Granted Patent B2

US 12,585,437 · App. 18/378,797 · Granted Mar 24, 2026

Inventors: Shailendra Singh (Thane West, IN); Ankit Dholakiya (Ahmedabad, IN); Arup Francis (Chennai, IN)

Assignee: BANK OF AMERICA CORPORATION

G06F8/33G06F11/3608G06N20/00

Abstract

Claims (76)

1 . A system for a decentralized machine learning source code generation framework via a holochain network, the system comprising:

a processing device;

a non-transitory storage device containing instructions when executed by the processing device, causes the processing device to perform the steps of:

receiving a predetermined code criteria of at least one selected from a group consisting of performance, security, complexity and scalability;

receiving a new code segment from an integrated development environment executing on an endpoint device;

retrieving characteristics of the new code segment;

determining, using a trained machine learning model, at least one subsequent code segment, based on at least the characteristics of the new code segment;

determining, using an evaluation engine, at least one score of the subsequent code segment, wherein the at least one score is associated with the predetermined code criteria; and

automatically transmitting, over a network interface, a predetermined number of the at least one subsequent code segments above a predetermined threshold of the at least one score to the integrated development environment executing on the endpoint device for display,

wherein the performance is determined based on a minimum number of CPU cycles needed to execute the subsequent code segment,

wherein the security is determined based on a data flow analysis of the subsequent code segment,

wherein the complexity is determined based on a complexity measure of the subsequent code segment,

wherein the scalability is determined based on scalability performance testing the subsequent code segment.

2 . The system of claim 1 , wherein executing the instructions further causes the processing device to perform the steps of:

retrieving, from a distributed holochain network, archived code segments; and

generating a training dataset comprising the archived code segments, characteristics of each archived data segment, and a previous code segment used immediately prior to the archived data segment.

3 . The system of claim 2 , wherein the characteristics of each archived data segment comprises at least one selected from a group consisting of the performance, the security, the complexity, and the scalability.

4 . The system of claim 3 , wherein executing the instructions further causes the processing device to perform the steps of:

generating the trained machine learning model by training a machine learning model using the training dataset.

5 . The system of claim 1 , wherein executing the instructions further causes the processing device to perform the steps of:

generating, using a clustering engine of the machine learning model, clusters of new code segments based on the predetermined code criteria.

6 . The system of claim 1 , wherein executing the instructions further causes the processing device to perform the steps of:

receiving, from the endpoint device, a selection of the at least one subsequent code segment; and

acquiring the at least one subsequent code segment by a component acquisition engine, wherein the at least one subsequent code is distributed across a distributed holochain network.

7 . The system of claim 1 , wherein executing the instructions further causes the processing device to perform the steps of:

receiving, from the endpoint device, a declining of the at least one subsequent code segment;

receiving, from the endpoint device, an alternatively generated code segment; and

acquiring the alternatively generated code segment, wherein the alternatively generated code segment is distributed across a distributed holochain network.

8 . A computer program product for a decentralized machine learning source code generation framework via a holochain network, the computer program product comprising a non-transitory computer-readable medium comprising code causing an apparatus to:

receive a predetermined code criteria of at least one selected from a group consisting of performance, security, complexity and scalability;

receive a new code segment from an integrated development environment executing on an endpoint device;

retrieve characteristics of the new code segment;

determine, using a trained machine learning model, at least one subsequent code segment, based on at least the characteristics of the new code segment;

determine, using an evaluation engine, at least one score of the subsequent code segment, wherein the at least one score is associated with the predetermined code criteria; and

automatically transmit, over a network interface, a predetermined number of the at least one subsequent code segments above a predetermined threshold of the at least one score to the integrated development environment executing on the endpoint device for display,

wherein the performance is determined based on a minimum number of CPU cycles needed to execute the subsequent code segment,

wherein the security is determined based on a data flow analysis of the subsequent code segment,

wherein the complexity is determined based on a complexity measure of the subsequent code segment,

wherein the scalability is determined based on scalability performance testing the subsequent code segment.

9 . The computer program product of claim 8 , wherein the code further causes the apparatus to:

retrieve, from a distributed holochain network, archived code segments; and

generate a training dataset comprising the archived code segments, characteristics of each archived data segment, and a previous code segment used immediately prior to the archived data segment.

10 . The computer program product of claim 9 , wherein the characteristics of each archived data segment comprises at least one selected from a group consisting of the performance, the security, the complexity, and the scalability.

11 . The computer program product of claim 10 , wherein the code further causes the apparatus to:

generate the trained machine learning model by training a machine learning model using the training dataset.

12 . The computer program product of claim 8 , wherein the code further causes the apparatus to:

generate, using a clustering engine of the machine learning model, clusters of new code segments based on the predetermined code criteria.

13 . The computer program product of claim 8 , wherein the code further causes the apparatus to:

receive, from the endpoint device, a selection of the at least one subsequent code segment; and

acquire the at least one subsequent code segment by a component acquisition engine, wherein the at least one subsequent code is distributed across a distributed holochain network.

14 . The computer program product of claim 8 , wherein the code further causes the apparatus to:

receive, from the endpoint device, a declining of the at least one subsequent code segment;

receive, from the endpoint device, an alternatively generated code segment; and

acquire the alternatively generated code segment, wherein the alternatively generated code segment is distributed across a distributed holochain network.

15 . A method for a decentralized machine learning source code generation framework via a holochain network, the method comprising:

receiving a predetermined code criteria of at least one selected from a group consisting of performance, security, complexity and scalability;

receiving a new code segment from an integrated development environment executing on an endpoint device;

retrieving characteristics of the new code segment;

determining, using a trained machine learning model, at least one subsequent code segment, based on at least the characteristics of the new code segment;

determining, using an evaluation engine, at least one score of the subsequent code segment, wherein the at least one score is associated with the predetermined code criteria; and

automatically transmitting, over a network interface, a predetermined number of the at least one subsequent code segments above a predetermined threshold of the at least one score to the integrated development environment executing on the endpoint device for display,

wherein the performance is determined based on a minimum number of CPU cycles needed to execute the subsequent code segment,

wherein the security is determined based on a data flow analysis of the subsequent code segment,

wherein the complexity is determined based on a complexity measure of the subsequent code segment,

wherein the scalability is determined based on scalability performance testing the subsequent code segment.

16 . The method of claim 15 , wherein the method further comprises:

retrieving, from a distributed holochain network, archived code segments; and

generating a training dataset comprising the archived code segments, characteristics of each archived data segment, and a previous code segment used immediately prior to the archived data segment.

17 . The method of claim 16 , wherein the characteristics of each archived data segment comprises at least one selected from a group consisting of the performance, the security, the complexity, and the scalability.

18 . The method of claim 17 , wherein the method further comprises:

generating the trained machine learning model by training a machine learning model using the training dataset.

19 . The method of claim 15 , wherein the method further comprises:

generating, using a clustering engine of the machine learning model, clusters of new code segments based on the predetermined code criteria.

20 . The method of claim 15 , wherein the method further comprises:

receiving, from the endpoint device, a selection of the at least one subsequent code segment; and

acquiring the at least one subsequent code segment by a component acquisition engine, wherein the at least one subsequent code is distributed across a distributed holochain network.

Assignments (1)

Continuity (1)

References Cited (30)