IP Library › Granted Patent US 12682203

Granted Patent B2

US 12682203 · App. 18/497,483 · Granted Jul 14, 2026

Artificial intelligence chat bot for configuring a distributed computing system

Inventor: Narayan Kapil (Charlotte, NC)

Assignee: Truist Bank

G06N3/006 G06F9/451 G06N3/045 G06N3/08 H04L41/0886 H04L41/16 H04L41/22

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 12682203
App. No.: 18/497,483
Granted: Jul 14, 2026
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

An artificial intelligence chat bot can be used to configure a cloud computing system. For example, a system can determine, using a first machine learning model, a target functionality for a distributed computing system based on an input provided by a user in a natural language format expressing the target functionality. The system can determine, using a second machine learning model, a recommended adjustment to an existing confirmation of the distributed computing system based on an incompatibility between the target functionality and a configuration setting of a software service executed by the distributed computing system. The system can output a response to the natural language input comprising the recommendation to the user in the natural language format. The system can automatically deploy or reconfigure the distributed computing system on the recommendation.

Claims (81)

1 . A system comprising:

a processing device; and

a non-transitory computer-readable memory comprising instructions that are executable by the processing device for causing the processing device to:

receive a natural language input from a user via a graphical user interface, the natural language input being in a natural language format and expressing a target functionality for a distributed computing system;

provide the natural language input to a first machine learning model, the first machine learning model being configured to analyze the natural language input to ascertain the target functionality from the natural language input and to generate an output indicating the target functionality for the distributed computing system;

provide the target functionality and an existing configuration for the distributed computing system as input into a second machine learning model, the second machine learning model being configured to output a recommendation for an adjustment to the existing configuration of the distributed computing system based on an incompatibility between the target functionality and a configuration setting of a software service executed by the distributed computing system, wherein the adjustment comprises a modification to the configuration setting to enable the distributed computing system to perform the target functionality;

generate a response to the natural language input comprising the recommendation to the user in the natural language format; and

output, via the graphical user interface, the response to the user.

2 . The system of claim 1 , wherein the natural language input is a first input, the response is a first response, and wherein the memory further comprises instructions that are executable by the processing device for causing the processing device to:

receive a second input from the user via the graphical user interface, the second input being in the natural language format;

provide the second input to the first machine learning model, the first machine learning model being configured to output a first selection of a first parameter for configuring the distributed computing system;

provide the first parameter as input into the second machine learning model, the second machine learning model being configured to output an additional set of parameters usable to configure the distributed computing system; and

provide the additional set of parameters as input to the first machine learning model, the first machine learning model being configured to output a second response to the second input comprising the additional set of parameters in the natural language format.

3 . The system of claim 2 , wherein the memory further comprises instructions that are executable by the processing device for causing the processing device to:

output, via the graphical user interface, the second response to the second input;

receive a third input from the user via the graphical user interface, the third input being in the natural language format;

provide the third input to the first machine learning model, the first machine learning model being configured to output a second selection of a second parameter of the additional set of parameters; and

automatically deploy the distributed computing system configured with the first parameter and the second parameter.

4 . The system of claim 3 , wherein the memory further comprises instructions that are executable by the processing device for causing the processing device to:

provide a previous selection made by the user to the first machine learning model, the first machine learning model being configured to generate a question in the natural language format for the user;

output, via the graphical user interface, the question to the user in the natural language format;

receive a fourth input from the user via the graphical user interface, the fourth input being in the natural language format and comprising a response to the question; and

provide the fourth input to the first machine learning model, the first machine learning model being configured to output the second selection of the second parameter of the additional set of parameters.

5 . The system of claim 2 , wherein the first parameter or the additional set of parameters comprise a particular software service provided by a service provider or a configuration setting for the particular software service.

6 . The system of claim 1 , wherein the memory further comprises instructions that are executable by the processing device for causing the processing device to:

train the first machine learning model with natural language data; and

train the second machine learning model with support documentation for software services provided by a service provider.

7 . The system of claim 1 , wherein the memory further comprises instructions that are executable by the processing device for causing the processing device to:

receive the recommendation from the second machine learning model; and

automatically perform the adjustment to the existing configuration of the distributed computing system by transmitting an application programming interface call to a service provider for the distributed computing system.

8 . A method comprising:

receiving, by a processing device, a natural language input from a user via a graphical user interface, the natural language input being in a natural language format and expressing a target functionality for a distributed computing system;

providing, by the processing device, the natural language input to a first machine learning model, the first machine learning model being configured to analyze the natural language input to ascertain the target functionality from the natural language input and to generate an output indicating the target functionality for the distributed computing system;

providing, by the processing device, the target functionality and an existing configuration for the distributed computing system as input to a second machine learning model, the second machine learning model being configured to output a recommendation for an adjustment to the existing configuration of the distributed computing system based on an incompatibility between the target functionality and a configuration setting of a software service executed by the distributed computing system, wherein the adjustment comprises a modification to the configuration setting to enable the distributed computing system to perform the target functionality;

generating, by the processing device, a response to the natural language input comprising the recommendation to the user in the natural language format; and

outputting, by the processing device and via the graphical user interface, the response to the user.

9 . The method of claim 8 , wherein the natural language input is a first input, the response is a first response, and wherein the method further comprises:

receiving a second input from the user via the graphical user interface, the second input being in the natural language format;

providing the second input to the first machine learning model, the first machine learning model being configured to output a first selection of a first parameter for configuring the distributed computing system;

providing the first parameter as input into the second machine learning model, the second machine learning model being configured to output an additional set of parameters usable to configure the distributed computing system; and

providing the additional set of parameters as input to the first machine learning model, the first machine learning model being configured to output a second response to the second input comprising the additional set of parameters in the natural language format.

10 . The method of claim 9 , further comprising:

outputting, via the graphical user interface, the second response to the second input;

receiving a third input from the user via the graphical user interface, the third input being in the natural language format;

providing the third input to the first machine learning model, the first machine learning model being configured to output a second selection of a second parameter of the additional set of parameters; and

automatically deploying the distributed computing system configured with the first parameter and the second parameter.

11 . The method of claim 10 , further comprising:

providing a previous selection made by the user to the first machine learning model, the first machine learning model being configured to generate a question in the natural language format for the user;

outputting, via the graphical user interface, the question to the user in the natural language format;

receiving a fourth input from the user via the graphical user interface, the fourth input being in the natural language format and comprising a response to the question; and

providing the fourth input to the first machine learning model, the first machine learning model being configured to output the second selection of the second parameter of the additional set of parameters.

12 . The method of claim 9 , wherein the first parameter or the additional set of parameters comprise a particular software service provided by a service provider or a configuration setting for the particular software service.

13 . The method of claim 8 , further comprising:

training the first machine learning model with natural language data; and

training the second machine learning model with support documentation for software services provided by a service provider.

14 . The method of claim 8 , further comprising:

receiving the recommendation from the second machine learning model; and

automatically performing the adjustment to the existing configuration of the distributed computing system by transmitting an application programming interface call to a service provider for the distributed computing system.

15 . A non-transitory computer-readable medium comprising program code that is executable by a processing device for causing the processing device to:

provide the target functionality and an existing configuration for the distributed computing system as input to a second machine learning model, the second machine learning model being configured to output a recommendation for an adjustment to the existing configuration of the distributed computing system based on an incompatibility between the target functionality and a configuration setting of a software service executed by the distributed computing system, wherein the adjustment comprises a modification to the configuration setting to enable the distributed computing system to perform the target functionality;

generate a response to the natural language input comprising the recommendation to the user in the natural language format; and

output, via the graphical user interface, the response to the user.

16 . The non-transitory computer-readable medium of claim 15 , wherein the natural language input is a first input, the response is a first response, and the non-transitory computer-readable medium further comprises program code that is executable by the processing device for causing the processing device to:

receive a second input from the user via the graphical user interface, the second input being in the natural language format;

17 . The non-transitory computer-readable medium of claim 16 , wherein the first parameter or the additional set of parameters comprise a particular software service provided by a service provider or a configuration setting for the particular software service.

18 . The non-transitory computer-readable medium of claim 16 , wherein the program code is further executable by the processing device for causing the processing device to: