Dissertations / Theses on the topic 'Assistant conversationnel'
To see the other types of publications on this topic, follow the link: Assistant conversationnel.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 30 dissertations / theses for your research on the topic 'Assistant conversationnel.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Bouchet, François. "Conception d'une chaîne de traitement de la langue naturelle pour un agent conversationnel assistant." Phd thesis, Université Paris Sud - Paris XI, 2010. http://tel.archives-ouvertes.fr/tel-00607298.
Abstract:
Avec le nombre croissant d'utilisateurs novices des applications informatiques, le besoin d'une aide efficace est devenu critique. Afin de répondre à ce besoins, nous suggérons d'utiliser un Agent Conversationnel Assistant (ACA), c'est-à-dire une interface permettant l'utilisation de la langue naturelle (en effet celle-ci est utilisée spontanément dès qu'un problème surgit) ainsi qu'une présence rassurante pour les utilisateurs.Une étude préliminaire détaille la constitution (en combinant la collecte et l'utilisation de thesaurus) d'un corpus de requêtes dont nous justifions le besoin. Ce corpus de 11626 requêtes est comparé avec d'autres corpus existants et nous montrons qu'il couvre le domaine étudié d'aide et que de plus, il contient des requêtes portant d'une part sur le contrôle de l'application et d'autre part des phrases de 'clavardage'. Ce corpus fournit une base saine pour la conception d'un analyseur syntactico-sémantique de requêtes en langage naturel, utilisant un jeu de classes (keys) sémantiques, un jeu de règles d'analyse et un jeu de règles de transformation. En entrée, les requêtes sont exprimées dans un langage formel (DAFT) pour lequel nous proposons une syntaxe et une sémantique. L'analyseur est alors évalué en comparant une annotation manuelle avec les requêtes produites automatiquement et nous étudions l'usage de techniques d'apprentissage supervisé afin d'identifier les classes d'activités conversationnelles. La méthodologie employée est validée via l'intégration d'un ACA dans une application Web existante , dédiée au prototypage collectif de la musique sur Internet. Enfin, nous décrivons l'architecture requise pour implémenter un agent rationnel qui a pour rôle de définir les réactions aux requêtes formelles des usagers, exprimées en DAFT ainsi que le modèle de l'application assistée, mettant ainsi en lumière le besoin d'un modèle cognitif.
2
Leray, David. "D'une famille de composants dialogiques à une méthodologie de synthèse de modèles d'assistance pour un Agent Conversationnel Assistant." Phd thesis, Université Paris Sud - Paris XI, 2009. http://tel.archives-ouvertes.fr/tel-00618732.
Abstract:
Les travaux effectués dans cette thèse explorent la problématique de la synthèse de modèles d'assistance pour un système d'assistance à l'utilisateur en langue naturelle. Cette problématique est complexe car les modèles utilisés doivent unifier deux visions différentes et parfois contradictoires d'un même objet : l'application en cours d'exécution.L'hypothèse défendue dans ces travaux est que le recours à une représentation, guidée par des traits perceptuels pour organiser les informations, permet de résoudre (en partie) ce problème d'unification. Nous explorons cette hypothèse sur la problématique du regroupement perceptuel de composants d'interface. Pour obtenir cette représentation, nous avons implémenté un algorithme de regroupement perceptuel issu de la théorie de la gestalt. Ces travaux ont permis le développement d'une famille de composants dialogiques utilisables comme éléments de modélisation. Cette famille de composants (Daft-swing), s'insère dans une architecture de traitement de requêtes (Daft). La synthèse de modèles est ensuite traitée dans deux études de cas différentes : la première met en oeuvre l'algorithme de regroupement perceptuel dans le cadre de la synthèse de modèles a partir d'une application web. La deuxième se focalise sur la synthèse de modèles à partir des actions d'un utilisateur. Ces deux outils produisent des modèles utilisant des composants de Daft-Swing directement utilisables par l'architecture Daft et son agent assistant.
3
Leray, David. "D’une famille de composants dialogiques à une méthodologie de synthèse de modèles d’assistance pour un agent conversationnel assistant." Paris 11, 2009. http://www.theses.fr/2009PA112277.
Abstract:
Les travaux effectues dans cette these explorent la problematique de la synthese de modeles d’assistance pour un systeme d’assistance a l’utilisateur en langue naturelle. Cette problematique est complexe car les modeles utilises doivent unifier deux visions differentes et parfois contradictoires d’un meme objet : l’application en cours d’execution. L’hypothese defendue dans ces travaux est que le recours a une representation, guidee par des traits perceptuels pour organiser les informations, permet de resoudre (en partie) ce probleme d’unification. Nous explorons cette hypothese sur la problematique du regroupement perceptuel de composants d’interface. Pour obtenir cette representation, et nous avons implemente un algorithme de regroupement perceptuel issu de la theorie de la gestalt. Ces travaux ont permis le developpement d’une famille de composants dialogiques utilisables comme elements de modelisation. Cette famille de composants, appelee daft-swing, s’insere dans une architecture de traitement de requetes appelee daft (developpee lors de travaux anterieurs). La synthese de modeles est ensuite traitee dans deux etudes de cas differentes : la premiere, qui a conduit au developpement d’un outil appele dom-filter, met en Œuvre l’algorithme de regroupement perceptuel dans le cadre de la synthese de modeles a partir d’une application web. La deuxieme, qui a conduit au developpement d’un outil appele kiwi, se focalise sur la synthese de modeles a partir des actions d’un utilisateur. Ces deux outils produisent des modeles utilisant des composants de daft-swing directement utilisables par l’architecture daft et son agent assistantIn this thesis we deal with the problem of the synthesis of assistance models dedicated to the support of help systems based on natural language interaction with users of computer applications. This problem is challenging because assistance models have to unify two different, sometimes contradictory, points of view upon the same entity: the application at runtime. The hypothesis defended in this work is that using a perceptual-driven representation to organize information in the assistance model resolves (at least partially) the unification problem. We explore this hypothesis on the issue of perceptual grouping of interface components (or widgets). To obtain the representation, we implement an algorithm derived from the gestalt theory. This work has led to the development of a family of so-called “dialogical components” used as modeling items. This family of components, called daft-swing, fits into a generic architecture of query/answer processing, called daft, developed in previous work. The problematic of perceptual grouping and the synthesis of assistance models are then handled via two case studies: the first one, which led to the development of a software tool called dom-filter, describes the implementation of the perceptual grouping algorithm in the context of an experience of model synthesis from a web application. The second one, which led to the development of a software tool called kiwi, is more focused on the synthesis of models involving user’s actions as the main source of information. Each tool produces assistance models based on daft-swing components. Hence these models are directly embeddable in the daft architecture and can be used by its assisting agent
4
Rystedt, Beata, and Mia Zdybek. "Conversational agent as kitchen assistant." Thesis, KTH, Skolan för teknikvetenskap (SCI), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-230904.
Abstract:
Chatbots, also called conversational agents, with speech interfaces are being used to a greater and greater extent, but there are still many areas that are not completely explored. The idea of this project was born out of the belief that there is a need for an assistant in the kitchen that is able to search for recipes, answer questions regarding them and guide and assist the user throughout the cooking process, all through conversation since the hands are busy. This paper begins with an introduction in the subject of conversational agents and the related technology, then similar, already existing studies and methods are presented with their pros and cons. After follows an in-depth explanation on how the program was constructed into a working kitchen assistant. Lastly, the users’ experiences of the performance and usability of the program was evaluated through tests and discussed. It turns out that conversational agents definitely can be integrated in the kitchen, and according to several sources, in a few years they will be implemented in all possible areas and change the technology of our time.Konversationsrobotar med talgränssnitt används i allt större och större utsträckning men det finns fortfarande många områden som inte är helt utforskade. Idén till det här arbetet föddes ur uppfattningen att det existerar ett behov av en hjälpreda till köket som kan söka recept, svara på frågor kring receptet och vägleda och hjälpa användaren genom hela matlagningsprocessen i muntligt form eftersom händerna är upptagna med annat. Det här arbetet börjar med en introduktion i ämnet kring konversationsrobotar och tekniken bakom, sedan presenteras liknande arbeten och metoder som redan existerar inom området. Sedan följer en djupdykning i hur det framtagna programmet i detta arbete utvecklats fram till en fungerande matlagningsassisten. Till slut presenteras och diskuteras upplevelsen och användbarheten av konversationsroboten hos människor baserat på tester som gjorts. Det visar sig att konversationsrobotar mycket väl kan vara av användning i köket, och enligt flera källor kommer de att inom en snar framtid lavinartat implementeras i alla möjliga områden och förändra tekniken i vårt samhälle.
5
Mavridis, Nikolaos. "Grounded Situation Models for Situated Conversational Assistants." Thesis, Massachusetts Institute of Technology, 2007. http://hdl.handle.net/1721.1/38523.
Abstract:
Thesis (Ph. D.)--Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences, 2007.This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Includes bibliographical references (p. 259-267).
A Situated Conversational Assistant (SCA) is a system with sensing, acting and speech synthesis/recognition abilities, which engages in physically situated natural language conversation with human partners and assists them in carrying out tasks. This thesis addresses some prerequisites towards an ideal truly cooperative SCA through the development of a computational model of embodied, situated language agents and implementation of the model in the form of an interactive, conversational robot. The proposed model produces systems that are capable of a core set of situated natural language communication skills, and provides leverage for many extensions towards the ideal SCA, such as mind reading skills. The central idea is to endow agents with a sensor-updated "structured blackboard" representational structure called a Grounded Situation Model (GSM), which is closely related to the cognitive psychology notion of situation models. The GSM serves as a workspace with contents similar to a "theatrical stage" in the agent's "mind". The GSM may be filled either with the contents of the agent's present here-and-now physical situation, or a past situation that is being recalled, or an imaginary situation that is being described or planned.
(cont.) Furthermore, the GSM contains descriptions of both physical (such as objects) as well as mental aspects of situations (such as beliefs of others). Most importantly, the proposed GSM design enables bidirectional translation between linguistic descriptions and perceptual data / expectations. To demonstrate viability, an instance of the model was implemented on a manipulator robot with touch, vision, and speech synthesis/recognition. The robot grasps the semantics of a range of words and speech acts related to cooperative manipulation of objects on a table top situated between the robot and human. The robot's language comprehension abilities are comparable to those implied by a standard and widely used test of children's language comprehension (the Token Test), and in some directions also surpass those abilities. Not only the viability but also the effectiveness of the GSM proposal is thus demonstrated, through a real-world autonomous robot that performs comparably to those capabilities of a normally-developing three-year old child which are assessed by the token test.
by Nikolaos Mavridis.
Ph.D.
6
Fuckner, Márcio. "A personal assistant for the enactment of business processes." Thesis, Compiègne, 2016. http://www.theses.fr/2016COMP2270/document.
Abstract:
Ces dernières années, les progrès en sciences de la gestion et de l’information ont transformé la Gestion de Processus d’Affaires (Business Process Management, BPM) en un sujet important, tant du côté de l’industrie que de celui de la recherche. Le BPM utilise des processus métiers pour améliorer la performance opérationnelle des organisations. Les processus métiers établissent un lien entre les personnes, les systèmes, et les différentes organisations, dans le but de créer de la valeur pour les parties prenantes. La cible de notre travail est la famille des systèmes BPM. Un système BPM est un système logiciel générique guidé par des modèles explicites de processus métier avec pour objectif d’exécuter et de gérer des processus opérationnels. Malgré le vaste éventail de sujets traités par ce domaine de recherche, il reste encore quelques questions qui méritent une étude plus approfondie. Un problème particulier concerne la médiation entre les systèmes BPM et les humains. L’interaction homme-machine dans ces systèmes repose sur des interfaces standard basées sur des listes de taches et des formulaires, ce qui est très contraignant pour les utilisateurs.Ceux-ci ont non seulement des difficultés à exécuter leurs processus métier, mais aussi a trouver le processus métier le mieux adapté à leurs besoins. Il serait beaucoup plus efficace d’utiliser des dialogues en langage naturel. Malheureusement les langages de modélisation de processus ne permettent pas de capturer ni de modéliser un domaine de discours. Le travail présent propose une approche originale de gestion du dialogue basée sur des systèmes multi-agents pour l’exécution des processus métier. La motivation globale pour ce travail fut de concevoir un modèle de dialogue extensible à différents domaines. Ce modèle s’appuie sur les ontologies de domaine, nécessitant un minimum d’effort d’adaptation pour améliorer l’interaction. Les résultats montrent tout le potentiel de notre approche multi-agent pour réaliser une médiation automatiquement, sans qu’il soit nécessaire de reconstruire les modèles de processus métierOver the last few years, the advances in management science and information technology have transformed the business process management (BPM) discipline into an important topic for both industry and academy. BPM uses business processes as the means for improving the operational performance of organizations, and setting processes are at the heart of BPM allows linking together people, systems, and different organizations to deliver value to stakeholders. The target of our work is the family of BPM systems. A BPM system is a generic software system that is driven by explicit process designs to enact and manage operational business processes. Despite the wide range of topics addressed by the academy on business processes, there are still aspects not addressed by prior research. A particular problem in this regard is the mediation between BPM systems and humans. Human interaction in those systems follows a standard user interface based predominantly on work item lists and forms. Thus, there is little room for creativity for users. They have not only difficulties in enacting their processes but also for searching the most suitable one for their needs. It would be more efficient to let humans interact in natural language. However, process modeling languages are an insufficient means of capturing and representing the domain of discourse. The present thesis develops an original approach to agent dialog management for the problem of business process enactment. The overarching motivation for this work was to design a dialog model scalable to different domains. The model relies on domain and business process ontologies, and necessitates a minimum effort of adaptation on ontologies to improve the interaction. Results indicate the potential of our agent-based approach to generate natural language
7
Schild, Erwan. "De l’importance de valoriser l’expertise humaine dans l’annotation : application à la modélisation de textes en intentions à l’aide d’un clustering interactif." Electronic Thesis or Diss., Université de Lorraine, 2024. http://www.theses.fr/2024LORR0024.
Abstract:
La tâche d'annotation, nécessaire à l'entraînement d'assistants conversationnels, fait habituellement appel à des experts du domaine à modéliser. Toutefois, l'annotation de données est connue pour être une tâche difficile en raison de sa complexité et sa subjectivité : elle nécessite par conséquent de solides compétences analytiques dans le but de modéliser les textes en intention de dialogue. De ce fait, la plupart des projets d'annotation choisissent de former les experts aux tâches d'analyse pour en faire des "super-experts". Dans cette thèse, nous avons plutôt décidé mettre l'accent sur les connaissances réelles des experts en proposant une nouvelle méthode d'annotation basée sur un Clustering Interactif. Celle-ci se base sur une coopération Homme/Machine, où la machine réalise un clustering pour proposer une base initiale d'apprentissage, et où l'expert annote des contraintes MUST-LINK ou CANNOT-LINK entre les données pour affiner itérativement la base d'apprentissage proposée. Une telle annotation présente l'avantage d'être plus instinctive, car les experts peuvent associer ou différencier les données en fonction de la similarité de leur cas d'usage, permettant ainsi de traiter les données comme ils le feraient professionnellement au quotidien. Au cours de nos études, nous avons pu montrer que cette méthode diminuait sensiblement la complexité de conception d'une base d'apprentissage, réduisant notamment la nécessité de formation des experts intervenant dans un projet d'annotation. Nous proposons une implémentation technique de cette méthode (algorithmes et interface graphique associée), ainsi qu'une étude des paramètres optimaux pour obtenir une base d'apprentissage cohérente en un minimum d'annotation. Nous réalisons également une étude de coûts (techniques et humains) permettant de confirmer que l'utilisation d'une telle méthode est réaliste dans un cadre industriel. De plus, afin que la méthode atteigne son plein potentiel, nous fournissons un ensemble de conseils, notamment : (1) des recommandations visant à cadrer la stratégie d'annotation, (2) une aide à l'identification et à la résolution des divergences d'opinion entre annotateurs, (3) des indicateurs de rentabilité pour chaque intervention de l'expert, et (4) des méthodes d'analyse de la pertinence de la base d'apprentissage en cours de construction. En conclusion, cette thèse offre une approche innovante pour concevoir une base d'apprentissage d'un assistant conversationnel, permettant d'impliquer les experts du domaine métier pour leurs vraies connaissances, tout en leur demandant un minimum de compétences analytiques et techniques. Ces travaux ouvrent ainsi la voie à des méthodes plus accessibles pour la construction de ces assistantsUsually, the task of annotation, used to train conversational assistants, relies on domain experts who understand the subject matter to model. However, data annotation is known to be a challenging task due to its complexity and subjectivity. Therefore, it requires strong analytical skills to model the text in dialogue intention. As a result, most annotation projects choose to train experts in analytical tasks to turn them into "super-experts". In this thesis, we decided instead to focus on the real knowledge of experts by proposing a new annotation method based on Interactive Clustering. This method involves a Human-Machine cooperation, where the machine performs clustering to provide an initial learning base, and the expert annotates MUST-LINK or CANNOT-LINK constraints between the data to iteratively refine the proposed learning base. Such annotation has the advantage of being more instinctive, as experts can associate or differentiate data according to the similarity of their use cases, allowing them to handle the data as they would professionally do on a daily basis. During our studies, we have been able to show that this method significantly reduces the complexity of designing a learning base, notably by reducing the need for training the experts involved in an annotation project. We provide a technical implementation of this method (algorithms and associated graphical interface), as well as a study of optimal parameters to achieve a coherent learning base with minimal annotation. We have also conducted a cost study (both technical and human) to confirm that the use of such a method is realistic in an industrial context. Finally, we provide a set of recommendations to help this method reach its full potential, including: (1) advice aimed at framing the annotation strategy, (2) assistance in identifying and resolving differences of opinion between annotators, (3) rentability indicators for each expert intervention, and (4) methods for analyzing the relevance of the learning base under construction. In conclusion, this thesis provides an innovative approach to design a learning base for a conversational assistant, involving domain experts for their actual knowledge, while requiring a minimum of analytical and technical skills. This work opens the way for more accessible methods for building such assistants
8
Chi, Pei-Yu S. M. Massachusetts Institute of Technology. "Raconteur : intelligent assistance for conversational storytelling with media libraries." Thesis, Massachusetts Institute of Technology, 2010. http://hdl.handle.net/1721.1/61944.
Abstract:
Thesis (S.M.)--Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences, 2010.Cataloged from PDF version of thesis.
Includes bibliographical references (p. 99-103).
People who are not professional storytellers sometimes have difficulty putting together a coherent and engaging story, even when it is about their own experiences. However, consider putting the same person in a conversation with a sympathetic, interested and questioning listener, suddenly the story comes alive. There's something about the situation of being in a conversation that encourages people to stay on topic, make coherent points, and make the story interesting for a listener. Raconteur is a system for conversational storytelling between a storyteller and a viewer. It provides intelligent assistance in illustrating a life story with photos and videos from a personal media library. Raconteur performs natural language processing on a text chat between two users and recommends appropriate media items from the annotated library, each file with one or a few sentences in unrestricted English. A large commonsense knowledge base and a novel commonsense inference technique are used to understand event relations and determine narration similarity using concept vector computation that goes beyond keyword matching or word co-occurrence based techniques. Furthermore, by identifying larger scale story patterns such as problem and resolution or expectation violation, it assists users in continuing the chatted story coherently. A small user study shows that people find Raconteur's suggestions helpful in real-time storytelling and its interaction design engaging to explore stories together.
by Pei-Yu (Peggy) Chi.
S.M.
9
Simonin, Jérôme. "Aide en ligne adaptative et assistants conversationnels animés : mise en oeuvre et évaluation ergonomique." Thesis, Nancy 1, 2007. http://www.theses.fr/2007NAN10076/document.
Abstract:
La thèse vise à évaluer de nouvelles formes d'interaction Homme-Machine. Plus précisément, la thématique générale de ce travail, divisée en deux axes, vise à mettre en oeuvre et à évaluer l'apport d'Agents Conversationnels Animés (ACAs) et d'Interfaces dites "Adaptatives" à l'utilisation d'un logiciel. Ainsi, comportements et réactions d'utilisateurs sont recueillis à l'aide de méthodes ergonomiques et techniques de suivi du regard (eye-tracking). Une approche expérimentale a été adoptée afin d'évaluer l'apport de chaque axe. Pour cela, des participants (étudiants de niveau Licence) ont manipulé un logiciel de création d'animation qui leur était inconnu (Flash) afin de réaliser trois scénarios. Tout au long de leur découverte du logiciel, les participants étaient accompagnés d'un dispositif d'aide intégrant, suivant l'expérimentation, un ACA (fourni par FT R & D) ou une technique d'adaptation (détection d'intention et évolution suivant les connaissances). Les différentes études réalisées montrent que les deux sources d'innovation employées ont été perçues positivement par la majorité des participants. Elles ont montré d'autre part qu'un ACA a un effet rassurant et qu'il peut vraisemblablement être utilisé lors de la prise en main d'un logiciel. Pour le système adaptatif, le fait que le système évolue de manière autonome n'a pas perturbé les participants, mais n'améliore guère les performancesThe goal of the thesis is to evaluate new forms of Human-Computer Interaction. More precisely, the general set of themes of this work, divided into two parts at aims implementing and evaluating the contribution of Embodied Conversational Agent (ECAs) and of adaptive interfaces for the use of software. Thus, behaviours and reactions of users are collected using ergonomic methods and eye-tracking technologies. An experimental approach was adopted in order to evaluate the contribution of each part. For that, participants (student of bachelor's degree) handled a software of animation's creation which was unknown for them (Flash) in order to carry out three scenarios. Throughout their exploration of the software, participants were accompanied by a help system. In the first experiment an ECA (provided by FT R & D) enunciate help messages; in the second one a adaptive system (detection of intention and evolution according to knowledge) was used. The various studies carried out show that the two innovations employed were perceived positively by the majority of the participants. They showed in addition that a ECA has a reassuring effect and that it can probably be used in first experiences with a software. For the adaptive system, the fact that the system evolves in an autonomous way did not disturb the participants, but hardly improves the performances
10
Simonin, Jérôme Carbonell Noëlle. "Aide en ligne adaptative et assistants conversationnels animés mise en oeuvre et évaluation ergonomique /." Nancy : Université de Nancy 1, 2007. http://www.scd.uhp-nancy.fr/docnum/SCD_T_2007_0076_SIMONIN.pdf.
11
Fernández, Canales Rocío Daniela, and Salvador Gianfranco Monzón. "Implementación de un capacitador virtual para visitadores médicos con integración de un asistente de voz." Bachelor's thesis, Universidad Peruana de Ciencias Aplicadas (UPC), 2020. http://hdl.handle.net/10757/652326.
Abstract:
La creciente popularidad y las capacidades mejoradas de los asistentes personales inteligentes, como Google Assistant, Siri y Alexa, han permitido su aplicación en numerosos campos, algunos de los cuales son: servicio al cliente, banca y turismo. No obstante, la aplicación de estos asistentes para la capacitación y el aprendizaje de trabajadores profesionales ha sido limitada y no ha sido bien investigada.
El presente documento validará la propuesta de una solución para la capacitación continua y el aprendizaje de los visitadores médicos sobre la información de los medicamentos mediante el uso de un agente de conversación basado en la voz. Esto permitirá que los representantes de ventas farmacéuticas puedan preguntar al agente acerca de las propiedades de los medicamentos y realizar exámenes frecuentes sobre la información disponible para verificar su conocimiento.
Esta validación se realizará a través del seguimiento y aplicación de una metodología de investigación centrada en las soluciones y arquitecturas existentes que brinden una base para iniciar el desarrollo del proyecto.The increasing popularity and enhanced capabilities of intelligent personal assistants, such as Google Assistant, Siri, and Alexa, have allowed them to disrupt in many fields, some of which are: customer service, banking, and tourism. Notwithstanding, the application of intelligent personal assistants for training and learning of professional workers has been limited and not well researched. This document will validate the proposal of a solution for the continuous training and learning of the medical visitors on the information of the medications using a voice-based conversation agent. This will allow pharmaceutical sales representatives to ask the agent about the properties of the drugs and conduct frequent reviews of the information available to verify their knowledge. This validation will be carried out through the monitoring and application of a research methodology focused on the existing solutions and architectures that provide a basis to start the development of the project.
Trabajo de investigación
12
Gersil, Tuna, and Ismail Hilal. "The Role of Conversational Interfaces in the Future of Digitaland Technology." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-279688.
Abstract:
Conversational interfaces (CIs) have been a trending topic in recent years. As of the last decade, CIs have emerged with the aim of simplifying human-machine interactions and found a wide use case in the market. For example, Siri and Google Assistant are some of the most well-known CIs developed by the tech giants Apple and Google. The digital landscape has evolved from web, to mobile apps, to recently CIs. Nowadays, CIs, in particular chatbots and voicebots, are becoming increasingly common. Whether navigating the web or messaging on a phone, it is likely that CIs have been confronted offering the user help.However, CIs have not managed to reach a large-scale use. Furthermore, the reasons regarding the challenges faced by CIs as well as their usability are not greatly explored. In this thesis, we explore the most relevant uses of CIs and the reasons hindering a widespread use of CIs. Our goal is to provide an insight into CIs’ uses and list the reasons regarding the challenges faced by CIs. The research study followed a mixed method approach connecting an explorative qualitative literature study, a survey and an interview. The data was collected by using a systematic mapping approach for it being more suitable for conducting an effective literature review. The survey and the interview were conducted in order to confirm the findings.According to our research, it was found that the most common use cases of CIs were in customer service, sales, travel and bookings, education, healthcare and as voice assistants. The most prominent challenges faced by CIs were poor usability, language processing and understanding, speech recognition and natural language generation and security and privacy. As a conclusion, the future looks promising for CIs, however, they need to be furher researched and developed in order to help them reach a widespread use in the future.Konversation Gränssnitt (CIs) har varit ett trendande ämne de senaste åren. Sedan det senaste decenniet har CIs kommit fram i syfte att förenkla interaktioner mellan människor och maskiner och har hittat ett brett användningsfall på marknaden. Det digitala landskapet har utvecklats från webb, till mobila appar till nyligen CI. Numera blir CIs, i synnerhet chatbots och voicebots, allt vanligare. Vare sig du navigerar på webben eller meddelanden i en telefon, är det troligt att CIs har konfronterats med att erbjuda användaren hjälp.CIs har dock inte lyckats uppnå storskalig användning. Dessutom är orsakerna till de utmaningar som CIs står inför och deras användbarhet inte utforskas i hög grad. I den här avhandlingen undersöker vi de mest relevanta användningarna av CIs och orsakerna till en utbredd användning av CIs. Vårt mål är att ge en inblick i CI: s användningar och lista orsakerna till de utmaningar som CIs står inför. Forskningsstudien följde en blandad metodstrategi som ansluter en utforskande kvalitativ litteraturstudie, en undersökning och en intervju. Uppgifterna samlades in med hjälp av en systematisk kartläggningsätt för att göra dem mer lämpliga för att genomföra en effektiv litteraturgranskning. Undersökningen och intervjun genomfördes för att bekräfta resultaten.Enligt vår forskning konstaterades att de vanligaste användningsfallen för CIs var kundservice, försäljning, resor och bokningar, utbildning, sjukvård och som röstassistenter. De mest framstående utmaningarna för CIs var dålig användbarhet, språkhantering och förståelse, taligenkänning och naturlig språkgenerering och säkerhet och integritet. Sammanfattningsvis ser framtiden lovande ut för CIs, men de måste undersökas och utvecklas ytterligare för att hjälpa dem att uppnå utbredd användning i framtiden.
13
Cabrera, Paraiso Emerson. "Icai : une interface conversationnelle pour une aide intelligente." Compiègne, 2005. http://www.theses.fr/2005COMP1590.
Abstract:
Cette thèse concerne la conception d'une interface conversationnelle pour les agents assistants personnels. Ce travail s'inscrit dans un processus de développement d'un modèle générique d'agent assistant personnel. Après avoir examiné les divers types d'interfaces utilisées par des agents assistants, nous avons conclu que les interfaces conversationnelles étaient particulièrement bien adaptées à nos besoins. Cette thèse est donc focalisée sur la définition et la conception d'une interface conversationnelle pour un agent assistant, en tenant compte de plusieurs contraintes et hypothèses liées à l'agent lui-même, à son pilotage et à la nature du rapport utilisateur-agent, mais aussi aux caractéristiques des applications potentielles. Nous estimons qu'une interface conversationnelle spécialement conçue pour l'agent assistant, simplifiera son pilotage, entraînant une amélioration de la qualité de l'aide apportée par rapport aux interfaces classiques purement graphiques. Ceci diminuera la charge cognitive de l'utilisateur, puisque le travail d'interprétation et reconnaissance des intentions de ce dernier devient de responsabilité de la machine. Nous postulons aussi que le comportement intelligent de l'agent peut contribuer à l'amélioration de la performance liée à une telle interface, grâce à une politique d'affichage d'informations. De notre travail est né le concept d'interface conversationnelle pour une aide intelligente - ICAI. Une interface conversationnelle pour une aide intelligente est le résultat de la conjonction d'un mécanisme conversationnel en langage naturel parlé et de la gestion intelligente de ce mécanisme, permettant le déroulement d'un dialogue coopératif, et capable de gérer le déclenchement de plusieurs tâches à la demande de l'utilisateur, tout en n'exigeant qu'un minimum d'effort de la part de ce dernier. Notre approche s'appuie sur les ontologies, fil conducteur de nos travaux, qui nous permettent d'interpréter les messages, provenant de l'utilisateur ou d'ailleursThis thesis concerns the design of a conversational interface for personal assistant agents. We studied the typical user interface used in personal assistants. We conclude that conversational interfaces are the one especially suitable for personal assistants. To design the conversational interface, we took in account several constraints related to the agent itself and the potential applications. As the result of this approach we expect to improve the quality of assistance and to reduce the user's cognitive load. Ln this thesis we present a new concept called ICAI: A Conversational Interface for an Intelligent Assistance. An ICAI is the result of the conjunction of a conversational spoken natural language mechanism and an intelligent management of such mechanism, enabling a cooperative dialogue between the user and the assistant agent. Our approach is based on ontologies that allow us to interpret messages from human and artificial agents
14
Pecune, Florian. "Modélisation de la prise de décision d'un agent conversationnel animé en fonction de son attitude sociale." Electronic Thesis or Diss., Paris, ENST, 2016. http://www.theses.fr/2016ENST0054.
Abstract:
Afin d’être considérés comme des partenaires crédibles lors d’une interaction, les agents virtuels doivent transmettre une attitude sociale adéquate. Cette attitude sociale exprimée par l’agent doit refléter la situation dans laquelle il se trouve. L’agent doit donc prendre en compte son rôle et sa relation sociale vis à vis de son interlocuteur lorsqu’il choisit comment réagir au cours de l’interaction. Afin de construire un tel agent capable de raisonner en fonction de son rôle et de sa relation, et capable d’adapter son attitude sociale, nous avons construit un modèle de prise de décision sociale. Dans un premier temps, nous formalisons la dynamique de la relation sociale à travers une combinaison de buts et de croyances. Puis, nous définissons un modèle de prise de décision basé sur les buts sociaux et situationnels de l’agent. Pour finir, nous avons réalisé une étude perceptive dans un contexte d’interaction tuteur/enfant virtuels au cours de laquelle les participants évaluaient l’attitude sociale du tuteur envers l’enfant. La relation sociale et le rôle social du tuteur étaient manipulés par notre modèle. Les résultats montrent qu’à la fois le rôle et la relation du tuteur ont une influence sur son attitude sociale perçueTo be perceived as believable partners in human-machine interactions, virtual agents have to express adequate social attitudes. The social attitude expressed by an agent should reflect the social situation of the interaction. The agent ought to take into account its role and its social relation toward its interactants when deciding how to react in the interaction. To build such an agent able to reason about its role and relation and to adapt its social attitude, we built a model of social decision making. First, we formalized the dynamics of the social relation through a combination of goals and beliefs. Then, we designed a decision making model based on the social goals and the situational goals of the agent. Finally, we conducted an empirical study in the context of virtual tutor-child interaction where participants evaluated the tutor’s perceived social attitude towards the child while the tutor’s social role and relation were manipulated by our model. Results showed that both role and social relation have an influence on the agent’s perceived social attitude
15
Gómez, Montoya Héctor Erasmo. "A crowd-powered conversational assistant for the improvement of a neural machine translation system in native peruvian language." Master's thesis, Pontificia Universidad Católica del Perú, 2019. http://hdl.handle.net/20.500.12404/14989.
Abstract:
Para las comunidades más pequeñas y nativas en un país, es muy difícil encontrar información que se encuentre en su idioma original, esto debido a que su lengua no tiene el alcance ni la cantidad suficiente de hablantes, para poder seguir siendo transmitida. A este tipo de lengua se le denomina minoritaria o de pocos recursos.
Una de las principales formas en las que el gobierno incentiva el proceso de multilingüismo es proporcionando educación en el idioma nativo a su población, tal es el caso de los hablantes de Shipibo-Konibo que se encuentran dispersos a lo largo de la amazonía del Perú. Ellos cuentan con colegios donde se les imparten clases en su lengua nativa para los niveles de primaria y secundaria. Sin embargo, una necesidad con la que cuentan los pobladores es que la cantidad de material educativo completamente traducido a Shipibo-Konibo es reducida. Esto debido a que el proceso de traducción es muy costoso y poco confiable.
El Grupo de investigación en Inteligencia Artificial de la PUCP (IA-PUCP, ex GRPIAA) ha desarrollado una plataforma que utiliza corpus paralelos la creación de un modelo estadístico de traducción automática para las lenguas Shipibo-Konibo y español. Este modelo sufre de ciertas limitantes, entre las cuales tenemos: la cantidad de recursos bibliográficos y material completamente traducido, esto debido a que al ser una lengua minoritaria o de pocos recursos carecen de facilidades para la generación de nuevos corpus. Por otro lado, se desea mejorar el modelo actual en parámetros de eficiencia y obtener mejores resultados en las traducciones.
En este contexto nace la pregunta que motiva el presente trabajo: ¿de qué manera podemos incrementar el corpus paralelo de forma eficiente y confiable para la mejora del modelo actual de traducción automática? Por consiguiente, en el presente trabajo se propone desarrollar un agente conversacional que permita la generación de nuevos corpus paralelos entre Shipibo-Konibo y español que permitan mejorar un modelo de traducción automática neuronal en las lenguas ya mencionadas.Tesis
16
Orwick, Ogden Sherri L. "Agent for Interactive Student Assistance: A Study of an Avatar-Based Conversational Agent's Impact on Student Engagement and Recruitment at BGSU's College of Technology." Bowling Green State University / OhioLINK, 2011. http://rave.ohiolink.edu/etdc/view?acc_num=bgsu1319804597.
17
Kozlova, Iryna. "Negotiation of Identities by International Teaching Assistants through the Use of Humor in University Classrooms." Digital Archive @ GSU, 2008. http://digitalarchive.gsu.edu/alesl_diss/2.
Abstract:
Research on international teaching assistants (ITAs) often highlights that ITAs have at least two identities, an identity of a teacher and a student (e.g., Jenkins, 2000). Since American classrooms foster a variety of behaviors that are negotiated by instructors and students, ITAs may identify themselves with students during behavior negotiation when building rapport, especially by exchanging jokes (Unger-Gallagher, 1991). Making their student identity relevant may distort the teacher-student relationship, which ITAs might need to renegotiate. Little research has been done to show whether ITA student identity actually emerges and if does, then how. This study addresses the questions of what attributes of ITA's identities emerge during humorous exchanges with their students, how these attributes shape the teacher-student relationship, and what role humor plays in the identity negotiation process between the ITAs and their students in the university classroom. Four ITAs, all non-native English speakers, participated in this microethnographic study. This study informs research on social identity in that, most of the time, participants made the attributes of their teacher identity relevant, with teacher authority emerging as the most important attribute. While enacting their teacher identity through humorous exchanges, ITAs built rapport and created affiliation with their students. Although humor led to establishing good relationships, it did not lead to the emergence of ITA student identity. This study also contributes to research on humor in that it makes a distinction between the concepts of the target and the butt which allows for deeper understanding of how humor is used to negotiate identity. It also introduces the target switch, or a particular type of counter teasing, in which the initial target redirects humorous aggression to the teaser, thus making her/him the target and a potential butt of the tease. An optimistic finding for ITA research and research on the use of humor by non-native speakers is that even without extensive experience with American culture in general, ITAs can use humor rooted in the local context to negotiate different classroom behaviors and their identities with their students.
18
Bondanini, Andrea. "Chatbot ed Elaborazione Naturale del Linguaggio. Progettazione e realizzazione di un assistente sanitario." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2019.
Abstract:
La tesi concerne lo studio e sviluppo di un agente conversazionale che trova applicazione in ambito sanitario, nell'ambito di un progetto in cooperazione con un'azienda del territorio (Onit srl). In particolare si vuole facilitare l'accesso alle prestazioni mediche erogate dal Servizio Sanitario Nazionale, permettendo ad paziente di prenotare i propri appuntamenti chattando in modo naturale tramite una applicazione di messaggistica. Il sistema predispone anche un servizio di FAQ, che l'utente può utilizzare per richiedere informazioni su una tipologia di prestazione medica.
19
Kröger, Felix Jan, and Filip Johansson. "Conversational Commerce : A Quantitative Study on Preferences towards AI-Fueled C-Commerce Platforms among Digital Natives in Sweden and Germany." Thesis, Högskolan i Jönköping, Internationella Handelshögskolan, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:hj:diva-43819.
Abstract:
Background: E-commerce is widespread in today’s shopping routines and conversational commerce (CC) as an expansion, aims at integrating customers and businesses on a whole new level. Through the application of chatbots fueled by artificial intelligence, a more personal and individual way of remote shopping is offered. Purpose: Our research question What potential attributes of AI-fueled CC applications and their possible inherent characteristics are determining the willingness to use them and to what extent, in the context of digital natives living in Sweden and Germany? aims at identifying the demanded attributes of conversational commerce from a consumer perspective. Method: We facilitate a quantitative questionnaire with 118 valid answers to administer a traditional full-profile conjoint analysis. Conclusion: Our results indicate that German digital natives deem a CC application’s behavior as the most important attribute, followed by payment method, personality and communication form (voice or text). The Swedish digital natives however, attach the most importance to the payment method, followed by behavior, communication form and personality. Both have in common that they prefer a rather passive behavior over being actively approached, a personality that is balanced between humor and seriousness and text-based communication over voice. A difference is the Swedish preference for direct in-app payment while German digital natives would select a redirection to a secondary payment provider (e.g. PayPal).
20
Raoufi, Matthew M. "How can I help you? : The delivery of e-government services by means of a digital assistant." Doctoral thesis, Umeå : Umeå University, 2005. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-526.
21
Sassi, Hajer. "Assistance et conseil aux utilisateurs dans le cadre d'une intelligence ambiante : une étude des usages en contexte : X-CAMPUS." Thesis, Lille 1, 2013. http://www.theses.fr/2013LIL10183/document.
Abstract:
Ce travail de thèse s'inscrit dans un contexte multidisciplinaire à la frontière entre les domaines de l'intelligence ambiante, de l'interaction homme-machine et des agents conversationnels. Nous y étudions la problématique de l'assistance proactive contextuelle dans le cadre de l'informatique ambiante. A cet égard, notre challenge consiste à fournir à l'utilisateur souhaitant disposer d'un assistant virtuel, des services proactifs capables de communiquer selon le contexte de l'utilisateur. Mais l'intelligence ambiante proactive, ou encore l'assistance proactive contextuelle, n'a pas suivi un développement aussi important que l'intelligence ambiante réactive où l'utilisateur doit exprimer explicitement ses besoins. C'est pourquoi l'objectif de cette thèse CIFRE consiste à étudier et évaluer la notion d'assistance proactive contextuelle via la mise en place d'un agent conversationnel en ligne nommé X-CAMPUS. Cet acronyme signifie eXtensible Conversational Agent for Multichannel Proactive Ubiquitous Services. Ce système a pour vocation d'assister l'utilisateur dans ses tâches quotidiennes grâce à sa capacité de percevoir l'état de l'environnement et d'interagir pertinemment selon les besoins de l'utilisateur (météo, programmes TV, etc.). Nous avons mené une étude expérimentale pour étudier l'intérêt de X-CAMPUS et évaluer la satisfaction qu'il procure aux utilisateurs. Nous décrivons ensuite les résultats quantitatifs et qualitatifs de cette étude obtenus via un ensemble de scénarios et utilisant différents paramètres d'interaction (multimodalité, multicanalité, comportement réactif/proactif de l'agent, type de capteurs, contexte mono/multi-utilisateurs...)This thesis is part of a multidisciplinary context on the border between the domains of the ambient intelligence, the human-machine interaction and the conversational agents. We study the problem of contextual proactive assistance in the course of the ambient computing. In this regard, our challenge is to provide to the user who wish have a virtual assistant, a proactive services which can communicate according to the user’s context. However proactive ambient intelligence, or contextual proactive assistance, did not follow an important development as reactive ambient intelligence where the user must explicitly express their needs. This is why the objective of this CIFRE thesis is to study and evaluate the concept of contextual proactive assistance through the implementation of an online conversational agent named X-CAMPUS. This acronym stands for eXtensible Proactive Multichannel Conversational Agent for Ubiquitous Services. This system aims to assist the user in their daily tasks thanks to its ability to perceive the state of the environment and interact effectively according to user’s needs (weather, TV programs, etc.). We conducted an experimental study to investigate the interest of X-CAMPUS and evaluate the satisfaction that it provides to users. We describe quantitative and qualitative results of this study obtained through a set of scenarios using different parameters of interaction (multimodal, multi-channels, behavior reactive/proactive agent, type of sensors, context mono/multi-user…)
22
Tykesson-Bergman, Ingela. "Samtal i butik : Språklig interaktion melllan biträden och kunder." Doctoral thesis, Stockholms universitet, Institutionen för nordiska språk, 2006. http://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-1058.
Abstract:
The subject of this study is language use in a special type of social activity: the exchange of goods, services and information in a commercial setting. The main aim is to gain an understanding of the work that shop assistants perform using language. In the analysis, the focus is on verbal routine work. One part of the analysis thus entails mapping the typical utterances and conversational sequences related to such activities. Another part involves investigating how much non-task-oriented interaction the various activities require or “tolerate”, for instance, in the form of “small talk”. A central theme in the study is the interactants’ conversational rights and obligations, from the perspective of politeness theory, especially Fraser’s theory of the conversational contract. The service encounters are categorised as activity types, according to Levinson’s activity theory. In the comparative parts of the study, the concept of pragmeme is used as a tool to examine different realisations of prototypical situated communicative acts. The empirical material consists of authentic conversations, analysed by methods borrowed from conversation analysis. The conversations were recorded at a supermarket checkout till, a deli counter with manual service and an information desk in a bookshop. It turned out that only a few of the customer conversations were without complications. At the supermarket till, for instance, only one out of four conversations was completely routine and unproblematic. Also presented is a diachronic investigation of the norms relating to service encounters that have been taking place in shops since the 1940s. The main sources here are manuals and study materials for shop employees, together with interviews and material gathered from role playing. In this part of the study, a number of features in the historical change process are described, for instance in the manner of addressing people and the use of politeness expressions.
23
Kadariya, Dipesh. "kBot: Knowledge-Enabled Personalized Chatbot for Self-Management of Asthma in Pediatric Population." Wright State University / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=wright1565944979193573.
24
Bernard, Christophe. "Vers une gestion informatisée des cahiers de laboratoire : Le système "MANIP"." Nancy 1, 1989. http://www.theses.fr/1989NAN10006.
Abstract:
Réalisation d'un logiciel pour des chimistes permettant la saisie de données concernant la mise en oeuvre de réactions chimiques et l'uniformatisation des cahiers de manipulation. Cette base de données, pouvant être exploitée dans sa totalité. Le logiciel est écrit en turbo pascal et implémenté sur un microordinateur
25
Fafiotte, Georges. "Multiprototypage d'un logiciel d'aide à la découverte de connaissances lexicales : cacao, environnement d'apprentissage assisté par ordinateur des caractères chinois." Université Joseph Fourier (Grenoble), 1994. http://www.theses.fr/1994GRE10024.
Abstract:
Le développement actuel, en TAO personnelle, d'environnements interactifs pour rédacteur monolingue conduit à modéliser des fonctions de documentation, d'autodocumentation, d'autoformation, de gestion de bases de connaissances personnelles, portant sur les propriétés linguistiques de la langue de travail. D'autre part, de nombreux Occidentaux se motivent pour la découverte et l'apprentissage autonome des idéogrammes utilisés à la fois en chinois, japonais et coréen écrits. Locuteurs ou scripteurs autochtones sont également intéressés par de tels composants. Dans ces contextes se situe notre contribution à la modélisation et au prototypage d'une base des propriétés lexicographiques des caractères chinois ― le projet «Apprentissage Assisté par Ordinateur des Caractères Chinois», dont les prototypes prennent l'acronyme CACAO. La base d'informations, structurée en hyperdocument, place l'utilisateur en situation d'exploration encyclopédique, lui permettant de se construire une vue progressive, différenciée, des propriétés des caractères: propriétés «hors-langue» (morphologie, sémantique universelle), propriétés «en-langue» ― spécifiques d'une langue, ici chinoise (phonétique, sémantique contextuelle, utilisations en composition…). Nous proposons un modèle conceptuel des propriétés des caractères à stocker dans la base de connaissances. La démarche retenue est celle d'un prototypage évolutif, en HyperCard. Une première maquette valide les options de l'interface-apprenant. Un prototypage en vraie grandeur (1026 caractères) affine ensuite certains choix fonctionnels. Des prototypages parallèles explorent également différentes vues (Base à Objets en LOOPS, SGBD sous Oracle, système à règles en Prolog) des fonctions principales: structuration de la base, navigation, recherche multicritère des caractères, observatoire de l'activité de l'utilisateur. Ce multiprototypage est aussi une contribution au développement d'environnements hétérogènes, multiplateforme, de production de logiciels didactiques. Nous souhaitons conduire sur CACAO des expérimentations didactiques, ouvertes sur la modélisation des comportements d'apprenants. Indépendamment du développement possible d'un produit à finalité didactique, le système réalisé constitue le socle applicatif d'une recherche sur les interfaces coopérants et les architectures d'assistants intelligents de découverte de connaissances
26
Gonçalves, Ana Pedro Ferreira Gomes Portela. "Prototype of a Conversational Assistant for Satellite Mission Operations." Master's thesis, 2018. http://hdl.handle.net/10400.6/8554.
Abstract:
The very first artificial satellite, Sputnik, was launched in 1957 marking a new era. Concurrently,
satellite mission operations emerged. These start at launch and finish at the end of mission, when
the spacecraft is decommissioned. Running a satellite mission requires the monitoring and control
of telemetry data, to verify and maintain satellite health, reconfigure and command the spacecraft,
detect, identify and resolve anomalies and perform launch and early orbit operations.
The very first chatbot, ELIZA was created in 1966, and also marked a new era of Artificial Intelligence
Systems. Said systems answer users’ questions in the most diverse domains, interpreting
the human language input and responding in the same manner. Nowadays, these systems are
everywhere, and the list of possible applications seems endless.
The goal of the present master’s dissertation is to develop a prototype of a chatbot for mission
operations. For this purpose implementing a Natural Language Processing (NLP) model for satellite
missions allied to a dialogue flow model. The performance of the conversational assistant is
evaluated with its implementation on a mission operated by the European Space Agency (ESA),
implying the generation of the spacecraft’s Database Knowledge Graph (KG).
Throughout the years, many tools have been developed and added to the systems used to monitor
and control spacecrafts helping Flight Control Teams (FCT) either by maintaining a comprehensive
overview of the spacecraft’s status and health, speeding up failure investigation, or allowing to easily
correlate time series of telemetry data. However, despite all the advances made which facilitate the
daily tasks, the teams still need to navigate through thousands of parameters and events spanning
years of data, using purposely built user interfaces and relying on filters and time series plots.
The solution presented in this dissertation and proposed by VisionSpace Technologies focuses on
improving operational efficiency whilst dealing with the mission’s complex and extensive databases.O primeiro satélite artificial, Sputnik, foi lançado em 1957 e marcou o início de uma nova era. Simultaneamente, surgiram as operações de missão de satélites. Estas iniciam com o lançamento e terminam com desmantelamento do veículo espacial, que marca o fim da missão. A operação de satélites exige o acompanhamento e controlo de dados de telemetria, com o intuito de verificar e manter a saúde do satélite, reconfigurar e comandar o veículo, detetar, identificar e resolver anomalias e realizar o lançamento e as operações iniciais do satélite. Em 1966, o primeiro Chatbot foi criado, ELIZA, e também marcou uma nova era, de sistemas dotados de Inteligência Artificial. Tais sistemas respondem a perguntas nos mais diversos domínios, para tal interpretando linguagem humana e repondendo de forma similar. Hoje em dia, é muito comum encontrar estes sistemas e a lista de aplicações possíveis parece infindável. O objetivo da presente dissertação de mestrado consiste em desenvolver o protótipo de um Chatbot para operação de satélites. Para este proposito, criando um modelo de Processamento de Linguagem Natural (NLP) aplicado a missoões de satélites aliado a um modelo de fluxo de diálogo. O desempenho do assistente conversacional será avaliado com a sua implementação numa missão operada pela Agência Espacial Europeia (ESA), o que implica a elaboração do grafico de conhecimentos associado à base de dados da missão. Ao longo dos anos, várias ferramentas foram desenvolvidas e adicionadas aos sistemas que acompanham e controlam veículos espaciais, que colaboram com as equipas de controlo de missão, mantendo uma visão abrangente sobre a condição do satélite, acelerando a investigação de falhas, ou permitindo correlacionar séries temporais de dados de telemetria. No entanto, apesar de todos os progressos que facilitam as tarefas diárias, as equipas ainda necessitam de navegar por milhares de parametros e eventos que abrangem vários anos de recolha de dados, usando interfaces para esse fim e dependendo da utilização de filtros e gráficos de series temporais. A solução apresentada nesta dissertação e proposta pela VisionSpace Technologies tem como foco melhorar a eficiência operacional lidando simultaneamente com as suas complexas e extensas bases de dados.
27
Mendes, Filipe Eduardo Fonseca Ramos Tinoco. "Human Assistance Dashboard." Master's thesis, 2019. http://hdl.handle.net/10316/86796.
Abstract:
Dissertação de Mestrado em Engenharia Informática apresentada à Faculdade de Ciências e TecnologiaA assistência humana tem sido fundamental para os serviços de suporte a clientes. Contudo, o aparecimento de chatbots trouxe uma nova forma de alcançar casos de uso que antes eram cumpridos por humanos. Estes agentes virtuais ainda não são 100% assertivos, sendo insuficientes na maior parte das tarefas mais complexas.O WIT Bot Engine é uma plataforma para criar, desenhar e lançar bots em canais de conversação, como o Facebook Messenger, vivendo lado a lado com todos os outros contactos e são capazes de atuar de diferentes formas, incluindo serviço de suporte a cliente. Ainda assim, este produto não providencia planos de salvaguarda para situações em que os bots não são capazes de resolver. Dado que os bots ainda não são capazes de ocupar o lugar dos agentes humanos nesta matéria, a combinação da versatilidade dos chatbots e da experiência dos agentes humanos pode ser a resposta para estes sistemas de assistência a clientes. O módulo da Dashboard de Assistência Humana está completamente integrado na restante plataforma que disponibiliza um largo espectro de formas para o agente humano intervir nas conversas em que os bots não conseguem satisfazer.Este novo módulo, o resultado deste estágio, torna a plataforma WIT Bot Engine numa solução híbrida, composta por agentes humanos e virtuais e disponibilizando formas para os seus utilizadores assistirem os seus bots.
Human assistance has been essential for customer support services. The arising of chatbots, however, brought a new way to accomplish use-cases that before have been satisfied by humans. These virtual agents are not 100% accurate yet, being insufficient in most of the more complex and not trivial tasks.WIT Bot Engine is a platform to create, build and deploy bots in communication channels, like Facebook Messenger, living side-by-side with every other contact and being able to perform plentiful tasks, including customer support. Still, WIT Bot Engine does not have safeguard measures to situations that bots are not able to solve.Since bots are not entirely able to take the human’s place in this subject yet, the combination of the versatility of chatbots and the expertise of human agents can be the answer to recent customer support services. The Human Assistance Dashboard is a fully integrated module of WIT Bot Engine platform that enables an extensive set of ways for the intervention of human agents in conversations which bots fail to satisfy.This new module, the result of this internship, turns WIT Bot Engine platform into a hybrid solution, composed by virtual and human agents and enabling ways for businesses to assist their bots.
28
Díaz, Herrera Juan Camilo. "Conversational AI Assistant Using Artificial Neural Networks: Implementation of a contextual chatbot framework in a Point-of-Sale system." Master's thesis, 2021. http://hdl.handle.net/10362/127803.
Abstract:
Internship Report presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Business AnalyticsArtificial intelligence is changing the way how businesses are affronting their day-to-day difficulties. Chatbots are the perfect demonstration of how simple tasks and queries such as customer support or sales metrics and reporting could be solved without human intervention. This project introduced a task-oriented chatbot framework for Spanish language in a Point-Of-Sale webpage. We applied Natural Language Processing (NLP) techniques such as NER and evaluated two supervised learning methods: (i) an Artificial Neural Network (ANN) and (ii) a Support Vector Machines (SVM) model to create a contextualized chatbot that classifies the user’s intention in a text conversation, allowing bidirectional human-to-machine communication. These intents could go from simple chitchatting to detailed reports, always providing a natural flow in conversation. The results using an augmented and balanced corpus suggested that ANN model performed statistically better than SVM. Additionally, a real-word scenario with a small-talk survey made to five users gave positive feedback about the quality of predictions. Finally, a software architecture using a PaaS computing service and an API framework was proposed to implement this dialog system in further works.
29
Buinhas, Susana dos Santos. "Assistente virtual para facilitar o autocuidado de pessoas mais velhas com diabetes tipo 2." Master's thesis, 2018. http://hdl.handle.net/10451/35514.
Abstract:
Trabalho de projecto de mestrado, Engenharia Informática (Interação e Conhecimento) Universidade de Lisboa, Faculdade de Ciências, 2018Neste projeto apresenta-se uma solução tecnológica para o autocuidado de idosos com diabetes tipo 2, na qual se encontra incluído um avatar com representação antropomórfica e dotado de inteligência artificial, que desempenha a função de assistente virtual. O objetivo é preencher uma lacuna existente na falta de acompanhamento entre consultas médicas presenciais da diabetes, respondendo às necessidades diárias do doente: i) motivando-o à prática de exercício físico com planos adaptados às suas limitações; ii) aconselhar nas suas escolhas alimentares e no planeamento de refeições; e iii) relembrar a toma da medicação receitada por profissionais de saúde. O assistente responde consoante a motivação do utilizador, felicitando-o por etapas já conquistadas e promovendo a continuação de um bom trabalho, propondo-lhe novos desafios. Este sistema está disponível para dispositivos tablet com o sistema operativo Android. O desenvolvimento da solução foi seguido da realização de testes com doentes do grupo alvo e profissionais de saúde em centros de saúde da área de Lisboa e na Escola Superior de Enfermagem de Lisboa (ESEL). Este trabalho recebeu o apoio financeiro da Fundação para a Ciência e a Tecnologia (FCT) através de dois financiamentos distintos, o da Unidade de I&D BioISI - Biosystems & Integrative Sciences Institute (referência UID/MULTI/04046/2013) e o do projeto VASelfCare, projeto nº 024250. Neste projeto, liderado pela ESEL, trabalha uma equipa multidisciplinar composta por investigadores da própria ESEL, da Faculdade de Farmácia da Universidade de Lisboa (FFUL), da Faculdade de Ciências da Universidade de Lisboa (FCUL) e da Escola Superior de Desporto de Rio Maior (ESDRM) do Instituto Politécnico de Santarém.
This project presents a technological solution for the selfcare of elderly people with type 2 diabetes, in which an avatar with an anthropomorphic representation and artificial intelligence are incorporated. The main goal is to fill a gap in the lack of follow-up between face-to-face diabetes medical appointments, responding to the patient's daily needs by: i) motivating him/her to practice physical activity, with plans adapted to his/her limitations; ii) advising on his/her food choices and meal planning; and iii) reminding him/her to take the medication prescribed by health professionals. The assistant will respond according to the users’ motivation, congratulating him/her on the steps already taken and promoting the continuation of a ‘good job’ by proposing new challenges. This system is available for tablet devices. The development of the solution has been followed by tests with real patients of the target group and health professionals in health centers in the Lisbon area and in Escola Superior de Enfermagem de Lisboa (ESEL). This project received financial support from the Fundação para a Ciência e a Tecnologia (FCT), sponsored by two different funding, one from Unidade de I&D BioISI - Biosystems & Integrative Sciences Institute (reference UID/MULTI/04046/2013), and the other from VASelfCare project, no. 024250. It is led by ESEL, and involves a multidisciplinary team composed by researchers from ESEL, from Faculdade de Farmácia da Universidade de Lisboa (FFUL), from Faculdade de Ciências da Universidade de Lisboa (FCUL), and from Escola Superior de Desporto de Rio Maior (ESDRM) of Instituto Politécnico de Santarém.
30
Santos, Catarina Betencourt da Costa Rodrigues dos. "Impact of the virtual assistant's interactive dimensions in the Portuguese young adults' customer experience expectations and patronage intentions, in the retail context." Master's thesis, 2020. http://hdl.handle.net/10071/21862.
Abstract:
Throughout the times it has been witnessed a continuous evolution in the way people make
business transactions, across sectors. This has been highly influenced by technological
developments and the constant need for companies to adjust to their clients’ needs and
expectations. The retail sector has been no exception, evolving alongside innovation, and
adapting to new trends. One of its results is the emergence of conversational commerce, a new
form of commerce that combines the trend of communicating via instant messages and the use
of artificial intelligence, introducing virtual assistants to the retail context.
The aim of this study is to better understand the potentialities virtual assistants have in the
Portuguese retail context, amongst young adults. By identifying which of the dimensions of the
interaction with a retailer virtual assistant - "Cognitive Perception, Affective Engagement, and
Communication Quality" - have a significant impact on the expectation users create towards their
customer experience and how this is determinant to their patronage intentions towards the
retailer. A quantitative methodology was used to perform this investigation, with the
development of an introductory chatbot and an online survey, completed by 385 individuals
(Portuguese young adults, with ages ranging from 18 to 35, and that had access to the Facebook
Messenger app).
The Customer Experience Expectation was proven to have a significant impact on the
respondent' patronage intentions towards the virtual assistant and the retailer. However, only
the cognitive dimension of the virtual assistant was confirmed to significantly impact the
expectations on the customer experienceAo longo dos tempos, tem-se vindo a testemunhar uma evolução na forma como o comércio é feito nos vários setores de atividade. As empresas têm de se reinventar constantemente para satisfazer as necessidades e expectativas dos consumidores, que resultam dos avanços tecnológicos. O mesmo acontece no setor do Retalho, que tem vindo a inovar, acompanhando a tecnologia e as tendências dos consumidores. Um exemplo disto é o aparecimento da uma nova forma de comércio, o comércio conversacional. Este combina a tendência de comunicação via mensagens instantâneas com o desenvolvimento da inteligência artificial, introduzindo assistentes virtuais neste setor. O principal objetivo deste estudo prende-se com a investigação do impacto que a inclusão de um assistente virtual teria no setor do retalho interagindo com os jovens adultos portugueses. Para tal, procurou identificar-se quais as dimensões da interação com um assistente virtual - cognitiva, afetiva e comunicativa - que influenciariam as expectativas relativas à experiência de compra e consequentemente as intenções de uso e compra dos consumidores. Para a investigação foi utilizada uma metodologia quantitativa, com a criação de um "chatbot" informativo e de um questionário "online", ao qual responderam 385 portugueses com idades desde os 18 até aos 35 anos, com acesso ao Facebook Messenger. Neste estudo foi provado que as expectativas dos consumidores em relação à experiência de compra influenciam as suas intenções de uso (assistente virtual) e compra (retalhista). No entanto, apenas a dimensão cognitiva mostrou ter um impacto significativo na criação de expectativas relativas à experiência de compra.