magistrsko delo
Janez Eržen (Author), Slavko Žitnik (Mentor)

Abstract

Izdelava pametnih asistentov zahteva implementacijo sistemov za zajem podatkov, prepoznavanje namena, ekstrakcijo podatkov, priporočilne sisteme ipd. V magistrskem delu smo izdelali celostnega pametnega asistenta za predlaganje obrokov, bolj podrobno pa smo se osredotočili na prepoznavanje alergenov in hranil vsebovanih v jedeh glede na delno strukturirane podatke o menijih na spletnih straneh restavracij. Z namenom reševanja omenjenega problema smo razvili algoritem za ločevanje besedila menija na posamezne jedi vsebovane v njem, algoritem za detekcijo alergenov iz besedila na podlagi pravil ter algoritem za detekcijo alergenov z uporabo nevronske mreže. Omenjene algoritme smo uporabili za implementacijo pametnega asistenta, ki uporabniku omogoča obogaten in prilagojen prikaz dnevno pridobljenih jedilnikov s spleta. Asistent je integriran v različne sisteme sporočanja (Microsoft Teams, Discord, Slack ter Facebook Messenger), pogovor z uporabnikom pa poteka v slovenskem jeziku. S preizkusom asistenta v praksi smo pokazali, da uporabnikom olajša izbiro menija ali restavracije za dnevno kosilo. Algoritem za avtomatsko ekstrakcijo alergenov z uporabo nevronske mreže dosega uspešnost 68% (ocena F1), kar je dovolj uporabno za opozarjanje uporabnika na možno vsebnost alergenov v jedi, je pa smiselno, da uporabnik to opozorilo asistenta dodatno preveri pri osebju restavracije.

Keywords

pametni asistent;obdelava naravnega jezika;ekstrakcija podatkov s spleta;prehrana;priporočanje uporabniku;računalništvo;računalništvo in informatika;magisteriji;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UL FRI - Faculty of Computer and Information Science
Publisher: [J. Eržen]
UDC: 004.8:612.39(043.2)
COBISS: 40021507 Link will open in a new window
Views: 743
Downloads: 142
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Smart assistant for suggesting meals
Secondary abstract: The construction of a smart assistant requires the implementation of software components for data acquisition, data extraction, intent recognition, recommendation and so on. In this master’s thesis we implement a smart assistant for meal suggestion and center the focus more specifically on the allergen and nutrient recognition from semi-structured HTML data from restaurant websites. To solve this problem we implement algorithms for menu text separation to stand-alone dishes included inside the menu, rule based algorithm for allergen detection from text and allergen detection algorithm using neural network. The software components mentioned above are used to implement a chatbot that provides users enriched and customized previews of daily menus. It is integrated into different communication platforms (Microsoft Teams, Discord, Slack and Facebook Messenger), where the conversation is held in Slovene. A case study with users has shown, that the assistant makes menu and restaurant selection for lunch easier for the user. The algorithm for the automatic extraction of allergens with a neural network reaches an accuracy of 68% (F1 score), which is suitable for warning users about the possible content of allergens in a dish, although it is wise for the user to check this information with restaurant staff.
Secondary keywords: chatbot;natural language processing;web scraping;nutrition;user recommendation;computer science;computer and information science;master's degree;
Type (COBISS): Master's thesis/paper
Study programme: 1000471
Embargo end date (OpenAIRE): 1970-01-01
Thesis comment: Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages: 70 str.
ID: 12171775