Virtual Table Generation for Form Auto-Registration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automatic registration of forms with irregular or floating layouts is challenging due to the difficulty in accurately associating keywords and content, especially when keywords appear in non-uniform locations and multiple tabular formats, leading to failures in applying modified rules without breaking earlier tested cases.
Innovation Solution
A virtual table-based algorithm using deep learning techniques to identify and associate keywords and content, employing geometric and semantic distances to align keywords and content in a unified manner, even in complicated tables with subdivided cells, and storing these associations in a database.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If fixed rules for keyword association are modified to account for floating forms, then adaptability to irregular layouts is improved, but reliability of earlier tested cases deteriorates
Solution Approach 1:
The patent introduces a virtual table as an intermediary structure that mediates between the diverse form layouts and the keyword association rules. The virtual table generation module creates a standardized tabular representation from various form types (fixed, floating, irregular), allowing uniform association rules to work reliably across all cases without modifying the original rules for each form type.
Solution Approach 2:
The system changes the parameter representation of form data by converting physical form layouts into virtual table parameters (rows, columns, cell positions). This parameter transformation allows the same association rules to apply consistently across different form types, as the virtual table abstracts away the physical layout variations while preserving the logical structure needed for keyword-content association.
2Adaptability or versatility
If multiple tabular formats are supported, then versatility of form processing is improved, but device complexity increases
Solution Approach 1:
The patent extracts the tabular structure information from various form formats and separates it into a standardized virtual table representation. By taking out the essential tabular characteristics (row-column relationships, cell positions) from diverse formats and representing them uniformly, the system supports multiple formats without increasing the complexity of the core association logic.
Solution Approach 2:
The virtual table structure serves as a universal representation that can accommodate multiple tabular formats (fixed forms, floating forms, irregular layouts). This single unified structure performs multiple functions: it represents different form types, enables consistent keyword association, and simplifies the processing logic, thereby reducing overall system complexity despite supporting format diversity.
3Adaptability or versatility
If keywords are associated in non-uniform locations, then adaptability to free-form layouts is improved, but measurement precision of keyword-content association deteriorates
Solution Approach 1:
The patent resolves the precision issue by adding a virtual table dimension layer above the physical form layout. Instead of relying on spatial proximity in the original form (which varies in free-form layouts), the system uses the structured row-column dimensionality of the virtual table to precisely define keyword-content relationships, ensuring accurate association regardless of physical layout irregularities.
Data Source
AI summary
In different kinds of forms with incomplete lines, or with different color cells in lieu of lines, virtually completing or providing the lines enables formation of tables from which keywords and content in the forms may be identified. Where a form may have one or more such tables, as can be the case with forms with irregular formats, multiple tables may be identified, to facilitate identification of keywords and content in each such table. In embodiments, deep learning techniques may be applied. Cost analysis involving minimum distances between keywords and content may be performed, with the cost analysis also facilitating formation of a keyword dictionary and a content dictionary.