Document Structuring Device Layout Adaptation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing structuring technologies face challenges in accurately processing documents with varying layouts, leading to noise and inaccuracies, especially when dealing with documents that span multiple columns.
Innovation Solution
A structuring device and method that utilize a processor and storage device with a processing module pool and template data pool, allowing for the selection and execution of specific processing modules based on the layout features of the document, to extract and structure document data accurately, including modules for data loading, row extraction, foot note extraction, chart extraction, and others, ensuring precise formatting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single fixed structuring method is used for all documents, then the processing flow is simple, but the structuring accuracy deteriorates when dealing with different layouts
Solution Approach 1:
The patent implements dynamic selection of structuring methods based on document layout detection. The system automatically identifies whether a document is single-column or double-column and selects the appropriate structuring method accordingly, making the processing flow adaptable rather than fixed, thus maintaining simplicity while improving accuracy for different layouts
Solution Approach 2:
The system changes the structuring parameters and processing steps based on the detected layout type. For single-column documents, one set of processing parameters is applied, while for double-column documents, different parameters and additional column-specific processing are applied, enabling accurate structuring across varying document formats
2Extent of automation
If deep learning-based end-to-end extraction is used, then the automation level is high, but the handling of complex layouts like double-column documents deteriorates
Solution Approach 1:
The patent segments the structuring process into distinct modules: layout detection, method selection, and layout-specific structuring processing. This segmentation allows the system to maintain high automation through automatic layout detection while improving reliability by applying specialized processing techniques for complex layouts like double-column documents through separate, optimized processing stages
3Ease of operation
If rule-based processing is used, then the processing transparency is high, but the adaptability to different layouts deteriorates
Solution Approach 1:
The system dynamically adjusts the rule-based processing approach based on detected layout characteristics. The same transparent rule-based framework is maintained, but the specific rules applied vary according to whether the document is single-column or double-column, enabling both transparency and adaptability through a flexible, conditionally-applied rule system
Data Source
AI summary
A structuring device accesses a processing module pool that stores a plurality of processing modules capable of executing processing based on a feature related to a layout in document data, and a template data pool that stores template data in which two or more processing modules combined according to a dependency relationship among the plurality of processing modules are defined, acquires structuring target document data, extracts specific template data from the template data pool based on a result of a selection input of a feature related to a layout of the structuring target document data, and outputs first structured data in which the structuring target document data is structured by the feature related to the layout, by executing two or more specific processing modules forming the extracted specific template data according to a dependency relationship among the two or more specific processing modules.