Exception Element Zoom for Financial Document Accuracy

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Automated systems for processing financial documents face challenges in deciphering and processing elements that are difficult to recognize, leading to inefficiencies and errors in data extraction.

Innovation Solution

A system that identifies exception elements in financial documents, provides a zoomed-in view of their location, and allows users to select and replace these elements with correct ones, enabling accurate analysis and processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated OCR processing is used to extract financial data, then processing speed and volume are improved, but accuracy deteriorates for difficult-to-recognize elements

Engineering Contradiction:

Improveprocessing speedVSAvoiddata extraction accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system segments the financial document into individual elements and presents them one at a time to the user. Each element is isolated and displayed with enhanced visibility, allowing the user to review and correct only the problematic portions rather than reviewing the entire document, thus maintaining high processing volume while improving accuracy for difficult elements.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system introduces an intermediary review layer between automated OCR processing and final data extraction. Users act as intermediaries who review the OCR output for difficult elements and provide corrections. This intermediary human review mechanism bridges the gap between automated processing speed and accuracy requirements.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If users are presented with the entire financial document for review, then completeness is maintained, but efficiency deteriorates due to time required to locate and correct exceptions

Engineering Contradiction:

Improvedata completenessVSAvoidtime to locate and correct exceptions

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system extracts only the problematic elements that require user attention from the complete financial document. By isolating and presenting only the exception elements rather than the entire document, the system maintains data completeness for corrected elements while significantly reducing the time users spend locating and correcting exceptions.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The automated OCR system performs preliminary processing and identification of potential errors before presenting elements to the user. The system pre-processes the document to locate and flag exception elements, so when users receive the document for review, the problematic areas are already highlighted and ready for correction, eliminating the need to search through the entire document.

Inventive Principle:

Principle #10Preliminary action

3Device complexity

If exception elements are presented at normal size, then display simplicity is maintained, but detectability deteriorates for difficult-to-recognize elements

Engineering Contradiction:

Improvedisplay simplicityVSAvoidelement recognizability

Core Design Contradiction:

Device complexityVSDifficulty of detecting and measuring

Solution Approach 1:

The system changes the display dimension by providing a zoomed-in view of exception elements at a larger size than in the original document. This dimensional change from normal document size to enlarged view enhances the detectability and recognizability of difficult elements while maintaining display simplicity through focused presentation of only the problematic areas.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

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

Enhances the ability to accurately process financial documents by allowing users to correct ambiguous elements, improving the system's efficiency in handling previously unprocessable data.

Implementation Method 1

lift financial data off of the financial document using an optical character recognition (OCR) process

Methodology Applied

Scientific EffectOptical character recognition:

Data Source

PatentUS10049350B2Element level presentation of elements of a payment instrument for exceptions processing

Publication Date: 2018.08.14 BANK OF AMERICA CORP

AI summary

Disclosed are systems, methods, and computer program products that provide for element level presentation of elements of a payment instrument for exceptions processing. More specifically, the invention involves identifying an exception element from an image of a financial document, determining the location of the exception element based on its coordinates within the image of the financial document, and providing a zoomed-in view of the exception element to the user along with information and resources to allow a user to conveniently conduct accurate analysis of the exception element. The system then receives a correct element from the user to replace the exception element, and then processes the financial document using the replaced correct element instead of the exception element.