RPA Robot Step Generation from Process Mining Activity Names

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current process mining technologies are unable to directly and automatically translate discovered processes into robotic process automation (RPA) implementations, requiring manual user analysis and definition of each step, which is time-consuming and complex.

Innovation Solution

A system and method for generating a natural language representation of RPA robot steps using a large language model based on process mining activity names, instructions, and system descriptions, allowing automatic translation into RPA steps.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual user analysis and definition of each step is used to translate process mining results into RPA implementations, then the automation can be accurately created, but the process becomes time-consuming and complex

Engineering Contradiction:
Improveaccuracy of automationVSAvoidtime required for automation setup
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent introduces an intermediary system comprising a process mining module, activity recognition module, and RPA generation module that automatically translates process mining activity names into RPA robot actions. This intermediary automation framework bridges the gap between process discovery and RPA implementation, eliminating the need for manual step-by-step analysis while maintaining accuracy through structured activity recognition and automated code generation.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If manual user analysis and definition of each step is used to translate process mining results into RPA implementations, then the automation can be accurately created, but the process complexity increases

Engineering Contradiction:
Improveaccuracy of automationVSAvoidcomplexity of automation setup process
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system enables self-service automation generation by automatically analyzing process mining activity names and translating them into RPA robot actions without requiring manual user intervention for each step. The activity recognition module autonomously interprets activity meanings, and the RPA generation module automatically creates the corresponding automation code, significantly reducing process complexity while maintaining accuracy.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the manual mechanical process of analyzing and defining each automation step with an automated computational system. The activity recognition module uses natural language processing to interpret activity names, and the RPA generation module automatically generates robot actions, substituting human manual analysis with intelligent automated systems that reduce complexity.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If automatic translation from process mining activity names to RPA steps is implemented, then time and effort are reduced, but the system complexity increases

Engineering Contradiction:
Improvespeed of automation creationVSAvoidsystem architecture complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system is segmented into distinct functional modules: a process mining module for discovering processes, an activity recognition module for interpreting activity names, and an RPA generation module for creating robot actions. This segmentation allows each module to specialize in a specific task, improving productivity through automated translation while managing system complexity through modular architecture that can be developed and maintained independently.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS20250111187A1Generating RPA robots from process mining activity names
Publication Date: 2025.04.03 UIPATH INC
  • US20250111187A1 patent drawing
  • US20250111187A1 patent drawing
  • US20250111187A1 patent drawing

AI summary

Systems and methods for generating a natural language representation of one or more steps to be performed by one or more RPA (robotic process automation) robots for performing an activity are provided. One or more prompts defining 1) instructions, 2) a description of a process, 3) a name of a source system from which the process was extracted, and 4) a name of an activity of the process are received. A natural language representation of one or more steps to be performed by one or more RPA (robotic process automation) robots for performing the activity is performed using a large language model based on the instructions, the description of the process, the name of the source system, and the name of the activity. The natural language representation of the one or more steps to be performed by the one or more RPA robots for performing the activity is output.