{"?xml":{"@version":"1.0"},"edm:RDF":{"@xmlns:dc":"http://purl.org/dc/elements/1.1/","@xmlns:edm":"http://www.europeana.eu/schemas/edm/","@xmlns:wgs84_pos":"http://www.w3.org/2003/01/geo/wgs84_pos","@xmlns:foaf":"http://xmlns.com/foaf/0.1/","@xmlns:rdaGr2":"http://rdvocab.info/ElementsGr2","@xmlns:oai":"http://www.openarchives.org/OAI/2.0/","@xmlns:owl":"http://www.w3.org/2002/07/owl#","@xmlns:rdf":"http://www.w3.org/1999/02/22-rdf-syntax-ns#","@xmlns:ore":"http://www.openarchives.org/ore/terms/","@xmlns:skos":"http://www.w3.org/2004/02/skos/core#","@xmlns:dcterms":"http://purl.org/dc/terms/","edm:WebResource":[{"@rdf:about":"http://www.dlib.si/stream/URN:NBN:SI:doc-AAJKWJ63/3f5aae8e-885d-42e0-a332-b1c8f1d0d83c/PDF","dcterms:extent":"1115 KB"},{"@rdf:about":"http://www.dlib.si/stream/URN:NBN:SI:doc-AAJKWJ63/a82f1bf9-2595-4f50-a667-36db2b20d882/TEXT","dcterms:extent":"43 KB"}],"edm:TimeSpan":{"@rdf:about":"1951-2026","edm:begin":{"@xml:lang":"en","#text":"1951"},"edm:end":{"@xml:lang":"en","#text":"2026"}},"edm:ProvidedCHO":{"@rdf:about":"URN:NBN:SI:doc-AAJKWJ63","dcterms:isPartOf":[{"@rdf:resource":"https://www.dlib.si/details/URN:NBN:SI:spr-OE4S1HGI"},{"@xml:lang":"sl","#text":"Gradbeni vestnik"}],"dcterms:issued":"2025","dc:creator":["Brelih, Anja","Dujc, Jaka","Klinc, Robert","Srdič, Aleksander"],"dc:format":[{"@xml:lang":"sl","#text":"številka:letn. 74"},{"@xml:lang":"sl","#text":"str. 210-219"}],"dc:identifier":["ISSN:0017-2774","COBISSID_HOST:262447363","URN:URN:NBN:SI:doc-AAJKWJ63"],"dc:language":"sl","dc:publisher":{"@xml:lang":"sl","#text":"Zveza društev gradbenih inženirjev in tehnikov Slovenije"},"dc:subject":[{"@xml:lang":"en","#text":"construction management"},{"@xml:lang":"en","#text":"data privacy"},{"@xml:lang":"en","#text":"document preprocessing"},{"@xml:lang":"en","#text":"large language models"},{"@xml:lang":"en","#text":"name entity recognition"},{"@xml:lang":"sl","#text":"operativno gradbeništvo"},{"@xml:lang":"sl","#text":"predobdelava dokumentov"},{"@xml:lang":"sl","#text":"prepoznavanje imenskih entitet"},{"@xml:lang":"sl","#text":"veliki jezikovni modeli"},{"@xml:lang":"sl","#text":"zasebnost podatkov"}],"dcterms:temporal":{"@rdf:resource":"1951-2026"},"dc:title":{"@xml:lang":"sl","#text":"Predobdelava podatkov za zagotavljanje varnosti in zasebnosti pri uporabi velikih jezikovnih modelov v gradbeništvu| Data preprocessing to ensure security and privacy when using large language models in construction|"},"dc:description":[{"@xml:lang":"sl","#text":"This paper addresses the challenge of ensuring data privacy when using Large Language Models (LLMs) in Construction Management Workflows. It analyses how well existing Named Entity Recognition (NER) tools can identify and redact sensitive information in technical construction documents, particularly in the Slovenian language. A qualitative evaluation was performed with four NLP frameworks (SpaCy, SpaCy SLO, Flair, NLTK) applied to a sample of five real-world construction documents and compared with manually annotated baseline data. The evaluation also included anonymization with VJM, which masked sensitive data using regular expressions. The results show that while basic anonymisation is possible, all classical NER frameworks underperform in identifying domain-specific entities such as project codes, engineering titles and structured numerical data. These findings emphasise the urgent need for domain-adapted preprocessing tools, as inaccurate redaction po ses legal and ethical risks when integrating LLMs in regulated domains such as construction. Future work should focus on building hybrid redaction pipelines and training custom models on annotated corpora to improve accuracy and compliance in technical domains"},{"@xml:lang":"sl","#text":"Prispevek predstavlja izzive zagotavljanja varstva podatkov pri uporabi velikih jezikovnih modelov (VJM) v delovnih tokovih operativnega gradbeništva. Analizira, kako uspešno obstoječa orodja za prepoznavanje imenskih entitet (angl. Named Entity Recognition, NER) zaznajo in anonimizirajo občutljive informacije v tehničnih gradbenih dokumentih, zlasti v slovenskem jeziku. Opravljena je bila kvalitativna evalvacija štirih ogrodij za obdelavo naravnega jezika (SpaCy, SpaCy SLO, Flair, NLTK), ki so bile preizkušene na vzorcu petih dejanskih gradbenih dokumentov in primerjane z ročno anotiranimi referenčnimi podatki. V evalvacijo je bila vključena tudi anonimizacija z VJM, ki je občutljive podatke zakrival z uporabo regularnih izrazov. Rezultati kažejo, da je osnovna anonimizacija sicer mogoča, vendar vsa klasična ogrodja NER slabše prepoznavajo entitete specifične za področje, kot so projektne šifre, inženirski nazivi ter strukturirani šte vilčni podatki. Ugotovitve kažejo na potrebe po prilagojenih orodjih za predobdelavo, saj netočna anonimizacija predstavlja pravna in etična tveganja pri vključevanju VJM v regulirane panoge, kot je gradbeništvo. Prihodnje raziskave se morajo osredotočiti na gradnjo hibridnih anonimizacijskih tokov in učenje modelov na anotiranih podatkih, da bi izboljšali natančnost in skladnost v tehničnih panogah"}],"edm:type":"TEXT","dc:type":[{"@xml:lang":"sl","#text":"znanstveno časopisje"},{"@xml:lang":"en","#text":"journals"},{"@rdf:resource":"http://www.wikidata.org/entity/Q361785"}]},"ore:Aggregation":{"@rdf:about":"http://www.dlib.si/?URN=URN:NBN:SI:doc-AAJKWJ63","edm:aggregatedCHO":{"@rdf:resource":"URN:NBN:SI:doc-AAJKWJ63"},"edm:isShownBy":{"@rdf:resource":"http://www.dlib.si/stream/URN:NBN:SI:doc-AAJKWJ63/3f5aae8e-885d-42e0-a332-b1c8f1d0d83c/PDF"},"edm:rights":{"@rdf:resource":"http://creativecommons.org/licenses/by-sa/4.0/"},"edm:provider":"Slovenian National E-content Aggregator","edm:intermediateProvider":{"@xml:lang":"en","#text":"National and University Library of Slovenia"},"edm:dataProvider":{"@xml:lang":"sl","#text":"Zveza društev gradbenih inženirjev in tehnikov Slovenije"},"edm:object":{"@rdf:resource":"http://www.dlib.si/streamdb/URN:NBN:SI:doc-AAJKWJ63/maxi/edm"},"edm:isShownAt":{"@rdf:resource":"http://www.dlib.si/details/URN:NBN:SI:doc-AAJKWJ63"}}}}