Umjetna inteligencija u korisničkoj podršci: razvoj chatbota s prirodnim jezikom – studija slučaja FINA chatbot za e-Račun.

graduate thesis

• Title (english): Artificial intelligence in customer support: chatbot development with natural language - case study FINA chatbot for e-Invoice.
• Author: Ivana Marušić
• Mentor: Dalia Suša Vugec (mentor)
• Committee member: Dalia Suša Vugec (predsjednik povjerenstva)
• Committee member: Mirjana Pejić Bach (član povjerenstva)
• Committee member: Jasmina Pivar (član povjerenstva)
• Granter: University of Zagreb; Faculty of Economics and Business; Zagreb
• Defense date and country: 2024-09-30, Croatia
• Scientific / art field, discipline and subdiscipline: SOCIAL SCIENCES; Economics; Business Informatics

Abstract

Predmet ovog rada je uloga umjetne inteligencije u korisničkoj podršci s fokusom na razvoj chatbota s prirodnim jezikom. Radom se anlizira poslovni slučaj uvođenja chatbota za e-Račun u Financijskoj agenciji (FINA), koja prepoznaje potencijal umjetne inteligencije u korisničkoj podrššci. Cilj uvođenja chatbot je da odgovori na često postavljana pitanja o e-Računu te da pruži korisnicima brzu i jednostavnu pomoć.
Ciljevi rada:
C1.Proučiti ulogu umjetne inteligencije u korisničkoj podršci,
C2.Analizirati potrebe i zahtjeve korisnika FINA e-Računa,
C3.Dizajnirati i implementirati chatbot za FINA e-Račun,
C4.Evaluirati i usavršiti chatbot,
C5.Donijeti zaključak o doprinosu umjetne inteligencije u korisničkoj podršci.
U istraživanju se koristile sljedeće metode: kompilacije, komparacije, deskripcije, dedukcije, sinteze te metoda analize. Korištena dostupna literatura, kako u tiskanom tako i u digitalnom obliku.
Analizom dostupne znanstvene i stručne literature zaključeno je da se sofisticirani alati poput chatbota mogu koristiti za optimizaciju poslovnih procesa. Evaluacija chatbota, provedena kroz detaljno testiranje i definiranje metrika evaluacije, pokazuje da je chatbot sposoban zadovoljiti potrebe korisnika u velikom broju slučajeva, uz visoku točnost i učinkovitost.
Nastavak istraživanja i inovacija u ovoj oblasti može donijeti dodatne koristi i prilike za poboljšanje korisničkog iskustva i učinkovitosti poslovnih operacija. Preporuka za buduće projekte uključuje kontinuirano praćenje performansi chatbota, pravovremeno ažuriranje informacija i održavanje visoke razine kvalitete korisničkog iskustva.

Abstract (english)

The subject of this paper is the role of artificial intelligence in customer support with a focus
on the development of chatbots with natural language. The paper analyzes the business case
of introducing a chatbot for e-Invoice in the Financial Agency (FINA), which recognizes the
potential of artificial intelligence in customer support. The goal of introducing a chatbot is to
answer frequently asked questions about the e-Invoice and to provide users with quick and
simple help.
Objectives of the work:
C1. Study the role of artificial intelligence in customer support,
C2. Analyze the needs and requirements of FINA e-Invoice users,
C3. Design and implement a chatbot for FINA e-Invoice,
C4. Evaluate and improve the chatbot,
C5. Draw a conclusion about the contribution of artificial intelligence in customer support.
The following methods were used in the research: compilations, comparisons, descriptions,
deductions, syntheses and analysis methods. Used available literature, both in print and in
digital form.
Analysis of the available scientific and professional literature concluded that sophisticated
tools such as chatbots can be used to optimize business processes. The evaluation of the
chatbot, carried out through detailed testing and the definition of evalua tion metrics, shows
that the chatbot is capable of meeting the needs of users in a large number of cases, with high
accuracy and efficiency.
Continued research and innovation in this area can bring additional benefits and opportunities to improve the user experience and the efficiency of business operations. The recommendation for future projects includes continuous monitoring of chatbot performance, timely updating of information and maintaining a high level of quality of user experience.

• Keywords: Ključne riječi: umjetna inteligencija; UI; chatbot; NLP; korisnička podrška.
• Keywords (english): Keywords: artificial intelligence; UI; chatbot; NLP; customer support.
• Language: croatian
• URN:NBN: urn:nbn:hr:148:945440
• Study programme: Title: /; Study programme type: professional; Study level: graduate; Academic / professional title: magistar ekonomije/magistra ekonomije (magistar ekonomije/magistra ekonomije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Access restricted to authenticated users
• Created on: 2024-10-01 14:30:52