CN-121998072-A - Generating AI industrial automation enhanced remote support services

CN121998072ACN 121998072 ACN121998072 ACN 121998072ACN-121998072-A

Abstract

The invention relates to a generated AI industrial automation enhanced remote support service. Industrial remote support systems act as interactive assistants that utilize generated Augmented Reality (AR) and Artificial Intelligence (AI) technologies to provide dynamic support information for industrial assets. The system may suggest solutions to performance problems based on earlier recorded solutions, thereby speeding up the process of finding solutions. A user may submit information about an industrial asset requesting support via an optical or data scan of the asset using an AR-capable client device. The system uses relevant context data retrieved from stored documents and relevant past chat history to enhance the user's prompts to assist the system's generated AI model in suggesting an accurate solution to the alarm condition or performance problem described by the user's prompts.

Inventors

Abu Sheikh sanjay mehrotra
Steven. P. Taylor
Jessica. L. Wante
Apana Ravenclanath
Brittany Floris

Assignees

罗克韦尔自动化技术公司

Dates

Publication Date: 20260508
Application Date: 20251031
Priority Date: 20241101

Claims (20)

1. A system, comprising: a memory storing an executable component, and A processor operatively coupled to the memory, the processor executing the executable component, the executable component comprising: a user interface component configured to receive visual data from a client device associated with an industrial client representative of a shape of an object within a field of view of the client device; An asset identification component configured to identify an industrial asset within a field of view of the client device based on a first analysis of the visual data; A context retrieval component configured to retrieve context data determined to be relevant to the industrial asset from a repository of industrial documents based on a result of the first analysis performed by the asset identification component, and A generating AI component configured to generate a natural language response including information about the industrial asset based on a result of the first analysis performed by the asset identification component, the contextual data, and a second analysis of a response prompted from a generating AI model, Wherein the user interface component is configured to present the natural language response on the client device.
2. The system of claim 1, wherein the information about the industrial asset comprises at least one of training information describing how to operate or maintain the industrial asset, problem solution information describing operation or maintenance actions designed to solve performance problems experienced by the industrial asset, an identity of the industrial asset, a function of the industrial asset, operational statistics for the industrial asset, information describing how to activate software on the industrial asset, or contact information of field technical support personnel capable of providing technical support for the industrial asset.
3. The system of claim 1, wherein, The user interface component is further configured to receive, in conjunction with receiving the visual data, a natural language prompt requesting some type of information about the industrial asset, and The generated AI component is configured to further perform the second analysis on the natural language prompt.
4. The system of claim 1, wherein the natural language hint specifies at least one of a description of a performance problem being experienced by the industrial asset, an identity of an alert generated by the industrial asset, a request for suggested precautions to be performed on the industrial asset for mitigating future performance problems, or a request for guidance in performing maintenance tasks on the industrial asset.
5. The system of claim 1, wherein the industrial document stored in the repository of industrial documents comprises at least one of a programming manual, an industrial equipment product specification document, a functional specification document, a knowledge base article describing a solution to a problem associated with industrial equipment or software, or a fault code document.
6. The system of claim 1, wherein, The generated AI component is configured to formulate a hint to the generated AI model as part of the second analysis, and the hint is designed to obtain information used by the generated AI component to generate the natural language response as a response from the generated AI model, and The generated AI component generates the hint based on the results of the first analysis and the context data.
7. The system of claim 1, wherein the context retrieval component is further configured to retrieve chat history data determined to be relevant to the industrial asset based on a result of the first analysis, and the generated AI component is configured to further perform the second analysis on the chat history data.
8. The system of claim 1, wherein the user interface component is configured to present the natural language response as an augmented reality presentation on the client device.
9. The system of claim 1, wherein, The visual data is a first visual data, The industrial asset is a first industrial asset, and The executable component further includes an asset registration component configured to create an asset record for a second industrial asset in response to identifying the second industrial asset based on analysis of the second visual data received by the user interface component and store the asset record as part of asset data maintained for the industrial customer.
10. The system of claim 1, wherein the industrial asset is at least one of an industrial controller, an I/O module, a motor drive, a human interface terminal, a contactor, an industrial machine, a component of the industrial machine, or a maintenance tool.
11. The system of claim 1, further comprising a device interface component configured to generate control instructions for the industrial asset based on a result of the second analysis.
12. The system of claim 11, wherein the control instructions are at least one of instructions to modify a set point of the controlled industrial process, instructions to change an operating mode of a device or machine, or instructions to change a speed of the controlled industrial process.
13. A method, comprising: Receiving, by a system including a processor, visual data from a client device associated with an industrial client, wherein the visual data represents a shape of an object within a field of view of the client device; Responsive to the receiving, identifying, by the system, an industrial asset within a field of view of the client device based on a first analysis of the visual data; retrieving, by the system, context data determined to be relevant to the industrial asset from a repository of industrial documents based on a result of the first analysis; Generating, by the system, a natural language response including information about the industrial asset based on a result of the first analysis, the contextual data, and a second analysis of the response prompted from a generated artificial intelligence AI model, and The natural language response is presented by the system on the client device.
14. The method of claim 13, wherein the information about the industrial asset comprises at least one of training information describing how to operate or maintain the industrial asset, problem solution information describing operation or maintenance actions designed to solve performance problems experienced by the industrial asset, an identity of the industrial asset, a function of the industrial asset, operational statistics for the industrial asset, information describing how to activate software on the industrial asset, or contact information of field technical support personnel capable of providing technical support for the industrial asset.
15. The method of claim 13, further comprising receiving, by the system in association with receiving the visual data, a natural language prompt requesting some type of information about the industrial asset, Wherein the second analysis is performed on a result of the first analysis, the context data, a response from the generated AI model prompt, and the natural language prompt.
16. The method of claim 15, wherein the natural language hint specifies at least one of a description of a performance problem being experienced by the industrial asset, an identity of an alert generated by the industrial asset, a request for suggested precautions to be performed on the industrial asset for mitigating future performance problems, or a request for guidance in performing maintenance tasks on the industrial asset.
17. The method of claim 13, further comprising, as part of the second analysis: a hint for the generated AI model is formulated by the system based on the results of the first analysis and the context data, and the hint is designed to obtain information used by the system to generate the natural language response as a response to the hint from the generated AI model.
18. The method of claim 13, wherein the industrial document stored in the repository of industrial documents comprises at least one of a programming manual, an industrial equipment product specification document, a functional specification document, a knowledge base article describing a solution to a problem associated with industrial equipment or software, or a fault code document.
19. A non-transitory computer-readable medium having instructions stored thereon that, in response to execution, cause a system comprising a processor to perform operations comprising: Receiving visual data from a client device associated with an industrial client, wherein the visual data represents a shape of an object within a field of view of the client device; in response to the receiving: identifying an industrial asset within a field of view of the client device based on a first analysis of the visual data; retrieving context data determined to be relevant to the industrial asset from a repository of industrial documents based on a result of the first analysis; Generating a natural language response including information about the industrial asset based on a result of the first analysis, the contextual data, and a response prompted from a generated artificial intelligence AI model, and The natural language response is presented on the client device.
20. The non-transitory computer-readable medium of claim 19, wherein the information about the industrial asset comprises at least one of training information describing how to operate or maintain the industrial asset, problem solution information describing operation or maintenance actions designed to solve performance problems experienced by the industrial asset, an identity of the industrial asset, a function of the industrial asset, operational statistics for the industrial asset, information describing how to activate software on the industrial asset, or contact information of field technical support personnel capable of providing technical support for the industrial asset.

Description

Generating AI industrial automation enhanced remote support services Technical Field The subject matter disclosed herein relates generally to industrial automation systems and, for example, to digital assistance technical support for industrial assets. Background Maintenance and troubleshooting of industrial control systems of a plant and its associated machines and equipment is typically performed by field service engineers or machine operators. While certain types of conventional machine alarms or fault conditions can be easily addressed, unfamiliar alarm conditions or system performance problems require service personnel to spend a significant amount of time and effort looking for solutions to the problem. These resolution efforts may include referencing a device or software manual or contacting customer support personnel of the provider to aid in diagnosing and resolving the condition. The above-described drawbacks of current methods of addressing industrial alarm conditions and performance problems are intended only to provide an overview of some of the problems of the current art, and are not intended to be exhaustive. Other problems of the prior art, as well as corresponding benefits of some of the various non-limiting embodiments described herein, may become more apparent upon review of the detailed description that follows. Disclosure of Invention The following presents a simplified summary in order to provide a basic understanding of some aspects described herein. This summary is not an extensive overview, nor is it intended to identify key/critical elements or to delineate the scope of the various aspects described herein. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is presented later. In one or more embodiments, a system is provided that includes a user interface component configured to receive visual data from a client device associated with an industrial client that represents a shape of an object within a field of view of the client device, an asset identification component configured to identify an industrial asset within the field of view of the client device based on a first analysis of the visual data, a context retrieval component configured to retrieve context data from a repository of an industrial document that is determined to be relevant to the industrial asset based on a result of the first analysis performed by the asset identification component, and a generation-type AI component configured to generate a natural language response that includes information about the industrial asset based on a result of the first analysis performed by the asset identification component, the context data, and a response from a generation-type AI model hint, wherein the user interface component is configured to present the natural language response on the client device. Further, one or more embodiments provide a method comprising receiving, by a system comprising a processor, visual data from a client device associated with an industrial client, wherein the visual data represents a shape of an object within a field of view of the client device, identifying, by the system, an industrial asset within the field of view of the client device based on a first analysis of the visual data in response to the receiving, retrieving, by the system, context data determined to be relevant to the industrial asset from a repository of the industrial document based on a result of the first analysis, generating, by the system, a natural language response comprising information about the industrial asset based on a result of the first analysis, the context data, and a response prompted from a generated Artificial Intelligence (AI) model, and presenting, by the system, the natural language response on the client device. Further, in accordance with one or more embodiments, a non-transitory computer-readable medium having instructions stored thereon that, in response to execution, cause a system to perform operations including receiving visual data from a client device associated with an industrial client, wherein the visual data represents a shape of an object within a field of view of the client device, and in response to the receiving, identifying an industrial asset within the field of view of the client device based on a first analysis of the visual data, retrieving context data determined to be related to the industrial asset from a repository of the industrial document based on a result of the first analysis, generating a natural language response including information about the industrial asset based on a result of the first analysis, the context data, and a response from a generated Artificial Intelligence (AI) model hint, and presenting the natural language response on the client device is provided. To the accomplishment of the foregoing and related ends, certain illustrative aspects are described herein in connection with the following de