AI Boring Log Extraction for Reliable Geotechnical Databases
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The process of converting boring logs into a digital database is resource-intensive and prone to errors due to variations in format and manual data entry, which affects the accuracy and reliability of geotechnical information.
Innovation Solution
A system and method using artificial intelligence, specifically a deep learning-based classification model, to automatically extract and store boring log information by identifying log formats, extracting standard penetration test (SPT) and stratum information, and generating database-ready data frames.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual data entry is used to convert boring logs into a digital database, then the process is simple to implement, but the accuracy and reliability of geotechnical information deteriorates due to human error
Solution Approach 1:
The patent replaces the manual mechanical typing process with an automated optical character recognition (OCR) system and image processing algorithms. The system captures images of boring log documents, automatically recognizes the text and tabular data, and converts it into digital database format, eliminating human error while maintaining implementation feasibility through software automation.
Solution Approach 2:
The system enables the boring log conversion process to be self-executing by automatically performing document scanning, image processing, data extraction, and database integration without requiring manual intervention. The automated workflow includes form recognition, data validation, and error detection, allowing the system to serve itself in completing the entire conversion pipeline.
2Productivity
If automated conversion is implemented, then productivity and accuracy improve, but the complexity of the system increases
Solution Approach 1:
The patent divides the automated conversion system into distinct functional modules: document scanning module, image preprocessing module, OCR recognition module, data extraction module, validation module, and database integration module. Each module handles a specific task independently, which improves overall productivity while managing system complexity through modular design that allows for easier maintenance and troubleshooting.
Solution Approach 2:
The system introduces intermediate processing layers between the original document and the final database, including image preprocessing as an intermediary step before OCR, and data validation as an intermediary step before database storage. These intermediaries enhance conversion accuracy and productivity by preparing data for subsequent processing stages while keeping the overall system architecture manageable through clear separation of concerns.
3Loss of time
If manual typing is used, then the system is easy to operate, but time consumption increases and errors occur frequently
Solution Approach 1:
The patent implements a continuous automated workflow where document scanning, image processing, data extraction, and database storage occur in an unbroken sequence without manual intervention between steps. This continuous operation dramatically reduces conversion time compared to manual typing, while the system maintains ease of operation through automated file management and processing queuing that requires minimal user input.
Solution Approach 2:
The system performs preliminary actions automatically before the main conversion task, including document scanning and image preprocessing prior to data extraction. By preparing the data in advance through automated means, the system reduces the time required for the critical data extraction and typing phases, while the preliminary automation does not complicate operation since users simply initiate the process with a single command.
4Reliability
If format variations are handled manually, then flexibility is maintained, but reliability of extracted information deteriorates
Solution Approach 1:
The patent implements a dynamic data extraction system that automatically adapts to different boring log formats through machine learning and pattern recognition. The system learns from training data to identify format-specific characteristics and adjusts its extraction algorithms accordingly, maintaining high reliability across varied formats without requiring manual configuration for each format type. This dynamic adaptation manages complexity through automated format detection and selection of appropriate processing pipelines.
Solution Approach 2:
The system changes processing parameters automatically based on the detected document format, including adjusting OCR settings, data extraction patterns, and validation rules according to the specific format type. By dynamically modifying these parameters based on format identification, the system maintains reliable data extraction across diverse formats while managing complexity through parameter-based configuration rather than hard-coded format-specific logic.
Data Source
AI summary
The present invention relates to a system and method for automatically storing boring logs information using artificial intelligence. The present invention can make a database of boring logs with high reliability without input errors by training a classification model using various forms of boring logs in advance by using artificial intelligence, identifying a form of a boring log to be actually stored in a database using the classification model when the boring log is input, and then extracting data from the boring log according to the identified form.