# US 2025/0148477 A1 · Generative ai for customer support acceleration

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

- Number: US 2025/0148477 A1
- Document ID: US20250148477A1
- Status: Published application
- Kind: A1
- Application number: 18/531,109
- Filed: 2023-12-06
- Published: 2025-05-08
- Earliest claimed: 2023-11-02
- Assignees: Rockwell Automation Technologies, Inc.
- Applicants: Rockwell Automation Technologies, Inc.
- Inventors: Abhishek Mehrotra; Steven P. Taylor; Jessica L. Wiant; Aparna Ravindranath; Britney Flores; Pratyush Kumar Rout
- Web page: https://patentgrep.com/patent/US20250148477A1

## CPC

- G06Q 30/01: Customer relationship services
- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- G06N 3/0475: Generative networks
- G06Q 10/20: Administration of product repair or maintenance
- H04L 12/1895: {for short real-time information, e.g. alarms, notifications, alerts, updates}
- H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
- H04L 51/04: Real-time or near real-time messaging, e.g. instant messaging [IM]
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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

An industrial technical support system acts as an interactive assistant that leverages generative artificial intelligence (AI) techniques to suggest solutions to industrial alarm conditions or other performance problems based on earlier documented solutions, thereby expediting the process of finding alarm resolutions. The system enhances a user's prompt with relevant contextual data retrieved from stored documentation as well as relevant past chat histories to assist the system's generative AI model in recommending accurate resolutions to alarm conditions or performance issues described by the user's prompt.

## Claims

### Claim 1

A system, comprising:
a memory that stores executable components and a generative artificial intelligence (AI) model; and
a processor, operatively coupled to the memory, that executes the executable components, the executable components comprising:
a user interface component configured to receive, as natural language input, a prompt specifying a technical support issue relating to an industrial automation system;
a context retrieval component configured to retrieve contextual data determined to be relevant to the technical support issue from a repository of industrial documentation, and to retrieve chat history data determined to be relevant to the technical support issue from archived chat histories; and
a generative AI component configured to generate, using the generative AI model, a natural language response to the prompt based on analysis of the prompt, the contextual data, and the chat history data,
wherein the natural language response describes one or more recommended actions for addressing the technical support issue.

### Claim 2 (depends on 1)

The system of claim 1, wherein the industrial documentation stored in the repository of industrial documentation comprises at least one of programming manuals, industrial device manuals, industrial device product specification documents, functional specification documents, knowledgebase articles describing solutions to problems associated with industrial devices or software, or failure code documentation.

### Claim 3 (depends on 1)

The system of claim 1, wherein the archived chat histories comprise prompts submitted to the system requesting assistance with technical support issues and responses generated by the generative AI model indicating resolutions to the technical support issues.

### Claim 4 (depends on 1)

The system of claim 1, wherein the prompt specifies at least one of an industrial asset experiencing a performance issue, a description of the performance issue, an identity of an alarm generated by an industrial asset, a request for recommended preventative measures to perform on an industrial asset for mitigating future performance issues, or a request for guidance in performing a maintenance task on an industrial asset.

### Claim 5 (depends on 1)

The system of claim 1, wherein the natural language response comprises at least one of an explanation of an alarm condition, an ordered list of steps for performing a corrective measure that addresses the technical support issue, or an estimate of an amount of time required to perform the one or more recommended actions for addressing the technical support issue.

### Claim 6 (depends on 1)

The system of claim 1, wherein the generative AI component is further configured to store the prompt and the natural language response with the archived chat histories.

### Claim 7 (depends on 1)

The system of claim 1, wherein
the contextual data is first contextual data,
the chat history data is first chat history data,
the executable further comprising a device interface component configured to monitor runtime data generated by industrial assets in operation within an industrial facility, and
the context retrieval component is further configured to, in response to detection of an alarm condition based on monitoring of the runtime data:
retrieve second contextual data determined to be relevant to the alarm condition from the repository of industrial documentation,
retrieve second chat history data determined to be relevant to the alarm condition from the archived chat histories, and
submit the second contextual data, the second chat history data, and information about the alarm condition to the generative AI component.

### Claim 8 (depends on 7)

The system of claim 7, wherein
the generative AI component is further configured to determine, using the generative AI model, a countermeasure that at least one of mitigates the alarm condition or mitigates an effect of the alarm condition, and
the device interface component is further configured to send a control instruction to one or more industrial assets that causes the one or more industrial assets to perform the countermeasure.

### Claim 9 (depends on 8)

The system of claim 8, wherein the countermeasure is at least one of placing a machine in a safe operating mode, placing a machine in a stopped mode, modifying a setpoint value of a controlled industrial process, changing an operating mode of a machine, clearing an alarm, or initiating a notification of the alarm condition.

### Claim 10

A method, comprising:
receiving, from a client device by a system comprising a processor, a prompt formatted as natural language input and requesting assistance with a technical support issue relating to an industrial automation system; and
in response to the receiving:
retrieving, by the system, contextual data determined to be relevant to the technical support issue from a repository of industrial documentation;
retrieving, by the system, chat history data determined to be relevant to the technical support issue from archived chat histories;
generating, by the system using a generative artificial intelligence (AI) model, a natural language response to the prompt based on analysis of the prompt, the contextual data, and the chat history data, wherein the natural language response describes one or more recommended actions for addressing the technical support issue; and
rendering, by the system, the natural language response on the client device.

### Claim 11 (depends on 10)

The method of claim 10, wherein the industrial documentation stored in the repository of industrial documentation comprises at least one of programming manuals, industrial device manuals, industrial device product specification documents, functional specification documents, knowledgebase articles describing solutions to problems associated with industrial devices or software, or failure code documentation.

### Claim 12 (depends on 10)

The method of claim 10, wherein the archived chat histories comprise prompts submitted to the system requesting assistance with technical support issues and responses generated by the generative AI model in response to the prompts indicating resolutions to the technical support issues.

### Claim 13 (depends on 10)

The method of claim 10, wherein the prompt specifies at least one of an industrial asset experiencing a performance issue, a description of the performance issue, an identity of an alarm generated by an industrial asset, a request for recommended preventative measures to perform on an industrial asset for mitigating future performance issues, or a request for guidance in performing a maintenance task on an industrial asset.

### Claim 14 (depends on 10)

The method of claim 10, wherein the natural language response comprises at least one of an explanation of an alarm condition, an ordered list of steps for performing a corrective measure that addresses the technical support issue, or an estimate of an amount of time required to perform the one or more recommended actions for addressing the technical support issue.

### Claim 15 (depends on 10)

The method of claim 10, further comprising storing the prompt and the natural language response as part of the archived chat histories.

### Claim 16 (depends on 10)

The method of claim 10, wherein
the contextual data is first contextual data,
the chat history data is first chat history data,
the method further comprises:
monitoring, by the system, runtime data generated by industrial assets in operation within an industrial facility, and
in response to detection of an alarm condition based on monitoring of the runtime data:
retrieve second contextual data determined to be relevant to the alarm condition from the repository of industrial documentation,
retrieve second chat history data determined to be relevant to the alarm condition from the archived chat histories, and
submit the second contextual data, the second chat history data, and information about the alarm condition to the generative AI component.

### Claim 17 (depends on 16)

The method of claim 16, further comprising:
determining, by the system using the generative AI model, a countermeasure that at least one of mitigates the alarm condition or mitigates an effect of the alarm condition, and
sending, by the system, a control instruction to one or more industrial assets, wherein the control instruction is configured to cause the one or more industrial assets to perform the countermeasure.

### Claim 18 (depends on 17)

The method of claim 17, wherein the countermeasure is at least one of placing a machine in a safe operating mode, placing a machine in a stopped mode, modifying a setpoint value of a controlled industrial process, changing an operating mode of a machine, clearing an alarm, or initiating a notification of the alarm condition.

### Claim 19

A non-transitory computer-readable medium having stored thereon instructions that, in response to execution, cause a system comprising a processor to perform operations, the operations comprising:
receiving, from a client device, a natural language prompt requesting assistance with a technical support issue relating to an industrial automation system; and
in response to the receiving:
retrieving contextual data determined to be relevant to the technical support issue from a repository of industrial documentation;
retrieving chat history data determined to be relevant to the technical support issue from archived chat histories;
generating, using a generative artificial intelligence (AI) model, a natural language response to the prompt based on analysis of the natural language prompt, the contextual data, and the chat history data, wherein the natural language response describes one or more recommended actions for addressing the technical support issue; and
displaying the natural language response on the client device.

### Claim 20 (depends on 19)

The non-transitory computer-readable medium of claim 19, wherein the industrial documentation stored in the repository of industrial documentation comprises at least one of programming manuals, industrial device manuals, industrial device product specification documents, functional specification documents, knowledgebase articles describing solutions to problems associated with industrial devices or software, or failure code documentation.
