Semantic AI Field Matching for Cross-Format RPA Data Transfer

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current robotic process automation (RPA) technologies require manual intervention to create workflows and transfer data between sources and targets, which is time-consuming and lacks full automation.

Innovation Solution

The implementation of semantic artificial intelligence (AI) for RPA, which enables automatic data transfer between sources and targets by using AI/ML models trained for semantic matching, allowing for the automatic mapping and copying of data between different formats and interfaces.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If manual creation of RPA workflows is used, then developers can create workflows with full control, but the process is time-consuming and lacks full automation

Engineering Contradiction:

Improveautomation of RPA workflow creationVSAvoidtime to create RPA workflows

Core Design Contradiction:

Extent of automationVSLoss of time

Solution Approach 1:

The system enables self-service automation by allowing the RPA robot to automatically create workflows and map data fields without requiring manual developer intervention for each workflow creation task

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary actions by pre-training AI/ML models on semantic matching before deployment, enabling the robot to autonomously create workflows and map fields without real-time human assistance

Inventive Principle:

Principle #10Preliminary action

2Productivity

If manual indication of target graphical elements is required, then precise data transfer can be achieved, but the process becomes time-consuming

Engineering Contradiction:

Improvedata transfer efficiencyVSAvoidtime to indicate target elements

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The patent replaces the mechanical manual indication process with an AI/ML-based semantic matching system that automatically identifies and maps data fields between source and target systems using trained models

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The AI/ML model acts as an intermediary between the source and target systems, performing semantic matching to automatically determine data field correspondences without requiring manual intervention

Inventive Principle:

Principle #24Intermediary (Mediator)

3Extent of automation

If fully automated RPA workflow creation is implemented, then time consumption is reduced, but current technology does not support intuitive data transfer

Engineering Contradiction:

Improvefull automation of RPA workflow creationVSAvoidintuitive data transfer capability

Core Design Contradiction:

Extent of automationVSEase of operation

Solution Approach 1:

The RPA robot performs self-service by automatically creating workflows and mapping data fields using its trained AI/ML models, enabling full automation while maintaining intuitive operation through semantic understanding

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS12314017B2Automatic data transfer between a source and a target using semantic artificial intelligence for robotic process automation

Publication Date: 2025.05.27 UIPATH INC

AI summary

Automatic data transfer between a source and a target using semantic artificial intelligence (AI) for robotic process automation (RPA) is disclosed. A user may be provided with the option of selecting a source and a target and indicating through an intuitive user interface that he or she would like to copy data from the source to the destination, regardless of format. This may be done at design time or at run time. For instance, the source and/or target may be a web page, a graphical user interface (GUI) of an application, an image, a file explorer, a spreadsheet, a relational database, a flat file source, any other suitable format, or any combination thereof. The source and the target may have different formats. The source, target, or both may not necessarily be visible to the user.