Intelligent text recognition based on multi-feature channels network for construction quality control

Construction quality control is achieved primarily through various testing and inspections and subsequent analysis of the massive unstructured quality records. The quality professionals are required to classify and review the inspection texts according to the project category. However, manual processing of a sheer amount of textual data is not only time-consuming, laborious but also error-prone, which could lead to overlooked quality issues and harm the overall project performance. In response, this paper uses the text mining method to mine the hidden information from unstructured text records. First, obtain quality text records on-site, use data cleaning method to obtain 9859 clean data, then use both Bidirectional Encoder Representation from Transformers (BERT) pre-training and Word2vec methods to quantify the text into a digital representation, next improve the Convolutional Neural Network (CNN) model by expanding input channels, and input the quantified text into the model to extract key features to realize the integration of quality records according to established categories. The results show that the average precision of the proposed model is 89.69%. Compared with CNN, BERT, and other models, this model has less manual intervention, less time-consuming training, and higher precision. Finally, through data augmentation of small sample data, the precision of the model is further improved, reaching 92.02%. The proposed model can assist quality professionals to quickly spot key quality issues and reference corresponding quality standards for further actions, and allow them to focus on more value-added efforts, e.g., making decisions and planning for corrective actions. This research also provides a reference for the ultimate goal of constructing an intelligent project management system.

Automated summary

This research applies text mining to extract hidden information from unstructured quality records and improve the integration and classification of quality records through an enhanced CNN model and quantification using BERT and Word2vec methods. The proposed model achieves high precision with less manual intervention required.