{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T04:27:55Z","timestamp":1786508875995,"version":"3.56.0"},"reference-count":23,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T00:00:00Z","timestamp":1777248000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["RS-2025-00521452"],"award-info":[{"award-number":["RS-2025-00521452"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["RS-2025-15002982"],"award-info":[{"award-number":["RS-2025-15002982"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["SoftwareX"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.softx.2026.102696","type":"journal-article","created":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T01:58:35Z","timestamp":1777600715000},"page":"102696","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["ConsBASE: End-to-end ETL pipeline for Korean construction document integration"],"prefix":"10.1016","volume":"34","author":[{"given":"Seung-Kyu","family":"Hong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong-Seok","family":"Seo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bum-Soo","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1125-6533","authenticated-orcid":false,"given":"Hyuk-Yoon","family":"Kwon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.softx.2026.102696_bib0005","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1287\/isre.3.1.60","article-title":"Information systems success: the quest for the dependent variable","volume":"3","author":"DeLone","year":"1992","journal-title":"Inf Syst Res"},{"issue":"1","key":"10.1016\/j.softx.2026.102696_bib0010","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1108\/JEDT-08-2021-0442","article-title":"Digital transformation in the construction industry: a bibliometric review","volume":"22","author":"Adekunle","year":"2024","journal-title":"Journal of Engineering, Design and Technology"},{"issue":"4","key":"10.1016\/j.softx.2026.102696_bib0015","first-page":"1298","article-title":"End-to-End digitization of image format piping and instrumentation diagrams at an industrially applicable level","volume":"9","author":"Kim","year":"2022","journal-title":"J Comput Des Eng"},{"key":"10.1016\/j.softx.2026.102696_bib0020","series-title":"Ninth international conference on document analysis and recognition (ICDAR 2007)","first-page":"629","article-title":"An overview of the tesseract OCR engine","volume":"vol. 2","author":"Smith","year":"2007"},{"issue":"11","key":"10.1016\/j.softx.2026.102696_bib0025","doi-asserted-by":"crossref","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","article-title":"An End-to-End trainable neural network for Image-Based sequence recognition and its application to scene text recognition","volume":"39","author":"Shi","year":"2016","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10.1016\/j.softx.2026.102696_bib0030","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"13094","article-title":"TrOCR: Transformer-Based optical character recognition with Pre-Trained models","volume":"vol. 37","author":"Li","year":"2023"},{"key":"10.1016\/j.softx.2026.102696_bib0040","author":"Du"},{"key":"10.1016\/j.softx.2026.102696_bib0050","series-title":"Advances in structural and syntactic pattern recognition","first-page":"270","article-title":"The document spectrum for Bottom-Up page layout analysis","author":"O\u2019Gorman","year":"1992"},{"issue":"11","key":"10.1016\/j.softx.2026.102696_bib0055","doi-asserted-by":"crossref","first-page":"1162","DOI":"10.1109\/34.244677","article-title":"The document spectrum for page layout analysis","volume":"15","author":"O\u2019Gorman","year":"2002","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10.1016\/j.softx.2026.102696_bib0060","series-title":"2019 international conference on document analysis and recognition (ICDAR)","first-page":"1015","article-title":"PubLayNet: largest dataset ever for document layout analysis","author":"Zhong","year":"2019"},{"key":"10.1016\/j.softx.2026.102696_bib0065","author":"Li"},{"key":"10.1016\/j.softx.2026.102696_bib0075","series-title":"International conference on document analysis and recognition","first-page":"131","article-title":"LayoutParser: a unified toolkit for deep learning based document image analysis","author":"Shen","year":"2021"},{"key":"10.1016\/j.softx.2026.102696_bib0080","series-title":"Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining","first-page":"1192","article-title":"LayoutLM: Pre-Training of text and layout for document image understanding","author":"Xu","year":"2020"},{"key":"10.1016\/j.softx.2026.102696_bib0085","series-title":"Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing (volume 1: long papers)","first-page":"2579","article-title":"Layoutlmv2: Multi-Modal Pre-Training for Visually-Rich document understanding","author":"Xu","year":"2021"},{"key":"10.1016\/j.softx.2026.102696_bib0090","series-title":"Proceedings of the 30th ACM international conference on multimedia","first-page":"4083","article-title":"Layoutlmv3: Pre-Training for document AI with unified text and image masking","author":"Huang","year":"2022"},{"key":"10.1016\/j.softx.2026.102696_bib0095","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"993","article-title":"DocFormer: End-to-End transformer for document understanding","author":"Appalaraju","year":"2021"},{"issue":"6","key":"10.1016\/j.softx.2026.102696_bib0100","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3355610","article-title":"Document layout analysis: a comprehensive survey","volume":"52","author":"Binmakhashen","year":"2019","journal-title":"ACM Computing Surveys (CSUR)"},{"issue":"12","key":"10.1016\/j.softx.2026.102696_bib0105","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3657281","article-title":"Deep learning for table detection and structure recognition: a survey","volume":"56","author":"Kasem","year":"2024","journal-title":"ACM Comput Surv"},{"key":"10.1016\/j.softx.2026.102696_bib0110","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops","first-page":"572","article-title":"CascadeTabNet: an approach for end to end table detection and structure recognition from Image-Based documents","author":"Prasad","year":"2020"},{"key":"10.1016\/j.softx.2026.102696_bib0115","series-title":"Proceedings of the 30th ACM international conference on multimedia","first-page":"6473","article-title":"TSRFormer: table structure recognition with transformers","author":"Lin","year":"2022"},{"key":"10.1016\/j.softx.2026.102696_bib0120","author":"Kasem"},{"key":"10.1016\/j.softx.2026.102696_bib0125","unstructured":"AIHub. Aihub. https:\/\/www.aihub.or.kr"},{"key":"10.1016\/j.softx.2026.102696_bib0130","series-title":"The state of AI in 2022\u2014and a half decade in review: AI adoption and use survey","year":"2022"}],"container-title":["SoftwareX"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2352711026001883?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2352711026001883?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T03:41:06Z","timestamp":1786506066000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2352711026001883"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":23,"alternative-id":["S2352711026001883"],"URL":"https:\/\/doi.org\/10.1016\/j.softx.2026.102696","relation":{},"ISSN":["2352-7110"],"issn-type":[{"value":"2352-7110","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"ConsBASE: End-to-end ETL pipeline for Korean construction document integration","name":"articletitle","label":"Article Title"},{"value":"SoftwareX","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.softx.2026.102696","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"102696"}}