Intelligent BIM Searching via Deep Embedding of Geometric, Semantic, and Topological Features

As a digital representation of buildings, building information models (BIMs) encapsulate geometric, semantic, and topological features (GSTFs), to express the visual and functional characteristics of building components and their connections to create building systems. However, searching for BIMs pa...

Full description

Saved in:
Bibliographic Details
Main Authors: Pin-Hao Huang, Sheng-Yu Song, Zhen Xu, Zhen-Zhong Hu, Jia-Rui Lin
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Buildings
Subjects:
Online Access:https://www.mdpi.com/2075-5309/15/6/951
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850204892949381120
author Pin-Hao Huang
Sheng-Yu Song
Zhen Xu
Zhen-Zhong Hu
Jia-Rui Lin
author_facet Pin-Hao Huang
Sheng-Yu Song
Zhen Xu
Zhen-Zhong Hu
Jia-Rui Lin
author_sort Pin-Hao Huang
collection DOAJ
description As a digital representation of buildings, building information models (BIMs) encapsulate geometric, semantic, and topological features (GSTFs), to express the visual and functional characteristics of building components and their connections to create building systems. However, searching for BIMs pays much attention to semantic features, while overlooking geometric and topological features, making it difficult to find and reuse rich knowledge in BIMs. Thus, this study proposes a novel approach to intelligent BIM searching by embedding GSTFs via deep learning (DL). First, algorithms for extracting GSTFs from BIMs and identifying required GSTFs from search queries are developed. Then, different GSTFs are embedded via DL models, creating vector-based representations of BIMs or search queries. Finally, similarity-based ranking is adopted to find BIMs highly related to the queries. Experiments show that the proposed approach demonstrates an efficiency of 780 times greater than manual retrieval methods and 4–6% more efficient than traditional methods. This study advances the field of BIM searching by providing a more comprehensive, accurate, and efficient method for finding and reusing rich knowledge in BIMs, ultimately contributing to better building design and knowledge management.
format Article
id doaj-art-ca4d9557347d46ebbd028f705a98fbf8
institution OA Journals
issn 2075-5309
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Buildings
spelling doaj-art-ca4d9557347d46ebbd028f705a98fbf82025-08-20T02:11:12ZengMDPI AGBuildings2075-53092025-03-0115695110.3390/buildings15060951Intelligent BIM Searching via Deep Embedding of Geometric, Semantic, and Topological FeaturesPin-Hao Huang0Sheng-Yu Song1Zhen Xu2Zhen-Zhong Hu3Jia-Rui Lin4Department of Civil Engineering, Tsinghua University, Beijing 100084, ChinaDepartment of Civil Engineering, Tsinghua University, Beijing 100084, ChinaSchool of Civil and Resource Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaShenzhen International Graduate School, Tsinghua University, Shenzhen 518055, ChinaDepartment of Civil Engineering, Tsinghua University, Beijing 100084, ChinaAs a digital representation of buildings, building information models (BIMs) encapsulate geometric, semantic, and topological features (GSTFs), to express the visual and functional characteristics of building components and their connections to create building systems. However, searching for BIMs pays much attention to semantic features, while overlooking geometric and topological features, making it difficult to find and reuse rich knowledge in BIMs. Thus, this study proposes a novel approach to intelligent BIM searching by embedding GSTFs via deep learning (DL). First, algorithms for extracting GSTFs from BIMs and identifying required GSTFs from search queries are developed. Then, different GSTFs are embedded via DL models, creating vector-based representations of BIMs or search queries. Finally, similarity-based ranking is adopted to find BIMs highly related to the queries. Experiments show that the proposed approach demonstrates an efficiency of 780 times greater than manual retrieval methods and 4–6% more efficient than traditional methods. This study advances the field of BIM searching by providing a more comprehensive, accurate, and efficient method for finding and reusing rich knowledge in BIMs, ultimately contributing to better building design and knowledge management.https://www.mdpi.com/2075-5309/15/6/951building information model (BIM)model searchfeature extractionsimilarity calculationdeep learningfeature embedding
spellingShingle Pin-Hao Huang
Sheng-Yu Song
Zhen Xu
Zhen-Zhong Hu
Jia-Rui Lin
Intelligent BIM Searching via Deep Embedding of Geometric, Semantic, and Topological Features
Buildings
building information model (BIM)
model search
feature extraction
similarity calculation
deep learning
feature embedding
title Intelligent BIM Searching via Deep Embedding of Geometric, Semantic, and Topological Features
title_full Intelligent BIM Searching via Deep Embedding of Geometric, Semantic, and Topological Features
title_fullStr Intelligent BIM Searching via Deep Embedding of Geometric, Semantic, and Topological Features
title_full_unstemmed Intelligent BIM Searching via Deep Embedding of Geometric, Semantic, and Topological Features
title_short Intelligent BIM Searching via Deep Embedding of Geometric, Semantic, and Topological Features
title_sort intelligent bim searching via deep embedding of geometric semantic and topological features
topic building information model (BIM)
model search
feature extraction
similarity calculation
deep learning
feature embedding
url https://www.mdpi.com/2075-5309/15/6/951
work_keys_str_mv AT pinhaohuang intelligentbimsearchingviadeepembeddingofgeometricsemanticandtopologicalfeatures
AT shengyusong intelligentbimsearchingviadeepembeddingofgeometricsemanticandtopologicalfeatures
AT zhenxu intelligentbimsearchingviadeepembeddingofgeometricsemanticandtopologicalfeatures
AT zhenzhonghu intelligentbimsearchingviadeepembeddingofgeometricsemanticandtopologicalfeatures
AT jiaruilin intelligentbimsearchingviadeepembeddingofgeometricsemanticandtopologicalfeatures