Hybrid extraction of air handling unit configurations from building design documentation: formal grammars and large language models
Received: 08 Nov 2026 Accepted: 08 Nov 2026
Published: 2026, vol. 30, issue 4, pp. 389–392
Abstract
HVAC equipment manufacturers transfer air handling unit data from building designs into selection software by hand. We describe a scheme for extracting this data automatically: a large language model reads the sheet image into a JSON schema and classifies sheets not recognised from text; the remaining sheet selection, parsing of unit designations by formal grammars, source merging and all decisions are done by verifiable code. Recall of system-table and specification sheets is 100 % on the training corpus and 94–99 % on a held-out sample; a recheck of 560 extracted fields found no number-reading errors.
Keywords: large language models, information extraction, formal grammars, design documentation, air handling units.
BibTeX
@article{IS-Osokin-Alimov2026,
author = {Osokin, Viktor Vladimirovich and Alimov, Rustamzhon Fakhriddinovich},
title = {{Hybrid extraction of air handling unit configurations from building design documentation: formal grammars and large language models}},
journal = {Intelligent Systems. Theory and Applications},
year = {2026},
volume = {30},
number = {4},
pages = {389--392},
}
AMSBIB
\Bibitem{IS-Osokin-Alimov2026}
\by V.\,V.~Osokin, R.\,F.~Alimov
\paper Hybrid extraction of air handling unit configurations from building design documentation: formal grammars and large language models
\jour Intelligent Systems. Theory and Applications
\yr 2026
\vol 30
\issue 4
\pages 389--392
\lang In Russian
RU