Machine Learning System for Automating Building Parameter Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current architectural design practices require manual specification and layout of building parameters, which is time-consuming and requires expertise, making it inefficient for generating new building designs.
Innovation Solution
A machine learning system that trains on images of buildings and corresponding parameters to predict new building parameters, which can be input into a BIM data generation system for creating 3D architectural models, simplifying the design process by automating the generation of building information models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual specification and layout of building parameters is used, then design precision and control are maintained, but time consumption and operational complexity increase significantly
Solution Approach 1:
The patent replaces manual mechanical operations (architects manually specifying and laying out building parameters in CAD programs) with an automated image processing system using machine learning models. The system automatically extracts building parameters from images and generates BIM data, eliminating the need for manual intervention and significantly reducing design time.
Solution Approach 2:
The system enables self-service by allowing building parameters to be automatically extracted and processed without human intervention. The machine learning model independently analyzes building images, predicts parameters, and generates BIM data, making the design process autonomous and eliminating dependency on manual labor.
2Ease of operation
If manual building parameter specification is used, then design accuracy and expertise control are maintained, but ease of operation deteriorates due to required program expertise
Solution Approach 1:
The patent replaces complex manual operations requiring specialized CAD program expertise with an automated image processing system. The machine learning model handles all parameter extraction and BIM data generation automatically, eliminating the need for users to learn or operate complex design software.
Solution Approach 2:
The system creates accurate copies of building parameters by extracting them directly from building images through machine learning. Instead of requiring manual recreation of parameters in CAD software, the system automatically copies and translates visual information into structured BIM data, simplifying the operation significantly.
3Productivity
If automated machine learning parameter prediction is used, then productivity and ease of operation improve, but measurement precision and manufacturing precision may deteriorate
Solution Approach 1:
The patent implements feedback mechanisms where the machine learning model is trained on labeled building data with known parameters. The system continuously improves its prediction accuracy by learning from training data and can be refined through feedback loops that compare predicted parameters against actual building measurements, ensuring high precision while maintaining automated efficiency.
Solution Approach 2:
The system performs preliminary action by pre-training machine learning models on extensive building datasets before actual use. This preliminary training phase enables the model to learn accurate parameter extraction patterns, ensuring that when the system operates on new building images, it produces precise results without requiring manual verification or adjustment.
Data Source
AI summary
In general, the disclosure describes techniques for parameterizing building information using images. In an example, a method includes receiving an image of a building; applying, by a machine learning system, a machine learning model to the received image of a building to generate, for a new building, new building parameters to be input to a building information modeling (BIM) data generation system, wherein the machine learning model is trained using images of buildings and corresponding building parameters for the buildings; and outputting, by the machine learning system, the new building parameters for the new building.