Integrating semantic NLP and logic reasoning into a unified system for fully-automated code checking

详细信息    查看全文

• 作者：Jiansong Zhang^a ; Nora M. El-Gohary^b ; ^{gohary@illinois.edu}
• 关键词：Automated code checking ; Automated information extraction ; Automated reasoning ; Building information modeling (BIM) ; Natural language processing ; Logic ; Semantic systems ; Automated construction management systems
• 刊名：Automation in Construction
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：73
• 期：Complete
• 页码：45-57
• 全文大小：2019 K
• 卷排序：73

文摘

A fully-automated approach to code compliance checking in construction is proposed. Requirements are extracted from the code and formalized into rules, automatically. Natural language processing & a logic representation enable such full automation. Semantic transformation aligns design information with regulatory information. A prototype achieved 98.7% recall & 87.6% precision in noncompliance detection.