AI Correlators for Dynamic Building Digital Twin Ontology
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Building management systems struggle to capture all relationships between entities in a building, as data used to generate digital twins may not explicitly indicate correlations, leading to incomplete representation and adaptation challenges.
Innovation Solution
Implementing an artificial intelligence service, such as a large language model, to infer correlations between entities not explicitly stated in the data, allowing the digital twin to adapt and change over time by generating new relationship types and updating the ontology, enabling dynamic representation of building entities and their interactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If data is used to generate a digital twin without explicit relationship indicators, then the system complexity is reduced and data processing is simpler, but the completeness of entity relationships is lost and the digital twin cannot capture all correlations between building entities
Solution Approach 1:
An AI service acts as an intermediary between the input data and the digital twin generation process. This service analyzes the input data and generates relationship indicators that explicitly define correlations between entities, thereby recovering relationship information that would otherwise be lost while maintaining simplicity in the overall system architecture
Solution Approach 2:
The system performs preliminary analysis using the AI service before generating the digital twin. This preliminary action identifies and establishes entity relationships in advance, ensuring that the digital twin is populated with complete relationship information from the outset without requiring complex post-processing
2Ease of manufacture
If a static digital twin is generated from initial data, then the manufacturing and setup process is simpler, but the adaptability to building changes over time is reduced
Solution Approach 1:
The digital twin system transitions from a static to a dynamic model by continuously receiving new building data and using the AI service to identify updated entity relationships. This allows the digital twin to adapt to building changes over time while maintaining ease of manufacture through automated relationship inference rather than manual updates
3Measurement precision
If AI services are used to infer correlations between entities, then the completeness and accuracy of entity relationships is improved, but the computational processing requirements and system complexity increase
Solution Approach 1:
The AI service is designed as a universal component that handles multiple functions: analyzing input data, inferring entity relationships, generating relationship indicators, and updating the digital twin. This multi-functionality improves relationship detection accuracy while containing system complexity by consolidating AI capabilities into a single service module
Data Source
AI summary
A building system can include one or more storage devices storing instructions thereon, that, when executed by one or more processors, cause the one or more processors to generate a building graph, the building graph including nodes representing entities of a building and edges between the nodes, the edges representing relationships between the entities. The building system can execute an artificial intelligence service, the artificial intelligence service to receive at least one of data describing the entities, at least one node of the nodes, or at least one edge of the edges as an input and output a correlator type that identifies that a first entity type of a first entity of the entities impacts a second entity type of a second entity of the entities. The building system can update the building graph to include data representing a correlator based on the correlator type.