Hybrid deep learning model for automating constraint modelling in advanced working packaging

Abstract

Management of constraints (e.g. materials and labour) is a major challenge in construction projects. Advanced working packaging (AWP) is an effective constraint-management method. However, one prerequisite for AWP, i.e. constraint modelling, is generally performed manually. Information extraction methods in the industry cannot meet the demands for AWP, because they focus on entity extraction but ignore extraction of semantically rich relations. To address this problem, this study proposes a hybrid deep learning model. A bidirectional long short-term memory and conditional random field (Bi-LSTM-CRF) model and knowledge representation learning (KRL) model are developed to extract entities and relations among entities from text documents, respectively. To better apply the KRL model, the study maps domain classes of entities and then stacks class information in the model structure, while employing synonym mapping to handle entities unseen during training. The overall accuracies for extracting entities and relations can reach 0.936 and 0.884, respectively, and adding class information increases relation extraction performance metrics by 6.63%. In a scenario implementation, it is shown that the model can automate constraint modelling for ongoing projects. Therefore, the model is useful for AWP and can reduce delays and reworks by saving a significant amount of time for constraint monitoring and removal.