{"id":"https://openalex.org/W2948032604","doi":"https://doi.org/10.1108/el-12-2018-0232","title":"Disambiguating USPTO inventor names with semantic fingerprinting and DBSCAN clustering","display_name":"Disambiguating USPTO inventor names with semantic fingerprinting and DBSCAN clustering","publication_year":2019,"publication_date":"2019-04-01","ids":{"openalex":"https://openalex.org/W2948032604","doi":"https://doi.org/10.1108/el-12-2018-0232","mag":"2948032604"},"language":"en","primary_location":{"id":"doi:10.1108/el-12-2018-0232","is_oa":false,"landing_page_url":"https://doi.org/10.1108/el-12-2018-0232","pdf_url":null,"source":{"id":"https://openalex.org/S902750600","display_name":"The Electronic Library","issn_l":"0264-0473","issn":["0264-0473","1758-616X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Electronic Library","raw_type":"journal-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/A5112079158","display_name":"Hongqi Han","orcid":null},"institutions":[{"id":"https://openalex.org/I2801770497","display_name":"State Administration of Press, Publication, Radio, Film and Television","ror":"https://ror.org/00qrrpx34","country_code":"CN","type":"government","lineage":["https://openalex.org/I2801770497"]},{"id":"https://openalex.org/I4210101880","display_name":"Institute of Scientific and Technical Information","ror":"https://ror.org/0170b6c09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I107851509","https://openalex.org/I4210101880","https://openalex.org/I4210127390","https://openalex.org/I4210151987"]},{"id":"https://openalex.org/I4210104311","display_name":"Institute of Scientific and Technical Information of China","ror":"https://ror.org/01b2av652","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210104311","https://openalex.org/I4210120069","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongqi Han","raw_affiliation_strings":["Data Mining Group, Institute of Scientific and Technical Information of China, Haidian-qu, China and Key Laboratory of Rich-media Knowledge Organization and Service of Digital Publishing Content, SAPPRFT, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Mining Group, Institute of Scientific and Technical Information of China, Haidian-qu, China and Key Laboratory of Rich-media Knowledge Organization and Service of Digital Publishing Content, SAPPRFT, Beijing, China","institution_ids":["https://openalex.org/I2801770497","https://openalex.org/I4210101880","https://openalex.org/I4210104311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103750140","display_name":"Yongsheng Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104311","display_name":"Institute of Scientific and Technical Information of China","ror":"https://ror.org/01b2av652","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210104311","https://openalex.org/I4210120069","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongsheng Yu","raw_affiliation_strings":["Institute of Scientific and Technical Information of China, Haidian-qu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Scientific and Technical Information of China, Haidian-qu, China","institution_ids":["https://openalex.org/I4210104311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318893","display_name":"Lijun Wang","orcid":"https://orcid.org/0000-0003-2824-6582"},"institutions":[{"id":"https://openalex.org/I4210101880","display_name":"Institute of Scientific and Technical Information","ror":"https://ror.org/0170b6c09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I107851509","https://openalex.org/I4210101880","https://openalex.org/I4210127390","https://openalex.org/I4210151987"]},{"id":"https://openalex.org/I4210104311","display_name":"Institute of Scientific and Technical Information of China","ror":"https://ror.org/01b2av652","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210104311","https://openalex.org/I4210120069","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijun Wang","raw_affiliation_strings":["Data Mining Group, Institute of Scientific and Technical Information of China, Haidian-qu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Mining Group, Institute of Scientific and Technical Information of China, Haidian-qu, China","institution_ids":["https://openalex.org/I4210101880","https://openalex.org/I4210104311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102789675","display_name":"Xiaorui Zhai","orcid":"https://orcid.org/0000-0002-4244-9485"},"institutions":[{"id":"https://openalex.org/I4210101880","display_name":"Institute of Scientific and Technical Information","ror":"https://ror.org/0170b6c09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I107851509","https://openalex.org/I4210101880","https://openalex.org/I4210127390","https://openalex.org/I4210151987"]},{"id":"https://openalex.org/I4210104311","display_name":"Institute of Scientific and Technical Information of China","ror":"https://ror.org/01b2av652","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210104311","https://openalex.org/I4210120069","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaorui Zhai","raw_affiliation_strings":["Data Mining Group, Institute of Scientific and Technical Information of China, Haidian-qu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Mining Group, Institute of Scientific and Technical Information of China, Haidian-qu, China","institution_ids":["https://openalex.org/I4210101880","https://openalex.org/I4210104311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078039099","display_name":"Yaxin Ran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101880","display_name":"Institute of Scientific and Technical Information","ror":"https://ror.org/0170b6c09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I107851509","https://openalex.org/I4210101880","https://openalex.org/I4210127390","https://openalex.org/I4210151987"]},{"id":"https://openalex.org/I4210104311","display_name":"Institute of Scientific and Technical Information of China","ror":"https://ror.org/01b2av652","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210104311","https://openalex.org/I4210120069","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaxin Ran","raw_affiliation_strings":["Data Mining Group, Institute of Scientific and Technical Information of China, Haidian-qu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Mining Group, Institute of Scientific and Technical Information of China, Haidian-qu, China","institution_ids":["https://openalex.org/I4210101880","https://openalex.org/I4210104311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101514811","display_name":"Jingpeng Han","orcid":"https://orcid.org/0009-0005-7093-8744"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingpeng Han","raw_affiliation_strings":["Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.713,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.73564938,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"37","issue":"2","first_page":"225","last_page":"239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T11719","display_name":"Data Quality and Management","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9613000154495239,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10856","display_name":"Intellectual Property and Patents","score":0.9226999878883362,"subfield":{"id":"https://openalex.org/subfields/1405","display_name":"Management of Technology and Innovation"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8143717646598816},{"id":"https://openalex.org/keywords/dbscan","display_name":"DBSCAN","score":0.7336807250976562},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7218241691589355},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5507725477218628},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5061125159263611},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48171812295913696},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.4685187041759491},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4588066339492798},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4438367486000061},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4190019369125366},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.4114142954349518},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32411423325538635},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.16827207803726196},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.1129898726940155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8143717646598816},{"id":"https://openalex.org/C46576248","wikidata":"https://www.wikidata.org/wiki/Q1114630","display_name":"DBSCAN","level":5,"score":0.7336807250976562},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7218241691589355},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5507725477218628},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5061125159263611},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48171812295913696},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4685187041759491},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4588066339492798},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4438367486000061},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4190019369125366},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.4114142954349518},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32411423325538635},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.16827207803726196},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.1129898726940155},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1108/el-12-2018-0232","is_oa":false,"landing_page_url":"https://doi.org/10.1108/el-12-2018-0232","pdf_url":null,"source":{"id":"https://openalex.org/S902750600","display_name":"The Electronic Library","issn_l":"0264-0473","issn":["0264-0473","1758-616X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Electronic Library","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W138776972","https://openalex.org/W1673310716","https://openalex.org/W1856480505","https://openalex.org/W1879177791","https://openalex.org/W1964879903","https://openalex.org/W1975812896","https://openalex.org/W1999254925","https://openalex.org/W2006153666","https://openalex.org/W2012833704","https://openalex.org/W2017651100","https://openalex.org/W2041971736","https://openalex.org/W2057401327","https://openalex.org/W2065858398","https://openalex.org/W2073471108","https://openalex.org/W2079361215","https://openalex.org/W2089581779","https://openalex.org/W2106808680","https://openalex.org/W2111116800","https://openalex.org/W2112931132","https://openalex.org/W2113227740","https://openalex.org/W2115723149","https://openalex.org/W2116690618","https://openalex.org/W2129558264","https://openalex.org/W2145349611","https://openalex.org/W2212947330","https://openalex.org/W2338237122","https://openalex.org/W2411309731","https://openalex.org/W2588865615","https://openalex.org/W2601885645","https://openalex.org/W2612944374","https://openalex.org/W3122640307","https://openalex.org/W3124074313","https://openalex.org/W3125274062"],"related_works":["https://openalex.org/W3163639875","https://openalex.org/W3176449234","https://openalex.org/W2807508722","https://openalex.org/W2767235736","https://openalex.org/W2353158678","https://openalex.org/W4225278791","https://openalex.org/W2045002201","https://openalex.org/W2971352445","https://openalex.org/W4322502698","https://openalex.org/W2604015980"],"abstract_inverted_index":{"Purpose":[0],"The":[1],"aim":[2],"of":[3,24,52,59,76,106,179,226,244],"this":[4,101,165,189],"study":[5],"is":[6,43,70],"to":[7,33,47,61,72,81,140,167,240],"present":[8],"a":[9,17,44,49,57,134,148,218],"novel":[10],"approach":[11],"based":[12,90,163],"on":[13,91,164,174,262],"semantic":[14,39,128,214],"fingerprinting":[15],"and":[16,55,80,110,118,184,204,217,265,274],"clustering":[18,23,228,235],"algorithm":[19,216],"called":[20],"density-based":[21],"spatial":[22],"applications":[25],"with":[26,194,205,252],"noise":[27],"(DBSCAN),":[28],"which":[29],"can":[30],"be":[31,238],"used":[32,46,154],"convert":[34],"investor":[35],"records":[36,123,162],"into":[37,126],"128-bit":[38,127],"fingerprints.":[40,129],"Inventor":[41],"disambiguation":[42,246],"method":[45,190,258],"discover":[48],"unique":[50],"set":[51,58],"underlying":[53],"inventors":[54,69],"map":[56],"patents":[60],"their":[62],"corresponding":[63],"inventors.":[64],"Resolving":[65],"the":[66,74,77,104,116,142,160,175,180,242,245,253,256],"ambiguities":[67],"between":[68,144],"necessary":[71],"improve":[73,223,241],"quality":[75],"patent":[78],"database":[79,178],"ensure":[82],"accurate":[83],"entity-level":[84],"analysis.":[85],"Most":[86,270],"existing":[87,254],"methods":[88],"are":[89,124,277],"machine":[92],"learning":[93],"and,":[94],"while":[95],"they":[96],"often":[97],"show":[98,187],"good":[99],"performance,":[100],"comes":[102],"at":[103],"cost":[105],"time,":[107],"computational":[108],"power":[109],"storage":[111,208,275],"space.":[112],"Design/methodology/approach":[113],"Using":[114],"DBSCAN,":[115],"meta":[117],"textual":[119],"data":[120],"in":[121,155,201],"inventor":[122,161,169,192],"converted":[125],"However,":[130],"rather":[131],"than":[132,197],"using":[133],"string":[135],"comparison":[136,151,268],"or":[137,233],"cosine":[138],"similarity":[139],"calculate":[141],"distance":[143,166,220],"pair-wise":[145],"fingerprint":[146,215],"records,":[147],"binary":[149],"number":[150],"function":[152,221],"was":[153],"DBSCAN.":[156],"DBSCAN":[157],"then":[158],"clusters":[159],"disambiguate":[168],"names.":[170],"Findings":[171],"Experiments":[172],"conducted":[173],"PatentsView":[176],"campaign":[177],"United":[181],"States":[182],"Patent":[183],"Trademark":[185],"Office":[186],"that":[188],"disambiguates":[191],"names":[193],"recall":[195],"greater":[196],"99":[198],"per":[199],"cent":[200],"less":[202],"time":[203,273],"substantially":[206],"smaller":[207],"requirement.":[209],"Research":[210],"limitations/implications":[211],"A":[212],"better":[213,219],"may":[222],"precision.":[224],"Setting":[225],"different":[227],"parameters":[229],"for":[230],"each":[231],"block":[232],"other":[234],"algorithms":[236],"will":[237],"considered":[239],"accuracy":[243],"results":[247],"even":[248],"further.":[249],"Originality/value":[250],"Compared":[251],"methods,":[255],"proposed":[257],"does":[259],"not":[260],"rely":[261],"feature":[263,267],"selection":[264],"complex":[266],"computation.":[269],"importantly,":[271],"running":[272],"requirements":[276],"drastically":[278],"reduced.":[279]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}