Rule-Based Label Data Extraction System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The transportation and logistics industry faces inefficiencies in retrieving data from printed labels due to manual processes and limitations in text recognition systems, which are often based on predefined templates that fail to account for variations in document types and company-specific labels.
Innovation Solution
A computing device and method that extracts target data from source documents by using text recognition data to define text lines, identify reference strings, and select relevant data subsets based on predefined rules, allowing for automated extraction without the need for storing templates for each variation of source document.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If predefined templates are used to identify data locations, then text recognition accuracy is improved, but system adaptability to different document types deteriorates
Solution Approach 1:
The system changes the approach from fixed template parameters to dynamic rule-based parameter extraction. Instead of using predefined templates with fixed locations, the system extracts rules that define data locations dynamically based on the document content and structure, allowing adaptation to different document types while maintaining recognition accuracy.
Solution Approach 2:
The system enables self-service by allowing the extraction rules to be automatically learned and applied to different document types without requiring manual template creation for each type. The rules are derived from the document structure itself, making the system self-adapting to various formats.
2Measurement precision
If manual data retrieval processes are used, then accuracy can be controlled, but time consumption increases
Solution Approach 1:
The system replaces manual mechanical data retrieval processes with an automated computational system. The mechanical process of manually locating and extracting data is substituted with an automated rule-based extraction system that processes documents electronically, maintaining accuracy while significantly reducing time consumption.
Solution Approach 2:
The automated system performs self-service by automatically extracting data without human intervention. The rule-based system independently processes documents, identifies data locations, and extracts information, eliminating the need for manual retrieval while maintaining controlled accuracy through rule validation.
3Reliability
If templates are stored for each document variation, then extraction reliability is improved, but device complexity increases
Solution Approach 1:
The system extracts the essential extraction logic from complex template storage systems. Instead of storing complete templates for each document variation, the system extracts and stores only the essential rules that define data locations and extraction criteria, significantly reducing complexity while maintaining reliability through rule-based processing.
Solution Approach 2:
The system changes from storing comprehensive templates with all possible variations to storing parameterized extraction rules. These rules use variables and conditions that can adapt to different document variations, reducing the amount of stored data while maintaining extraction reliability across different document types.
Data Source
AI summary
A computing device for extracting target data from a source document includes: a memory storing target data extraction rules; a processor connected with the memory, the processor configured to: obtain text recognition data extracted from an image of the source document, the text recognition data indicating locations of text structures in the source document; define text lines based on the text recognition data; identify a reference string from the text recognition data; select a subset of the text lines based on a location of the reference string and the target data extraction rules; and output the subset of the text lines as the target data.