US 2026/0300830 A1Published application

System and Method for Context-Aware Multi-Module Routing and Dynamic Workflow Execution

AssigneeABB Schweiz AG

InventorsNitesh Reddy, Lokesh Shelva, Dharshen K, Anisha Agrahari, Shubham Roy, Karthikeyan K, Ravisastry Panyam, Jagadish Songapa Gounder, Ajaykumar Rajkumar

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

A system and method for performing context-aware multi-module routing and dynamic workflow execution for assisting a user in an industrial environment includes a master agent that receives and analyzes an input to identify one or more tasks to fulfil, identifies one or more ML modules among a plurality of ML modules suitable to perform the one or more tasks, based on at least one of: historical usage patterns, context of the one or more tasks, and one or more keywords associated with the one or more tasks; generates a dynamic workflow of sequence for invoking the identified one or more ML modules and executes the dynamic workflow; generates a final result based on aggregation of the intermediate results generated by the one or more ML modules, where the final result is provided as a response to the input to assist the user.

Claims14

Dependent claims

A system that performs context-aware multi-module routing and dynamic workflow execution, for assisting a user in an industrial environment, comprising:

a master agent;
a plurality of machine learning (ML) modules communicatively coupled with the master agent;
wherein the master agent is configured to:
receive an input comprising one or more user requirements related to the industrial environment;
analyze the input to identify one or more tasks to fulfil the one or more user requirements;
identify one or more ML modules among the plurality of ML modules suitable to perform the one or more tasks, based on at least one of:
historical usage patterns, context of the one or more tasks, and one or more keywords associated with the one or more tasks;
generate a dynamic workflow of sequence for invoking the identified one or more ML modules;
execute the dynamic workflow by invoking the identified one or more ML modules according to the sequence, wherein each of the identified one or more ML modules is selected to perform at least one task among the one or more tasks and generate intermediate results;
and
generate a final result based on aggregation of the intermediate results generated by the one or more ML modules by the execution of the dynamic workflow;
wherein the final result is provided as a response to the input to assist the user;
and
wherein the dynamic workflow is adjustable based on real-time outcomes of the execution of the dynamic workflow.

11 more elements

A method of context-aware multi-module routing and dynamic workflow execution for assisting a user in an industrial environment, the method comprising:

receiving, by a master agent, an input comprising one or more user requirements related to the industrial environment;
analyzing, by the master agent, the input to identify one or more tasks to fulfil the one or more user requirements;
identifying, by the master agent, one or more machine learning (ML) modules among a plurality of ML modules suitable to perform the one or more tasks, based on at least one of:
historical usage patterns, context of the one or more tasks, and one or more keywords associated with the one or more tasks;
generating, by the master agent, a dynamic workflow of sequence for invoking the identified one or more ML modules;
executing, by the master agent, the dynamic workflow by invoking the identified one or more ML modules according to the sequence, wherein each of the identified one or more ML modules is selected to perform at least one task among the one or more tasks and generate intermediate results;
and
generating, by the master agent, a final result based on aggregation of the intermediate results of the identified one or more ML modules;
wherein the final result is provided as a response to the input to assist the user, and wherein the dynamic workflow is adjustable based on real-time outcomes of the execution of the dynamic workflow.

6 more elements

Dependencies are inferred from the claim text.