Google DialogFlow Research Articles

The "Flapbot": A Global Perspective on the Validity and Usability of a Flap Monitoring Chatbot.

The Flapbot chatbot assists in free-flap monitoring, emphasizing accessibility, user-friendliness, and global reliability. This study assesses Flapbot's worldwide validity and usability and uses qualitative analysis to identify areas for future enhancement. Flapbot, built on Google's DialogFlow, was evaluated by international plastic surgeons. Invitations were sent to the International Lower Limb Reconstruction Collaborative (INTELLECT), International Confederation of Plastic Surgery Societies (ICOPLAST), and the International Microsurgery Club. Out of the 42 surgeons who agreed to participate, 21 tested the Flapbot and completed an online survey on its validity and usability. The survey had 13 validity items and 10 usability items. Data analysis involved computing the individual content validity index (I-CVI) and scale-wide content validity index (S-CVI) for validity, and the system usability score (SUS) for usability. Thematic analysis distilled free-text responses to identify key themes. Nine of 13 items had an I-CVI over 0.78, denoting significant relevance. The S-CVI score stood at 0.82, indicating high relevance. The SUS score was 68, representing average usability. Themes highlighted issues with the current model, development suggestions, and surgeons' concerns regarding growing reliance on digital tools in health care. Flapbot is a promising digital aid for free-flap monitoring. While it showcases notable validity and usability, improvements in functionality, usability, and accessibility are needed for broader global use.

Implementing a google dialogflow chatbot for restaurant websites - A serverless approach with fastAPI

Implementing a google dialogflow chatbot for restaurant websites - A serverless approach with fastAPI

Implementation of Engagement Detection for Human-Robot Interaction in Complex Environments.

This study develops a comprehensive robotic system, termed the robot cognitive system, for complex environments, integrating three models: the engagement model, the intention model, and the human-robot interaction (HRI) model. The system aims to enhance the naturalness and comfort of HRI by enabling robots to detect human behaviors, intentions, and emotions accurately. A novel dual-arm-hand mobile robot, Mobi, was designed to demonstrate the system's efficacy. The engagement model utilizes eye gaze, head pose, and action recognition to determine the suitable moment for interaction initiation, addressing potential eye contact anxiety. The intention model employs sentiment analysis and emotion classification to infer the interactor's intentions. The HRI model, integrated with Google Dialogflow, facilitates appropriate robot responses based on user feedback. The system's performance was validated in a retail environment scenario, demonstrating its potential to improve the user experience in HRIs.

Comparative Analysis of Artificial Intelligence Virtual Assistant and Large Language Models in Post-Operative Care.

In postoperative care, patient education and follow-up are pivotal for enhancing the quality of care and satisfaction. Artificial intelligence virtual assistants (AIVA) and large language models (LLMs) like Google BARD and ChatGPT-4 offer avenues for addressing patient queries using natural language processing (NLP) techniques. However, the accuracy and appropriateness of the information vary across these platforms, necessitating a comparative study to evaluate their efficacy in this domain. We conducted a study comparing AIVA (using Google Dialogflow) with ChatGPT-4 and Google BARD, assessing the accuracy, knowledge gap, and response appropriateness. AIVA demonstrated superior performance, with significantly higher accuracy (mean: 0.9) and lower knowledge gap (mean: 0.1) compared to BARD and ChatGPT-4. Additionally, AIVA's responses received higher Likert scores for appropriateness. Our findings suggest that specialized AI tools like AIVA are more effective in delivering precise and contextually relevant information for postoperative care compared to general-purpose LLMs. While ChatGPT-4 shows promise, its performance varies, particularly in verbal interactions. This underscores the importance of tailored AI solutions in healthcare, where accuracy and clarity are paramount. Our study highlights the necessity for further research and the development of customized AI solutions to address specific medical contexts and improve patient outcomes.

Baristax: The Coffee Selection Recommender Bot

This study aims to develop a prototype of a coffee recommender bot that uses the expert's knowledge to give its users a standardised suggestion based on their preferences. This prototype is integrated with Telegram Bot for more accessible and convenient use, as Telegram is safer than any other online communication platform. Furthermore, it uses Google DialogFlow with Natural Language Processing (NLP) tools that enable the chatbot to identify what the users want. Finally, the project is validated on students, mainly from the UiTM Shah Alam campus and a barista, to determine the usefulness and correctness of the prototype chatbot's overall performance. This initiative received evaluations from 45 students and ten baristas. The research intends to be integrated into the company's mobile application, allowing for other functionalities. As a result, coffee enthusiasts may now have customised applications to satisfy their coffee addiction.

Enhancing User Experience: A Study on Dialogflow Chatbot Implementation

In recent years, chatbots have become essential for customer service, task automation, and information dissemination. Google's Dialogflow platform offers intuitive tools for building conversational agents. This paper provides an overview of developing smart chatbots with Dialogflow, emphasizing natural language understanding. It covers Dialogflow's architecture, including intents, entities, and fulfillment, and discusses training techniques for chatbot optimization. Additionally, it explores advanced features like external service integration and multilingual support. Overall, it serves as a practical guide for developers and organizations interested in leveraging Dialogflow to create personalized chatbot experiences. Keywords : User input, Conversation flow, Dialog management, User experience (UX)

Development of a natural language chatbot interface for website users

Today, there are a variety of technology solutions for creating chatbots, including universal platforms such as Google's Dialogflow, Microsoft's Azure Bot Service, and IBM's Watson Assistant, as well as chatbot builders such as ActiveChat, SendPulse, and BotPress. The disadvantage of the considered platforms and designers is the limitation of the free plan. This study considered the development and integration of an informative chatbot into the department's website in order to create a virtual assistant for potential applicants and applicants. The relevance of the study is due to the modern conditions of admission, limited opportunities to conduct career guidance events in connection with the consequences of the COVID 19 pandemic and the war on the territory of Ukraine. The object of research is a system of informing website users using natural language. A software product has been developed, which is an information system for applicants. The dynamic JavaScript programming language combined with the Node.js code execution environment and the Telegraf library was chosen to create the chatbot. The Heroku cloud platform with an integrated Heroku PostgreSQL database became the server for the operation of the chatbot. The system is implemented using the @BotFather Telegram service, which makes it possible to integrate it into any web resource. The stages of chatbot development are highlighted with examples of information, linguistic, and technical support. An analysis of the compliance of the developed chatbot with regard to the criteria of informativeness, multimodality, emotionality, productivity, and interactivity was carried out. The structure of the information content of the chatbot, which includes a set of modules, has been developed. A test version of the chatbot has been designed, tested, and integrated into the website of the Department of Applied Linguistics, which will continue to be tested and improved in 2023–2024. Practical significance: the structure of information content and the method of developing a chatbot could be used to develop authentic systems for informing applicants in institutions of higher education

KIA-CHAT: A QnA Chatbot for Postnatal and Newborn Care

Background: Postnatal care information is relatively less provided than information about prenatal or pregnancy. Several causes of this is the mothers already delivered the baby safely, and soon after the baby's birth, mothers will be busy taking care of the newborns. They frequently miss their postnatal meeting with doctors because of these reasons. Aims: Therefore, this article aims to develop a chatbot in which the knowledge is taken from Buku KIA and focus group discussion. Method: The targeted users of the KIA chatbot are postpartum mothers with live newborns. Rapid Application Development method is used to develop the KIA chatbot. The KIA chatbot is constructed using Google Dialog Flow with Telegram-based messenger. Results: The chatbot evaluation follows the Chatbot Usability Questionnaire with an overall score is 84.23 out of 100. Sixty-nine respondents confess that the KIA chatbot is easy to use and the knowledge is easy to comprehend. But, since the chatbot provides the answer options, the users feel some limitations. One of the limitations is they are unable to type their questions to the chatbot; only type the numerical order of the answer options. Conclusion: However, this limitation also brings another advantage to the mothers who have no time to type because of busy taking care of the newborns.

Artificial Intelligence-Based Chatbots to Combat COVID-19 Pandemic: A Scoping Review

Context: Artificial intelligence (AI) Chatbots are computer programs that simulate human conversation and use artificial intelligence, including machine learning and natural language processing, to interact with users via natural language. With the outbreak of the COVID-19 pandemic, the use of digital health technologies such as chatbots has accelerated. Objectives: This study aims to investigate the application of AI chatbots in combating the COVID-19 pandemic and explore their features. Methods: We reviewed the literature on health chatbots during the COVID-19 pandemic. PubMed, Scopus, Web of Science, and Google Scholar were searched using relevant keywords such as “chatbot”, “conversational agent,” and “artificial intelligence”. To select the relevant articles, we conducted title, abstract, and full-text screening based on inclusion and exclusion criteria. Chatbots, their applications, and design features were extracted from the selected articles. Results: Out of 673 articles initially identified, 17 articles were eligible for inclusion. We categorized the selected AI chatbots based on their roles, applications, and design characteristics. Around 70% of chatbots were designed to play a preventive role. Our review identified 8 key applications of the AI chatbots during the COVID-19 pandemic, which include (1) information dissemination and education, (2) self-assessment and screening, (3) connecting to health centers, (4) combating misinformation and fake news, (5) patient tracking and service delivery (6) mental health (7) monitoring exposure (8) vaccine information and scheduling. AI chatbots were deployed on various platforms, including mobile apps, web, and social media. Mobile-based chatbots were the most frequent. All chatbots used Natural Language Understanding (NLU) methods to understand natural language input and act on the user’s request. More than 50% of AI chatbots used NLU platforms, including Google Dialogflow, Rasa framework, and IBM Watson. Conclusions: AI chatbots can play an effective role in combating the COVID-19 pandemic. Increasing people’s awareness, optimizing the use of health resources, and reducing unnecessary encounters are some of the advantages of using AI chatbots during the COVID-19 outbreak. Using NLU platforms can be a suitable solution for developing AI chatbots in the healthcare domain. With advancements in the field of artificial intelligence, it seems that AI chatbots will have a promising future in healthcare, particularly in public health, chronic disease management, and mental health.

Streamlining Medical Services: A Virtual Chatbot for Stomach- related Illnesses

The stomach is an important part of the digestive system as it stores and breaks down food for the body's energy. In Indonesia, some people engage in dense work activities but eat late, which can lead to stomach problems. The younger generation often consumes high-fat and junk foods, increasing their risk of stomach-related. Raising public awareness through social media platforms about the various stomach illnesses, including symptoms, risks, and treatments, is important. To achieve this, a chatbot called "A.L.T.H.A" has been proposed to provide information on diseases related to the stomach, utilizing Google Dialogflow and third-party applications, it’s programmed to understand different intents, actions, parameters, and entities, and respond appropriately to user queries. The chatbot was tested on 10 end-users and successfully provided relevant information on different stomach-related issues, including welcome, fallback, main, also closing intents.

Revolutionizing Journal Publishing: Unleashing The Power Of Web-Based Chatbot Development With Dialogflow And Natural Language Processing

The chatbot is a manifestation of Artificial Intelligence that can replace humans in engaging in conversational interactions and providing information services to users or visitors. Chatbots generally interact through text messages, voice, images, and other mediums. In this study, a web-based chatbot application was developed for a journal website called the Journal of Multidisciplinary Issues, aiming to relieve site administrators from having to repeatedly answer the same visitor questions. The development of the chatbot application followed the Rapid Application Development method, involving several stages including planning, design, system development, implementation, and testing. The application was built using Google Dialogflow services, employing Natural Language Processing techniques, along with the integration feature called Dialogflow Messenger, which offers a wide range of response options for journal websites utilizing Open Journal Systems. The chatbot application was evaluated using Alpha and Closed Beta Testing methodologies, which yielded promising results. The chatbot demonstrated the ability to provide appropriate responses after being tested with various question scenarios, achieving a score of 85.25% in the questionnaire-based assessment, which aimed to gauge visitor perspectives on the developed chatbot application. Future research endeavors should focus on integrating the chatbot with popular social media platforms such as Facebook, WhatsApp, or LINE.

How people interact with a chatbot against disinformation and fake news in COVID-19 in Brazil: The CoronaAI case

BackgroundThe search for valid information was one of the main challenges encountered during the COVID-19 pandemic, which resulted in the development of several online alternatives. ObjectivesTo describe the development of a computational solution to interact with users of different levels of digital literacy on topics related to COVID-19 and to map the correlations between user behavior and events and news that occurred throughout the pandemic. MethodCoronaAI, a chatbot based on Google's Dialogflow technology, was developed at a public university in Brazil and made available on WhatsApp. The dataset with users’ interactions with the chatbot comprises approximately 7,000 hits recorded throughout eleven months of CoronaAI usage. ResultsCoronaAI was widely accessed by users in search of valuable and updated information on COVID-19, including checking the veracity of possible fake news about the spread of cases, deaths, symptoms, tests and protocols, among others. The mapping of users' behavior revealed that as the number of cases and deaths increased and as COVID-19 became closer, users showed a greater need for information applicable to self-care compared to following the statistical data. In addition, they showed that the constant updating of this technology may contribute to public health by enhancing general information on the pandemic and at the individual level by clarifying specific doubts about COVID-19. ConclusionOur findings reinforce the potential usefulness of chatbot technology to resolve a wide spectrum of citizens' doubts about COVID-19, acting as a cost-effective tool against the parallel pandemic of misinformation and fake news.

AI-powered Digital Transformation: Tools, Benefits and Challenges for Marketers – Case Study of LPP

The article aims to show the role (benefits and challenges) of AI-powered digital marketing tools for marketers in the age of digital transformation. The considerations were related to the Polish market and a case study of LPP, a Polish clothing retailer. The starting point for this study was the analysis of the literature on the concept of artificial intelligence (AI) with reference to digital marketing. In the next steps, the results of the research on the Polish market conducted by the Digital Poland Foundation and presented in the report entitled “State of Polish AI 2021” were reviewed, and an application case study of the largest Polish clothing company – LPP – was conducted. The study is of an introductory and exploratory nature. It recognises the significant role of AI in digital transformation in the context of digital marketing in the Polish market. The implementation of solutions based on artificial intelligence algorithms, such as the Google Cloud, analytical platform and data repository, e-commerce infrastructure, chatbot, Genesys PureCloud, Google Dialogflow and the AI-based function in the PSIwms Warehouse Management System in LPP's distribution centre significantly improves the efficiency of online order processing without compromising the quality of products and order fulfilment time. By applying a case study analysis, the importance of AI-based tools in the digital transformation process, including digital marketing, in the Polish market was demonstrated. Marketers, including CMOs, were shown the benefits of applying AI-related technological solutions in the field of e-commerce optimisation and customer service.

Framework for A Foreign Language Teaching Software for Children Utilizing AR, Voicebots and ChatGPT (Large Language Models)

The cognitive capabilities of children develop during the early years of their life. Research shows that learning a foreign language helps develop cognitive skills. Moreover, learning a foreign language has become essential and an increasing number of parents would like their kids to start learning a foreign language at an early age. However, engaging little kids with learning activities is challenging. In this study, we propose a framework for developing a language learning software tool utilizing Augmented Reality (AR), Voicebots, and ChatGPT (an AI utilizing the Large Language Model) technologies to provide a unique product for small kids to teach a foreign language. With AR and Voicebots, the product will grab attention, motivate and provide an entertaining learning environment. The capabilities of ChatGPT will be utilized to efficiently prepare the content for the software tool. We utilize the capabilities of ChatGPT to generate interactive dialogs that will be hosted at Google DialogFlow. We believe the framework and the design principles we propose in this study can be a blueprint for developing highly effective foreign language teaching software.

The Use of Conversational Natural Language Processing Chatbots For Simulated Intelligence in Home Cooking While Integrating with Meta Messenger

Abstract: Conversational Man-made consciousness (computer based intelligence), which permits individuals to have human-like collaborations with PCs, has encountered a blast lately. A large number of fields, for example, medical care, money, and retail have applied conversational simulated intelligence in their sites to save endeavors of getting done with simple jobs and give voice collaboration with end-clients. It empowers clients to find speedy solutions to every now and again got clarification on pressing issues and specialist co-ops to save time to handle more perplexing issues. This paper presents the Natural Language Processing Chatbots Cooking Assistance, which is a conversational specialist that gives matching recipes in view of the data given by clients. The expectation of Natural Language Processing Chatbots Cooking Assistance is to assist clients with disposing of unused fixings in the refrigerator by giving related recipes. Natural Language Processing Chatbots Cooking Assistance permits clients to enter a particular dish name or give a district, type, or potentially elements of the food they might want to have, and afterward it returns a recipe list as indicated by arranging and supplements prerequisites given by clients. The chatbot is assembled utilizing Google Dialog Flow stage to perceive the client's expectations and Spoonacular Programming interface to track down recipes that match the pursuit question. This paper talks about Natural Language Processing Chatbots Cooking Assistance's engineering, usefulness, and insufficiencies to be moved along. It gives a definite illustration of the communication between the chatbot and a client, which illustrates how the UI will work on the issue of finding a user interested recipe.

A comparison of chatbot platforms with the state-of-the-art sentence BERT for answering online student FAQs

Online learning enables academic institutions to accommodate increased student numbers at scale. With this scale comes high demands on support staff for help in dealing with general questions relating to qualifications and registration. Chatbots that implement Frequently Asked Questions (FAQs) can be a valuable part in this support process. A chatbot can provide constant availability in answering common questions, allowing support staff to engage on higher value one-to-one communication with prospective students. A variety of approaches can be used to create these chatbots including vertical platforms, frameworks, and direct model implementation. A comparative analysis is required to establish which approach provides the most accuracy for an existing, available dataset.This paper compares intent classification results of two popular chatbot frameworks to a state-of-the-art Sentence BERT (SBERT) model that can be used to build a robust chatbot. A methodology is outlined which includes the preparation of a university FAQ dataset into a chatbot friendly format for upload and training of each implementation. Results obtained from the framework-based implementations are generated using their published Application Programming Interfaces (APIs). This enables intent classification using testing phrases and finally comparison of F1 scores.Using ten intents comprising 284 training phrases and 85 testing phrases it was found that a SBERT model outperformed all others with an F1-score of 0.99. Initial comparison with the literature suggests that the F1-scores obtained for Google Dialogflow (0.96) and Microsoft QnA Maker (0.95) are very similar to other benchmarking exercises where NLU (Natural Language Understanding) has been compared.

Chatbot-based Culinary Tourism Recommender System Using Named Entity Recognition

Over the time, culinary tourism in several cities of Indonesia is growing rapidly, one example is culinary tourism in Bandung city. This makes it difficult for tourists to decide their choice. To overcome these problems, a recommendation system is needed. Thus, in this study we developed a chatbot-based conversational recommendation system to assist users in finding culinary tourism recommendations. The chatbot was built using Google Dialogflow platform and uses methods in Natural Language Processing, namely Named Entity Recognition. Named Entity Recognition was used to extract entities from user’s input, such as usernames and culinary preferences. To find culinary recommendations, TF-IDF and cosine similarity was used to find similarities between each culinary based on reviews, telegram was used as a medium to implement the chatbot that has been built. The chatbot has a good performance in providing culinary recommendations, it can be seen from the score obtained from usability testing on the recommendation aspect, which is 85.7%.

ICSA: Intelligent chatbot security assistant using Text-CNN and multi-phase real-time defense against SNS phishing attacks

SNS phishing attack is one of the representative social engineering attacks exploiting humans’ emotions and trust and thus usually proceeds in multi-phases such that the attacker first forms an intimate bond with victims emotionally and then forces victims to conduct serious actions according to the attacker’s malicious intents. Meanwhile, according to our extensive survey, we observed that existing works on defending against SNS phishing attacks are inefficient in that they detect the attack mostly in the final stage of the attack or after the incident is reported. This is mainly because they neglect the characteristics of SNS phishing attacks following social engineering attack cycles. By this motivation, we first formalize SNS phishing attack phases based on the existing social engineering attack cycles and propose an Intelligent Chatbot Security Assistant (ICSA) that detects the progress phase of an SNS phishing attack by using Text-CNN-based attack phase classifiers and AI Chatbot technology. ICSA provides appropriate suggestions to victims and conducts necessary actions according to pre-defined defense produces designed by security experts. In addition, we implement ICSA as Telegram Chatbot by using Google Dialogflow and AWS (Amazon Web Services) server in the Telegram messenger. To validate our idea, we conduct extensive experiments to show our Telegram Chatbot works properly in real-time according to its design purpose and also we compare two representative ML models (Text-CNN and LSTM) in terms of the training and test accuracy to show why we choose the Text-CNN model to generate attack phase classifiers.

Survey of designing tools for chatbot application

The invention of chatbot brought us to the new era of technology. As Artificial Intelligence continues to gain traction in modern customer service, chatbots are becoming an integrated part of user experience. A chatbot has the capability to study and influence user behavior by asking and answering user’s questions. Chatbots help with human- computer interaction and address customers’ queries instantly, without the need for a support agent. Now a days there are many tools available for designing and deploying the chatbot such as Google dialogflow, Amazon Lex, Microsoft bot, Facebook Wit.AI, RASA, IBM Watson, Botpress, Botkit, Botsify, Pandorabots, MobileMonkey, SAP Conversational AI, CoRover, Chatfuel and many more. This paper represents the different types of tools used for developing chatbot.

Chatbot integration with Google Dialogflow environment for conversational intervention

Chatbots are computer programs that execute protocols for supporting human-machine conversations and perform various functions such as searching the web, ordering food, making appointments, and many more. To facilitate timely responses and actions, and enable interactive human-like conversations, chatbots require Natural Language Processing (NLP) to understand user's messages and respond appropriately. NLP is an area of computer science and artificial intelligence concerned with the interactions between computers and human languages. Google Dialogflow is a natural language understanding platform that makes it easy to design and integrate a conversational user interface into your mobile app, web application, device, bot, interactive voice response system, and so on. Dash Messaging is a smart chatbot platform that enables creation of chatbots based on the provided protocol for long-term conversations. In this paper, we discuss how to integrate Google Dialogflow NLP service to a case study chatbot launched with our Dash Messaging platform.