A method and a system for automatically extracting and classifying construction process constraints

Abstract

The invention discloses a method and a system for automatically extracting and classifying construction process constraints, belonging to the field of natural language processing and construction engineering. The method comprises building BI-LSTM-CRF model that identifies named entities in the specification and tags entity attributes; building LSTM-MLP model, which can judge the pattern type of the process constraint contained in the specification, and expressing the process constraint structurally; the model training is carried out by using the labeled training samples. Using the marked testsamples, the model is tested, the error between the test results and the actual results is analyzed, and the parameters of the model are modified by feedback. The method and system of the invention adopting BI-LSTM-CRF and LSTM-MLP model can realize the automatic extraction and classification of construction process constraints in building engineering specifications, and the structural expressionof constraint knowledge, which is conducive to the learning, query and application of construction process constraint knowledge.

Description

technical field [0001] The invention belongs to the fields of natural language processing and construction engineering, and more specifically relates to a method and system for automatic extraction and classification of construction process constraints based on machine learning. Background technique [0002] In recent years, my country's construction industry has developed very rapidly, and the efficiency of construction projects has improved significantly. However, from the perspective of project construction quality management, there are still many problems, such as: construction practitioners are not skilled in construction technology, project quality acceptance work Insufficient strength, insufficient timely and smooth communication of information, etc. These problems will affect the quality of construction projects to a certain extent, and even cause engineering safety accidents. Therefore, in order to ensure the quality of construction projects, it is necessary to do a...

AI Technical Summary

Problems solved by technology

For quantitative constraints, often accompanied by obvious features such as mathematical symbols, the process of information extraction is relatively easy, but for qualitative constraints, especially process constraints, the process of knowledge learning, query and application is more difficult due to the inconsistency of description methods

Images