La gestion et la selection des informations pertinentes pour un tour de parole donne restent un probleme pour les systemes de dialogue a domaine ouvert. Pour ces derniers, les interactions possibles entre un utilisateur et un agent sont a priori infinies et indefinies. La possibilite d'une reponse erronee de l'agent a l'utilisateur demeure donc elevee. Pour les systemes orientes-but, le probleme est considere comme resolu, mais d'apres notre experience aucun systeme ne montre une robustesse remarquable lorsqu'il est evalue en situation reelle. Dans cet article, nous dressons un etat de l'art des methodes d'apprentissage de l'agent et des differents modeles d'agent conversationnel. Selon nous, l'une des pistes d'amelioration de l'agent reside dans sa memoire, car cette derniere (souvent representee par le triplet : tour de parole courant, historique du dialogue et base de connaissances) n'est pas encore modelisee avec assez de precision. En dotant l'agent d'un modele de memoire d'inspiration cognitive, nous pensons pouvoir augmenter les performances d'un systeme de dialogue oriente-but en situation reelle, par l'emploi d'algorithmes d'apprentissage automatique avec une approche antagoniste en support d'un nouveau modele de memoire pour l'agent. ABSTRACT Goal-oriented dialog systems : a recent overview and research prospects Determining which information is relevant for a given dialog turn is still a problem for open-domain dialog systems since the interaction between a user and the system is a priori infinite and indefinite. Thus, the possibility for error remains high for the dialog system. Although the problem is considered solved, to our experience, no system has shown outstanding performance when confronted to "real-world" situation. We review the state-of-the-art of machine learning approaches used for dialog system development and present the various models of agent architecture. We claim that one of the main directions for improvement is the agent architecture. Often the agent's memory (represented by the triple : dialog turn, dialogue history and knowledge base) is not modeled accurately enough. Thus we decided to investigate more cognitive oriented models of memory. We hypothesize that combining machine learning approaches in an adversarial setup with a new memory model for the agent would result in improved performances for goal-oriented dialog systems. MOTS-CLES : systemes de dialogue, apprentissage par renforcement, modele de memoire, appren-tissage par antagonisme, systemes orientes-buts.

https://hal.archives-ouvertes.fr/hal-02180287/document

Les systèmes de dialogue orientés-but : état de l'art et perspectives d'amélioration

AI-Powered Health Chatbots: Toward a general architecture

This work exploits the potential of two important technologies which are UAVs (Unmanned Aerial Vehicles) and blockchain in the context of Agriculture 4.0. We propose a cattle health monitoring system based on UAVs that collect health measures from IoT devices equipping the animals. The main objectives of our system are twofold. First, the consumer will be aware of the quality of his/her food. Second, the national ecosystem (e.g. agriculture ministry, trade ministry) will get useful information about the quality and the number of cattle that can be put on the market. Thus, smart cattle management strategies could be undertaken afterward. The involved entities in such a system are multiple: the farmer, the veterinaries, the ministry of agriculture, etc… We first start by studying the system’s security by applying the FMEA risk assessment methodology. Our findings motivate us to integrate blockchain technology to manage the data collected as well as the attribution of the UAVs missions via a marketplace. Thanks to its properties, this technology ensures the transparent tracking of cattle status and fairness in the payment of the UAVs managed by private operators. Finally, we develop a proof of concept using the Sui blockchain platform.

Veterinary Drone: Blockchain-Based System for Cattle Health Monitoring

As the world moves forward, the restaurant industry is rapidly expanding. Customers may never physically evaluate a restaurant based on its services until that customer has practical experience with it. A better recommendation mechanism can always direct the customer to the correct location, resulting in a positive outcome. The paper discusses an approach of a context rich chatbot that can identify the customer’s mode of thinking using a restaurant ontology that suggests relevant restaurants and foods. Most importantly the defined methodology will use a hybrid version of knowledge bases along with a two-way bind to the primary knowledge base. The chatbot will proceed to find relationships in the ontology by tracing concept definitions and properties while feeding information from the database. The main components related to the proposed system are Natural Language Understanding (NLU) pipeline, dialog management module, action server, knowledge query module, and data repository (MongoDB). This mechanism was evaluated through information retrieval measures.

Ontology Based Restaurant Recommendation Approach

Technology has been increased in massive part of today's healthcare scenario. The advancement and improvement of information and communication technologies had led to increase the usage of chatbots in almost all the healthcare sectors. And the technology has changed the way of communication between the patients and doctors in medical sectors. Nowadays, chatbots were used for computer medical communication in order replace the human agents due to high efficiency and cost effectiveness. Artificial Intelligence (AI) and Chatbots are the two base breaking technologies that have changed the patients and doctors perceive in healthcare. In the field of healthcare sector, the use of AI (Artificial Intelligence) has been explored for automating the applications and appointments for public users. A WhatsApp chatbot is program which can reply to messages automatically on WhatsApp. In this paper, to make the healthcare system more effective, and interactive a diagnostic chatbot is designed and developed using machine learning algorithms, to help the public users in booking, cancelling, and rescheduling the Doctor's appointment based on their timings. This proposed work is used to employ an artificial chatbot, to do a live chat with a patient and users regarding to the medical appointment with the concerned doctors. This application can well be extended from B2B to a B2C utilization, where service providers like doctors, ayurvedic, physiotherapist, psychologist as well as therapist, dietician, nutrition, trainer can cater to specific users. Thus, the indention to more focus on Natural Language Processing (NLP) techniques to improve the chatbot conservation aspects in future studies.

Design and Development of AI-Powered Healthcare WhatsApp Chatbot

Today is the era of intelligence in machines. With the advances in Artificial Intelligence, machines have started to impersonate different human traits, a chatbot is the next big thing in the domain of conversational services. A chatbot is a virtual person who is capable to carry out a natural conversation with people. They can include skills that enable them to converse with the humans in audio, visual, or textual formats. Artificial intelligence conversational entities, also called chatbots, conversational agents, or dialogue system, are an excellent example of such machines. Obtaining the right information at the right time and place is the key to effective disaster management. The term "disaster management" encompasses both natural and human-caused disasters. To assist citizens, our project is to create a COVID Assistant to provide the need of up to date information to be available 24 hours. With the growth in the World Wide Web, it is quite intelligible that users are interested in the swift and relatedly correct information for their hunt. A chatbot can be seen as a question-and-answer system in which experts provide knowledge to solicit users. This master thesis is dedicated to discuss COVID Assistant chatbot and explain each component in detail. The design of the proposed chatbot is introduced by its seven components: Ontology, Web Scraping module, DB, State Machine, keyword Extractor, Trained chatbot, and User Interface.

An ontology-based chatbot for crises management: use case coronavirus.

Unmanned Aerial Vehicles (UAVs) and blockchain Technologies are relevant systems that have a significant performance in numerous sectors. In particular, applying these emerging technologies will affect positively the agricultural ecosystem. In this paper, we investigate the opportunities offered by UAV s and blockchain (BC) in the agricultural sector. We review recent research efforts in the subject with a synthesis illustrated by a classification table. Finally, open challenges and future directions for IoT-based agriculture applications are discussed.

Khouloud Hwerbi

Papers

An ontology-based chatbot for crises management: use case coronavirus.

A Survey on the Opportunities of Blockchain and UAVs in Agriculture

Veterinary Drone: Blockchain-Based System for Cattle Health Monitoring