Extract construction drawing information in the US
Register for free Trial
Problem to be Solved
Every day, Customers have to work with thousands of technical drawings in PDF format. In each file, employees must search, measure, and enter data into tools to calculate material costs in technical drawings. Therefore, customers want to use AI to support employees and increase productivity. OCR is considered the first step to filter important drawings and extract some useful information for the next steps.
Problem Statement
How to automatically extract information on the construction drawing, thereby reducing effort and improving work efficiency with the following requirements:
- Large number of large, complex documents?
- How to process very large size images?
How QAI solution solves the problem?
- Integrate the portal system to display information after extracting from the construction drawing for Customers to evaluate and use.
- In case of data errors or low accuracy, it will be sent back for operator review.
- In case the operator completes the review and sends back corrected data, the system records it and this data is collected to enhance the model in the future.
- Specialized OCR models that combine text detection algorithm and recognition algorithm and many other image processing models to help identify and extract technical drawing data based on sota models architecture.
- The AI system can evaluate the reliability of extracted information, thereby highlighting invoices that need operator review.
Why the problem was not solved before?
- Too many files.
- Large size file.
- Workers need to manually search for information, measure and input data into the system for calculations.
Results from the solution
Accuracy on characters >= 80%
3/4/2025
NEW
Apply AI-Model to optimize the identification and classification of products (based on analysis, product details, unit price, unit of measurement, etc.)
NEW
"Use a large language model (LLM) to identify descriptive features from a reference image.
Based on these features, users can customize specific attributes and use the customized information to search for or generate images with similar characteristics."
NEW
Crawl data from websites and use a large language model (LLM) to extract and summarize information that aligns with the user's needs.
QaiDora Products
QaiDora draws inspiration from the myth of Pandora’s box—a symbol of unexpected possibilities and hope. For us, AI models are like modern Pandora’s boxes, holding untapped potential to turn challenges into opportunities. At QAI, QaiDora serves as an ecosystem of AI products designed to drive innovation and deliver competitive advantages.
Trusted by
