Granted Patent B2

US 12,596,690 · App. 18/408,655 · Granted Apr 7, 2026

Inventors: Raja Arumugam Maharaja (Tamil Nadu, IN); Ankit Singh Negi (Gurugram, IN)

Assignee: BANK OF AMERICA CORPORATION

G06F16/21G06F8/61G06N20/00G06T11/00G06V30/18G06V30/422G06T2200/24

Abstract

Claims (105)

1 . A system for intelligent database modelling, the system comprising:

at least one non-transitory storage device; and

at least one processing device coupled to the at least one non-transitory storage device, wherein the at least one processing device is configured to:

retrieve one or more database models from a data repository;

extract one or more entities and one or more attributes from the one or more database models;

initiate a machine learning algorithm on the one or more database models, the extracted one or more entities and the extracted one or more attributes;

train, using the machine learning algorithm, a first machine learning model, wherein training further comprises determining one or more classification parameters for the first machine learning model;

provide an augmented reality application for installation on a computing device of a user;

capture, using the augmented reality application, a drawing made by the user on a medium, wherein the drawing comprises a diagram of a logical structure;

initiate the trained first machine learning model on the captured drawing made by the user on the medium;

determine, based on an output of the trained first machine learning model exceeding a predetermined threshold value, that the user is attempting to design a database model;

extract at least a first entity from the captured drawing made by the user on the medium based on at least determining that the user is attempting to design the database model;

determine, using the trained first machine learning model, one or more attributes for the first entity;

initiate, via the augmented reality application, a first push notification for display on the computing device of the user, wherein the first push notification comprises at least the one or more attributes;

electronically receive, via the augmented reality application, a user selection of a subset of attributes from the one or more attributes;

generate, using the augmented reality application, a conceptual database model based on at least the first entity and the subset of attributes;

determine, using the trained first machine learning model, one or more database schema based on at least the conceptual database model;

initiate, via the augmented reality application, a second push notification for display on the computing device of the user, wherein the second push notification comprises at least the one or more database schema;

electronically receive, via the augmented reality application, a user selection of a database schema from the one or more database schema;

in response, generate a physical database model using the database schema;

automatically generate an entity relationship diagram (ERD) based on the physical database model illustrating a logical structure of the database model;

initiate a second machine learning model on one or more data sources and the physical database model;

determine, using the second machine learning model, at least one data source that is likely to be triggered when populating a database created using the physical database model, wherein the at least one data source is likely to be triggered by specific entities, attributes, and relationships in the physical database model and wherein the least one data source is associated with an authorization requirement;

determine that an authentication level of the user does not meet the authorization requirement of the at least one data source;

based on determining that the authentication level of the user does not meet the authorization requirement of the at least one data source,

generate a new transaction object for the physical database model; and

broadcast the new transaction object for the physical database model to the at least one data source in a distributed ledger for validation.

2 . The system of claim 1 , wherein the at least one processing device is further configured to:

determine, using the classification parameters, the one or more attributes for the first entity.

3 . The system of claim 1 , wherein the at least one processing device is further configured to:

automatically generate, using the first machine learning model, a relationship between the first entity and the subset of attributes; and

record the relationship in the conceptual database model.

4 . The system of claim 3 , wherein the at least one processing device is further configured to:

transmit control signals configured to cause the computing device of the user to display the conceptual database model for user approval; and

electronically receive, via the computing device of the user, the user approval for the conceptual database model.

5 . The system of claim 1 , wherein broadcasting the new transaction object further comprises:

receiving, from a computing device associated with the at least one data source, an indication validating the physical database model; and

authorizing a generation of a database using the physical database model based on at least receiving the validation.

6 . A computer program product for intelligent database modelling, the computer program product comprising a non-transitory computer-readable medium comprising code causing a first apparatus to:

retrieve one or more database models from a data repository;

extract one or more entities and one or more attributes from the one or more database models;

initiate a machine learning algorithm on the one or more database models, the extracted one or more entities and the extracted one or more attributes;

train, using the machine learning algorithm, a first machine learning model, wherein training further comprises determining one or more classification parameters for the first machine learning model;

provide an augmented reality application for installation on a computing device of a user;

capture, using the augmented reality application, a drawing made by the user on a medium, wherein the drawing comprises a diagram of a logical structure;

initiate the trained first machine learning model on the captured drawing made by the user on the medium;

determine, based on an output of the trained first machine learning model exceeding a predetermined threshold value, that the user is attempting to design a database model;

extract at least a first entity from the captured drawing made by the user on the medium based on at least determining that the user is attempting to design the database model;

determine, using the first machine learning model, one or more attributes for the first entity;

initiate, via the augmented reality application, a first push notification for display on the computing device of the user, wherein the first push notification comprises at least the one or more attributes;

electronically receive, via the augmented reality application, a user selection of a subset of attributes from the one or more attributes;

generate, using the augmented reality application, a conceptual database model based on at least the first entity and the subset of attributes;

determine, using trained the first machine learning model, one or more database schema based on at least the conceptual database model;

initiate, via the augmented reality application, a second push notification for display on the computing device of the user, wherein the second push notification comprises at least the one or more database schema;

electronically receive, via the augmented reality application, a user selection of a database schema from the one or more database schema;

in response, generate a physical database model using the database schema;

automatically generate an entity relationship diagram (ERD) based on the physical database model illustrating a logical structure of the database model;

initiate a second machine learning model on one or more data sources and the physical database model;

determine, using the second machine learning model, at least one data source that is likely to be triggered when populating a database created using the physical database model, wherein the at least one data source is likely to be triggered by specific entities, attributes, and relationships in the physical database model and wherein the least one data source is associated with an authorization requirement;

determine that an authentication level of the user does not meet the authorization requirement of the at least one data source;

based on determining that the authentication level of the user does not meet the authorization requirement of the at least one data source, generate a new transaction object for the physical database model; and

broadcast the new transaction object for the physical database model to the at least one data source in a distributed ledger for validation.

7 . The computer program product of claim 6 , wherein the first apparatus is further configured to:

determine, using the classification parameters, the one or more attributes for the first entity.

8 . The computer program product of claim 6 , wherein the first apparatus is further configured to:

automatically generate, using the first machine learning model, a relationship between the first entity and the subset of attributes; and

record the relationship in the conceptual database model.

9 . The computer program product of claim 8 , wherein the first apparatus is further configured to:

transmit control signals configured to cause the computing device of the user to display the conceptual database model for user approval; and

electronically receive, via the computing device of the user, the user approval for the conceptual database model.

10 . A method for intelligent database modelling, the method comprising:

retrieve one or more database models from a data repository;

extract one or more entities and one or more attributes from the one or more database models;

initiate a machine learning algorithm on the one or more database models, the extracted one or more entities and the extracted one or more attributes;

train, using the machine learning algorithm, a first machine learning model, wherein training further comprises determining one or more classification parameters for the first machine learning model;

providing an augmented reality application for installation on a computing device of a user;

capturing, using the augmented reality application, a drawing made by the user on a medium, wherein the drawing comprises a diagram of a logical structure;

initiating the trained first machine learning model on the captured drawing made by the user on the medium;

determining, based on an output of the trained first machine learning model exceeding a predetermined threshold value, that the user is attempting to design a database model;

extracting at least a first entity from the captured drawing made by the user on the medium based on at least determining that the user is attempting to design the database model;

determining, using the trained first machine learning model, one or more attributes for the first entity;

initiating, via the augmented reality application, a first push notification for display on the computing device of the user, wherein the first push notification comprises at least the one or more attributes;

electronically receiving, via the augmented reality application, a user selection of a subset of attributes from the one or more attributes;

generating, using the augmented reality application, a conceptual database model based on at least the first entity and the subset of attributes;

determining, using the trained first machine learning model, one or more database schema based on at least the conceptual database model;

initiating, via the augmented reality application, a second push notification for display on the computing device of the user, wherein the second push notification comprises at least the one or more database schema;

electronically receiving, via the augmented reality application, a user selection of a database schema from the one or more database schema;

in response, generating a physical database model using the database schema;

automatically generating an entity relationship diagram (ERD) based on the physical database model illustrating a logical structure of the database model;

initiating a second machine learning model on one or more data sources and the physical database model;

determining, using the second machine learning model, at least one data source that is likely to be triggered when populating a database created using the physical database model, wherein the at least one data source is likely to be triggered by specific entities, attributes, and relationships in the physical database model and wherein the least one data source is associated with an authorization requirement;

determine that an authentication level of the user does not meet the authorization requirement of the at least one data source;

based on determining that the authentication level of the user does not meet the authorization requirement of the at least one data source, generating a new transaction object for the physical database model; and

broadcasting the new transaction object for the physical database model to the at least one data source in a distributed ledger for validation.

11 . The method of claim 10 , wherein the method further comprises:

determining, using the classification parameters, the one or more attributes for the first entity.

12 . The method of claim 10 , wherein the method further comprises:

automatically generating, using the first machine learning model, a relationship between the first entity and the subset of attributes; and

recording the relationship in the conceptual database model.

13 . The method of claim 12 , wherein the method further comprises:

transmitting control signals configured to cause the computing device of the user to display the conceptual database model for user approval; and

electronically receiving, via the computing device of the user, the user approval for the conceptual database model.

14 . The method of claim 10 , wherein broadcasting the new transaction object further comprises:

receiving, from a computing device associated with the at least one data source, an indication validating the physical database model; and

authorizing a generation of a database using the physical database model based on at least receiving the validation.

Assignments (1)

Continuity (2)

References Cited (74)