Graph Schema Mapping for Building Point Data Interoperability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Building systems face challenges in managing and controlling subsystems due to incompatible data formats from various equipment manufacturers, leading to inefficiencies in application design and deployment, and existing rule-based converters struggle with adaptability and resource utilization.
Innovation Solution
A building system uses machine learning and artificial intelligence techniques to map point data into a graph schema, employing embedding and clustering methods to identify and establish relationships between building entities, reducing configuration time and improving adaptability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If rule-based converters are used to translate data formats, then implementation is straightforward, but adaptability to new equipment and formats is poor
Solution Approach 1:
The patent replaces rule-based converters (mechanical/systematic approach) with machine learning models (intelligent system). The ML models learn translation patterns from training data and automatically adapt to new equipment and data formats without requiring manual rule updates, thereby improving adaptability while managing complexity through automated model training pipelines.
Solution Approach 2:
The system changes from fixed translation rules to dynamic parameter-based translation. ML models learn optimal translation parameters from training data and can adjust these parameters based on the specific equipment and data format being processed, enabling flexible adaptation to new formats without redesigning the entire translation system.
2Reliability
If extensive configuration is performed for each building application, then application requirements are met, but deployment time increases
Solution Approach 1:
The system performs preliminary action by pre-training machine learning models on comprehensive building data before actual deployment. The models are trained in advance to understand various building formats, equipment types, and relationships. During deployment, this pre-learned knowledge is directly applied, eliminating the need for extensive manual configuration and significantly reducing deployment time while maintaining configuration accuracy.
Solution Approach 2:
The ML-based system enables self-service configuration where the system automatically translates and configures building data without requiring extensive manual intervention. The models autonomously process building files, identify equipment, establish relationships, and generate application configurations, thereby reducing both deployment time and the need for expert configuration while maintaining reliability.
3Adaptability or versatility
If multiple data formats from different manufacturers are supported, then system compatibility improves, but processing complexity increases
Solution Approach 1:
The patent implements universality by creating a unified ML-based translation framework that can handle multiple data formats from different manufacturers through a single system. The ML models are trained on diverse building data formats and equipment types, enabling them to universally process various formats using the same underlying architecture, thereby improving compatibility without proportionally increasing processing complexity.
Data Source
AI summary
A system including a processing circuit configured to receive tags describing points of a piece of equipment, the piece of equipment connected to the system. The processing circuit configured to map the tags to classes of a schema of a graph data structure. The processing circuit configured to perform clustering to generate clusters of the points. The processing circuit configured to identify, based on the clusters, relationships in the schema of the graph data structure between the tags mapped to the classes of the schema of the graph data structure. The processing circuit configured to communicate data to a second system based at least in part on the tags mapped to the classes and the relationships.