Razvoj digitalnog asistenta u domeni bankarstva

undergraduate thesis

• Title (english): Development of a digital assistant in banking domain
• Author: Antoni Pišonić
• Mentor: Sanja Seljan (mentor)
• Committee member: Ivan Dunđer (predsjednik povjerenstva)
• Committee member: Vjera Lopina (član povjerenstva)
• Committee member: Sanja Seljan (član povjerenstva)
• Granter: University of Zagreb; Faculty of Humanities and Social Sciences; (Department of information and Communication sciences); Zagreb
• Defense date and country: 2021-12-06, Croatia
• Scientific / art field, discipline and subdiscipline: SOCIAL SCIENCES; Information and Communication Sciences

Abstract

Cilj rada bio je prikaz izrade i implementacija chatbota u programskom jeziku Python u domeni bankarstva. Digitalni asistent (eng. chatbot) je sustav koji oponaša razgovor čovjeka kroz tekstualnu ili audio interakciju. U industriji sve više se koriste za rješavanje jednostavnih zadataka pretraživanja, kako u poslovnom tako i u potrošačkom okruženju. Implementacija chatbota može smanjiti troškove poslovanja smanjenjem radne snage ili prenamjenom osoblja za druge poslove, može se povećati kvaliteta poslovanja. Chatbot sustave dijelimo na dvije glavne vrste: sustav temeljen na pravilima i sustav temeljen na umjetnoj inteligenciji. Kod sustava temeljenog na pravilima jasno su definirana pravila kod interakcije digitalnog asistenta i čovjeka, odgovori digitalnog asistenta u potpunosti su unaprijed definirani i vraćaju se korisniku na osnovu prepoznatih ključnih riječi njegovog upita. Sustav temeljen na umjetnoj inteligenciji koristi strojno i duboko učenje kako bi čovjek u razgovoru s digitalnim asistentom dobio iskustvo pričanja s pravom osobom, gdje kao prava osoba, digitalni asistent zna prepoznati gramatičke greške te i dalje shvatiti smisao upita. Glavni nedostatak vog sustava je je mogućnost unaprijed definiranog toka komunikacije.

Abstract (english)

The aim of the paper was to present the development and implementation of a chatbot in the Python programming language in the field of banking. A digital assistant (chatbot) is a system that mimics a person's conversation through textual or audio interaction. In industry, they are increasingly used to solve simple search tasks, both in the business and consumer environment. Implementing a chatbot can reduce business costs by reducing the workforce or reassigning staff for other jobs, it can increase the quality of business. We divide chatbot systems into two main types: a rules-based system and an artificial intelligence-based system. In a rule-based system, the rules for digital assistant-human interaction are clearly defined, the digital assistant's responses are fully predefined, and are returned to the user based on the identified keywords of his query. The system based on artificial intelligence uses machine and deep learning to give a person in conversation with a digital assistant the experience of talking to the right person, where as a real person, the digital assistant knows how to recognize grammatical errors and continue to understand the meaning of queries. The main disadvantage of this system is the possibility of a predefined flow of communication.

• Keywords: chatbot; digitalni asistent; bankarstvo; Python; umjetna inteligencija
• Keywords (english): chatbot; digital assistant; banking; Python; artificial intelligence
• Language: croatian
• URN:NBN: urn:nbn:hr:131:892645
• Study programme: Title: Information Sciences; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) informacijskih znanosti (sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) informacijskih znanosti)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2021-12-07 08:20:17