BMS Semantic Tagging Using Context-Aware Learning Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Building management systems face challenges in accurately and efficiently applying semantic information to data from diverse and legacy equipment, leading to ambiguities and manual sorting requirements, which is time-consuming and requires expertise.
Innovation Solution
A method using machine learning and rule-based models to generate semantic data tags by evaluating unrecognized data from equipment, combining individual and contextual evaluations, and applying tags based on probability distributions and user confirmation, with the ability to update equipment models and utilize Brick Schema or Project Haystack for tagging.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual sorting and semantic tagging is performed by subject matter experts, then data accuracy and semantic information quality is improved, but time consumption and operational effort increase significantly
Solution Approach 1:
The system enables automatic semantic tagging through machine learning models that self-learn from historical data and automatically apply semantic information to unrecognized data points, eliminating the need for manual expert intervention while maintaining high accuracy through continuous learning and improvement
Solution Approach 2:
The patent replaces the manual mechanical process of expert sorting and tagging with an automated machine learning system that uses algorithms to analyze data patterns, generate semantic tags, and apply them automatically, substituting human cognitive work with computational processes
2Loss of information
If manual semantic tagging is performed, then semantic information quality is improved, but operational complexity and expertise requirements increase
Solution Approach 1:
The machine learning system performs automatic semantic analysis and tagging without requiring manual expert operations, making the process as easy as initiating the automated system while maintaining high semantic information quality through sophisticated algorithmic analysis
3Productivity
If automated methods are used for semantic tagging, then productivity and efficiency are improved, but measurement precision and data accuracy may deteriorate
Solution Approach 1:
The system performs preliminary training on historical data with known semantic information before deployment, pre-learning patterns and relationships to ensure high accuracy from the start of automated operation, and continues to learn and improve over time
Solution Approach 2:
The system incorporates feedback mechanisms where tagging results are continuously evaluated against ground truth data, and the machine learning models are retrained and refined based on performance metrics to maintain and improve accuracy over time
Data Source
AI summary
A method for applying semantic information to data in a building management system (BMS). The method includes receiving unrecognized data from equipment associated with the BMS, the unrecognized data comprising a first value and an associated device identifier; providing the unrecognized data as input to a first learning model to generate a first output, the first output indicative of semantic information corresponding to the first value evaluated individually; providing the unrecognized data as input to a second learning model to generate a second output, the second output indicative of semantic information corresponding to the first value evaluated in context of a second value associated with the device identifier; and applying semantic information to the unrecognized data based on the first output and the second output. The method allows for users to configure building management systems with automatically generated semantic data tags.