Selection Mark Extraction Using Vector-Based Text Linking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing document recognition systems struggle to accurately link text with selection boxes in user-filled documents, leading to inefficiencies and decreased accuracy in data extraction, particularly when forms contain selection marks and corresponding text.
Innovation Solution
A computing system determines vectors between selection boxes and adjacent text lines in multiple directions, identifies the direction with minimal variance, generates key-value pairs, and creates a document model to accurately associate selection boxes with their corresponding text, using techniques like the Hungarian matching algorithm to establish a one-to-one mapping.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If document recognition systems use traditional text detection methods, then they can identify text lines, but they cannot consistently and accurately link text to selection boxes
Solution Approach 1:
The patent introduces a spatial dimension by calculating vectors between selection boxes and text lines in multiple directions (up, down, left, right). This dimensional approach transforms the linking problem from a simple proximity detection into a structured spatial relationship analysis, enabling accurate text-box association through vector variance minimization
2Measurement precision
If human intervention is used to link text with selection boxes, then accuracy improves, but efficiency decreases
Solution Approach 1:
The system performs self-service by automatically linking text lines to selection boxes through vector-based spatial analysis. The algorithm independently determines the correct associations by calculating and comparing vectors in multiple directions, eliminating the need for human intervention while maintaining high accuracy and improving processing efficiency
3Productivity
If extracted data is not properly classified and associated, then processing speed increases, but reclassification is required
Solution Approach 1:
The system performs preliminary action by establishing accurate text-to-selection-box associations during the initial extraction phase using vector variance analysis. By correctly classifying and linking data in advance, the system eliminates the need for subsequent reclassification operations, thereby maintaining both high processing speed and data reliability
Data Source
AI summary
A method may include detecting one or more selection boxes and one or more text lines in a primary document. The method may include determining respective vectors associated with the selection box and adjacent text lines to the selection box in a plurality of directions. The method may include determining a set of respective vectors associated with a unique selection box. The method may include determining a variance between respective vectors in the set of respective vectors and identifying a particular direction corresponding to a minimal variance between the respective vectors in the set of respective vectors as compared to a variance of other sets of respective vectors. The method may include generating a key-value pair based on the set of respective vectors characterized by the minimal variance. The method may include generating a document model, including the key-value pair, and extracting data according to the document model.