Granted Patent B2

US 12,567,074 · App. 18/531,109 · Granted Mar 3, 2026

Inventors: Abhishek Mehrotra (New Berlin, WI); Steven P. Taylor (Madison, WI); Jessica L. Wiant (Chagrin Falls, OH); Aparna Ravindranath (Mayfield Heights, OH); Britney Flores (Sussex, WI); Pratyush Kumar Rout (Pune, IN)

Assignee: ROCKWELL AUTOMATION TECHNOLOGIES, INC.

G06Q30/01G06F40/40G06N3/0475

Abstract

Claims (65)

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 device interface component configured to monitor runtime data generated by industrial assets of an industrial automation system;

a context retrieval component configured to, in response to detection of an alarm condition based monitoring of the runtime data:

retrieve contextual data determined to be relevant to the alarm condition from a repository of industrial documentation, and

retrieve chat history data determined to be relevant to the alarm condition from archived histories of chats with the generative AI model; and

a generative AI component configured to

submit, as a prompt, the contextual data, the chat history data, and information about the alarm condition to the generative AI model, and

determine, based on a response to the prompt generated by the generative AI model, a countermeasure that at least one of mitigates the alarm condition or mitigates an effect of the alarm condition,

wherein the device interface component is further configured to send a control instruction to one or more of the industrial assets that causes the one or more industrial assets to perform the countermeasure.

2 . 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.

3 . The system of claim 1 , wherein the archived histories of chats 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.

4 . The system of claim 1 , wherein

the prompt is a first prompt,

the contextual data is first contextual data,

the chat history data is first chat history data,

the executable further comprise a user interface component configured to receive, as natural language input, a second prompt specifying a technical support issue relating to the industrial automation system, and

the context retrieval component is further configured to, in response to receipt of the second prompt:

retrieve second contextual data determined to be relevant to the technical support issue from the repository of industrial documentation,

retrieve second chat history data determined to be relevant to the technical support issue from the archived chat histories, and

submit the second contextual data, the second chat history data, and the second prompt to the generative AI component.

5 . The system of claim 4 , wherein

the generative AI component is further configured to generate, using the generative AI model, a natural language response to the second prompt based on analysis of the second prompt, the second contextual data, and the second chat history data,

wherein the natural language response describes one or more recommended actions for addressing the technical support issue.

6 . The system of claim 4 , wherein the second 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.

7 . The system of claim 4 , 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.

8 . The system of claim 4 , wherein the generative AI component is further configured to store the second prompt and the natural language response with the archived histories of chats.

9 . The system of claim 1 , 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.

10 . A method, comprising:

monitoring, by a system comprising a processor, runtime data generated by industrial assets of an industrial automation system;

in response to detecting an alarm condition based on the monitoring of the runtime data:

retrieving, by the system, contextual data determined to be relevant to the alarm condition from a repository of industrial documentation;

retrieving, by the system, chat history data determined to be relevant to the alarm condition from archived chat histories;

submitting, by the system as a prompt, the contextual data, the chat history data, and information about the alarm condition to a generative artificial intelligence (AI) component;

determining, by the system based on a response to the prompt generated by 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 of the industrial assets that causes the one or more industrial assets to perform the countermeasure.

11 . 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.

12 . 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.

13 . The method of claim 10 , wherein

the prompt is a first prompt,

the contextual data is first contextual data,

the chat history data is first chat history data,

the method further comprises:

receiving, from a client device, a second prompt formatted as a natural language input and requesting assistance with a technical support issue relating to the industrial automation system;

in response to the receiving:

retrieve second contextual data determined to be relevant to the technical support issue from the repository of industrial documentation,

retrieve second chat history data determined to be relevant to the technical support issue from the archived chat histories, and

submit the second contextual data, the second chat history data, and the second prompt to the generative AI component.

14 . The method of claim 13 , further comprising:

generating, by the system using the generative AI model, a natural language response to the second prompt based on analysis of the second prompt, the second contextual data, and the second chat history data,

wherein the natural language response describes one or more recommended actions for addressing the technical support issue.

15 . The method of claim 13 , 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.

16 . The method of claim 13 , 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.

17 . The method of claim 13 , further comprising storing the prompt and the natural language response as part of the archived chat histories.

18 . The method of claim 10 , 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.

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:

monitoring runtime data generated by industrial assets of an industrial automation system;

in response to detecting an alarm condition based on the monitoring of the runtime data:

retrieving contextual data determined to be relevant to the alarm condition from a repository of industrial documentation;

retrieving chat history data determined to be relevant to the alarm condition from archived chat histories;

submitting, as a prompt, the contextual data, the chat history data, and information about the alarm condition to a generative artificial intelligence (AI) component;

determining, based on a response to the prompt generated by 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 a control instruction to one or more of the industrial assets that causes the one or more industrial assets to perform the countermeasure.

20 . 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.

Assignments (1)

Continuity (2)

References Cited (71)