Building Elements Graph Generation via ML Relationship Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for generating building elements graphs lack the ability to fully incorporate both physical and logical relationships between building elements, making it difficult to streamline troubleshooting, estimate design changes, and manage construction projects effectively.
Innovation Solution
Utilizing machine-learning and artificial intelligence technologies to determine relationship models and rules based on various documentation and historical input associated with construction projects, enabling the generation of building elements graphs that include both physical and logical relationships.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If traditional methods are used to generate building elements graphs, then the graph can be generated with basic physical relationships, but logical relationships between building elements cannot be captured
Solution Approach 1:
A relationship determination model acts as an intermediary component that processes building element data and documentation to automatically identify and capture both physical and logical relationships. This model serves as a mediator between raw data and the final graph structure, enabling comprehensive relationship extraction without requiring manual analysis of all connections.
Solution Approach 2:
The patent replaces manual or traditional rule-based relationship determination with machine learning-based automated analysis. The system uses AI models to process construction documentation, drawings, and building element data to automatically infer relationships, substituting complex manual analysis with computational intelligence that can handle unstructured data effectively.
2Loss of information
If manual analysis of construction documentation is performed to identify relationships, then comprehensive relationships can be identified, but time and resources are consumed
Solution Approach 1:
The system enables self-service relationship extraction by automatically analyzing construction documentation, drawings, and building element data without requiring manual intervention. The machine learning models process the data independently, extracting relationships autonomously and eliminating the need for manual review of each connection, thereby reducing time consumption while maintaining completeness.
Solution Approach 2:
The system performs preliminary relationship determination by pre-processing and analyzing construction documentation before the graph generation process. The machine learning models are trained on historical data and can quickly infer relationship patterns, allowing the system to prepare relationship mappings in advance and reduce real-time analysis requirements.
3Productivity
If existing graph generation systems are used, then building elements can be mapped, but troubleshooting and design change estimation are not streamlined
Solution Approach 1:
The system incorporates feedback mechanisms that allow continuous refinement of relationship mappings based on actual construction data and documentation. The machine learning models can learn from discrepancies between expected and actual relationships, improving their accuracy over time and enabling more effective troubleshooting and design change analysis through iterative improvement.
Data Source
AI summary
A computing platform is configured to: (i) train a machine-learning model by carrying out a machine learning process on a training data set that includes that includes construction-based data objects including indications of a plurality of building elements and indications of respective logical relationships between pairs of the building elements, (ii) receive a request to generate a building elements graph for a given construction project, (iii) input construction project data associated with the given construction project into the machine-learning model, thereby (a) identifying building elements of the given construction project, (b) determining a set of respective physical relationships between pairs of the building elements and a given set of respective logical relationships between pairs of the building elements, and (c) based on the given set of respective physical relationships and the given set of respective logical relationships, generating a building elements graph for the given construction project.