US-20260129008-A1 - CHATBOT MULTIUSER PROMPT INTERACTIONS

US20260129008A1US 20260129008 A1US20260129008 A1US 20260129008A1US-20260129008-A1

Abstract

An industrial chatbot system and associated chatbot interface support various user experience features designed to improve the chatbot's utility within an industrial context. These features include the ability to invite selected users or teams to participate in an ongoing chatbot thread or conversation, the ability to switch between knowledge domains during a chatbot session, the ability to save prompts for selective resubmission to the system, the ability to organize and share multiple chatbot threads among different teams or team members, constraining submission of prompts in a collaborative multiuser context so that prompts are submitted and processed in an organized manner, and the ability to define prompt-based dashboards that can be stored and deployed on demand or in response to defined conditions.

Inventors

Mario Noble
Kelly Ceballos
Lucas G. Thompson
Sylwia Koloczek

Assignees

ROCKWELL AUTOMATION TECHNOLOGIES, INC.

Dates

Publication Date: 20260507
Application Date: 20251006

Claims (20)

1 . A system, comprising: a memory that stores executable components; and a processor, operatively coupled to the memory, that executes the executable components, the executable components comprising: a user interface component configured to render instances of a chatbot interface of a multi-user chatbot thread on respective client devices of participants of the multi-user chatbot thread, and to receive, via interaction with the instances of the chatbot interface, natural language prompts requesting information about industrial operations within an industrial facility; and a generative artificial intelligence (AI) component configured to process the natural language prompts of the chatbot thread and to generate, based on generative AI analysis of the natural language prompts, responses to the natural language prompts, the responses comprising at least one of natural language information or graphical content, wherein the user interface component is configured to render the natural language prompts and the responses to the natural language prompts on the instances of the of the chatbot interface, and the user interface component is further configured to, in response to determining that a participant of the multi-user chatbot thread is entering text into a prompt entry field of an instance of the chatbot interface associated with the participant, render, in prompt entry fields of other instances of the chatbot interface associated with other participants of the multi-user chatbot thread, an indication that the participant is entering the text.
2 . The system of claim 1 , wherein the user interface component is further configured to prevent entry of text in the prompt entry fields of the other instances of the chatbot interface associated with the other participants while the participant is entering the text.
3 . The system of claim 1 , wherein the indication identifies the participant entering the text.
4 . The system of claim 1 , wherein the user interface component is further configured to, in response to determining that the generative AI component is processing a natural language prompt submitted as part of the chatbot thread, render, in the prompt entry field of the instance of the chatbot interface and the prompt entry fields of the other instances of the chatbot interface, an indication that the system is processing the natural language prompt.
5 . The system of claim 1 , wherein the instances of the chatbot interface render a sequential list of the natural language prompts that were submitted for the multi-user chatbot thread by the participants and the responses to the natural language prompts that were generated by the generative AI component.
6 . The system of claim 5 , wherein the user interface component is configured to receive, via interaction with one of the instances of the chatbot interface, selection of one or more of the natural language prompts to be added to a dashboard definition, and the generative AI component is further configured to, based on the selection, define and store a dashboard definition that, in response to execution, generates and renders a dashboard based on generative AI processing of the one or more of the natural language prompts.
7 . The system of claim 1 , wherein the multi-user chatbot thread has an associated permission setting that defines, as the participants, a first team of participants permitted to participate in the multi-user chatbot thread; the user interface component is configured to, in response to receipt, via interaction with one of the instances of the chatbot interface, of a request to share the multi-user chatbot thread with a second team of participants, modify the permission setting to permit the second team of participants to view and interact with the multi-user chatbot thread.
8 . The system of claim 1 , wherein the generative AI analysis is performed using an analytic model, of a set of available analytic models, trained with a set of training data relevant to a knowledge domain that is currently selected for the multi-user chatbot thread, and the generative AI component is further configured to switch the knowledge domain that is currently selected for the multi-user chatbot thread from a first knowledge domain to a second knowledge domain in response to receipt, via interaction with one of the instances of the chatbot interface, of a request to switch the multi-user chatbot thread to the second knowledge domain.
9 . The system of claim 8 , wherein the user interface is configured to render, on the one of the instances of the chatbot interface, a domain switching window that renders icons representing respective knowledge domains available for processing the natural language prompts, and the request to switch the multi-user chatbot thread to the second knowledge domain is received via selection of one of the icons representing the second knowledge domain.
10 . A method, comprising: rendering, by an industrial chatbot system comprising a processor, instances of a chatbot interface of a multi-user chatbot thread on respective client devices of participants of the multi-user chatbot thread; receiving, by the industrial chatbot system via interaction with the instances of the chatbot interface, natural language prompts requesting information about industrial operations within an industrial facility; generating, by the industrial chatbot system based on generative artificial intelligence (AI) analysis of the natural language prompts, responses to the natural language prompts, the responses comprising at least one of natural language information or graphical content; rendering, by the industrial chatbot system, the natural language prompts and the responses to the natural language prompts on the instances of the of the chatbot interface; and in response to determining that a participant of the multi-user chatbot thread is submitting text into a prompt entry field of an instance of the chatbot interface associated with the participant, rendering, in prompt entry fields of other instances of the chatbot interface associated with other participants of the multi-user chatbot thread, an indication that the participant is submitting the text.
11 . The method of claim 10 , further comprising preventing, by the industrial chatbot system, submission of text in the prompt entry fields of the other instances of the chatbot interface associated with the other participants while the participant is submitting the text.
12 . The method of claim 10 , wherein the indication identifies the participant entering the text.
13 . The method of claim 10 , further comprising, in response to determining that the generative AI analysis is processing a natural language prompt submitted as part of the chatbot thread, rendering, by the industrial chatbot system in the prompt entry field of the instance of the chatbot interface and the prompt entry fields of the other instances of the chatbot interface, an indication indicating that the system is processing the natural language prompt.
14 . The method of claim 10 , wherein the instances of the chatbot interface render a sequential list of the natural language prompts that were submitted for the multi-user chatbot thread by the participants and the responses to the natural language prompts that were generated by the generative AI analysis.
15 . The method of claim 14 , further comprising: receiving, by the industrial chatbot system via interaction with one of the instances of the chatbot interface, selection of one or more of the natural language prompts to be added to a dashboard definition, and define and store, based on the selection, a dashboard definition that, in response to execution, generates and renders a dashboard based on generative AI processing of the one or more of the natural language prompts.
16 . The method of claim 10 , wherein the multi-user chatbot thread has an associated permission setting that defines, as the participants, a first team of participants permitted to participate in the multi-user chatbot thread; the method further comprises, in response to receiving, via interaction with one of the instances of the chatbot interface, a request to share the multi-user chatbot thread with a second team of participants, modify the permission setting to permit the second team of participants to view and interact with the multi-user chatbot thread.
17 . The method of claim 10 , wherein the generative AI analysis is performed using an analytic model, of a set of available analytic models, trained with a set of training data relevant to a knowledge domain that is currently selected for the multi-user chatbot thread, and the method further comprises switching, by the industrial chatbot system, the knowledge domain that is currently selected for the multi-user chatbot thread from a first knowledge domain to a second knowledge domain in response to receiving, via interaction with one of the instances of the chatbot interface, a request to switch the multi-user chatbot thread to the second knowledge domain.
18 . The method of claim 17 , wherein the receiving of the request to switch the multi-user chatbot thread to the second knowledge domain comprises: rendering, on the one of the instances of the chatbot interface, a domain switching window that renders icons representing respective knowledge domains available for processing the natural language prompts, and receiving, via interaction with the domain switching window, selection of one of the icons representing the second knowledge domain.
19 . A non-transitory computer-readable medium having stored thereon instructions that, in response to execution, cause an industrial chatbot system comprising a processor to perform operations, the operations comprising: rendering instances of a chatbot interface of a multi-user chatbot thread on respective client devices of participants of the multi-user chatbot thread; receiving, via interaction with the instances of the chatbot interface, natural language prompts requesting information about industrial operations within an industrial facility; generating, based on generative artificial intelligence (AI) analysis of the natural language prompts, responses to the natural language prompts, the responses comprising at least one of natural language information or graphical content; rendering the natural language prompts and the responses to the natural language prompts on the instances of the of the chatbot interface, and in response to determining that a participant of the multi-user chatbot thread is submitting a natural language prompt into a prompt entry field of an instance of the chatbot interface associated with the participant, rendering, in prompt entry fields of other instances of the chatbot interface associated with other participants of the multi-user chatbot thread, an indication that the participant is submitting the natural language prompt.
20 . The non-transitory computer-readable medium of claim 19 , wherein the operations further comprises preventing submission of natural language prompts in the prompt entry fields of the other instances of the chatbot interface associated with the other participants while the participant is submitting the natural language prompt.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to U.S. Provisional Patent Application Ser. No. 63/716,429, filed on Nov. 5, 2024, and entitled “GENERATIVE AI INDUSTRIAL USER EXPERIENCE PROMPT WORKFLOWS,” the entirety of which is incorporated herein by reference. TECHNICAL FIELD The subject matter disclosed herein relates generally to industrial automation systems, and, for example, to the use of industrial chatbots BACKGROUND ART The industrial devices and assets that make up the manufacturing systems operating within an industrial facility generate a large amount of diverse operational, status, and maintenance data. Aggregated analysis of this information could yield useful insights into the plant's operations. However, industrial analysis and reporting systems can be difficult to use, particularly from the standpoint of the user interfaces used to engage with these systems. The above-described deficiencies of current approaches to resolving industrial alarm conditions and performance issues are merely intended to provide an overview of some of the problems of current technology, and are not intended to be exhaustive. Other problems with the state of the art, and corresponding benefits of some of the various non-limiting embodiments described herein, may become further apparent upon review of the following detailed description. BRIEF DESCRIPTION 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, comprising a user interface component configured to render instances of a chatbot interface of a multi-user chatbot thread on respective client devices of participants of the multi-user chatbot thread, and to receive, via interaction with the instances of the chatbot interface, natural language prompts requesting information about industrial operations within an industrial facility; and a generative artificial intelligence (AI) component configured to process the natural language prompts of the chatbot thread and to generate, based on generative AI analysis of the natural language prompts, responses to the natural language prompts, the responses comprising at least one of natural language information or graphical content, wherein the user interface component is configured to render the natural language prompts and the responses to the natural language prompts on the instances of the of the chatbot interface, and the user interface component is further configured to, in response to determining that a participant of the multi-user chatbot thread is entering text into a prompt entry field of an instance of the chatbot interface associated with the participant, render, in prompt entry fields of other instances of the chatbot interface associated with other participants of the multi-user chatbot thread, an indication that the participant is entering the text. Also, one or more embodiments provide a method, comprising rendering, by an industrial chatbot system comprising a processor, instances of a chatbot interface of a multi-user chatbot thread on respective client devices of participants of the multi-user chatbot thread; receiving, by the industrial chatbot system via interaction with the instances of the chatbot interface, natural language prompts requesting information about industrial operations within an industrial facility; generating, by the industrial chatbot system based on generative artificial intelligence (AI) analysis of the natural language prompts, responses to the natural language prompts, the responses comprising at least one of natural language information or graphical content; rendering, by the industrial chatbot system, the natural language prompts and the responses to the natural language prompts on the instances of the of the chatbot interface; and in response to determining that a participant of the multi-user chatbot thread is submitting text into a prompt entry field of an instance of the chatbot interface associated with the participant, rendering, in prompt entry fields of other instances of the chatbot interface associated with other participants of the multi-user chatbot thread, an indication that the participant is submitting the text. Also, according to one or more embodiments, a non-transitory computer-readable medium is provided having stored thereon instructions that, in response to execution, cause an industrial chatbot system to perform operations, the operations comprising rendering instances of a chatbot interface of a multi-user chatbot thread on respective client devices of participants of the multi-user chatbot thread; receiving, via interacti