{"id":"https://openalex.org/W7160283294","doi":"https://doi.org/10.1016/j.softx.2026.102696","title":"ConsBASE: End-to-end ETL pipeline for Korean construction document integration","display_name":"ConsBASE: End-to-end ETL pipeline for Korean construction document integration","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7160283294","doi":"https://doi.org/10.1016/j.softx.2026.102696"},"language":"en","primary_location":{"id":"doi:10.1016/j.softx.2026.102696","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.softx.2026.102696","pdf_url":null,"source":{"id":"https://openalex.org/S2506067282","display_name":"SoftwareX","issn_l":"2352-7110","issn":["2352-7110"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SoftwareX","raw_type":"journal-article"},"type":"software-paper","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.softx.2026.102696","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090076556","display_name":"Seung-Kyu Hong","orcid":"https://orcid.org/0009-0002-8584-9187"},"institutions":[{"id":"https://openalex.org/I118373667","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07","country_code":"KR","type":"education","lineage":["https://openalex.org/I118373667"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seung-Kyu Hong","raw_affiliation_strings":["Graduate School of Data Science, Seoul National University of Science and Technology, 232 Gongneung-Ro, Nowon-Gu, Seoul, 01811, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Data Science, Seoul National University of Science and Technology, 232 Gongneung-Ro, Nowon-Gu, Seoul, 01811, South Korea","institution_ids":["https://openalex.org/I118373667"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135299596","display_name":"Dong-Seok Seo","orcid":null},"institutions":[{"id":"https://openalex.org/I118373667","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07","country_code":"KR","type":"education","lineage":["https://openalex.org/I118373667"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dong-Seok Seo","raw_affiliation_strings":["IISE Division, Department of Industrial Engineering, Seoul National University of Science and Technology, 232 Gongneung-Ro, Nowon-Gu, Seoul, 01811, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IISE Division, Department of Industrial Engineering, Seoul National University of Science and Technology, 232 Gongneung-Ro, Nowon-Gu, Seoul, 01811, South Korea","institution_ids":["https://openalex.org/I118373667"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135322370","display_name":"Bum-Soo Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I3019177047","display_name":"Korea Institute of Civil Engineering and Building Technology","ror":"https://ror.org/035enhp47","country_code":"KR","type":"government","lineage":["https://openalex.org/I2801339556","https://openalex.org/I3019177047","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bum-Soo Kim","raw_affiliation_strings":["Department of Future and Smart Construction Research, Korea Institute of Civil Engineering and Building Technology(KICT), 283, Goyang-daero, Ilsanseo-gu, Goyang-si, 10223, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Future and Smart Construction Research, Korea Institute of Civil Engineering and Building Technology(KICT), 283, Goyang-daero, Ilsanseo-gu, Goyang-si, 10223, South Korea","institution_ids":["https://openalex.org/I3019177047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057012645","display_name":"Hyuk-Yoon Kwon","orcid":"https://orcid.org/0000-0002-1125-6533"},"institutions":[{"id":"https://openalex.org/I118373667","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07","country_code":"KR","type":"education","lineage":["https://openalex.org/I118373667"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hyuk-Yoon Kwon","raw_affiliation_strings":["Graduate School of Data Science, Seoul National University of Science and Technology, 232 Gongneung-Ro, Nowon-Gu, Seoul, 01811, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-1125-6533","affiliations":[{"raw_affiliation_string":"Graduate School of Data Science, Seoul National University of Science and Technology, 232 Gongneung-Ro, Nowon-Gu, Seoul, 01811, South Korea","institution_ids":["https://openalex.org/I118373667"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5057012645"],"corresponding_institution_ids":["https://openalex.org/I118373667"],"apc_list":{"value":760,"currency":"USD","value_usd":760},"apc_paid":{"value":760,"currency":"USD","value_usd":760},"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"102696","last_page":"102696"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.45879998803138733,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.45879998803138733,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.0746999979019165,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.04039999842643738,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5922999978065491},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.3427000045776367},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.257099986076355},{"id":"https://openalex.org/keywords/information-integration","display_name":"Information integration","score":0.25189998745918274}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7346000075340271},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5922999978065491},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.42340001463890076},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3352000117301941},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32339999079704285},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28450000286102295},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2637999951839447},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C33326189","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information integration","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.softx.2026.102696","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.softx.2026.102696","pdf_url":null,"source":{"id":"https://openalex.org/S2506067282","display_name":"SoftwareX","issn_l":"2352-7110","issn":["2352-7110"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SoftwareX","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.softx.2026.102696","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.softx.2026.102696","pdf_url":null,"source":{"id":"https://openalex.org/S2506067282","display_name":"SoftwareX","issn_l":"2352-7110","issn":["2352-7110"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SoftwareX","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4284137786","display_name":null,"funder_award_id":"RS-2025-00521452","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G8535278255","display_name":null,"funder_award_id":"RS-2025-15002982","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2057012437","https://openalex.org/W2135164809","https://openalex.org/W2194187530","https://openalex.org/W2980913015","https://openalex.org/W4200416685","https://openalex.org/W4394683372"],"related_works":[],"abstract_inverted_index":{"Construction":[0],"documents":[1],"are":[2],"predominantly":[3],"stored":[4],"as":[5],"unsearchable":[6],"scanned":[7],"images,":[8,41],"hindering":[9],"automated":[10,18],"data":[11,55,79,89],"utilization.":[12,80],"We":[13],"introduce":[14],"ConsBASE":[15,29,66],",":[16],"an":[17],"ETL":[19],"(Extract,":[20],"Transform,":[21],"Load)":[22],"pipeline":[23],"tailored":[24],"for":[25],"Korean":[26],"construction":[27,92],"documents.":[28],"extracts":[30],"unstructured":[31],"content":[32],"by":[33,61],"recognizing":[34],"complex":[35],"tables":[36],"and":[37,51,77,86],"text":[38],"from":[39],"raw":[40],"normalizes":[42],"the":[43,53,72],"extracted":[44],"features":[45],"into":[46,56],"a":[47,57,62],"unified":[48],"JSON":[49],"schema,":[50],"loads":[52],"structured":[54],"searchable":[58],"database.":[59],"Accompanied":[60],"web-based":[63],"user":[64],"interface,":[65],"eliminates":[67],"manual":[68],"document":[69],"inspection,":[70],"bridging":[71],"gap":[73],"between":[74],"static":[75],"archives":[76],"active":[78],"This":[81],"software":[82],"enables":[83],"advanced":[84],"analytics":[85],"significantly":[87],"enhances":[88],"accessibility":[90],"in":[91],"workflows.":[93]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-05-06T00:00:00"}
