Automated Submittal Register Generation via OCR and ML
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The process of generating a submittal register in construction projects is tedious and time-consuming, often resulting in incomplete registers due to the voluminous specifications from architects, which can affect project outcomes and schedules.
Innovation Solution
A system and method for electronically generating submittal registers using a web application interface that inputs project specifications, converts them into a spreadsheet format, applies algorithms for quality control, and allows for modification, thereby streamlining the process and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional manual methods are used to generate submittal registers, then human reviewers can understand and classify specifications, but the process becomes extremely time-consuming and labor-intensive
Solution Approach 1:
The patent replaces the manual mechanical process of reading and classifying specifications with an automated optical character recognition (OCR) system combined with natural language processing algorithms. The system captures specification documents, converts them to text using OCR, and automatically extracts and classifies submittal information using computational algorithms, thereby eliminating the time-consuming manual review process while maintaining accuracy through structured data extraction rules.
2Reliability
If reviewers manually read voluminous specifications to create submittal registers, then complete information can be captured, but the workload becomes unmanageable and errors increase
Solution Approach 1:
The patent segments the complex task of submittal register creation into distinct automated stages: document capture, optical character recognition, text parsing, data extraction, classification, and output generation. Each stage handles a specific aspect of the process, with algorithms designed to process particular types of information independently, thereby managing complexity through modularization while ensuring complete information capture through systematic processing of all specification sections.
3Productivity
If traditional methods are used, then human judgment can interpret specifications, but the process remains tedious and prone to human error
Solution Approach 1:
The patent incorporates feedback mechanisms where the system validates extracted data against predefined classification rules and specification structures. The algorithm continuously refines its extraction process by checking for completeness and consistency, comparing extracted submittal information against the original specification document, and automatically correcting or flagging potential errors, thereby maintaining high accuracy while operating at automated speeds.
Data Source
AI summary
A system and method for generating a submittal register for various construction projects or other items is disclosed. Among other things, the system and method include inputting the construction project specifications in a file format, such as PDF, into a web application interface to convert the specification to a text file, applying an algorithm to the text file based on a set of rules, that are iteratively revised using machine learning, to identify all required submittals, generating a final submittal register, and delivering the final submittal register.