Document Conversion via Zone Extraction and Segmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The increasing quantity, information, and size of documents make existing optical character recognition (OCR) processes costly and time-consuming when converting diverse document types into editable or searchable formats.

Innovation Solution

A system that allows users to create a batch file containing multiple documents of different types, specifying conversion and zone information to extract only necessary portions, which is then processed by a conversion device to generate uniformly formatted documents, reducing the computational load and user interaction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If OCR processing is applied to entire diverse document sets, then comprehensive text recognition is achieved, but computing resource usage and conversion time increase significantly

Engineering Contradiction:

Improvetext recognition completenessVSAvoidconversion time

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent segments the document conversion process by identifying and processing specific zones or portions of documents that contain the required information, rather than processing entire documents. This segmentation allows the system to focus computational resources on relevant areas, reducing overall processing time while maintaining recognition accuracy for the needed content.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent extracts and processes only the necessary portions or zones from documents based on conversion requirements. By taking out and processing only the relevant parts of documents rather than entire documents, the system reduces computing resource usage and conversion time while still achieving complete text recognition for the required information.

Inventive Principle:

Principle #2Taking out (Extraction)

2Measurement precision

If OCR processing is applied to entire diverse document sets, then comprehensive text recognition is achieved, but computing resource usage increases

Engineering Contradiction:

Improvetext recognition completenessVSAvoidcomputing resource usage

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Inventive Principle:

Principle #2Taking out (Extraction)

3Reliability

If multiple documents of different types are converted individually, then conversion accuracy is maintained, but processing efficiency decreases

Engineering Contradiction:

Improveconversion accuracyVSAvoidprocessing efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent merges multiple documents of different types into a single batch conversion process. By combining the conversion of multiple documents into one unified process that utilizes zone information and conversion criteria, the system maintains conversion accuracy for each document type while significantly improving overall processing efficiency through batch operations.

Inventive Principle:

Principle #5Merging (Combining)

4Productivity

If zone information is used to process only specific portions of documents, then computing resource usage is reduced, but conversion completeness may be compromised

Engineering Contradiction:

Improvecomputing resource efficiencyVSAvoidconversion completeness

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent applies local quality by using zone information to identify specific portions of documents that contain the required information for conversion. This approach ensures that computational resources are focused on relevant areas while maintaining conversion completeness for the needed content, achieving both resource efficiency and reliability.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS9886436B2Conversion of documents of different types to a uniform and an editable or a searchable format

Publication Date: 2018.02.06 ACCENTURE GLOBAL SERVICES LTD

AI summary

A device may obtain a set of documents, including at least two documents of different document types, for conversion to a uniform and an editable or a searchable format. The set of documents may include at least two documents of a different document type. The device may determine conversion information, associated with converting the set of documents, that includes an editable or a searchable document type to which the set of documents is to be converted. The device may determine zone information, associated with converting the set of documents, that includes information that identifies a portion of the set of documents that is to be converted. The device may generate a set of converted documents based on the conversion information and the zone information. Each document, of the set of converted documents, may be of the document type. The device may provide the set of converted documents.