Drawing Symbol Detection for Automated Progress Markups
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing CAD/BIM applications require manual and inefficient processes for creating field progress markups on vector/raster-based drawing sheets, which are complex for non-expert users and time-consuming for large projects.
Innovation Solution
Automated symbol detection using heuristic or ML models to identify regions on drawing sheets for markups, allowing users to efficiently create and update markups linked to construction objects, with iterative learning from user corrections.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual processes are used to create field progress markups on drawing sheets, then users can create markups with full control and precision, but the process becomes time-consuming and inefficient for large projects
Solution Approach 1:
The system enables self-service by allowing the automated markup creation process to autonomously identify symbols, detect their properties, and generate markup instances without requiring manual intervention for each individual markup, thereby dramatically improving productivity while reducing time investment
Solution Approach 2:
The patent replaces the mechanical manual process of creating markups with an automated computer-based system that uses optical character recognition and machine learning models to automatically detect symbols and generate markups, substituting human manual operations with automated computational processes
2Measurement precision
If CAD/BIM applications are used for creating markups, then precise and context-rich markups can be generated, but the applications become complex and difficult for non-expert users to operate
Solution Approach 1:
The system introduces an intermediary layer that automatically detects symbol properties and generates markup instances based on predefined templates, acting as a mediator between the user's simple selection and the complex CAD/BIM markup creation process, thereby maintaining precision while simplifying operation
Solution Approach 2:
The patent uses copying by creating markup instances that replicate the properties and characteristics of detected symbols through automated template application, allowing precise markups to be generated by copying proven templates rather than creating each markup from scratch, which simplifies the user interface while maintaining accuracy
3Productivity
If automated symbol detection is implemented, then markup creation becomes near-instantaneous and highly efficient, but the system complexity increases due to ML models and heuristic algorithms
Solution Approach 1:
The system applies preliminary action by pre-training machine learning models and preparing heuristic algorithms before the actual markup creation process, so that during operation, the automated detection and generation can proceed rapidly without requiring complex real-time computations, thereby achieving high productivity while managing system complexity through advance preparation
Data Source
AI summary
A method and system provide the ability to track object progress in a drawing sheet. An object type is created and activity types are assigned to the object type. The activity types represent a progression of an object of the object type. A drawing sheet, without computer aided design (CAD) or building information model (BIM) context, that has multiple symbol instances, is obtained. A symbol instance is selected in the drawing sheet. A markup is created on the drawing sheet based on the symbol instance. Multiple symbol instances are autonomously detected based on the selected symbol instance. Progress tracking markup instances of the markup are autonomously created for the detected symbol instances and are linked to the object type. The progress of the object instances is tracked based on the markups.