{"id":"https://openalex.org/W4415340334","doi":"https://doi.org/10.24887/0028-2448-2025-9-108-111","title":"Development of a large language model for data extraction from unstructured text documents: a case study on production geophysical survey reports","display_name":"Development of a large language model for data extraction from unstructured text documents: a case study on production geophysical survey reports","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415340334","doi":"https://doi.org/10.24887/0028-2448-2025-9-108-111"},"language":"en","primary_location":{"id":"doi:10.24887/0028-2448-2025-9-108-111","doi":"https://doi.org/10.24887/0028-2448-2025-9-108-111","is_oa":false,"landing_page_url":"https://doi.org/10.24887/0028-2448-2025-9-108-111","pdf_url":null,"source":{"id":"https://openalex.org/S2764996131","display_name":"Neftyanoe khozyaystvo - Oil Industry","issn_l":"0028-2448","issn":["0028-2448"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4360969432","host_organization_name":"Oil Industry Corporation","host_organization_lineage":["https://openalex.org/P4360969432"],"host_organization_lineage_names":["Oil Industry Corporation"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neftyanoe khozyaystvo - Oil Industry","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"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/A5087494770","display_name":"\u0411\u0443\u043b\u0430\u0442 \u041c\u0430\u0440\u0430\u0442\u043e\u0432\u0438\u0447 \u041b\u0430\u0442\u044b\u043f\u043e\u0432","orcid":"https://orcid.org/0000-0002-3559-1811","observed_orcids":["https://orcid.org/0000-0002-3559-1811"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"B.M. Latypov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114119966","display_name":"E.V. Yudin","orcid":"https://orcid.org/0000-0003-1356-6671","observed_orcids":["https://orcid.org/0000-0003-1356-6671"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E.V. Yudin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Gazprom Neft Compan\u0443 Group, RF, Saint Petersburg","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gazprom Neft Compan\u0443 Group, RF, Saint Petersburg","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120059303","display_name":"R.A. Bondorov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R.A. Bondorov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5123006453","display_name":"N.A. Zyryanov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"N.A. Zyryanov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":"9","first_page":"108","last_page":"111"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9369999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9369999766349792,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.021400000900030136,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.008299999870359898,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9990000128746033},{"id":"https://openalex.org/keywords/data-extraction","display_name":"data extraction","score":0.8809999823570251},{"id":"https://openalex.org/keywords/unstructured-text","display_name":"unstructured text","score":0.972000002861023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5756000280380249},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.4749999940395355},{"id":"https://openalex.org/C2776542497","wikidata":"https://www.wikidata.org/wiki/Q5266672","display_name":"Development (topology)","level":2,"score":0.4462999999523163},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42649999260902405},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.42559999227523804},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4253000020980835},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3901999890804291},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.3407999873161316},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33309999108314514},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3158999979496002},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.3025999963283539},{"id":"https://openalex.org/C2987528665","wikidata":"https://www.wikidata.org/wiki/Q854845","display_name":"Earth observation satellite","level":3,"score":0.28859999775886536},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C2992770021","wikidata":"https://www.wikidata.org/wiki/Q7247850","display_name":"Production model","level":3,"score":0.27129998803138733},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.27070000767707825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24887/0028-2448-2025-9-108-111","doi":"https://doi.org/10.24887/0028-2448-2025-9-108-111","is_oa":false,"landing_page_url":"https://doi.org/10.24887/0028-2448-2025-9-108-111","pdf_url":null,"source":{"id":"https://openalex.org/S2764996131","display_name":"Neftyanoe khozyaystvo - Oil Industry","issn_l":"0028-2448","issn":["0028-2448"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4360969432","host_organization_name":"Oil Industry Corporation","host_organization_lineage":["https://openalex.org/P4360969432"],"host_organization_lineage_names":["Oil Industry Corporation"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neftyanoe khozyaystvo - Oil Industry","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7204668459","https://openalex.org/W7039755666","https://openalex.org/W7136231597","https://openalex.org/W7213422790","https://openalex.org/W7125650683","https://openalex.org/W4417217013","https://openalex.org/W4407021510","https://openalex.org/W7071885575","https://openalex.org/W3109075124","https://openalex.org/W7202394027"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2025-10-20T00:00:00"}
