Building Point Graph Mapping for Cross-Format Data Integration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Building management systems face challenges in integrating and interpreting data from various building subsystems due to incompatible data formats and languages, leading to inefficiencies in application design and deployment.
Innovation Solution
A building system that uses machine learning and artificial intelligence techniques to map points into a graph schema, identifying relationships and adapting to different data formats by clustering points and generating embeddings for classification, thereby reducing configuration and deployment time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional rule-based conversion methods are used to translate data between building subsystems, then data compatibility can be achieved, but the system complexity and configuration time increase significantly
Solution Approach 1:
The patent introduces a graph data structure as an intermediary layer between building subsystems with different data formats. This graph schema acts as a universal mediator that translates and integrates data from various subsystems (HVAC, security, lighting) without requiring complex point-to-point conversion rules, thereby reducing system complexity while maintaining adaptability
Solution Approach 2:
The system transforms data from traditional building automation formats into a graph-based representation format. By changing the data structure parameters from hierarchical/flat formats to graph schemas with nodes and edges, the system achieves better compatibility and reduced complexity in data integration
2Measurement precision
If extensive rule-based conversions are implemented to handle different data formats, then data accuracy can be maintained, but deployment time and resource consumption increase
Solution Approach 1:
The system performs preliminary mapping of data points to graph schema nodes during the initial setup phase. By pre-defining the graph data structure and relationships between nodes, the system eliminates the need for extensive runtime rule evaluations, thereby reducing deployment time while maintaining data accuracy through structured validation
Solution Approach 2:
The graph data structure serves multiple functions simultaneously: it acts as a data model, a translation layer, a validation schema, and a relationship map. This multi-functionality reduces the need for separate rule-based conversion systems, decreasing deployment time while maintaining data accuracy through the unified structure
3Measurement precision
If machine learning techniques are used to map points to graph schema, then classification accuracy improves, but computational resources and processing time increase
Solution Approach 1:
The system applies machine learning techniques selectively rather than universally. It uses ML for mapping data points to graph schema nodes where ambiguity exists, while relying on predefined rules and heuristics for straightforward cases. This partial application of ML reduces computational resource consumption while maintaining high classification accuracy for complex mappings
Solution Approach 2:
The system employs self-training mechanisms where the machine learning models are continuously improved using feedback from the graph data structure and accumulated data. This self-service approach allows the system to achieve high accuracy over time with reduced computational resources, as the models become more efficient at classification tasks
Data Source
AI summary
A building system of a building including one or more memory devices having instructions thereon, that, when executed by one or more processors, cause the one or more processors to receive tags describing points of the building. The instructions cause the one or more processors to map the tags to classes of a schema of a graph data structure, perform clustering to generate clusters of the points. The instructions cause the one or more processors 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 instructions cause the one or more processors to construct the graph data structure in the schema based on the tags mapped to the classes and the relationships in the schema of the graph data structure.