Spatial-Aware Information Extraction from Electronic Documents
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for processing electronic documents lack spatial-aware information extraction capabilities, making it difficult to efficiently search and select information from scanned or photographed documents, especially when the information is presented in a format that is not spatially organized.
Innovation Solution
A system and method that utilize machine-readable instructions to obtain electronic source documents, extract information using OCR and other techniques, and generate a character-based representation using a grid of character positions, allowing users to search and select information through a user interface.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If traditional OCR extraction methods are used, then information can be extracted from electronic documents, but spatial positioning and organization of extracted information is lost
Solution Approach 1:
The document processing system segments the extraction process into distinct components: OCR text extraction, spatial coordinate detection, and grid representation generation. Each component handles a specific aspect, allowing spatial information to be preserved through coordinated segmentation rather than losing it in a monolithic extraction process.
Solution Approach 2:
A character-based grid representation serves as an intermediary data structure between the original document image and the extracted information. This grid maintains spatial relationships by mapping characters to specific grid positions, acting as a mediator that preserves spatial context while enabling information extraction.
2Ease of operation
If a grid-based character representation is implemented, then spatial-aware search and selection is enabled, but processing complexity increases
Solution Approach 1:
The system transforms the two-dimensional document space into a structured grid representation with explicit character positions. By adding the dimension of grid coordinates to the extraction process, users can perform spatial-aware searches and selections based on position, making information retrieval more intuitive despite increased processing requirements.
3Reliability
If relative positioning of characters is maintained, then spatial context is preserved, but data structure complexity increases
Solution Approach 1:
The system changes the parameter representation of character positions from continuous image coordinates to discrete grid positions. By transforming spatial parameters into a normalized grid system, the patent preserves relative positioning accuracy while simplifying the data structure through standardized position encoding.
Data Source
AI summary
Systems and methods for spatial-aware information extraction from electronic source documents are disclosed. Exemplary implementations may: obtain an electronic source document in electronic format, including human-readable information; obtain extracted information that has been extracted from the electronic source document; generate a character-based representation of the electronic source document that uses a grid of character positions; and present a user interface to a user to search and/or select information in the electronic source document based on the character-based representation.