{"id":"https://openalex.org/W3094003856","doi":"https://doi.org/10.1145/3422713.3422719","title":"A Column-Level Data Lineage Processing System Based on Hive","display_name":"A Column-Level Data Lineage Processing System Based on Hive","publication_year":2020,"publication_date":"2020-09-18","ids":{"openalex":"https://openalex.org/W3094003856","doi":"https://doi.org/10.1145/3422713.3422719","mag":"3094003856"},"language":"en","primary_location":{"id":"doi:10.1145/3422713.3422719","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3422713.3422719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 3rd International Conference on Big Data Technologies","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079562577","display_name":"Zehua Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zehua Tan","raw_affiliation_strings":["School of computer science Beijing University of Posts and Telecommunications Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of computer science Beijing University of Posts and Telecommunications Beijing, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075117055","display_name":"E Haihong","orcid":"https://orcid.org/0000-0003-2087-586X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haihong E","raw_affiliation_strings":["School of computer science Beijing University of Posts and Telecommunications Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of computer science Beijing University of Posts and Telecommunications Beijing, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005632451","display_name":"Meina Song","orcid":"https://orcid.org/0000-0001-6626-9932"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meina Song","raw_affiliation_strings":["School of computer science Beijing University of Posts and Telecommunications Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of computer science Beijing University of Posts and Telecommunications Beijing, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079562577"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.16174524,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"47","last_page":"52"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/data-warehouse","display_name":"Data warehouse","score":0.878499448299408},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7111055850982666},{"id":"https://openalex.org/keywords/data-transformation","display_name":"Data transformation","score":0.6227389574050903},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.6118733286857605},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.5941663384437561},{"id":"https://openalex.org/keywords/lineage","display_name":"Lineage (genetic)","score":0.5342572927474976},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.43095147609710693},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42801880836486816},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2010459005832672}],"concepts":[{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.878499448299408},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7111055850982666},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.6227389574050903},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6118733286857605},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.5941663384437561},{"id":"https://openalex.org/C2776817793","wikidata":"https://www.wikidata.org/wiki/Q6553369","display_name":"Lineage (genetic)","level":3,"score":0.5342572927474976},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43095147609710693},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42801880836486816},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2010459005832672},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3422713.3422719","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3422713.3422719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 3rd International Conference on Big Data Technologies","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/1","display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W180519810","https://openalex.org/W1543225912","https://openalex.org/W2110086534","https://openalex.org/W2743230100","https://openalex.org/W2919933843","https://openalex.org/W4291801915","https://openalex.org/W4302442555"],"related_works":["https://openalex.org/W2348093825","https://openalex.org/W2390710026","https://openalex.org/W2364425891","https://openalex.org/W2347601812","https://openalex.org/W3022239989","https://openalex.org/W3015205082","https://openalex.org/W1505247071","https://openalex.org/W2364409751","https://openalex.org/W4211040133","https://openalex.org/W2181836431"],"abstract_inverted_index":{"For":[0],"big":[1],"data,":[2],"the":[3,11,18,27,40,50,54,62,69,84,102,107,115,119,129,135,142,146,151],"data":[4,9,15,19,24,30,36,41,46,51,55,65,96,104,109,125,136,147,153],"warehouse":[5,20,56,66,105],"stores":[6],"all":[7],"business":[8],"of":[10,29,61,64,86,122,134],"entire":[12],"enterprise.":[13],"The":[14,111],"collected":[16],"in":[17,39,53,83],"will":[21],"generate":[22],"new":[23],"collection":[25],"through":[26],"operations":[28],"union,":[31],"splitting,":[32],"and":[33,81,127,131,150],"transformation.":[34],"This":[35],"conversion":[37],"relationship":[38],"production":[42],"process":[43,63],"is":[44,57],"called":[45],"lineage.":[47],"Therefore,":[48,90],"tracking":[49],"lineage":[52,97,121,137,148],"an":[58],"important":[59],"part":[60],"construction.":[67],"However,":[68],"existing":[70],"open-source":[71],"solutions":[72],"have":[73],"shortcomings":[74],"such":[75],"as":[76],"high":[77,132],"coupling,":[78],"poor":[79],"accuracy,":[80],"intrusion":[82],"processing":[85,98],"this":[87,91],"critical":[88],"link.":[89],"paper":[92],"designs":[93],"a":[94],"column-level":[95],"system":[99,112],"based":[100],"on":[101],"Hive":[103,108,123,152],"for":[106],"warehouse.":[110,154],"has":[113],"realized":[114],"ability":[116],"to":[117],"analyze":[118],"Data":[120],"SQL":[124],"locally":[126],"realizes":[128],"fine-grained":[130],"accuracy":[133],"analysis":[138],"results":[139],"while":[140],"ensuring":[141],"low":[143],"coupling":[144],"between":[145],"function":[149]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}