Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Recolector de Cienci...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
Biblos-e Archivo
Bachelor thesis . 2017
Data sources: Biblos-e Archivo
versions View all 2 versions
addClaim

Agentes virtuales con capacidades cognitivas utilizando IBM Watson

Authors: Carrillo Calderón, Manuel Esteban;

Agentes virtuales con capacidades cognitivas utilizando IBM Watson

Abstract

Resumen (castellano) En la actualidad, los avances en la tecnología informática y la creciente globalización por medio de Internet y las redes sociales han obligado a que los comercios tradicionales luchen por digitalizarse, a la par que los comercios online traten de ser cada vez más personales y cercanos a los clientes. En esto consiste el comercio electrónico conversacional, una evolución del ecosistema del comercio electrónico. Hoy en día, los chats automáticos con mensajes estándar no cumplen con los requisitos de unos clientes cada vez más exigentes con sus necesidades a la hora de solicitar alguna clase de servicio (recomendación de productos, atención personalizada y en tiempo real, etc.), y la atención humano-a-humano presenta limitaciones económicas y temporales poco rentables para un negocio. Es aquí donde interviene la principal herramienta que hace posible el comercio electrónico conversacional: los agentes virtuales con capacidades cognitivas. Este Trabajo de Fin de Grado tiene como objetivo principal el diseño y desarrollo de un sistema conversacional, Watson AV, capaz de analizar e interpretar diversos tipos de datos, incluyendo texto no estructurado y audio para interactuar con una persona y proporcionar recomendaciones individualizadas mediante la comprensión de su personalidad, su tono y emoción. El entorno de desarrollo de esta aplicación se basa en los servicios de Watson Developer Cloud alojados en la plataforma IBM Bluemix y ofrecidos a través de una API Rest. La tecnología utilizada incluye, inicialmente, IBM Watson Conversation y los servicios de Speech to Text y Text to Speech. Watson Conversation incluye su propio entorno de desarrollo a través del cual se construye la conversación indicando las intenciones (acciones) a identificar en el diálogo y las principales entidades (objetos o valores) con las que eliminar la ambigüedad en la conversación. Todos estos servicios se integran a través de Node-Red, un entorno de diseño gráfico de flujos de integración basado en node.js que permite desplegar a la aplicación en un servidor web y mantenerla accesible a través de un navegador. Aunque el asistente virtual Watson AV construido en este proyecto está enfocado a un área específica (panel de control de un automóvil), se puede ver como una base adaptativa para la construcción de agentes virtuales dedicados a diversas áreas de la sociedad.

Nowadays, progress in information technology and the worldwide growth through Internet and social networks have forced traditional businesses to struggle to digitize, while online shops try to be more personal and close to the clients. This is the conversational electronic commerce, an evolution of the e-commerce ecosystem. Today, automatic chats with standard messages do not get the requirements of increasingly demanding customers with their needs when they request some kind of service (product recommendation, personalized and real-time attention, etc.), and human-to-human care has economic limits that are unprofitable for a business. Here the main tool that makes conversational electronic commerce possible intervenes: virtual agents with cognitive abilities. This bachelor thesis has as main objective the design and development of a conversational system, Watson AV, able to analyse and interpret diverse types of data, including unstructured text and audio to interact with people and to provide individualized recommendations through the understanding of their personality, tone and emotion. The development environment for this application is based on Watson Developer Cloud services hosted on the IBM Bluemix platform and offered through a Rest API. The technology used initially includes IBM Watson Conversation and the services of Speech to Text and Text to Speech. Watson Conversation includes its own development environment through which the conversation is built by indicating the intentions (actions) to be identified in the dialogue and the main entities (objects or values) with which the ambiguity in the conversation can be eliminated. These services are integrated through Node-Red, a node.js-based integration flow graphic design environment that allows you to deploy the application into a web server and keep it accessible through a browser. Although the virtual assistant Watson AV built on this project is focused on a specific area (control panel of a car), it can be seen as an adaptive base for the construction of virtual agents dedicated to various areas of society.

Country
Spain
Related Organizations
Keywords

Informática, Agente/Asistente Virtual, Capacidad Cognitiva, Comercio Electrónico

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green