Document type

Bachelor thesis

Publication date

Publication license

memòria: cc-nc-nd (c) Maite Mateo Gutiérrez, 2019
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/182860

Agents conversacionals: implementació de recerca a internet en el context de l’eficiència energètica i la sostenibilitat

Journal Title

Journal ISSN

Volume Title

Related resource

Abstract

[en] This project is a continuation of two previous works. In the first one, it was created a Cultural Probes application that was used to gather data about children’s behavior and the bahavior of their families in terms of the environment sustainability and energy consumption. This app consists of 4 activities related to the energy that the user should perform in a period of a week. In the second, it was added a Sentinent Embodied Conversational Agent (SECA), called Earth. This SECA is a Virtual Assistant who is in charge of answering the queries of the users, reminding them different things and giving them interesting information about energy. For this project, there were implemented two ways to respond to the user: keyword matching and Machine Learning. Finally, my work has focused on adding another method to respond to the user, the search on the internet. In addition, it has improved the user experience by changing the database for efficiency, adding a login for users directly on the app, adding more ways to start a conversation from part of the Earth as jokes, adding images and videos during conversations to give the users new knowledge related to the topic of the conversation, and using the method of search on the internet extensively.

Description

Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2019, Director: Maite López Sánchez

Citation

Citation

MATEO GUTIÉRREZ, Maite. Agents conversacionals: implementació de recerca a internet en el context de l’eficiència energètica i la sostenibilitat. [consulted: 16 of June of 2026]. Available at: https://hdl.handle.net/2445/182860

Export metadata

JSON - METS

Share record