| id |
cdrf2022_199 |
| authors |
Jingming Li |
| year |
2022 |
| title |
Using Text Understanding to Create Formatted Semantic Web from BIM |
| source |
Proceedings of the 2022 DigitalFUTURES The 4st International Conference on Computational Design and Robotic Fabrication (CDRF 2022) |
| doi |
https://doi.org/https://doi.org/10.1007/978-981-19-8637-6_17
|
| summary |
The application of BIM in the building life cycle needs to be continuous. The information collected and accumulated in the early stages should flow to the subsequent phases. However, BIM applications currently focus on collision inspection, compliance inspection, and engineering calculation, few models can be successively used in the following stages. Remodeling is required in the operation and maintenance period, resulting in waste. Meanwhile, some of the information accumulated by BIM might be frequently used in the operation and maintenance stage, while some data are relatively rarely used. The semantic web can help manage building information at all stages. But the generation of a semantic web is mostly manually completed. It is necessary to standardize the repeated semantic description in the model and convert BIM into a standard semantic model for information indexing, reducing the resource consumption of model loading and optimizing the efficiency of the operation and maintenance system. When the existing research transforms from BIM to the semantic web, there will be a lack of information and descriptions of the ownership relationship between entities due to the limitation of formats. To realize the standard transformation from BIM to the semantic web, this work proposes a method of using Natural Language Processing (NLP) to understand the text and infer the relationship between entities according to the knowledge map. First, the entities are extracted from BIM, such as air conditioning unit, electric lamp, fan, etc., if the name of the extracted entity is irregular, the names are translated with the help of NLP and Ontology (such as brick or haystack) to obtain the standard definition. By comparing the complete knowledge graph (such as the knowledge graph of the air conditioning system), the relationships can be deduced, and then a standardized semantic model can be generated. |
| series |
cdrf |
| email |
|
| full text |
 file.pdf (533,843 bytes) |
| references |
Content-type: text/plain
|
| last changed |
2024/05/29 14:02 |
|
