A Natural-language-based Approach to Intelligent Data Retrieval and Representation for Cloud BIM

Abstract

A building’s BIM (Building Information Model) grows in size when data from many fields is integrated over an AEC project’s lifespan. Because of this issue, consumers will have a hard time getting the information they want on a mobile device, which has limited area for interaction. Employees who aren’t BIM professionals or who don’t have a deep understanding of Industry 
Foundation Classes (IFC) will have it much worse. An intelligent data retrieval and representation strategy for cloud BIM applications based on natural language processing was developed to increase the value of the huge data of BIM. To begin managing the massive amounts of BIM data, methods for storing data and speeding up queries using the widely used cloud-based database were investigated. Then, to describe the user’s expectations in a natural-language phrase, the notions of “keyword” and “constraint” were suggested to capture the important objects and their specifications. The International Framework for Dictionaries (IFD) allows for the mapping of keywords and restrictions to entities or characteristics inside the International Financial Center (IFC). Data retrieval and analysis were made possible by route finding in a graph built from the IFC schema, which established 
the link between the user’s demand and the IFC-based data model. Lastly, the structure of the obtained data was used to depict the analyzed and summarized outcomes of the BIM data. Using data acquired during the construction of Kunming Airport’s terminal—the biggest single structure in China—a prototype application was created to test the suggested strategy. The following were shown by the case study: (1) user needs and data are linked; (2) cloud-based BIM allows for automated retrieval and aggregation of user-related data; and (3) data is delivered in an appropriate format for both visual representation and detailed 
reporting. Users may greatly benefit from information requests using this technique, and BIM’s value will be boosted..