Ledger Column Type Discrimination via Content Comparison

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional methods for discriminating column types in ledger sheets are time-consuming and fail to accurately distinguish between item name and item value columns when there is no visual information difference, especially when the style differs from the registration target.

Innovation Solution

An information processing device that acquires and compares column content across multiple ledger sheets with the same layout to automatically discriminate column types and specify style candidates, using a storage unit to store type information and a column type discrimination unit to compare and match content.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual designation of individual column types is performed, then column type discrimination accuracy is improved, but processing time increases considerably

Engineering Contradiction:

Improvecolumn type discrimination accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs self-service by automatically acquiring multiple ledger sheets with the same layout, comparing their column contents, and autonomously determining column types without requiring manual intervention. The column type discrimination unit uses the comparison results to automatically specify styles, making the system self-sufficient in eliminating the time-consuming manual designation process while maintaining discrimination accuracy.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary action by acquiring and comparing multiple ledger sheets in advance to establish column type information before actual processing. The storage unit stores this pre-acquired column type information, which is then reused for style specification, avoiding the need to perform manual column type designation repeatedly and thus reducing processing time.

Inventive Principle:

Principle #10Preliminary action

2Speed

If visual information such as background color is used for column type discrimination, then discrimination speed is improved, but reliability decreases when visual information is absent or differs from registration target

Engineering Contradiction:

Improvediscrimination speedVSAvoidcolumn type discrimination reliability

Core Design Contradiction:

SpeedVSReliability

Solution Approach 1:

The system changes the parameter used for column type discrimination from visual information (background color) to content-based information (column text content). By comparing column contents across multiple ledger sheets rather than relying on visual attributes, the system maintains discrimination speed while significantly improving reliability when visual information is absent or varies from the registration target style.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system achieves universality by using column content comparison as a universal method that works across different ledger sheet styles and visual configurations. Unlike visual information methods that are style-specific, the content-based approach can reliably discriminate column types regardless of visual information presence or style variations, making the discrimination process universally applicable.

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Ease of operation

If visual information is used to discriminate column types, then ease of operation is improved, but adaptability deteriorates when ledger sheet style differs from registration target

Engineering Contradiction:

Improveease of column type discriminationVSAvoidadaptability to different ledger sheet styles

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The system performs preliminary action by acquiring and comparing multiple ledger sheets in advance to build a robust column type discrimination model. This pre-processing creates content-based comparison data that can be applied universally across different styles, enhancing both ease of operation and adaptability when processing ledger sheets that differ from the registration target.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system changes the discrimination parameter from style-specific visual information to universal content attributes. This parameter change enables the system to maintain ease of operation through automated content comparison while simultaneously improving adaptability to handle various ledger sheet styles, as content structure remains consistent across different visual presentations.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS12124797B2Information processing device, discerning method, and discerning program

Publication Date: 2024.10.22 NIPPON TELEGRAPH & TELEPHONE CORP

AI summary

An information processing device (10) acquires a plurality of ledger sheets having the same layout, compares the contents of each column at the same position each of the acquired plurality ledger sheets having the same layout, discriminates the type of each column according to the comparison result, and stores the information on the type of each column in a storage unit (14). Moreover, the information processing device (10) acquires position information of a processing target ledger sheet, compares information on the type of a column and the content of each column using information on a registered style with respect to the acquired ledger sheet, discriminates the type of each column of the processing target ledger sheet according to the comparison result, and specifies style candidates of the processing target ledger sheet on the basis of the discrimination result.