, FEDS Working Paper No. 2020-95 , Finance and Economics Discussion Series, Federal Reserve Board, Washington, D.C., Nov. 17, 2020 (Year… [cited by examiner]