IP Library › Granted Patent US 12,406,214
Granted Patent B2
US 12,406,214 · App. 18/329,403 · Granted Sep 2, 2025

Process modeling techniques for providing user-specific process schedule data

Inventors: Dennis E. Montenegro (Concord, CA); Sadie S. Salim (Mill Valley, CA); Volkmar Scharf-Katz (San Francisco, CA); Miriam F. Clark (San Francisco, CA); Akhlaq M. Khan (San Ramon, CA); Samuel B. Martin (San Francisco, CA); Margaret S. Honeycutt (Crockett, CA)
Assignee: WELLS FARGO BANK, N.A.
G06Q10/063112
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 12,406,214
App. No.
18/329,403
Filed
Jun 5, 2023
Granted
Sep 2, 2025
Kind
B2
Art Unit
3625
USPC
705/7.14
Abstract

An process analysis computing system receives input data that identifies a subject-matter expert (SME) process, such as an SME process that requires detailed information regarding a very large quantity of information about the SME process. In the process analysis computing system, a scenario selection engine extracts process factors and user factors from the input data. Based on the process factors and user factors, the scenario selection engine determines initial schedule data describing event stages and milestone stages included in the SME process, and also generates user-specific process schedule data based on a modification of the initial schedule data. A user-specific execution engine in the process analysis computing system receives the user-specific process schedule data. Based on a milestone stage dependency in the user-specific process schedule data, the process analysis computing system controls access to a requested resource associated with the SME process.

Claims (86)

1. A system comprising:

a processor, and

a non-transitory computer-readable storage device storing instructions that are executable by the processor to:

implement a process analysis system including a scenario selection engine, a first instance of a user-specific execution engine, and a second instance of the user-specific execution engine;

receive first input data from a first additional computing system via the first instance of the user-specific execution engine and second input data from a second additional computing system via the second instance of the user-specific execution engine, wherein each of the first input data and the second input data identifies a particular subject-matter expert (SME) process;

extract, by the scenario selection engine from the first input data and the second input data, a set of process factors that describe the particular SME process, a first set of user factors, and a second set of user factors, wherein:

the first set of user factors describe a first user account implemented by the first additional computing system and associated with the first instance of the user-specific execution engine, and

the second set of user factors describe a second user account implemented by the second additional computing system and associated with the second instance of the user-specific execution engine;

determine, by the scenario selection engine based on the set of process factors, initial schedule data that describes a) event stages in the particular SME process and b) milestone stages in the particular SME process;

generate, by the scenario selection engine based on the first set of user factors, first user-specific process schedule data that includes a first modification of the initial schedule data, wherein the first modification comprises excluding at least one milestone stage described by the initial schedule data;

generate, by the scenario selection engine based on the second set of user factors, second user-specific process schedule data that includes a second modification of the initial schedule data, wherein the second modification comprises including an additional milestone stage in the milestone stages described by the initial schedule data, wherein the second modification is different from the first modification;

provide, from the scenario selection engine, the first user-specific process schedule data to the first additional computing system via the first instance of the user-specific execution engine and the second user-specific process schedule data to the second additional computing system via the second instance of the user-specific execution engine;

receive, by the scenario selection engine, first access request data from the first additional computing system via the first instance of the user-specific execution engine and second access request data from the second additional computing system via the second instance of the user-specific execution engine, wherein each of the first access request data and the second access request data requests to access a resource associated with a particular event stage included in i) the first user-specific process schedule data and ii) the second user-specific process schedule data;

permit access of the first additional computing system to the requested resource, based on a determination by the scenario selection engine that the particular event stage has a dependency on the at least one milestone stage excluded from the first user-specific process schedule data; and

deny access of the second additional computing system to the requested resource, based on a determination by the scenario selection engine that the particular event stage has a dependency on the additional milestone stage included in the second user-specific process schedule data.

2. The system of claim 1 , the instructions further executable to, subsequent to denying access of the second additional computing system to the requested resource:

identify one or more of a) the second user account associated with the second instance of the user-specific execution engine or b) an additional user account that is associated with the particular SME process;

generate alert data that describes the denied access of the second additional computing system to the requested resource; and

send the alert data to one or more of the second additional computing system implementing the second user account or another computing system implementing the additional user account.

3. The system of claim 1 , the instructions further executable to, subsequent to denying access of the second additional computing system to the requested resource:

receive, from the second instance of the user-specific execution engine, progress data; and

responsive to determining that the progress data describes completion of the additional milestone stage, permit access of the second additional computing system to the requested resource.

4. The system of claim 1 , wherein at least one of the first input data or the second input data identifying the particular SME process is natural-language data.

5. The system of claim 1 , wherein at least one of the first set of user factors or the second set of user factors describes one or more of:

a data visualization preference indicated by the first user account or the second user account,

a level of information access indicated by the first user account or the second user account, or

a level of user experience with the particular SME process, for a respective user of the first user account or the second user account.

6. The system of claim 1 , wherein the first additional computing system interacts with the first instance of the user-specific execution engine to provide the first input data identifying the particular SME process.

7. The system of claim 1 , wherein the requested resource is associated with the particular SME process.

8. A method of controlling access to resources associated with subject-matter expert processes, the method including operations executed by a processor, the operations comprising:

receiving first input data from a first additional computing system and second input data from a second additional computing system, wherein each of the first input data and the second input data identifies a particular subject-matter expert (SME) process;

extracting, from the first input data and the second input data, a set of process factors that describe the particular SME process;

extracting, from the first input data, a first set of user factors that describe a first user account implemented by the first additional computing system;

extracting, from the second input data, a second set of user factors that describe a second user account implemented by the second additional computing system;

determining, based on the set of process factors, initial schedule data that describes a) event stages in the particular SME process and b) milestone stages in the particular SME process;

generating, based on the first set of user factors, first user-specific process schedule data that includes a first modification of the initial schedule data, wherein the first modification comprises excluding at least one milestone stage described by the initial schedule data;

generating, based on the second set of user factors, second user-specific process schedule data that includes a second modification of the initial schedule data, wherein the second modification comprises including an additional milestone stage in the milestone stages described by the initial schedule data, wherein the second modification is different from the first modification;

providing the first user-specific process schedule data including the first modification to the first additional computing system via a first instance of a user-specific execution engine, and the second user-specific process schedule data including the second modification to the second additional computing system via a second instance of the user-specific execution engine;

receiving first access request data from the first additional computing system and second access request data from the second additional computing system, wherein each of the first access request data and the second access request data requests to access a resource associated with a particular event stage included in i) the first user-specific process schedule data and ii) the second user-specific process schedule data;

based on a determination that the particular event stage has a dependency on the at least one milestone stage excluded from the first user-specific process schedule data, permitting access of the first additional computing system to the requested resource; and

based on a determination that the particular event stage has a dependency on the additional milestone stage included in the second user-specific process schedule data, denying access of the second additional computing system to the requested resource.

9. The method of claim 8 , the operations further comprising, subsequent to denying access of the second additional computing system to the requested resource:

identifying one or more of a) the second user account implemented by the second additional computing system or b) an additional user account that is associated with the particular SME process;

generating alert data that describes the denied access of the second additional computing system to the requested resource; and

sending the alert data to one or more of a) the second additional computing system implementing the second user account or b) another computing system implementing the additional user account.

10. The method of claim 8 , the operations further comprising, subsequent to denying access of the second additional computing system to the requested resource:

receiving, from the second additional computing system, progress data; and

responsive to determining that the progress data describes completion of the additional milestone stage, permitting access of the second additional computing system to the requested resource.

11. The method of claim 8 , wherein at least one of the first input data or the second input data identifying the particular SME process is natural-language data.

12. The method of claim 8 , wherein at least one of the first set of user factors or the second set of user factors describes one or more of:

a data visualization preference indicated by the first user account or the second user account,

a level of information access indicated by the first user account or the second user account, or

a level of user experience with the particular SME process, for a respective user of the first user account or the second user account.

13. The method of claim 8 , the operations further comprising:

generating recommendation data describing an efficiency improvement for the particular SME process; and

providing the recommendation data to at least one of the first additional computing system or the second additional computing system.

14. The method of claim 8 , the operations further comprising:

generating, based on the first set of user factors, first visualization data describing a visualization of a portion of the first user-specific process schedule data, wherein the visualization is adjusted based on a particular user factor in the first set of user factors; and

providing the first visualization data to the first additional computing system.

15. A non-transitory computer-readable medium embodying program code for controlling access to resources associated with subject-matter expert processes, wherein, when executed by a processor, the program code causes the processor to perform operations comprising:

receiving first input data from a first additional computing system and second input data from a second additional computing system, wherein each of the first input data and the second input data identifies a particular subject-matter expert (SME) process;

extracting, from the first input data and the second input data, a set of process factors that describe the particular SME process;

extracting, from the first input data, a first set of user factors that describe a first user account implemented by the first additional computing system;

extracting, from the second input data, a second set of user factors that describe a second user account implemented by the second additional computing system;

determining, based on the set of process factors, initial schedule data that describes a) event stages in the particular SME process and b) milestone stages in the particular SME process;

generating, based on the first set of user factors, first user-specific process schedule data that includes a first modification of the initial schedule data, wherein the first modification comprises excluding at least one milestone stage described by the initial schedule data;

generating, based on the second set of user factors, second user-specific process schedule data that includes a second modification of the initial schedule data, wherein the second modification comprises including an additional milestone stage in the milestone stages described by the initial schedule data, wherein the second modification is different from the first modification;

providing the first user-specific process schedule data including the first modification to the first additional computing system via a first instance of a user-specific execution engine, and the second user-specific process schedule data including the second modification to the second additional computing system via a second instance of the user-specific execution engine;

receiving first access request data from the first additional computing system and second access request data from the second additional computing system, wherein each of the first access request data and the second access request data requests to access a resource associated with a particular event stage included in i) the first user-specific process schedule data and ii) the second user-specific process schedule data;

based on a determination that the particular event stage has a dependency on the at least one milestone stage excluded from the first user-specific process schedule data, permitting access of the first additional computing system to the requested resource; and

based on a determination that the particular event stage has a dependency on the additional milestone stage included in the second user-specific process schedule data, denying access of the second additional computing system to the requested resource.

16. The non-transitory computer-readable medium of claim 15 , the operations further comprising, subsequent to denying access of the second additional computing system to the requested resource:

identifying one or more of a) the second user account implemented by the second additional computing system or b) an additional user account that is associated with the particular SME process;

generating alert data that describes the denied access of the second additional computing system to the requested resource; and

sending the alert data to one or more of a) the second additional computing system implementing the second user account or b) another computing system implementing the additional user account.

17. The non-transitory computer-readable medium of claim 15 , the operations further comprising, subsequent to denying access of the second additional computing system to the requested resource:

receiving, from the second additional computing system, progress data; and

responsive to determining that the progress data describes completion of the additional milestone stage, permitting access of the second additional computing system to the requested resource.

18. The non-transitory computer-readable medium of claim 15 , wherein at least one of the first input data or the second input data identifying the particular SME process is natural-language data.

19. The non-transitory computer-readable medium of claim 15 , wherein at least one of the first set of user factors or the second set of user factors describes one or more of:

a data visualization preference indicated by the first user account or the second user account,

a level of information access indicated by the first user account or the second user account, or

a level of user experience with the particular SME process, for a respective user of the first user account or the second user account.

20. The non-transitory computer-readable medium of claim 15 , the operations further comprising:

generating recommendation data describing an efficiency improvement for the particular SME process; and

providing the recommendation data to at least one of the first additional computing system or the second additional computing system.

Assignments (2)
ADDRESS CHANGE Recorded May 29, 2025
From: WELLS FARGO BANK, N.A.
To: WELLS FARGO BANK, N.A.
Reel/Frame 071769/0139 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 21, 2023
From: MONTENEGRO, DENNIS E.; SALIM, SADIE S.; SCHARF-KATZ, VOLKMAR; CLARK, MIRIAM F.; KHAN, AKHLAQ M.; MARTIN, SAMUEL B.; HONEYCUTT, MARGARET S.
To: WELLS FARGO BANK, N.A.
Reel/Frame 064006/0290 →
Continuity (1)
Related Publication 20240403751A1 · Dec 5, 2024
References Cited (64)
US 10268974B2 · Wiig · 2019 [cited by examiner]
US 12094014B2 · Clayton · 2024 [cited by examiner]
US 20120215574A1 · Driessnack · 2012 [cited by examiner]
US 20130173327A1 · Lance et al. · 2013 [cited by applicant]
US 20160132804A1 · Croft · 2016 [cited by examiner]
US 20170316387A1 · Joshi · 2017 [cited by examiner]
US 20200019907A1 · Notani · 2020 [cited by examiner]
US 20200410424A1 · Bellaish · 2020 [cited by examiner]
US 20210055933A1 · Bulut · 2021 [cited by examiner]
US 20210287177A1 · Musialek · 2021 [cited by examiner]
US 20230153716A1 · Kumar · 2023 [cited by examiner]
US 20240169295A1 · Mathews · 2024 [cited by examiner]
US 20240412166A1 · Gilge · 2024 [cited by examiner]
CN 111768166A · 2020 [cited by applicant]
JP 5787733B2 · 2015 [cited by applicant]
KR 20200084385A · 2020 [cited by applicant]
“Intelligent Data Stack Automation”, Numbers Station, Believed to be published at least as early as Oct. 6, 2022, 5 pages, Available online at: https://www.numbersstation.ai. [cited by applicant]
Bach, et al., “Learning the Structure of Generative Models without Labeled Data”, Proceedings of Machine Learning Research, Aug. 6, 2017, pp. 273-282, vol. 70, HHS Public Access. [cited by applicant]
Bach, et al., “Snorkel DryBell: A Case Study in Deploying Weak Supervision at Industrial Scale”, Proceedings of the International Conference on Management of Data (SIGMOD), Jun. 3, 2019, 14 pages. [cited by applicant]
Bringer, et al., “Osprey: Weak Supervision of Imbalanced Extraction Problems without Code”, DEEM'30: Proceedings of the 3rd International Workshop on Data Management for End-to-End Machine Learning, Jun. 30, 2019, 11 pa… [cited by applicant]
Callahan, et al., “Medical Device Surveillance With Electronic Health Records”, NPJ Digital Medicine, Sep. 25, 2019, 10 pages, Scripps Research Translational Institute. [cited by applicant]
Chen, et al., “Scene Graph Prediction with Limited Labels”, International Conference on Computer Vision, Nov. 30, 2019, 13 pages. [cited by applicant]
Chen, et al., “Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices”, Advances in Neural Information Processing Systems, Dec. 2019, pp. 9392-9402, vol. 32, HHS Public Access. [cited by applicant]
Chen, et al., “Train and You'll Miss It: Interactive Model Iteration with Weak Supervision and Pre-Trained Embeddings”, Machine Learning, Jun. 26, 2020, 41 pages. [cited by applicant]
Cohen-Wang, et al., “Interactive Programmatic Labeling for Weak Supervision”, Workshop at KDD '19, Aug. 4-8, 2019, 5 pages, Anchorage, Alaska. [cited by applicant]
Dunnmon, et al., “Cross-Modal Data Programming Enables Rapid Medical Machine Learning”, Patterns, May 8, 2020, vol. 1, No. 100019, 16 pages. [cited by applicant]
Ehrenberg, et al., “Data Programming with DDLite: Putting Humans in a Different Part of the Loop”, HILDA '16: Proceedings of the Workshop on Human-In-the-Loop Data Analytics, Jun. 26, 2016, 6 pages, San Francisco, Calif… [cited by applicant]
Eyuboglu, et al., “Domino: Discovering Systematic Errors with Cross-Modal Embeddings”, Published as a conference paper at ICLR 2022, May 21, 2022 , 28 pages. [cited by applicant]
Fries, et al., “SwellShark: A Generative Model for Biomedical Named Entity Recognition without Labeled Data”, Computation and Language, Apr. 20, 2017, 11 pages. [cited by applicant]
Fries, et al., “Weakly supervised classification of aortic valve malformations using unlabeled cardiac MRI sequences”, Nature Communications, Jul. 15, 2019, vol. 10, No. 1, 10 pages. [cited by applicant]
Fries, et al., “Trove: Ontology-driven weak supervision for medical entity classification”, ArXiv, Available online at: https://arxiv.org/pdf/2008.01972v1.pdf, Aug. 5, 2020, 23 pages. [cited by applicant]
Fries, et al., “Ontology-driven Weak Supervision for Clinical Entity Classification in Electronic Health Records”, Nature Communications, Apr. 1, 2021, vol. 12, No. 1, 11 pages. [cited by applicant]
Fu, et al., “Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods”, ICML'20: Proceedings of the 37th International Conference on Machine Learning, Jul. 15, 2020, 42 pages. [cited by applicant]
Hancock, et al., “Training Classifiers with Natural Language Explanations”, Proceedings of the conference, Association for Computational Linguistics Meeting, Jul. 2018, pp. 1884-1895, HHS Public Access. [cited by applicant]
Krishnamurthy, et al., “Reference-based Weak Supervision for Answer Sentence Selection using Web Data”, Findings of the Association for Computational Linguistics: EMNLP 2021, Apr. 18, 2021, 5 pages. [cited by applicant]
Kuleshov, et al., “A machine-compiled database of genome-wide association studies”, Nature Communications, Jul. 26, 2019, vol. 10, No. 1, 8 pages. [cited by applicant]
Mallinar, et al., “Bootstrapping Conversational Agents With Weak Supervision”, The Thirty-First AAAI Conference on Innovative Application of Artificial Intelligence, Jul. 17, 2019, 6 pages, Available online at: https://… [cited by applicant]
Mazzetto, et al., “Adversarial Multiclass Learning Under Weak Supervision With Performance Guarantees”, Proceedings of the 38th International Conference on Machine Learning, Jul. 2021, 10 pages. [cited by applicant]
Mazzetto, et al., “Semi-Supervised Aggregation of Dependent Weak Supervision Sources With Performance Guarantees”, Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, San Diego, C… [cited by applicant]
Payne, “The Role of Chatbots in Project Management Strategy”, Botsify, May 21, 2021, Available online at: https://botsify.com/blog/the-role-of-chatbots-in-project-management-strategy/, 8 pages. [cited by applicant]
Piriyakulkij, et al., “TAGLETS: A System for Automatic Semi-Supervised Learning with Auxiliary Data”, Proceedings of the 5th MLSys Conference, Santa Clara, CA, May 5, 2022, 21 pages. [cited by applicant]
Ratner, et al., “Data Programming: Creating Large Training Sets, Quickly”, Advances in Neural Information Processing Systems, Dec. 2016, pp. 3567-3575, vol. 29, HHS Public Access. [cited by applicant]
Ratner, et al., “Snorkel: Fast Training Set Generation for Information Extraction”, SIGMOD '17: Proceedings of the 2017 ACM International Conference on Management of Data, Chicago, IL, May 14-19, 2017, 4 pages. [cited by applicant]
Ratner, et al., “Learning to Compose Domain-Specific Transformations for Data Augmentation”, Advances in Neural Information Processing Systems, Sep. 30, 2017, vol. 30, 18 pages. [cited by applicant]
Ratner, et al., “Snorkel: Rapid Training Data Creation with Weak Supervision”, Proceedings of the VLDB Endowment, Nov. 28, 2017, vol. 11, No. 3, 17 pages. [cited by applicant]
Ratner, et al., “Snorkel MeTaL: Weak Supervision for Multi-Task Learning”, Proceedings of the Second Workshop on Data Management for End-to-End Machine Learning, Houston, TX, Jun. 2018, 14 pages, HHS Public Access. [cited by applicant]
Ratner, et al., “Training Complex Models with Multi-Task Weak Supervision”, Proceedings of the AAAI Conference on Artificial Intelligence, AAAI Conference on Artificial Intelligence, Dec. 7, 2018, 31 pages. [cited by applicant]
Ratner, et al., “The Role of Massively Multi-Task and Weak Supervision in Software 2.0”, Conference on Innovative Data Systems Research, Monterey, CA, Jan. 2019, 8 pages. [cited by applicant]
Re, “Software 2.0 and Snorkel: Beyond Hand-Labeled Data”, KDD 201818: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Jul. 19, 2018, 1 page. [cited by applicant]
Sanh, et al., “Multitask Prompted Training Enables Zero-Shot Task Generalization”, Published as a conference paper at ICLR 2022, Mar. 17, 2022, 216 pages. [cited by applicant]
Shin, et al., “Universalizing Weak Supervision”, Published as a conference paper at ICLR 2022, Mar. 17, 2022, 32 pages. [cited by applicant]
Streebo, “Artificial Intelligence Powered Employee Self-Service HR Chatbot: Smart Bots for Human Resource (HR), IT, Operations & Support”, Streebo, Believed to be published at least as early as Sep. 28, 2020, Available … [cited by applicant]
Suri, et al., “Leveraging Organizational Resources to Adapt Models to New Data Modalities”, Proceedings of the VLDB Endowment, Aug. 23, 2020, vol. 13, No. 12, 15 pages. [cited by applicant]
Varma, et al., “Socratic Learning: Augmenting Generative Models to Incorporate Latent Subsets in Training Data”, Machine Learning, Sep. 28, 2017, 17 pages. [cited by applicant]
Varma, et al., “Inferring Generative Model Structure with Static Analysis”, Advances in Neural Information Processing Systems, Dec. 2017, pp. 239-249, vol. 30, HHS Public Access. [cited by applicant]
Varma, et al., “Snuba: Automating Weak Supervision to Label Training Data”, Proceedings of the VLDB Endowment. International Conference on Very Large Data Bases, Nov. 1, 2018, pp. 223-236, vol. 12, No. 3, HHS Public Acc… [cited by applicant]
Varma, et al., “Learning Dependency Structures for Weak Supervision Models”, Proceedings of the 36th International Conference on Machine Learning, Mar. 14, 2019, 23 pages. [cited by applicant]
Varma, et al., “Multi-Resolution Weak Supervision for Sequential Data”, Advances in Neural Information Processing Systems 32 (NeurIPS 2019), Oct. 21, 2019, 26 pages. [cited by applicant]
Wang, et al., “A Clinical Text Classification Paradigm Using Weak Supervision and Deep Representation”, BMC Medical Informatics and Decision Making, Jan. 7, 2019, vol. 19, No. 1, 13 pages. [cited by applicant]
Weng, et al., “Utilizing Weak Supervision to Infer Complex Objects and Situations in Autonomous Driving Data”, 2019 IEEE Intelligent Vehicles Symposium (IV), Paris, France, Jun. 9-12, 2019, pp. 119-125. [cited by applicant]
Wu, et al., “Fonduer: Knowledge Base Construction from Richly Formatted Data”, Proceedings. ACM-SIGMOD International Conference on Management of Data, Jun. 2018, pp. 1301-1316, HHS Public Access. [cited by applicant]
Yu, et al., “Learning from Multiple Noisy Partial Labelers” , Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, Mar. 25, 2022, 23 pages. [cited by applicant]
Zhang, et al., “WRENCH: A Comprehensive Benchmark for Weak Supervision”, Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, Oct. 11, 2021, 29 pages. [cited by applicant]
Zhang, et al., “Creating Training Sets via Weak Indirect Supervision”, Published as a conference paper at ICLR 2022, Mar. 14, 2022, 39 pages. [cited by applicant]