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.

Objective: To explore the genetic characteristics and evolution of hantavirus carried by rodents in port area of Ningde in Fujian province in the summer of 2020. Methods: Rodents were captured in the port area of Ningde, the RNA was extracted from rodent lung tissues and detected by using specific kit. The positive samples were used for whole-genome sequencing of the virus. Bioinformatics software was used for the analysis on the similarity and genetic variation of the sequences. Results: A total of 112 rodents were captured, including 5 Rattus norvegicus and 2 Rattus flavipectus, the positive rate of hantavirus was 6.25% (7/112). By virus gene sequencing, two hantavirus complete genome sequences were obtained (named as FJ35 and FJ36, GenBank accession numbers: MW449188-MW449193). The genetic analysis results showed that the hantavirus detected in positive samples were SEOV and shared 99% nucleotide similarity with hantavirus strains LZSF21 and JX20140581 isolated from Shandong province. Phylogenetic analysis using the maximum likelihood method showed that the hantavirus detected in positive samples belonged to S3 subtype, sharing the same subtype with hantavirus strains Z37 from Zhejiang province, LZSF21 from Shandong province, and zy27 and Gongzhuling 415 from northeastern China. Compared with FJ372, the amino acid variation of N259S was observed at sites 251-264 of nucleoprotein, which might be related to antigenicity. Another variation of Q81R was observed in glycoprotein compared with SEOV 80-39 segment of coded amino acid of international reference strain, which might also cause the change in antigenicity. Conclusion: The high positive rate of hantavirus in rodents in the port area of Ningde- would increase the risk of natural human infection and epidemic in local area. The hantavirus positive rodents in this focus might be from an endemic area in Shandong. It is necessary to strengthen the imported rodent control in the port area of Ningde. The virus detected in 2 positive samples belonged to SEOV subtype Ⅲ and shared high homologies of nucleotides and amino acid sequences with the hantavirus strains in surrounding area. However, some slight variations occurred in glycoprotein and nucleoprotein amino acid sequences, which might cause changes in its antigeniity.