Classifying devices from entity names based on contextual information
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated Fault Detection & Diagnostics (FDD) analytics in building management systems face challenges due to contextual information being unavailable in a machine-readable format, requiring human interpretation and varying naming conventions across regions and customers, which hinders efficient classification of devices like HVAC systems.
Innovation Solution
A controller is configured to extract core names from entity names, compare them to candidate core names, determine scores, and classify devices based on the highest score, using techniques such as constructing bigrams and summing results to facilitate accurate classification and improve FDD analytics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If contextual information is stored as text labels with varying naming conventions, then human interpretation is required for accurate classification, but this increases the complexity and time consumption of device classification processes
Solution Approach 1:
The system performs self-service by automatically extracting core names from entity names and comparing them against a database of candidate core names to determine device classes, eliminating the need for manual human interpretation while maintaining high classification accuracy through algorithmic processing
Solution Approach 2:
The patent replaces the mechanical human interpretation process with an automated computational system that extracts core names, constructs bigrams, compares against candidate names, and determines device classes through algorithmic operations, significantly reducing classification time while preserving accuracy
2Productivity
If automated classification methods are implemented to reduce manual interpretation, then classification speed improves, but accuracy may deteriorate due to varying naming conventions across regions and customers
Solution Approach 1:
The system extracts the essential core name from each entity name by removing varying prefixes, suffixes, and region-specific modifiers, isolating the invariant core identifier that enables accurate automated classification across different naming conventions while maintaining high classification speed
Solution Approach 2:
The patent creates a universal classification system that handles multiple naming conventions from different regions and customers by comparing extracted core names against a comprehensive database of candidate core names, enabling the same automated process to accurately classify diverse device types including HVAC, lighting, and security devices
3Extent of automation
If core name extraction and bigram construction methods are used to standardize device classification, then automated FDD analytics improve, but the processing complexity increases
Solution Approach 1:
The patent segments the entity name into distinct components by extracting the core name and constructing bigrams from it, breaking down the complex naming variation problem into manageable processing steps that can be systematically compared against candidate core names to enable automated FDD analytics
Solution Approach 2:
The system performs preliminary actions by pre-extracting core names and pre-constructing bigrams before the actual classification comparison, preparing the data in advance to streamline the automated FDD analytics process and reduce real-time processing complexity during device classification
Data Source
AI summary
A controller for classifying devices of a building management system (BMS). The controller may be configured to obtain an entity name for a device, extract a core name from the entity name, compare the core name to candidate core names, determine scores for each comparison, identify a highest score, identify a class of a candidate core name, and classify the device in the class.