AI Data Transformation for RPA Document Processing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Robotic process automation (RPA) systems face inefficiencies in processing and transforming diverse document and data formats, leading to time-consuming data entry and processing, especially when dealing with non-processor-readable formats like scanned images and varying file formats.

Innovation Solution

An AI-based data transformation system that categorizes documents, applies optical character recognition (OCR) for conversion, trains machine learning models to identify document structures and relationships, and generates mappings using ontologies to standardize data formats, enabling automated data extraction and processing for RPA systems.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If RPA systems process diverse document and data formats manually, then data accuracy is maintained, but processing time increases significantly

Engineering Contradiction:

Improvedata accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent introduces an AI-based data transformation system as an intermediary between diverse document formats and the RPA system. This intermediary automatically categorizes documents, applies OCR where needed, extracts data using trained ML models, and standardizes outputs - thereby maintaining data accuracy while dramatically reducing processing time compared to manual methods

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces manual mechanical data processing with automated AI-based processing. Machine learning models substitute for human operators in categorizing documents, extracting data, and transforming formats, achieving both high speed and maintained accuracy through intelligent automation rather than brute-force manual entry

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If RPA systems handle non-processor-readable formats like scanned images, then completeness of data input is improved, but processing complexity increases

Engineering Contradiction:

Improvedata format compatibilityVSAvoidprocessing complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the complex task of handling diverse formats into distinct modular steps: document intake, categorization, OCR application, data extraction, validation, and transformation. Each step is handled by specialized components (categorization models, OCR engines, extraction models), reducing overall system complexity while maintaining high format compatibility

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies preliminary OCR conversion to non-processor-readable formats like scanned images during the initial document intake phase. By pre-processing these formats before they enter the main RPA workflow, the system eliminates the need for complex real-time format handling downstream, thereby reducing processing complexity while maintaining versatility

Inventive Principle:

Principle #10Preliminary action

3Productivity

If automated data extraction is implemented without validation, then processing speed increases, but data reliability decreases

Engineering Contradiction:

Improveprocessing speedVSAvoiddata reliability

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent implements feedback loops where extracted data undergoes validation against predefined schemas, business rules, and quality criteria. The validation results feed back into the extraction process, allowing for correction and re-extraction when needed. This ensures data reliability is maintained while preserving high processing speeds through automated feedback rather than manual verification

Inventive Principle:

Principle #23Feedback

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This solution significantly enhances RPA system efficiency by automating data gathering and analysis, speeding up process execution, and providing graphical user interfaces for validation, thus overcoming the challenges of handling different document and data formats.

Implementation Method 1

The subset of documents are processed via optical character recognition (OCR) techniques for conversion to processor-readable formats.

Methodology Applied

Scientific EffectOptical character recognition:

Data Source

PatentUS11790262B2Data transformations for robotic process automation

Publication Date: 2023.10.17 ACCENTURE GLOBAL SOLUTIONS LTD

AI summary

An Artificial Intelligence (AI)-based data transformation system receives an input package and enables automatic execution of one or more processes in a robotic process automation system (RPA). The input package includes a plurality of documents and metadata required for the execution of the automated processes. The plurality of documents are categorized into a domain. Entities with their corresponding name-value pairs and entity relationships are extracted from the plurality of documents. An ontology is selected based on the domain. The entities are mapped to output fields identified from the selected ontology. The mappings thus generated are transmitted to the RPA system which employs the mappings to automatically execute the one or more processes.