Construction Location Entity Taxonomy for Connected Project Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The construction industry faces inefficiencies due to the siloed structure of construction project information, lacking a unifying characteristic to provide meaningful connectivity between data assets.
Innovation Solution
Utilizing machine-learning models to identify location entities within construction projects, determine interrelationships, and generate a data taxonomy that organizes and presents these entities and their relationships, leveraging various location planes and tracking entities throughout the project lifecycle.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If construction project information is stored in a siloed structure, then data storage is simple and organized, but data connectivity and meaningful relationships between data assets are lacking
Solution Approach 1:
The patent introduces location entities as intermediary elements that connect various construction project data assets. These location entities serve as mediators between different data sources (drawings, specifications, progress reports) and provide a common reference framework. By using location entities with unique identifiers and hierarchical relationships, the system establishes meaningful connections between previously siloed data without requiring complete structural redesign of the data storage system.
Solution Approach 2:
The patent creates a universal location entity framework that can represent multiple types of construction elements (rooms, floors, buildings, construction zones) using a single unified data structure. This universal approach allows the same location entity structure to serve multiple functions: organizing spatial information, tracking construction progress, managing documents, and coordinating activities across different project phases, thereby improving data connectivity without proportionally increasing complexity.
2Reliability
If machine-learning models are used to identify location entities and establish relationships, then data connectivity and intelligence are improved, but processing time and computational resources increase
Solution Approach 1:
The patent implements preliminary action by pre-processing construction drawings to automatically extract location entities, their hierarchical relationships, and spatial information before the main data processing occurs. The machine-learning models are trained in advance to recognize and classify location entities from various drawing types. This preliminary extraction creates a ready-to-use location entity framework that can be quickly populated with project-specific data, significantly reducing processing time during actual project execution while maintaining high data connectivity.
3Ease of operation
If a hierarchical data taxonomy is generated to organize location entities, then information presentation and navigation are improved, but system complexity and implementation difficulty increase
Solution Approach 1:
The patent applies segmentation by dividing the construction project information hierarchy into distinct, manageable levels: building-level location entities, floor-level location entities, room-level location entities, and component-level location entities. Each level is independently defined with specific attributes and relationships. This segmented hierarchical structure allows users to navigate and interact with information at the appropriate level of detail without being overwhelmed by the entire project's complexity, while the systematic segmentation actually reduces overall system complexity through modular organization.
Data Source
AI summary
An example computing platform is configured to: obtain a two-dimensional drawing of a portion of a construction project; perform an image processing analysis of the two-dimensional drawing to identify one or more location entities within the two-dimensional drawing; derive embeddings for each location entity in the two-dimensional drawing; based on the derived embeddings, determine relationships between the one or more location entities; and based on the determined relationships between the one or more location entities, generate a location entity data taxonomy that includes each identified location entity as a respective node that is related to at least one other location entity.