IP Library › Granted Patent US 12,572,674
Granted Patent B2
US 12,572,674 · App. 18/661,176 · Granted Mar 10, 2026

Neuro-symbolic artificial intelligence-based assessment system

Inventors: Saurabh Arora (Gurugram, IN); Shailendra Singh (Maharashtra, IN); Sunilkumar Sriperambudur (Telangana, IN); Sandeep Kumar Chauhan (Miyapur, IN)
Assignee: Bank of America Corporation
G06F21/604G06F21/316
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 12,572,674
App. No.
18/661,176
Granted
Mar 10, 2026
Kind
B2
Abstract

Various aspects of the disclosure relate to dynamically determining user access levels to manage access to enterprise information via application programming interfaces (APIs). A neuro-symbolic AI-based assessment enabled system manages assessments and response to API calls to ensure data security of information shared with external sources via the API. This system identifies and analyze access patterns via neural networks and symbolic reasoning to dynamically manage a rule set to determine access levels and corresponding data sub-objects that are built in real time to be shared with an API response message.

Claims (45)

1 . A system comprising:

an enterprise computing device hosting at least one data repository;

one or more Internet of things (IoT) edge devices;

a neuro-symbolic assessment platform, comprising:

a processor; and

memory storing computer-readable instructions that, when executed by the processor, cause the neuro-symbolic assessment platform to:

receive, from a data consuming application, an API function call;

receive, based on the API function call, user information from the one or more IoT edge devices;

generate a neuro-symbolic rule set based on the user information;

determine, based on neuro-symbolic analysis of the user information and the neuro-symbolic rule set, a data access level; and

build, based on the data access level and from the at least one data repository of the enterprise computing device, a consolidated data repository, wherein the consolidated data repository comprises data associated with a response to the API function call; and

return, to the data consuming application, at least one portion of data stored in the consolidated data repository.

2 . The system of claim 1 , wherein the instructions further cause the cause the neuro-symbolic assessment platform to receive, from the API function call, a user identifier and wherein the user information is received based on the user identifier.

3 . The system of claim 1 , wherein the data consuming application is operational on a third-party computing system external to an enterprise computing network comprising the enterprise computing device.

4 . The system of claim 1 , wherein the one or more IoT edge devices collect information from IoT devices in proximity to a user.

5 . The system of claim 1 , wherein the neuro-symbolic analysis of the user information comprises identifying a user behavioral pattern.

6 . The system of claim 1 , wherein the instructions cause the neuro-symbolic assessment platform to dynamically build each data object stored in the consolidated data repository.

7 . The system of claim 6 , wherein the instructions further cause the neuro-symbolic assessment platform to dynamically adjust the neuro-symbolic rule set based on geographic locations associated with the one or more IoT edge devices.

8 . A neuro-symbolic assessment platform, comprising:

a processor; and

memory storing computer-readable instructions that, when executed by the processor, cause the neuro-symbolic assessment platform to:

receive, from a data consuming application, an API function call;

receive, based on the API function call, user information from one or more IoT edge devices;

generate a neuro-symbolic rule set based on the user information;

determine, based on neuro-symbolic analysis of the user information and the neuro-symbolic rule set, a data access level; and

build, based on the data access level and from at least one data repository of an enterprise computing device, a consolidated data repository, wherein the consolidated data repository comprises data associated with a response to the API function call; and

return, to the data consuming application, at least one portion of data stored in the consolidated data repository.

9 . The neuro-symbolic assessment platform of claim 8 , wherein the instructions further cause the cause the neuro-symbolic assessment platform to receive, from the API function call, a user identifier and wherein the user information is received based on the user identifier.

10 . The neuro-symbolic assessment platform of claim 8 , wherein the data consuming application is operational on a third-party computing system external to an enterprise computing network comprising the enterprise computing device.

11 . The neuro-symbolic assessment platform of claim 8 , wherein the one or more IoT edge devices collect information from IoT devices in proximity to a user.

12 . The neuro-symbolic assessment platform of claim 8 , wherein the neuro-symbolic analysis of the user information comprises identifying a user behavioral pattern.

13 . The neuro-symbolic assessment platform of claim 8 , wherein the instructions cause the neuro-symbolic assessment platform to iteratively build each data object stored in the consolidated data repository.

14 . The neuro-symbolic assessment platform of claim 13 , wherein the instructions further cause the neuro-symbolic assessment platform to dynamically adjust the neuro-symbolic rule set based on geographic locations associated with the one or more IoT edge devices.

15 . Non-transitory computer readable media storing instructions that, when executed by a processor, cause a neuro-symbolic assessment platform to:

receive, from a data consuming application, an API function call;

receive, based on the API function call, user information from one or more IoT edge devices;

generate a neuro-symbolic rule set based on the user information;

determine, based on neuro-symbolic analysis of the user information and the neuro-symbolic rule set, a data access level; and

build, based on the data access level and from at least one data repository of an enterprise computing device, a consolidated data repository, wherein the consolidated data repository comprises data associated with a response to the API function call; and

return, to the data consuming application, at least one portion of data stored in the consolidated data repository.

16 . The non-transitory computer readable media of claim 15 , wherein the instructions further cause the cause the neuro-symbolic assessment platform to receive, from the API function call, a user identifier and wherein the user information is received based on the user identifier.

17 . The non-transitory computer readable media of claim 16 , wherein the data consuming application is operational on a third-party computing system external to an enterprise computing network comprising the enterprise computing device.

18 . The non-transitory computer readable media of claim 15 , wherein the one or more IoT edge devices collect information from IoT devices in proximity to a user.

19 . The non-transitory computer readable media of claim 15 , wherein the neuro-symbolic analysis of the user information comprises identifying a user behavioral pattern.

20 . The non-transitory computer readable media of claim 15 , wherein the instructions further cause the neuro-symbolic assessment platform to dynamically adjust the neuro-symbolic rule set based on geographic locations associated with the one or more IoT edge devices.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 10, 2024
From: ARORA, SAURABH; SINGH, SHAILENDRA; SRIPERAMBUDUR, SUNILKUMAR; CHAUHAN, SANDEEP KUMAR
To: BANK OF AMERICA CORPORATION
Reel/Frame 067378/0603 →
Continuity (1)
Related Publication 20250348603A1 · Nov 13, 2025
References Cited (16)
US 9269114B2 · Boss et al. · 2016 [cited by applicant]
US 10656975B2 · Zolotow et al. · 2020 [cited by applicant]
US 11170300B2 · Dalli · 2021 [cited by examiner]
US 11194716B2 · Noble et al. · 2021 [cited by applicant]
US 11579950B2 · Miedema et al. · 2023 [cited by applicant]
US 11704168B2 · Godwin · 2023 [cited by applicant]
US 12260328B2 · Kimura · 2025 [cited by examiner]
US 20180097905A1 · Todasco et al. · 2018 [cited by applicant]
US 20230123860A1 · Marquie et al. · 2023 [cited by applicant]
US 20230196063A1 · Latapie et al. · 2023 [cited by applicant]
US 20230297712A1 · Veeraraghavan et al. · 2023 [cited by applicant]
US 20240004973A1 · Bosch et al. · 2024 [cited by applicant]
US 20240029422A1 · Qasemi · 2024 [cited by examiner]
US 20240169129A1 · Cobb · 2024 [cited by examiner]
US 20240185081A1 · Agravante · 2024 [cited by examiner]
US 20240212348A1 · Latapie · 2024 [cited by examiner]