{"title":"使用机器学习自动检测建筑需求中的模糊性","authors":"Zijing Zhang, Ling Ma","doi":"10.35490/ec3.2023.211","DOIUrl":null,"url":null,"abstract":"The rule interpretation step is yet to be fully automated in the compliance checking process, which hinders the automation of compliance checking. Whilst existing research has developed numerous methods for automated interpretation of building requirements, none of them can identify or address ambiguous requirements. As part of interpreting ambiguous clauses automatically, this research proposed a supervised machine learning method to detect ambiguity automatically, where the best-performing model achieved recall, precision and accuracy scores of 99.0%, 71.1%, and 78.2%, respectively. This research contributes to the body of knowledge by developing a method for automated detection of ambiguity in building requirements to support automated compliance checking.","PeriodicalId":7326,"journal":{"name":"Advances in Informatics and Computing in Civil and Construction Engineering","volume":"114 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Using machine learning for automated detection of ambiguity in building requirements\",\"authors\":\"Zijing Zhang, Ling Ma\",\"doi\":\"10.35490/ec3.2023.211\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The rule interpretation step is yet to be fully automated in the compliance checking process, which hinders the automation of compliance checking. Whilst existing research has developed numerous methods for automated interpretation of building requirements, none of them can identify or address ambiguous requirements. As part of interpreting ambiguous clauses automatically, this research proposed a supervised machine learning method to detect ambiguity automatically, where the best-performing model achieved recall, precision and accuracy scores of 99.0%, 71.1%, and 78.2%, respectively. This research contributes to the body of knowledge by developing a method for automated detection of ambiguity in building requirements to support automated compliance checking.\",\"PeriodicalId\":7326,\"journal\":{\"name\":\"Advances in Informatics and Computing in Civil and Construction Engineering\",\"volume\":\"114 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-07-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Advances in Informatics and Computing in Civil and Construction Engineering\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.35490/ec3.2023.211\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advances in Informatics and Computing in Civil and Construction Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.35490/ec3.2023.211","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Using machine learning for automated detection of ambiguity in building requirements
The rule interpretation step is yet to be fully automated in the compliance checking process, which hinders the automation of compliance checking. Whilst existing research has developed numerous methods for automated interpretation of building requirements, none of them can identify or address ambiguous requirements. As part of interpreting ambiguous clauses automatically, this research proposed a supervised machine learning method to detect ambiguity automatically, where the best-performing model achieved recall, precision and accuracy scores of 99.0%, 71.1%, and 78.2%, respectively. This research contributes to the body of knowledge by developing a method for automated detection of ambiguity in building requirements to support automated compliance checking.