# US 2025/0291327 A1 · Systems and methods for large language model (llm) generated security configuration based on system characteristics

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0291327 A1
- Document ID: US20250291327A1
- Status: Published application
- Kind: A1
- Application number: 18/603,444
- Filed: 2024-03-13
- Published: 2025-09-18
- Earliest claimed: 2024-03-13
- Assignees: Rockwell Automation Technologies, Inc.
- Applicants: Rockwell Automation Technologies, Inc.
- Inventors: Jack M. Visoky; Diane E. Golden; Michael A. Spaner
- Web page: https://patentgrep.com/patent/US20250291327A1

## CPC

- G05B 19/0426: {Programming the control sequence}
- G06F 9/44505: {Configuring for program initiating, e.g. using registry, configuration files}
- G05B 19/056: {Programming the PLC}
- G05B 19/4185: {characterised by the network communication}
- G06N 3/045: Combinations of networks
- G06N 3/08: Learning methods
- G06N 20/00: Machine learning
- H04L 41/16: using machine learning or artificial intelligence
- G05B 2219/31103: Configure parameters of controlled devices
- G06F 9/455: Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

A method includes transmitting, from a computing device, a request to generate a configuration file for an industrial automation device disposed within an industrial automation system configured to perform an industrial automation process, wherein the industrial automation device is communicatively coupled to an operational technology (OT) network, transmitting, from the computing device, one or more characteristics of the industrial automation device, the industrial automation system, the industrial automation process, the OT network, or any combination thereof, receiving, at the computing device, the configuration file for the industrial automation device, wherein the configuration file for the industrial automation device was generated using one or more large language models (LLMs) based on the one or more characteristics of the industrial automation device, the industrial automation system, the industrial automation process, the OT network, or any combination thereof, and installing the configuration file on the industrial automation device.

## Claims

### Claim 1

A method, comprising:
receiving, from a computing device, a request to generate a configuration file for an industrial automation device disposed within an industrial automation system configured to perform an industrial automation process, wherein the industrial automation device is communicatively coupled to an operational technology (OT) network;
receiving, from the computing device, one or more characteristics of the industrial automation device, the industrial automation system, the industrial automation process, the OT network, or any combination thereof;
generating, via processing circuitry, using one or more large language models (LLMs), the configuration file for the industrial automation device based on the one or more characteristics of the industrial automation device, the industrial automation system, the industrial automation process, the OT network, or any combination thereof; and
providing the configuration file for the industrial automation device to the computing device.

### Claim 2 (depends on 1)

The method of claim 1, comprising training the one or more LLMs using a training data set, wherein the training data set comprises user data, one or more existing configuration files, one or more industry standards, one or more digested OT network incident logs, one or more security policies, one or more user-specific guidelines, time series data, log data, process data, one or more product manuals, or any combination thereof.

### Claim 3 (depends on 1)

The method of claim 1, comprising:
receiving, from the computing device, feedback on the configuration file;
generating, via the processing circuitry, using the one or more LLMs, an additional configuration file for the industrial automation device based on the feedback and the one or more characteristics of the industrial automation device, the industrial automation system, the industrial automation process, the OT network, or any combination thereof; and
providing the additional configuration file for the industrial automation device to the computing device.

### Claim 4 (depends on 3)

The method of claim 3, wherein the feedback comprises a modification to the request.

### Claim 5 (depends on 3)

The method of claim 3, wherein the feedback comprises a modification to the configuration file.

### Claim 6 (depends on 3)

The method of claim 3, comprising training the one or more LLMs based on the feedback.

### Claim 7 (depends on 1)

The method of claim 1, wherein the request comprises a natural language input.

### Claim 8 (depends on 1)

The method of claim 1, wherein the one or more characteristics of the industrial automation device, the industrial automation system, the industrial automation process, the OT network, or any combination thereof comprise identification of one or more assets on the OT network, a component list, discovery data, network topology data, OT network architecture, one or more security policies, one or more maintenance logs, one or more service logs, industry data, location data, process data, or some combination thereof.

### Claim 9

A method, comprising:
transmitting, from a computing device, a request to generate a configuration file for an industrial automation device disposed within an industrial automation system configured to perform an industrial automation process, wherein the industrial automation device is communicatively coupled to an operational technology (OT) network;
transmitting, from the computing device, one or more characteristics of the industrial automation device, the industrial automation system, the industrial automation process, the OT network, or any combination thereof;
receiving, at the computing device, the configuration file for the industrial automation device, wherein the configuration file for the industrial automation device was generated using one or more large language models (LLMs) based on the one or more characteristics of the industrial automation device, the industrial automation system, the industrial automation process, the OT network, or any combination thereof; and
installing the configuration file on the industrial automation device.

### Claim 10 (depends on 9)

The method of claim 9, wherein the one or more LLMs are hosted on a remote server or a cloud server.

### Claim 11 (depends on 10)

The method of claim 10, comprising:
transmitting the request and the one or more characteristics to the remote server or the cloud server; and
receiving, from the cloud server or the remote server, the configuration file.

### Claim 12 (depends on 9)

The method of claim 9, wherein the one or more LLMs are hosted on an edge device.

### Claim 13 (depends on 9)

The method of claim 9, wherein the one or more LLMs are hosted on a compute surface within the OT network.

### Claim 14 (depends on 9)

The method of claim 9, wherein the request comprises a natural language input.

### Claim 15 (depends on 9)

The method of claim 9, wherein the one or more characteristics of the industrial automation device, the industrial automation system, the industrial automation process, the OT network, or any combination thereof comprise identification of one or more assets on the OT network, a component list, discovery data, network topology data, OT network architecture, one or more security policies, one or more maintenance logs, one or more service logs, industry data, location data, process data, or some combination thereof.

### Claim 16

A non-transitory computer readable medium storing instructions that, when executed by processing circuitry, cause the processing circuitry to perform actions comprising:
receiving, via a user interface of a computing device, an input indicative of a request for a configuration file for an industrial automation device disposed within an industrial automation system configured to perform an industrial automation process, wherein the industrial automation device is communicatively coupled to an operational technology (OT) network;
providing, via the processing circuitry, the request for the configuration file for the industrial automation device to one or more large language models (LLMs);
providing, via the processing circuitry, one or more characteristics of the industrial automation device, the industrial automation system, the industrial automation process, the OT network, or any combination thereof to the one or more LLMs;
generating, via the processing circuitry, using the one or more LLMs, the configuration file for the industrial automation device based on the one or more characteristics of the industrial automation device, the industrial automation system, the industrial automation process, the OT network, or any combination thereof; and
providing the configuration file to the industrial automation device for installation.

### Claim 17 (depends on 16)

The non-transitory computer readable medium of claim 16, wherein the one or more LLMs are hosted on the computing device.

### Claim 18 (depends on 16)

The non-transitory computer readable medium of claim 16, wherein the one or more LLMs apply a role-based access control based on a user profile associated with the request, wherein the one or more LLMs consider an authority granted to the user profile when generating the configuration file.

### Claim 19 (depends on 16)

The non-transitory computer readable medium of claim 16, wherein the input indicative of the request comprises a natural language input.

### Claim 20 (depends on 16)

The non-transitory computer readable medium of claim 16, wherein the one or more characteristics of the industrial automation device, the industrial automation system, the industrial automation process, the OT network, or any combination thereof comprise identification of one or more assets on the OT network, a component list, discovery data, network topology data, OT network architecture, one or more security policies, one or more maintenance logs, one or more service logs, industry data, location data, process data, or some combination thereof.
