| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Uporaba generativne AI v ERP sistemih
Authors:ID Rečnik, Nejc (Author)
ID Sternad Zabukovšek, Simona (Mentor) More about this mentor... New window
Files:.pdf UN_Recnik_Nejc_2026.pdf (1,74 MB)
MD5: B9E6FF6DC76C49940C6D6463A0627BC6
 
Language:Slovenian
Work type:Bachelor thesis/paper
Typology:2.11 - Undergraduate Thesis
Organization:EPF - Faculty of Business and Economics
Abstract:Diplomska naloga obravnava uporabo generativne umetne inteligence v celovitih informacijskih sistemih. Tema je aktualna, saj ponudniki ERP sistemov GEN AI že aktivno vgrajujejo v svoje platforme, slovenska podjetja pa se na to spremembo pripravljajo z različno stopnjo pripravljenosti. Kljub naraščajočemu zanimanju za to področje v poslovnem svetu primanjkuje analiz, ki bi tematiko obravnavale z vidika konkretnih izkušenj iz prakse v srednje velikih podjetjih. V teoretičnem delu smo predstavili temeljne pojme umetne inteligence, njen zgodovinski razvoj ter aktualni trendi, vključno z regulatornim okvirom EU AI Act. Obravnavli smo arhitekturne osnove GEN AI, zlasti transformer arhitektura in mehanizem pozornosti, ter tri pristope za poslovno uvajanje: RAG, HITL in MITL. Analizirali smo tudi ERP sisteme, njihov razvoj od MRP do današnjih oblačnih platform ter integracije GEN AI pri vodilnih ponudnikih, to je SAP z asistentom Joule, Microsoftom s Copilotom za Dynamics 365 in Oraclom z AI agenti. Empirični del temelji na metodi študije primera v slovenskem proizvodnem podjetju, ki uporablja sistem SAP in je v oddelku prodaje uvedlo orodje Claude Pro. Ugotovljeno je bilo, da GEN AI ne nadomešča obstoječih sistemov, temveč deluje kot vezivo med njimi. Uvedba Claude Pro je prinesla merljive prihranke časa pri pripravi pregledov odprtih naročil, komunikaciji s strankami in pripravi gradiv za sestanke. Ugotovljeno je bilo tudi, da je polna avtomatizacija bistveno zahtevnejša od pričakovanj, integracija med splošno namenskimi AI modeli in ERP sistemi pa zahteva dodatne tehnične in organizacijske korake. Vse tri zastavljene hipoteze so bile potrjene. GEN AI merljivo zmanjšuje čas izvajanja rutinskih poslovnih procesov, uspešnost implementacije je pozitivno povezana z organizacijsko kulturo, ki spodbuja preizkušanje novih orodij, vodilni ponudniki ERP sistemov pa so GEN AI že sistematično vključili v svoje platforme.
Keywords:Generativna umetna inteligenca (GEN AI), ERP sistemi, SAP, veliki jezikovni modeli, poslovna informatika.
Place of publishing:Maribor
Publisher:N. Rečnik]
Year of publishing:2026
PID:20.500.12556/DKUM-99924 New window
UDC:004.8
COBISS.SI-ID:292330755 New window
Publication date in DKUM:24.09.2026
Views:27
Downloads:2
Metadata:XML DC-XML DC-RDF
Categories:EPF
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Link:http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:30.08.2026

Secondary language

Language:English
Title:The use of generative AI in ERP systems
Abstract:The thesis examines the use of generative artificial intelligence in enterprise resource planning systems. The topic is timely, as ERP providers are already actively embedding generative AI into their platforms, while Slovenian companies are adapting to this shift at varying levels of readiness. Despite growing interest in the subject, there is a lack of analyses addressing the topic from the perspective of practical experience in medium-sized companies. The theoretical part covers the fundamental concepts of artificial intelligence, its historical development, and current trends including the EU AI Act regulatory framework. It examines the architectural foundations of generative AI, particularly the transformer architecture and attention mechanism, along with three key approaches for business implementation: RAG, HITL, and MITL. ERP systems are also analysed, tracing their development from MRP to today's cloud platforms, alongside generative AI integrations at leading providers, namely SAP with Joule, Microsoft with Copilot for Dynamics 365, and Oracle with AI agents. The empirical part is based on a case study of a Slovenian manufacturing company using the SAP system, which introduced Claude Pro in its spare parts sales department. The findings show that generative AI does not replace existing systems but acts as a bridge between them. The introduction of Claude Pro resulted in measurable time savings in preparing open order reviews, customer communication, and meeting materials. It was also found that full automation is considerably more demanding than expected, and integration between general-purpose AI models and ERP systems requires additional technical and organisational steps. All three hypotheses were confirmed. GEN AI measurably reduces the time required to perform routine business processes, implementation success is positively linked to an organisational culture that encourages experimentation, and leading ERP providers have already systematically incorporated generative AI into their platforms.
Keywords:GEN AI, ERP systems, SAP, large language models, business informatics


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica