Building Point Naming With LLM Classification for BAS Tag Mapping

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Building devices are often installed without standardized naming conventions, making configuration challenging for building configuration systems due to unstructured object names.

Innovation Solution

A method using generative artificial intelligence to perform data augmentation and fine-tuning of large language models for PES classification, enabling automatic generation of standardized tags for building devices.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If contractors install building devices without standardized naming conventions, then installation flexibility is maintained, but configuration compatibility and classification accuracy deteriorate

Engineering Contradiction:

Improveinstallation flexibilityVSAvoidnaming accuracy

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The system performs preliminary action by training the machine learning model in advance with diverse building device naming patterns. The model is pre-trained to recognize and standardize various naming conventions before actual configuration tasks, enabling automatic conversion of non-standard names to standardized formats without requiring manual intervention during installation.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The machine learning model serves as an intermediary between contractors' non-standard naming and the building configuration system's standardized requirements. The model automatically translates and adapts various naming conventions into standardized formats, bridging the gap between installation flexibility and configuration compatibility.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If manual configuration of building devices is performed, then naming accuracy can be ensured, but configuration time and labor costs increase

Engineering Contradiction:

Improvenaming accuracyVSAvoidconfiguration time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system implements self-service by enabling building devices to automatically generate and assign standardized names through the machine learning model. The model processes device information and generates standardized names autonomously without requiring manual configuration, making the system self-sufficient in handling naming standardization.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual configuration process with an automated machine learning-based system. The ML model automatically performs naming standardization that previously required manual human intervention, substituting automated intelligent processing for manual mechanical configuration tasks.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Ease of manufacture

If non-standard object names are used for building devices, then installation simplicity is maintained, but system compatibility and control effectiveness deteriorate

Engineering Contradiction:

Improveinstallation simplicityVSAvoidsystem compatibility

Core Design Contradiction:

Ease of manufactureVSReliability

Solution Approach 1:

The system applies dynamics by making the naming standardization process adaptive and flexible. The machine learning model dynamically adjusts to various naming patterns encountered during installation, automatically converting them to standardized formats. This dynamic adaptation maintains installation simplicity while ensuring system compatibility through automatic standardization.

Inventive Principle:

Principle #15Dynamics

4Productivity

If automated naming systems are implemented, then configuration efficiency is improved, but system complexity and model training requirements increase

Engineering Contradiction:

Improveconfiguration efficiencyVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The machine learning model achieves universality by being trained to handle multiple building device types, protocols, and naming conventions within a single system. This multi-functional model can process various device categories (HVAC, lighting, security, etc.) and different communication protocols, reducing the need for separate specialized systems while maintaining high configuration efficiency.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20250355409A1Building system with generative artificial intelligence point naming, classification, and mapping

Publication Date: 2025.11.20 TYCO FIRE & SECURITY GMBH

AI summary

A method can include performing data augmentation of a dataset to generate an augmented dataset, fine-tuning at least one large language model (LLM) using the augmented dataset, performing point, equipment, or subtype (PES) classification of points of a building using the at least one fine-tuned LLM, and operating equipment of the building using the PES classification to affect a physical condition of the building.