AI Annotation Generation for Troubleshooting RPA Workflows

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing RPA workflows lack sufficient annotations and documentation, making troubleshooting and understanding the automation process difficult during debugging.

Innovation Solution

Implementing artificial intelligence and machine learning models to automatically generate annotations and technical specifications for RPA workflows, providing descriptions of activities, input/output parameters, and overall processes, and converting workflows between different RPA vendors.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If RPA workflows are built and deployed manually without automated documentation, then development speed is maintained, but troubleshooting and understanding become difficult due to lack of annotations

Engineering Contradiction:
Improvetroubleshooting capabilityVSAvoidannotations and documentation
Core Design Contradiction:
ReliabilityVSLoss of information

Solution Approach 1:

The system performs preliminary action by automatically generating annotations and documentation during the workflow design and execution phases. The cognitive AI layer analyzes workflow code and activity logs to create descriptive annotations before troubleshooting is needed, ensuring documentation is available when required without manual intervention.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The RPA system performs self-service by automatically documenting its own workflows through the integrated cognitive AI layer. The system analyzes its own activity logs and code to generate annotations, eliminating the need for external manual documentation and ensuring consistent, up-to-date documentation throughout the workflow lifecycle.

Inventive Principle:
Principle #25Self-service

2Ease of operation

If detailed manual annotations are added to RPA workflows, then troubleshooting and understanding improve, but development time and complexity increase

Engineering Contradiction:
Improveworkflow understandingVSAvoiddevelopment time
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The system automatically generates workflow annotations through the cognitive AI layer without requiring developer intervention. The AI analyzes workflow code and activity logs to create meaningful annotations, eliminating the time developers would spend manually documenting workflows while ensuring comprehensive coverage.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical process of manual annotation writing with an automated cognitive AI system. The AI layer processes workflow code and generates annotations using machine learning and natural language processing, substituting human cognitive effort with automated intelligence to reduce development time.

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

3Adaptability or versatility

If RPA workflows are converted between different vendor formats, then system flexibility and adaptability improve, but conversion accuracy and reliability may be compromised

Engineering Contradiction:
Improvevendor format compatibilityVSAvoidconversion accuracy
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The system achieves universality by implementing a vendor-agnostic workflow representation in the knowledge graph that can store and process workflows from multiple RPA vendors. The cognitive AI layer translates between different vendor formats through a common intermediate representation, enabling format conversion while preserving workflow semantics and ensuring accuracy.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent uses a knowledge graph as an intermediary structure between different RPA vendor formats. The cognitive AI layer translates source vendor workflows into the universal knowledge graph representation, then converts to the target vendor format, ensuring accurate transformation while maintaining workflow integrity through the intermediate standardized structure.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP4575768A1Automatic annotations and technical specification generation for robotic process automation workflows using artificial intelligence (AI)
Publication Date: 2025.06.25 UIPATH INC
  • EP4575768A1 patent drawingFigure 1
  • EP4575768A1 patent drawingFigure 2
  • EP4575768A1 patent drawingFigure 3

AI summary

Automatic annotations and technical specification generation for robotic process automation (RPA) workflows using artificial intelligence (AI) is disclosed. AI/ML models may enable smart searching of workflows and automatically generate documentation for the workflows, including descriptions of each activity, input/output parameters, and overall process explanations. Annotations and documentation may be provided for an entire complex business automation that is the sum of multiple workflows and applications. A Process Definition Document (PDD) for the business process may be generated from the RPA workflow code itself when it does not exist. Other documents, such as audit documents, compliance documents required by laws or regulations, etc. may be produced. The process may be iterative, where a generative AI model automatically converts text to RPA workflow code, a runtime automation is produced from this RPA workflow, and the other documentation is generated as well.