아파트 하자 보수 시설공사 세부공종머신러닝 분류 시스템에 관한 연구

Abstract

A number of construction companies in Korea invest considerable human and financial resources to construct a system for managingapartment defect data and for categorizing repair tasks. Thus, this study proposes machine learning models to automatically classify defectcomplaint text-data into one of the sub categories of ‘finishing work’ (i.e., one of the defect repair tasks). In the proposed models, we employedtwo word representation methods (Bag-of-words, Term Frequency-Inverse Document Frequency (TF-IDF)) and two machine learning classifiers(Support Vector Machine, Random Forest). In particular, we conducted both binary- and multi- classification tasks to classify 9 sub categoriesof finishing work: home appliance installation work, paperwork, painting work, plastering work, interior masonry work, plaster finishing work,indoor furniture installation work, kitchen facility installation work, and tiling work. The machine learning classifiers using the TF-IDFrepresentation method and Random Forest classification achieved more than 90% accuracy, precision, recall, and F1 score. We shed lighton the possibility of constructing automated defect classification systems based on the proposed machine learning models.