IP Library Granted Patent US 12,236,384
Granted Patent B1
US 12,236,384 · App. 17/809,147 · Granted Feb 25, 2025

Model automation

Inventors: Samuel Sender-Levi Ring (San Francisco, CA); Joel Toms (San Francisco, CA)
Assignee: Wells Fargo Bank, N.A.
G06Q10/067
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 12,236,384
App. No.
17/809,147
Granted
Feb 25, 2025
Kind
B1
Abstract

An example system can include: at least one processor; and non-transitory computer-readable storage storing instructions that, when executed by the at least one processor, cause the system to: generate a configuration manager programmed to configure a workstream including a plurality of models, wherein the workstream defines metadata associated with execution of each of the plurality of models; generate an execution manager programmed to execute each of the plurality of models in the workstream according to the metadata; and generate a results manager programmed to access results of the execution of the workstream.

Claims (36)

1. A system, comprising:

at least one processor; and

non-transitory computer-readable storage storing instructions that, when executed by the at least one processor, cause the system to:

generate a configuration manager programmed to configure a workstream including a plurality of models, wherein the workstream defines metadata associated with execution of each of the plurality of models;

generate an execution manager programmed to execute each of the plurality of models in the workstream according to the metadata; and

generate a results manager programmed to access results of the execution of the workstream;

wherein the configuration manager is programmed to define a visual depiction of the workstream showing each of the plurality of models and model dependencies associated therewith; and

wherein the visual depiction includes a legend providing source information for the plurality of models depicted on the visual depiction.

2. The system of claim 1 , wherein the execution manager is further programmed to programmatically execute a model of the plurality of models in the workstream.

3. The system of claim 2 , wherein the model is a legacy model configured for manual execution.

4. The system of claim 2 , wherein the execution manager includes a plurality of model runner nodes, wherein each of the plurality of model runner nodes is programmed to execute a different type of the plurality of models.

5. The system of claim 1 , wherein the configuration manager defines an acyclic construction of the model dependencies.

6. The system of claim 1 , wherein the configuration manager is programmed to allow a first model to be added to the workstream and a second model to be removed from the workstream.

7. The system of claim 1 , wherein the configuration manager visually maps each upstream model and each downstream model for the plurality of models in the workstream.

8. The system of claim 1 , comprising further instructions that, when executed by the at least one processor, cause the system to define a versioning for the workstream.

9. The system of claim 8 , wherein the versioning includes:

a first versioning for the data and the metadata associated with the plurality of models in the workstream;

a second versioning for the workstream; and

a third versioning for each of the plurality of models in the workstream.

10. A computer implemented method, comprising:

generating a configuration manager programmed to configure a workstream including a plurality of models, wherein the workstream defines metadata associated with execution of each of the plurality of models;

generating an execution manager programmed to execute each of the plurality of models in the workstream according to the metadata; and

generating a results manager programmed to access results of the execution of the workstream;

wherein the configuration manager is programmed to define a visual depiction of the workstream showing each of the plurality of models and model dependencies associated therewith; and

wherein the visual depiction includes a legend providing source information for the plurality of models depicted on the visual depiction.

11. The method of claim 10 , wherein the execution manager is further programmed to programmatically execute a model of the plurality of models in the workstream.

12. The method of claim 11 , wherein the model is a legacy model configured for manual execution.

13. The method of claim 11 , wherein the execution manager includes a plurality of model runner nodes, wherein each of the plurality of model runner nodes is programmed to execute a different type of the plurality of models.

14. The method of claim 10 , wherein the configuration manager defines an acyclic construction of the model dependencies.

15. The method of claim 10 , wherein the configuration manager is programmed to allow a first model to be added to the workstream and a second model to be removed from the workstream.

16. The method of claim 10 , wherein the configuration manager visually maps each upstream model and each downstream model for the plurality of models in the workstream.

17. The method of claim 10 , further comprising defining a versioning for the workstream.

18. The method of claim 17 , wherein the versioning includes:

a first versioning for the data and the metadata associated with the plurality of models in the workstream;

a second versioning for the workstream; and

a third versioning for each of the plurality of models in the workstream.

Assignments (2)
STATEMENT OF CHANGE OF ADDRESS OF ASSIGNEE Recorded Jun 17, 2025
From: WELLS FARGO BANK, N.A.
To: WELLS FARGO BANK, N.A.
Reel/Frame 071679/0784 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 15, 2022
From: RING, SAMUEL SENDER-LEVI; TOMS, JOEL
To: WELLS FARGO BANK, N.A.
Reel/Frame 060521/0345 →
References Cited (30)
US 3358339A · Strehlein · 1967 [cited by applicant]
US 3422551A · Blank · 1969 [cited by applicant]
US 8332864B2 · Bose et al. · 2012 [cited by applicant]
US 10963231B1 · Singh · 2021 [cited by examiner]
US 11074107B1 · Nandakumar · 2021 [cited by applicant]
US 11816618B1 · Cheek, Jr. · 2023 [cited by examiner]
US 11900169B1 · Dhandhania · 2024 [cited by examiner]
US 20020026507A1 · Sears · 2002 [cited by examiner]
US 20090087822A1 · Stanton · 2009 [cited by examiner]
US 20150052239A1 · Lamarca · 2015 [cited by examiner]
US 20180165604A1 · Minkin et al. · 2018 [cited by applicant]
US 20190095557A1 · Sehgal et al. · 2019 [cited by applicant]
US 20190272590A1 · Lin et al. · 2019 [cited by applicant]
US 20190340518A1 · Candido et al. · 2019 [cited by applicant]
US 20200285899A1 · Chen et al. · 2020 [cited by applicant]
US 20200344185A1 · Singaraju et al. · 2020 [cited by applicant]
US 20200356362A1 · Thiyagarajah · 2020 [cited by examiner]
US 20210042674A1 · Chan · 2021 [cited by applicant]
US 20210089944A1 · Zhou et al. · 2021 [cited by applicant]
US 20210192437A1 · Dhandapani et al. · 2021 [cited by applicant]
US 20210255886A1 · Von Niederhausern · 2021 [cited by examiner]
US 20210294580A1 · Oburu et al. · 2021 [cited by applicant]
US 20210390455A1 · Oglesby et al. · 2021 [cited by applicant]
US 20220108223A1 · Capelo · 2022 [cited by examiner]
US 20220342697A1 · MacFarlane · 2022 [cited by examiner]
US 20230306314A1 · Chandrasekaran · 2023 [cited by examiner]
WO 2020036590A1 · 2020 [cited by applicant]
WO 2021034932A1 · 2021 [cited by applicant]
Al-Shabandar et al., “The Application of Artificial Intelligence in Financial Compliance Management,” AIAM' 19: 2019 International Conference on Artificial Intelligence and Advanced Manufacturing, Oct. 17-19, 2019, Dubl… [cited by applicant]
Papadimitriou et al., “A Multi-Faceted Approach to Large Scale Financial Forecasting,” ACM International Conference on AI in Finance (ICAIF '20), Oct. 15-16, 2020, New York, NY, USA. ACM, 8 pages, https://doi.org/10.114… [cited by applicant]