Large Language Models for the Creation and Use of Semantic Ontologies in Buildings: Requirements and Challenges
Conference
·
· Proceedings of the 11th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation
- Carnegie Mellon University / Lawrence Berkeley National, Laboratory, Pittsburgh, PA, United States
- Lawrence Berkeley National, Laboratory, Berkeley, CA, United States
- Lawrence Berkeley National, Laboratory / Carnegie Mellon University, Berkeley, CA, United States
- Lawrence Berkeley National, Laboratory / University of California, Berkeley, Berkeley, CA, United States
- Colorado School of Mines, Golden, CO, United States
Semantic ontologies offer a formalized, machine-readable framework for representing knowledge, enabling the structured description of complex systems. In the building domain, the adoption of ontologies like the Brick schema has transformed how buildings and their systems are modeled by providing a standardized, interoperable language. However, the complexity and the steep learning curve involved in developing and querying semantic models present substantial challenges, often requiring a workforce with specialized expertise. This paper builds on our experience in investigating how Large Language Models (LLMs) can help address these challenges, focusing on their role in constructing and querying of semantic models, particularly using the Brick Schema. Our study outlines the requirements and metrics for evaluating the scalability and effectiveness of LLM-based tools, while also discussing the current challenges and limitations in developing such tools. Ultimately, this paper aims to orient research efforts as various groups experiment with diverse techniques, while enabling more effective comparison of emerging solutions and fostering collaboration across the field.
- Research Organization:
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
- Sponsoring Organization:
- USDOE Office of Energy Efficiency and Renewable Energy (EERE), Energy Efficiency Office. Building Technologies Office (EE-5B)
- DOE Contract Number:
- AC02-05CH11231
- OSTI ID:
- 2552949
- Conference Information:
- Journal Name: Proceedings of the 11th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation
- Country of Publication:
- United States
- Language:
- English
A survey of RDF stores & SPARQL engines for querying knowledge graphs
|
journal | November 2021 |
Advancing smart building readiness: Automated metadata extraction using neural language processing methods
|
journal | August 2021 |
Unified architecture for data-driven metadata tagging of building automation systems
|
journal | December 2020 |
A novel data-driven relationship inference approach for automatic data tagging in building heating, ventilation and air conditioning systems
|
journal | December 2023 |
SGPT: A Generative Approach for SPARQL Query Generation From Natural Language Questions
|
journal | January 2022 |
SP^2Bench: A SPARQL Performance Benchmark
|
conference | March 2009 |
Experiments with text-to-SPARQL based on ChatGPT
|
conference | February 2024 |
An evaluation of approaches to federated query processing over linked data
|
conference | September 2010 |
The Building Adapter: Towards Quickly Applying Building Analytics at Scale
|
conference | January 2015 |
Automated Metadata Construction to Support Portable Building Applications
|
conference | January 2015 |
Short Paper
|
conference | November 2015 |
Brick: Towards a Unified Metadata Schema For Buildings
|
conference | January 2016 |
Scrabble: converting unstructured metadata into brick for many buildings
|
conference | November 2017 |
Plaster: an integration, benchmark, and development framework for metadata normalization methods
|
conference | November 2018 |
Mortar
|
journal | February 2020 |
Query relaxation for portable brick-based applications
|
conference | November 2021 |
Application-driven creation of building metadata models with semantic sufficiency
|
conference | November 2022 |
What's The Point: AutoEncoding Building Point Names
|
conference | November 2023 |
Metadata Schemas and Ontologies for Building Energy Applications: A Critical Review and Use Case Analysis
|
journal | April 2021 |
LLMs4OL 2024 Datasets: Toward Ontology Learning with Large Language Models
|
journal | October 2024 |
Similar Records
Extraction and Analysis of Time Series Data from Building Automation Systems Using Large Language Models
VizBrick: A GUI-based Interactive Tool for Authoring Semantic Metadata for Building Datasets
Visual Brick model authoring tool for building metadata standardization
Conference
·
Sat May 31 20:00:00 EDT 2025
·
OSTI ID:2572118
VizBrick: A GUI-based Interactive Tool for Authoring Semantic Metadata for Building Datasets
Conference
·
Sat Oct 01 00:00:00 EDT 2022
·
OSTI ID:1997805
Visual Brick model authoring tool for building metadata standardization
Journal Article
·
Fri Oct 20 20:00:00 EDT 2023
· Automation in Construction
·
OSTI ID:2378109