AI Cost Engineering System for Architectural Design Measurement

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for capturing, representing, and utilizing building interior information, such as floor plans, are cumbersome and lack precision in scaling, populating, and visualizing room interiors, making it difficult to accurately estimate costs for construction projects.

Innovation Solution

A system utilizing artificial intelligence (AI) to convert input documents into image files, automatically set a scale unit, measure lengths and areas, label measurements, and integrate cost estimation using AI-trained models to analyze architectural designs, incorporating real-time data from libraries like RS Means Cost Books, with manual verification for accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If floor plans are used to represent building interiors, then some layout information can be obtained, but it is difficult to construct, maintain, accurately scale, and populate with room interior information

Engineering Contradiction:
Improvebuilding interior informationVSAvoidfloor plan construction and maintenance
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent uses photorealistic images and virtual reality representations as copies of building interiors, replacing traditional floor plans. These visual copies capture complete interior information including layout, furnishings, and spatial relationships without requiring manual construction or maintenance, thereby reducing information loss while eliminating the complexity associated with traditional floor plan management.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent replaces the mechanical process of manually constructing and maintaining floor plans with automated computer vision and machine learning systems. These systems automatically extract, scale, and populate building interior information from photographs or laser scans, eliminating the manual labor and expertise required for traditional floor plan creation while maintaining high information accuracy.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If traditional measurement methods are used on floor plans, then basic dimensions can be obtained, but it is difficult to accurately scale and measure room interiors

Engineering Contradiction:
Improvebuilding dimensionsVSAvoidroom interior measurements
Core Design Contradiction:
Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The patent replaces manual measurement techniques with automated computer vision algorithms and machine learning models. These systems automatically detect edges, corners, and spatial relationships in photographs or laser scan data, then calculate precise dimensions and scaling factors without requiring manual intervention. This substitution dramatically improves measurement precision while eliminating the difficulty of detecting and measuring room interiors through traditional methods.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces virtual reality environments and augmented reality overlays as intermediaries between the physical building and the measurement process. These intermediaries provide real-time visual feedback and automated dimension annotations, allowing users to accurately measure and understand spatial relationships without directly manipulating physical floor plans or performing complex calculations.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Loss of information

If physical inspection of buildings is conducted, then accurate interior information can be obtained, but it requires traveling to and entering the building

Engineering Contradiction:
Improvebuilding interior informationVSAvoidtravel time to building
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The patent creates digital copies of building interiors through photography, laser scanning, or other remote sensing techniques. These copies capture complete interior information including spatial relationships, furnishings, and architectural details without requiring physical presence at the building. The digital models can be viewed, measured, and analyzed remotely, eliminating travel time while preserving all necessary interior information.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent replaces physical inspection with remote sensing technologies and automated image analysis systems. Cameras, laser scanners, or drones capture building interior data from a distance, and machine learning algorithms automatically process this data to extract meaningful information. This substitution eliminates the need for inspectors to travel to and physically enter buildings, saving time while maintaining or improving information accuracy through comprehensive digital documentation.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250209683A1System, method, and computer product for planning and cost engineering
Publication Date: 2025.06.26 ATC PRINCE STREET LLC
  • US20250209683A1 patent drawing
  • US20250209683A1 patent drawing
  • US20250209683A1 patent drawing

AI summary

A method for planning and cost engineering using an artificial intelligence may be provided. The method may include receiving one or more input documents, the input documents including at least architectural design information. The method may further include converting the input documents into an image file and automatically setting a scale unit based on at least one known measurement of the input documents. The method may further verify the scale unit, automatically measure one or more lengths and one or more areas of the image file based on the architectural design information; and automatically label the one or more measured lengths and one or more measured areas on the image file to generate a labeled image.