Artigos de revistas sobre o tema "Chatbot dialog"
Siga este link para ver outros tipos de publicações sobre o tema: Chatbot dialog.
Crie uma referência precisa em APA, MLA, Chicago, Harvard, e outros estilos
Veja os 50 melhores artigos de revistas para estudos sobre o assunto "Chatbot dialog".
Ao lado de cada fonte na lista de referências, há um botão "Adicionar à bibliografia". Clique e geraremos automaticamente a citação bibliográfica do trabalho escolhido no estilo de citação de que você precisa: APA, MLA, Harvard, Chicago, Vancouver, etc.
Você também pode baixar o texto completo da publicação científica em formato .pdf e ler o resumo do trabalho online se estiver presente nos metadados.
Veja os artigos de revistas das mais diversas áreas científicas e compile uma bibliografia correta.
1
Le, Nhat, A. B. Siddique, Fuad Jamour, Samet Oymak e Vagelis Hristidis. "Generating Predictable and Adaptive Dialog Policies in Single- and Multi-domain Goal-oriented Dialog Systems". International Journal of Semantic Computing 15, n.º 04 (dezembro de 2021): 419–39. http://dx.doi.org/10.1142/s1793351x21400109.
Texto completo da fonteResumo:
Most existing commercial goal-oriented chatbots are diagram-based; i.e. they follow a rigid dialog flow to fill the slot values needed to achieve a user’s goal. Diagram-based chatbots are predictable, thus their adoption in commercial settings; however, their lack of flexibility may cause many users to leave the conversation before achieving their goal. On the other hand, state-of-the-art research chatbots use Reinforcement Learning (RL) to generate flexible dialog policies. However, such chatbots can be unpredictable, may violate the intended business constraints, and require large training datasets to produce a mature policy. We propose a framework that achieves a middle ground between the diagram-based and RL-based chatbots: we constrain the space of possible chatbot responses using a novel structure, the chatbot dependency graph, and use RL to dynamically select the best valid responses. Dependency graphs are directed graphs that conveniently express a chatbot’s logic by defining the dependencies among slots: all valid dialog flows are encapsulated in one dependency graph. Our experiments in both single-domain and multi-domain settings show that our framework quickly adapts to user characteristics and achieves up to 23.77% improved success rate compared to a state-of-the-art RL model.
2
Fang, Jiyang. "Analysis on Chatbot Performance based on Attention Mechanism". Highlights in Science, Engineering and Technology 39 (1 de abril de 2023): 151–56. http://dx.doi.org/10.54097/hset.v39i.6517.
Texto completo da fonteResumo:
The chatbot is a way to imitate the dialogue between people through natural language, enabling human beings to communicate with machines more naturally. The chatbot is a prevalent natural language processing task (NLP) because it has broad application prospects in real life. This is also a complex task involving many natural language processing tasks that must be studied. The chatbot is an intelligent dialogue system that can simulate human dialogue to achieve online guidance and support. The main work of this paper is to summarize the chatbot's academic background and research status and introduce the Cornell Movie-Dialogs Corpus dataset. The methods of artificial intelligence and natural language processing are outlined. Two attention mechanisms used to improve neural machine translation (NMT) are discussed. Finally, this paper tests the performance of chatbots under the influence of N_ITERATION and data scale summarizes the relevant optimization strategies and makes a prospect for the future of chatbots. The main work of this paper is to test the performance of the proposed method under different experimental Settings, including dialog templates, adjusting the amount of training data, and to adjust the number of iterations. The results show that the chatbot's vocabulary changes with N_ITERATION and that increasing the data in the training dataset improves the chatbot's understanding.
3
Suh, Jeehae. "A Study on the Conformity of Chatbot Builder as a Korean Speech Practice Tool". Korean Society of Culture and Convergence 45, n.º 1 (31 de janeiro de 2023): 61–70. http://dx.doi.org/10.33645/cnc.2023.01.45.01.61.
Texto completo da fonteResumo:
The purpose of this study is to verify whether chatbots made with chatbot builders are suitable as a Korean speaking practice tool. Chatbot builders, which can be easily produced as chatbots without separate coding knowledge and can design conversations meaningful for learning, have recently been in the spotlight as a learning tool. In this study, chatbots were created using dialog flows, and conversation patterns with chatbots shared by study participants were analyzed. As a result of the analysis, it was found that 35% of all conversations were not successfully completed. Such a conversation failure was found to be due to the inaccuracy of chatbot's recognition of Korean learner pronunciation, error in handling learner utterance intention, and inaccuracy in handling learner error sentences. In this regard, in order for chatbot builder to be used as a Korean language learning tool now, learner's proficiency or academic achievement should be considered for smooth processing of chatbot's learner utterance. In addition, this study is meaningful in that it verified the suitability of chatbot builders as a learning tool not covered in previous studies.
4
Dehankar, Archana, Shyamal Kirpan, Abhayraj Jha, Gitesh Thosare, Adarsh Bhaisare e Sumit Mankar. "AI CHATBOT USING DIALOG FLOW". International Journal of Computer Science and Mobile Computing 11, n.º 5 (30 de maio de 2022): 68–74. http://dx.doi.org/10.47760/ijcsmc.2022.v11i05.006.
Texto completo da fonteResumo:
A chatbot is a programme that uses Artificial Intelligence to provide human conversation (AI). Chatbots are intended to serve as VIRTUAL ASSISTANTS (VA). They themselves provide one platform for the online promotion of Products and Services. All Higher Educational Institutes provide comprehensive information to students via their websites, which permit the use of social networks such as Facebook, WhatsApp, but also College websites. Overall, searching functionality is required in any website to search for any information, and it includes Social Networking sites Applications such as Facebook and Snapchat regular response are utilised. As a result, Chatbot is both an effective auto-response system and an instant messaging platform. In this paper, AICMS, an AI-based CollegeBot management platform for professional Engineering colleges, provides auto-response to college queries about the college's basic information, class schedules, and academic examination schedules. The system can handle a large number of questions about subjects and placements. The AICMS system is built with Dialogflow, which is supported by the Google API. AI is running as a messenger on Facebook, taking input in the form of text and voice and responding in the form of text and voice. It responds quickly and accurately to student and staff inquiries in an interactive manner.
5
Dehankar, Archana, Shyamal Kirpan, Abhayraj Jha, Gitesh Thosare, Adarsh Bhaisare e Sumit Mankar. "AI CHATBOT USING DIALOG FLOW". International Journal of Computer Science and Mobile Computing 11, n.º 5 (30 de maio de 2022): 68–74. http://dx.doi.org/10.47760/ijcsmc.2022.v11i05.006.
Texto completo da fonteResumo:
A chatbot is a programme that uses Artificial Intelligence to provide human conversation (AI). Chatbots are intended to serve as VIRTUAL ASSISTANTS (VA). They themselves provide one platform for the online promotion of Products and Services. All Higher Educational Institutes provide comprehensive information to students via their websites, which permit the use of social networks such as Facebook, WhatsApp, but also College websites. Overall, searching functionality is required in any website to search for any information, and it includes Social Networking sites Applications such as Facebook and Snapchat regular response are utilised. As a result, Chatbot is both an effective auto-response system and an instant messaging platform. In this paper, AICMS, an AI-based CollegeBot management platform for professional Engineering colleges, provides auto-response to college queries about the college's basic information, class schedules, and academic examination schedules. The system can handle a large number of questions about subjects and placements. The AICMS system is built with Dialogflow, which is supported by the Google API. AI is running as a messenger on Facebook, taking input in the form of text and voice and responding in the form of text and voice. It responds quickly and accurately to student and staff inquiries in an interactive manner.
6
Zand, Aria, Arjun Sharma, Zack Stokes, Courtney Reynolds, Alberto Montilla, Jenny Sauk e Daniel Hommes. "An Exploration Into the Use of a Chatbot for Patients With Inflammatory Bowel Diseases: Retrospective Cohort Study". Journal of Medical Internet Research 22, n.º 5 (26 de maio de 2020): e15589. http://dx.doi.org/10.2196/15589.
Texto completo da fonteResumo:
Background The emergence of chatbots in health care is fast approaching. Data on the feasibility of chatbots for chronic disease management are scarce. Objective This study aimed to explore the feasibility of utilizing natural language processing (NLP) for the categorization of electronic dialog data of patients with inflammatory bowel diseases (IBD) for use in the development of a chatbot. Methods Electronic dialog data collected between 2013 and 2018 from a care management platform (UCLA eIBD) at a tertiary referral center for IBD at the University of California, Los Angeles, were used. Part of the data was manually reviewed, and an algorithm for categorization was created. The algorithm categorized all relevant dialogs into a set number of categories using NLP. In addition, 3 independent physicians evaluated the appropriateness of the categorization. Results A total of 16,453 lines of dialog were collected and analyzed. We categorized 8324 messages from 424 patients into seven categories. As there was an overlap in these categories, their frequencies were measured independently as symptoms (2033/6193, 32.83%), medications (2397/6193, 38.70%), appointments (1518/6193, 24.51%), laboratory investigations (2106/6193, 34.01%), finance or insurance (447/6193, 7.22%), communications (2161/6193, 34.89%), procedures (617/6193, 9.96%), and miscellaneous (624/6193, 10.08%). Furthermore, in 95.0% (285/300) of cases, there were minor or no differences in categorization between the algorithm and the three independent physicians. Conclusions With increased adaptation of electronic health technologies, chatbots could have great potential in interacting with patients, collecting data, and increasing efficiency. Our categorization showcases the feasibility of using NLP in large amounts of electronic dialog for the development of a chatbot algorithm. Chatbots could allow for the monitoring of patients beyond consultations and potentially empower and educate patients and improve clinical outcomes.
7
Bogdanova, A. N., e G. A. Fedorova. "Chatbots as a component of the content of teaching the basics of artificial intelligence at school". Informatics in school, n.º 2 (17 de julho de 2022): 39–45. http://dx.doi.org/10.32517/2221-1993-2022-21-2-39-45.
Texto completo da fonteResumo:
The article discusses the relevance of teaching schoolchildren the basics of artifcial intelligence. The importance of chatbots is emphasized as a component of the content of the theme "Fundamentals of artifcial intelligence" for the development of interdisciplinary links of the school course of informatics with other areas of knowledge. The theoretical aspects of teaching schoolchildren the technology of creating chatbots are considered: the characteristics of the basic concepts, historical information, the most common classifcation, the mechanism for processing user requests by the chatbot. Guidelines for teaching the technology of creating a chatbot are proposed. The designers for creating chatbots available for development by schoolchildren are listed. A plan of practical work "Creating a chatbot in the Aimylogic online constructor" is given. In order to illustrate the results of approbation of the educational material under consideration, examples of chatbots are given: a chatbot that talks about various types of algebraic equations; a chatbot — assistant for fractions; a chatbot — consultant on the theme "Algorithm and its properties. Ways of algorithm representation". The presented examples include the structure of the chatbot dialog created in the Aimylogic constructor and in the Pencil Code service.
8
Chen, Jenhui, Obinna Agbodike e Lei Wang. "Memory-Based Deep Neural Attention (mDNA) for Cognitive Multi-Turn Response Retrieval in Task-Oriented Chatbots". Applied Sciences 10, n.º 17 (22 de agosto de 2020): 5819. http://dx.doi.org/10.3390/app10175819.
Texto completo da fonteResumo:
One of the important criteria used in judging the performance of a chatbot is the ability to provide meaningful and informative responses that correspond with the context of a user’s utterance. Nowadays, the number of enterprises adopting and relying on task-oriented chatbots for profit is increasing. Dialog errors and inappropriate response to user queries by chatbots can result in huge cost implications. To achieve high performance, recent AI chatbot models are increasingly adopting the Transformer positional encoding and the attention-based architecture. While the transformer performs optimally in sequential generative chatbot models, recent studies has pointed out the occurrence of logical inconsistency and fuzzy error problems when the Transformer technique is adopted in retrieval-based chatbot models. Our investigation discovers that the encountered errors are caused by information losses. Therefore, in this paper, we address this problem by augmenting the Transformer-based retrieval chatbot architecture with a memory-based deep neural attention (mDNA) model by using an approach similar to late data fusion. The mDNA is a simple encoder-decoder neural architecture that comprises of bidirectional long short-term memory (Bi-LSTM), attention mechanism, and a memory for information retention in the encoder. In our experiments, we trained the model extensively on a large Ubuntu dialog corpus, and the results from recall evaluation scores show that the mDNA augmentation approach slightly outperforms selected state-of-the-art retrieval chatbot models. The results from the mDNA augmentation approach are quite impressive.
9
Wang, Youwei. "Discover two Neural Machine Translation model variables' effects on Chatbot's performance". Highlights in Science, Engineering and Technology 41 (30 de março de 2023): 17–22. http://dx.doi.org/10.54097/hset.v41i.6737.
Texto completo da fonteResumo:
To offer automatic online advice and help, chatbots are sophisticated conversational computer systems that resemble a human conversation. As chatbots' advantages grew, a variety of sectors began to use them extensively to give customers virtual support. Chatbots take advantage of methods and algorithms from two Artificial Intelligence areas: Machine Learning and Natural Language Processing. There are still several obstacles and restrictions to their use. In order to discover two NMT model variables' effects on chatbot performance, this paper does several experiments on a deep neural network chatbot model. Two straightforward and useful kinds of attentional mechanisms are used in this chatbot model: a local technique that only considers a small subset of source words at a time, as opposed to a global approach that always pays attention to all source words. This paper conducts experiments to examine how different model variables affect chatbot performance. This paper created a question template with eight general questions to test chatbot performance. Through the whole experiment results, increasing the number of iterations and increasing the dataset scale can improve the vocabulary and logic of the chatbot dialog to achieve better performance.
10
Reddy, Mr P. Rajashekar. "Enhancing User Experience: A Study on Dialogflow Chatbot Implementation". INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, n.º 03 (7 de março de 2024): 1–11. http://dx.doi.org/10.55041/ijsrem29070.
Texto completo da fonteResumo:
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)
11
Dehankar, Dr (Mrs) Archana, Shyamal Kirpan, Abhayraj Jha, Gitesh Thosare, Adarsh Bhaisare e Sumit Mankar. "AI Chatbot Using Dialog Flow". International Journal of Innovations in Engineering and Science 7, n.º 9 (9 de agosto de 2022): 7–11. http://dx.doi.org/10.46335/ijies.2022.7.9.2.
Texto completo da fonte
12
Varitimiadis, Savvas, Konstantinos Kotis, Dimitra Pittou e Georgios Konstantakis. "Graph-Based Conversational AI: Towards a Distributed and Collaborative Multi-Chatbot Approach for Museums". Applied Sciences 11, n.º 19 (1 de outubro de 2021): 9160. http://dx.doi.org/10.3390/app11199160.
Texto completo da fonteResumo:
Nowadays, museums are developing chatbots to assist their visitors and to provide an enhanced visiting experience. Most of these chatbots do not provide a human-like conversation and fail to deliver the complete requested knowledge by the visitors. There are plenty of stand-alone museum chatbots, developed using a chatbot platform, that provide predefined dialog routes. However, as chatbot platforms are evolving and AI technologies mature, new architectural approaches arise. Museums are already designing chatbots that are trained using machine learning techniques or chatbots connected to knowledge graphs, delivering more intelligent chatbots. This paper is surveying a representative set of developed museum chatbots and platforms for implementing them. More importantly, this paper presents the result of a systematic evaluation approach for evaluating both chatbots and platforms. Furthermore, the paper is introducing a novel approach in developing intelligent chatbots for museums. This approach emphasizes graph-based, distributed, and collaborative multi-chatbot conversational AI systems for museums. The paper accentuates the use of knowledge graphs as the key technology for potentially providing unlimited knowledge to chatbot users, satisfying conversational AI’s need for rich machine-understandable content. In addition, the proposed architecture is designed to deliver an efficient deployment solution where knowledge can be distributed (distributed knowledge graphs) and shared among different chatbots that collaborate when is needed.
13
Fadnis, Kshitij, Pankaj Dhoolia, Li Zhu, Q. Vera Liao, Steven Ross, Nathaniel Mills, Sachindra Joshi e Luis Lastras. "Doc2Bot: Document grounded Bot Framework". Proceedings of the AAAI Conference on Artificial Intelligence 35, n.º 18 (18 de maio de 2021): 16026–28. http://dx.doi.org/10.1609/aaai.v35i18.18001.
Texto completo da fonteResumo:
Conversational agents, or chatbots, are widely used to provide customer care and other informational support. Currently, the development of chatbots using standard frameworks requires a lot of manual crafting by subject matter experts (SMEs). On the other hand, while learning-based approaches to dialog have made significant advancements, they require training with a large volume of dialog data, which chatbot developers typically do not have access to. To tackle these challenges, we introduce DOC2BOT, a system that supports the automated construction of chatbots by digesting various forms of documents such as business manuals, HowTos, and customer support pages that organizations own. In addition to that, DOC2BOT provides a user-friendly experience to SMEs, and to minimize their effort by supporting intuitive interactions and streamlining their workflow.
14
Aksyonov, K. A., P. E. Ziomkovskaya, Dougandaga Danwitch, O. P. Aksyonova e E. K. Aksyonova. "Development of a text analysis agent for a logistics company's Q&A system". Journal of Physics: Conference Series 2134, n.º 1 (1 de dezembro de 2021): 012021. http://dx.doi.org/10.1088/1742-6596/2134/1/012021.
Texto completo da fonteResumo:
Abstract The "Twin" system is an omnichannel communication platform for building voice and chatbots, capable, in particular, of receiving data in one language and transmitting in another. "Twin" can record voice and text, display detailed statistics and analytics for each call or dialog. In this article, using the Twin system, a chatbot was created for the field of cargo transportation, it describes its advantages and disadvantages and the principle of creating of such chatbots.
15
Permadi, Iwan. "Criteria Selection and Comparative Analysis of Popular Chatbot Frameworks (Dialog flow, Microsoft Bot Framework, IBM Watson Assistant and Rasa) For Implementation in Libraries: a Systematic Literature Review". JPUA: Jurnal Perpustakaan Universitas Airlangga: Media Informasi dan Komunikasi Kepustakawanan 13, n.º 2 (4 de dezembro de 2023): 94–103. http://dx.doi.org/10.20473/jpua.v13i2.2023.94-103.
Texto completo da fonteResumo:
ABSTRACT Chatbots are increasingly popular in various fields, including in libraries, to improve services and interactions with users. In choosing a chatbot for libraries, proper criteria are needed. Some common chatbot frameworks are Dialogflow, Microsoft Bot Framework, IBM Watson Assistant, and Rasa, which have advantages and disadvantages in the library context. This research conducts a systematic literature review on the selection criteria and comparison of popular chatbot frameworks such as Dialogflow, Microsoft Bot Framework, IBM Watson Assistant, and Rasa in library implementation. The research method used a systematic literature review from sources such as IEEE, Proquest, and ScienceDirect. The keywords used were ("Chatbot" OR "Bot" OR "Conversational agent" OR "Virtual assistant") AND ("Dialogflow" OR "IBM Watson Assistant" OR "Microsoft Bot Framework" OR "Rasa"). The results show that the criteria in chatbot selection include Natural Language Understanding (NLU) pipeline customization capabilities, ease of use, integration with Machine Learning and Natural Language Processing, integration capabilities with communication channels, natural language understanding capabilities, validation with automated user story extraction systems, flexibility in development, and tools for natural language processing and machine learning. Although no articles specifically addressing chatbots were found in the library, this research provides an overview of chatbot selection criteria and provides information on the advantages and disadvantages of each chatbot framework as outlined in the results and discussion table. In conclusion, although research questions RQ1 and RQ2 cannot be answered due to the lack of specific articles about chatbots in libraries, this research provides an overview of chatbot selection criteria and can provide an understanding of the advantages and disadvantages of existing chatbot frameworks... ABSTRAK Chatbot semakin populer di berbagai bidang, termasuk di perpustakaan, untuk meningkatkan layanan dan interaksi dengan pengguna. Dalam memilih chatbot untuk perpustakaan, kriteria yang tepat diperlukan. Beberapa framework chatbot umum adalah Dialogflow, Microsoft Bot Framework, IBM Watson Assistant, dan Rasa, yang memiliki kelebihan dan kekurangan dalam konteks perpustakaan. Penelitian ini melakukan tinjauan literatur sistematis tentang kriteria pemilihan dan perbandingan framework chatbot populer seperti Dialogflow, Microsoft Bot Framework, IBM Watson Assistant, dan Rasa dalam implementasi perpustakaan. Metode penelitian menggunakan tinjauan literatur sistematis dari sumber seperti IEEE, Proquest, dan ScienceDirect. Kata kunci yang digunakan adalah ("Chatbot" OR "Bot" OR "Conversational agent" OR "Virtual assistant") AND ("Dialogflow" OR "IBM Watson Assistant" OR "Microsoft Bot Framework" OR "Rasa"). Hasil penelitian menunjukkan bahwa kriteria dalam pemilihan chatbot mencakup kemampuan penyesuaian pipeline Natural Language Understanding (NLU), kemudahan penggunaan, integrasi dengan Machine Learning dan Natural Language Processing, kemampuan integrasi dengan saluran komunikasi, kemampuan memahami bahasa alami, validasi dengan sistem ekstraksi cerita pengguna otomatis, fleksibilitas dalam pengembangan, dan alat untuk pemrosesan bahasa alami dan pembelajaran mesin. Meskipun tidak ditemukan artikel yang secara khusus membahas chatbot di perpustakaan, penelitian ini memberikan gambaran umum tentang kriteria pemilihan chatbot dan memberikan informasi tentang kelebihan dan kekurangan masing-masing framework chatbot seperti yang diuraikan dalam tabel hasil dan pembahasan. Dalam kesimpulannya, meskipun pertanyaan penelitian RQ1 dan RQ2 tidak dapat terjawab karena kurangnya artikel yang spesifik tentang chatbot di perpustakaan, penelitian ini memberikan gambaran umum tentang kriteria pemilihan chatbot dan dapat memberikan pemahaman tentang kelebihan dan kekurangan framework chatbot yang ada.
16
K, Harish. "CHATBOT WITH FACIAL RECOGNITION BY USING AI". INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, n.º 03 (22 de março de 2024): 1–5. http://dx.doi.org/10.55041/ijsrem29325.
Texto completo da fonteResumo:
Creating a concept for a facial recognition chatbot is the main objective of the project. The work of chatbots in a variety of fields, such as marketing, education, healthcare, entertainment, has grown significantly in recent years. A chatbot is a piece of software that performs text or text-to-speech internet chats in place of face-to-face contact. Chatbots and other dialog systems are utilized for a number of purposes, including information gathering, request routing, and customer assistance. Some chatbot solutions look for generic keywords and respond with frequently used phrases that are pulled from a related library, while others utilize sophisticated AI, natural language processing, and intricate word categorization techniques. Here, we have added additional features including facial and language recognition. A facial recognition system is a technological device that uses a database of faces and digital images or video frames to identify a person's face. This kind of equipment locates and quantifies face features from a picture, usually to confirm users' identities through ID verification services.
17
Kowald, Cäcilie, e Beate Bruns. "Chatbot Maxi: A Virtual Certification Trainer in a Blended-Learning Concept". International Journal of Advanced Corporate Learning (iJAC) 15, n.º 2 (29 de novembro de 2022): 34–40. http://dx.doi.org/10.3991/ijac.v15i2.34081.
Texto completo da fonteResumo:
Chatbot Maxi was developed as part of a blended-learning concept to make a training for insulation material processing more flexible and location-independent. As a kind of digital tutor, Maxi takes on the theoretical part of the certification course, giving participants information on the properties, areas of application and processing of the products as well as on regulatory issues. Maxi was realized with script-based chatbot tool Jix and uses a flexible structured dialog to guide users through topics and sub-topic in a didactical appealing, adaptive way. The positive feedback from the target group after the pilot phase shows that (and how) chatbots can become an integral part of a comprehensive blended learning concept in continuous education and company training offers.
18
Safi, Zeineb, Alaa Abd-Alrazaq, Mohamed Khalifa e Mowafa Househ. "Technical Aspects of Developing Chatbots for Medical Applications: Scoping Review". Journal of Medical Internet Research 22, n.º 12 (18 de dezembro de 2020): e19127. http://dx.doi.org/10.2196/19127.
Texto completo da fonteResumo:
Background Chatbots are applications that can conduct natural language conversations with users. In the medical field, chatbots have been developed and used to serve different purposes. They provide patients with timely information that can be critical in some scenarios, such as access to mental health resources. Since the development of the first chatbot, ELIZA, in the late 1960s, much effort has followed to produce chatbots for various health purposes developed in different ways. Objective This study aimed to explore the technical aspects and development methodologies associated with chatbots used in the medical field to explain the best methods of development and support chatbot development researchers on their future work. Methods We searched for relevant articles in 8 literature databases (IEEE, ACM, Springer, ScienceDirect, Embase, MEDLINE, PsycINFO, and Google Scholar). We also performed forward and backward reference checking of the selected articles. Study selection was performed by one reviewer, and 50% of the selected studies were randomly checked by a second reviewer. A narrative approach was used for result synthesis. Chatbots were classified based on the different technical aspects of their development. The main chatbot components were identified in addition to the different techniques for implementing each module. Results The original search returned 2481 publications, of which we identified 45 studies that matched our inclusion and exclusion criteria. The most common language of communication between users and chatbots was English (n=23). We identified 4 main modules: text understanding module, dialog management module, database layer, and text generation module. The most common technique for developing text understanding and dialogue management is the pattern matching method (n=18 and n=25, respectively). The most common text generation is fixed output (n=36). Very few studies relied on generating original output. Most studies kept a medical knowledge base to be used by the chatbot for different purposes throughout the conversations. A few studies kept conversation scripts and collected user data and previous conversations. Conclusions Many chatbots have been developed for medical use, at an increasing rate. There is a recent, apparent shift in adopting machine learning–based approaches for developing chatbot systems. Further research can be conducted to link clinical outcomes to different chatbot development techniques and technical characteristics.
19
Kapuskar, Vaibhavi, Sakshi Bobade, Srushti Diwan, Akshata Dholwade, Vaishnavi Kamble e Prof S. R. Gudadhe. "Efficient Chatbot Designing". International Journal for Research in Applied Science and Engineering Technology 10, n.º 4 (30 de abril de 2022): 2743–45. http://dx.doi.org/10.22214/ijraset.2022.41889.
Texto completo da fonteResumo:
Abstract: A conversational agent (chatbot) is a piece of software that is able to communicate with humans using natural language. Modeling conversation is an important task in natural language processing and artificial intelligence (AI). Indeed, ever since the birth of AI, creating a good chatbot remains one of the field’s hardest challenges. While chatbots can be used for various tasks, in general they have to understand users’ utterances and provide responses that are relevant to the problem at hand. In the past, methods for constructing chatbot architectures have relied on hand-written rules and templates or simple statistical methods. With the rise of deep learning these models were quickly replaced by end-to-end trainable neural networks around 2015. More specifically, the recurrent encoder-decoder model [Cho et al., 2014] dominates the task of conversational modeling. This architecture was adapted from the neural machine translation domain, where it performs extremely well. Since then a multitude of variations and features were presented that augment the quality of the conversation that chatbots are capable of the next section of my paper focuses on adapting the very recent Tranformer [Vaswani et al., 2017] model to the chatbot domain, which is currently the state-of-the-art in neural machine translation. I first present my experiments with the vanilla model, using conversations extracted from the Cornell Movie-Dialog Corpus [Danescu-Niculescu-Mizil and Lee, 2011]. Secondly, I augment the model with some of my ideas regarding the issues of encoder-decoder architectures. More specifically, I feed additional features into the model like mood or persona together with the raw conversation data. Finally, I conduct a detailed analysis of how the vanilla model performs on conversational data by comparing it to previous chatbot models and how the additional features, affect the quality of the generated responses
20
Bhalchandra B, Prof Mundhe. "Health Care Chatbot". INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 07, n.º 10 (1 de outubro de 2023): 1–11. http://dx.doi.org/10.55041/ijsrem26399.
Texto completo da fonteResumo:
Artificial intelligence (AI) is at the forefront of transforming numerous aspects of our lives by modifying the way we analyze information and improving decision-making through problem solving, reasoning, and learning. Machine learning (ML) is a subset of AI that improves its performance based on the data provided to a generic algorithm from experience rather than defining rules in traditional approaches. Advancements in ML have provided benefits in terms of accuracy, decision-making, quick processing, cost-effectiveness, and handling of complex data. Chatbots, also known as chatter robots, smart bots, conversational agents, digital assistants, or intellectual agents, are prime examples of AI systems that have evolved from ML. This paper presents Healthcare Chatbot using Artificial Intelligence that can make a human-system interaction to resolve basic queries regarding health parameters before consulting a doctor. The actual purpose behind this work is to work on the user's symptoms and to provide medical suggestions according to it, to reduce the time and cost required for the process. The chatbot works on provided input by the user, It takes sentence keywords and makes decisions to solve the user's query and answers it accordingly. Given these effectual benefits, it is not surprising that chatbots have rapidly evolved over the past 2 decades and integrated themselves into numerous fields, such as entertainment, travel, gaming, robotics, and security. Chatbots have been proven to be particularly applicable in various health care components that usually involve face-to-face interactions. With their ability for complex dialog management and conversational flexibility, integration of chatbot technology into clinical practice may reduce costs, refine workflow efficiencies, and improve patient outcomes. A user can be able to recognize the actual disease by providing symptoms of it. As if a person will also know about the solutions or we can say precautions and remedies that they should take accordingly.
21
Garner, Robby G. "Film Theory and Chatbots". International Journal of Synthetic Emotions 5, n.º 1 (janeiro de 2014): 17–22. http://dx.doi.org/10.4018/ijse.2014010103.
Texto completo da fonteResumo:
The tools described in film theory are used to invoke feelings in the viewer as a form of entertainment. Some of these tools apply more directly to chatbots than others. Film combines visual images, music, and dialog to accomplish its goals. Conversing with a chatbot is akin to using a telegraph, or instant messaging on a cell phone. However, written communication may still convey emotions and feelings that people interpret on their own as they chat. It is useful to speak of the emotional content of written communications using film theory terminology.
22
Abd-Alrazaq, Alaa, Zeineb Safi, Mohannad Alajlani, Jim Warren, Mowafa Househ e Kerstin Denecke. "Technical Metrics Used to Evaluate Health Care Chatbots: Scoping Review". Journal of Medical Internet Research 22, n.º 6 (5 de junho de 2020): e18301. http://dx.doi.org/10.2196/18301.
Texto completo da fonteResumo:
Background Dialog agents (chatbots) have a long history of application in health care, where they have been used for tasks such as supporting patient self-management and providing counseling. Their use is expected to grow with increasing demands on health systems and improving artificial intelligence (AI) capability. Approaches to the evaluation of health care chatbots, however, appear to be diverse and haphazard, resulting in a potential barrier to the advancement of the field. Objective This study aims to identify the technical (nonclinical) metrics used by previous studies to evaluate health care chatbots. Methods Studies were identified by searching 7 bibliographic databases (eg, MEDLINE and PsycINFO) in addition to conducting backward and forward reference list checking of the included studies and relevant reviews. The studies were independently selected by two reviewers who then extracted data from the included studies. Extracted data were synthesized narratively by grouping the identified metrics into categories based on the aspect of chatbots that the metrics evaluated. Results Of the 1498 citations retrieved, 65 studies were included in this review. Chatbots were evaluated using 27 technical metrics, which were related to chatbots as a whole (eg, usability, classifier performance, speed), response generation (eg, comprehensibility, realism, repetitiveness), response understanding (eg, chatbot understanding as assessed by users, word error rate, concept error rate), and esthetics (eg, appearance of the virtual agent, background color, and content). Conclusions The technical metrics of health chatbot studies were diverse, with survey designs and global usability metrics dominating. The lack of standardization and paucity of objective measures make it difficult to compare the performance of health chatbots and could inhibit advancement of the field. We suggest that researchers more frequently include metrics computed from conversation logs. In addition, we recommend the development of a framework of technical metrics with recommendations for specific circumstances for their inclusion in chatbot studies.
23
Pavlenko, Yaryna, e Iryna Yurchak. "Information currency converter based on Telegram messenger". Computer systems and network 4, n.º 1 (16 de dezembro de 2022): 106–21. http://dx.doi.org/10.23939/csn2022.01.106.
Texto completo da fonteResumo:
The work is dedicated to the development of a mobile chatbot containing an information currency converter, designed for use by a wide range of people. A chatbot is a subject-oriented text-based dialog interface that allows a user to perform a limited set of tasks: getting information about the current rate of currencies (USD or EUR) relative to the national currency and finding out the current rate of cryptocurrencies (Bitcoin, Ethereum, Litecoin) in dollars or euros. To achieve this goal, the selected subject area was analyzed and appropriate conclusions were made. A corresponding study of analogs who perform tasks similar in complexity was carried out, only a few chatbots were identified, as a certain number of bots posted in Telegram no longer provide their services or work incorrectly. The algorithm of the service for currency conversion based on the Telegram messenger is described. The chatbot is implemented in the Python programming language and uses the Pycharm development environment, as it is best suited for programming the intended project and is easy to use. There are two options available to the user: the cryptocurrency rate from the CoinGecko site or the exchange rate from PrivatBank. The article examines the development and improvement of chatbots. Similar Telegram bots, which function similarly to the created one, are reviewed. The author’s bot has been developed, and the architecture and algorithm of the CurrencyBot currency conversion service are presented.
24
Dall’Acqua, Anna, e Fabio Tamburini. "Toward a linguistically grounded dialog model for chatbot design". Italian Journal of Computational Linguistics 7, n.º 1 | 2 (1 de dezembro de 2021): 191–222. http://dx.doi.org/10.4000/ijcol.900.
Texto completo da fonte
25
Atmauswan, Pica Salsabila, e Akibu Mahmoud Abdullahi. "Intelligent Chatbot For University Information System Using Natural Language Approach". Vol.3, Issue 2, Dec 2022 3, n.º 2 (31 de dezembro de 2022): 59–64. http://dx.doi.org/10.55862/asbjv3i2a007.
Texto completo da fonteResumo:
High school students begin applying to university during the senior year or upon completion. This marks the beginning of a complete frustration for students as well as admissions staff. Students have countless questions and problems that need to be answered repeatedly and resolved by the admissions staff. The development of the chatbot was carried out with the aim of solving the problems faced by students interested in enrolling in the university by offering consolidated, authentic and accurate information through a live chat window. In the development, the university Chatbot obtains its knowledge from students frequently asked questions and implement dialog- flow as the platform to design the chatbot. Natural language processing is used to create the components required for developing a university chatbot design. The chatbot application implements a search for answers through questions entered from the user. The chatbot is expected to help prospective students register for admission procedures, study programs, and scholarship information. The chatbot will analyse and match categories based on the knowledge that the chatbot has. The goal of this project is to design a chatbot that can be utilized by students on the university's website to get their questions answered quickly and effortlessly.
26
Meo, Sultan Ayoub. "Chatbot-generative pretrained transformer: Potential role in medical education and clinical settings". Advances in Biomedical and Health Sciences 3, n.º 1 (2024): 1–4. http://dx.doi.org/10.4103/abhs.abhs_89_23.
Texto completo da fonteResumo:
ABSTRACT The chatbot-generative pretrained transformer (ChatGPT) was developed as a prototype by OpenAI on November 30, 2022. Artificial Intelligence software is designed to generate and enhance dialog and discussion among users. ChatGPT has attracted significant attention from the scientific community, physicians, and the public. It provides appropriate answers and explanations for various subjects. ChatGPT is a useful tool in scientific writing, generating essays, editorials, blogs, brief revisions, providing explanations, and generating initial drafts of articles. It uses multiple choice questions and helps in image identification and clinical settings. However, ChatGPT has ethical issues, with multiple risks of misinformation, inaccuracy, prejudice, and plagiarism. ChatGPT cannot replace human judgement, and the outcome must be examined by humans before being used in decision-making policies. When using ChatGPT, it is essential to exercise caution when verifying the accuracy, validity, and reliability of the contents and the source of information in medical education, scientific writing, and clinical settings.
27
Kowald, Cäcilie, e Beate Bruns. "Chatbot Kim: A Digital Tutor on AI. How Advanced Dialog Design Creates Better Conversational Learning Experiences". International Journal of Advanced Corporate Learning (iJAC) 13, n.º 3 (27 de outubro de 2020): 26. http://dx.doi.org/10.3991/ijac.v13i3.17017.
Texto completo da fonteResumo:
Conversational user interfaces, aka chatbots, offer new ways of interaction that can be used not only for task-led applications, but also for learning itself. Still, most conversational learning applications offer a predominantly one-directional dialog – either bot-led, with the user only confirming, or user-led, with the bot answering questions, but not going beyond. In contrast to these common approaches, learnbot Kim by time4you [1] not only conveys information, but wraps it in an equally entertaining and instructive chat, combining pre-defined dialog turns with a flexible dialog management. This article explains the design decisions made during the dialog development process and the underlying reasons. After having read this text, you will have a better idea of how dialog in conversational learning can be modeled to allow for a more natural conversational experience.
28
Zhong, Wanjun, Lianghong Guo, Qiqi Gao, He Ye e Yanlin Wang. "MemoryBank: Enhancing Large Language Models with Long-Term Memory". Proceedings of the AAAI Conference on Artificial Intelligence 38, n.º 17 (24 de março de 2024): 19724–31. http://dx.doi.org/10.1609/aaai.v38i17.29946.
Texto completo da fonteResumo:
Large Language Models (LLMs) have drastically reshaped our interactions with artificial intelligence (AI) systems, showcasing impressive performance across an extensive array of tasks. Despite this, a notable hindrance remains—the deficiency of a long-term memory mechanism within these models. This shortfall becomes increasingly evident in situations demanding sustained interaction, such as personal companion systems, psychological counseling, and secretarial assistance. Recognizing the necessity for long-term memory, we propose MemoryBank, a novel memory mechanism tailored for LLMs. MemoryBank enables the models to summon relevant memories, continually evolve through continuous memory updates, comprehend, and adapt to a user's personality over time by synthesizing information from previous interactions. To mimic anthropomorphic behaviors and selectively preserve memory, MemoryBank incorporates a memory updating mechanism, inspired by the Ebbinghaus Forgetting Curve theory. This mechanism permits the AI to forget and reinforce memory based on time elapsed and the relative significance of the memory, thereby offering a more human-like memory mechanism and enriched user experience. MemoryBank is versatile in accommodating both closed-source models like ChatGPT and open-source models such as ChatGLM. To validate MemoryBank's effectiveness, we exemplify its application through the creation of an LLM-based chatbot named SiliconFriend in a long-term AI Companion scenario. Further tuned with psychological dialog data, SiliconFriend displays heightened empathy and discernment in its interactions. Experiment involves both qualitative analysis with real-world user dialogs and quantitative analysis with simulated dialogs. In the latter, ChatGPT acts as multiple users with diverse characteristics and generates long-term dialog contexts covering a wide array of topics. The results of our analysis reveal that SiliconFriend, equipped with MemoryBank, exhibits a strong capability for long-term companionship as it can provide emphatic response, recall relevant memories and understand user personality.
29
Anindyati, Laksmi. "Analisis dan Perancangan Aplikasi Chatbot Menggunakan Framework Rasa dan Sistem Informasi Pemeliharaan Aplikasi (Studi Kasus: Chatbot Penerimaan Mahasiswa Baru Politeknik Astra)". Jurnal Teknologi Informasi dan Ilmu Komputer 10, n.º 2 (14 de abril de 2023): 291. http://dx.doi.org/10.25126/jtiik.20231026409.
Texto completo da fonteResumo:
<p>Chatbot menjadi suatu kebutuhan bisnis yang membutuhkan pelayanan interaksi secara <em>real-time</em> dan 24 jam. Kebutuhan tersebut juga diperlukan saat penerimaan mahasiswa baru di Politeknik Astra. Chatbot dapat menjadi salah satu penyedia informasi yang interaktif untuk calon mahasiswa Politeknik Astra, ketika mencari informasi terkait proses pendaftaran mahasiswa baru maupun terkait Politeknik Astra secara umum. Proses analisis dan perancangan sistem dilakukan, dimulai dengan studi literatur. Hasil dari studi literatur dipilihlah Framework RASA yang akan digunakan dalam pengembangan chatbot. Framework RASA memiliki performa yang baik karena memiliki Rasa NLU dan Rasa CORE. Rasa NLU sebagai basis library yang membangunteraksi antara komputer dan manusia dengan menerapkan dua metode dan algoritma kecerdasan buatan yaitu pemrosesan bahasa alami dan mesin pembelajaran. Rasa NLU bertanggung jawab membuat interaksi lebih nyata, pengguna layanan akan merasakan interaksi langsung seperti dengan manusia bukan dengan komputer. Rasa CORE juga berperan dalam membuat interaksi terasa nyata, dengan mengatur interaksi dialog antara antara bot (komputer dibalik chatbot) dengan pengguna. Framework Rasa juga bersifat <em>open source</em> sehingga memiliki adaptabilitas yang tinggi ketika diperlukan modifikasi untuk menyesuaikan kebutuhan bisnis yang ada. Proses pengembangan sistem dilanjutkan dengan melakukan analisis dan perancangan sistem informasi penunjang. Sistem informasi penunjang chatbot ini dibangun untuk mengakomodir kebutuhan proses CRUD (<em>Create, Read, Update</em> dan <em>Delete</em>) dari pertanyaan – respon yang nantinya dipelajari oleh chatbot sebelum dapat berinteraksi seperti manusia. Sistem informasi penunjang ini membantu penyesuaian konfigurasi chatbot dalam merespon pertanyaan sehingga operasional kebutuhan tersebut dapat mudah dilakukan oleh admin tanpa latar belakang IT. Hasil dari penelitian ini adalah kebutuhan sistem yang direpresentasikan pada use case diagram dan flowchart lalu pemilihan pipeline NLU untuk chatbot, arsitektur sistem, perancangan database dalam bentuk physical data model, dan perancangan desain antarmuka (mockup) sistem penunjang chatbot framework RASA.</p><p> </p><p><em><strong>Abstract</strong></em></p><p><em>Chatbots have become essential in business that requires interaction with customers in real-time and 24 hours. The requirements have become a necessity in Polytechnic Astra especially during the acceptance period of new students. Chatbot can be an interactive provider of information to prospective students of Polytechnic Astra who are looking information about the registration process or information related to Polytechnic Astra in general. The analysis and design process are conducted, starting with study literature. The results of the literature study, the RASA Framework were chosen as a tool to develop chatbots. RASA Framework performs well with the Rasa NLU and Rasa Core. Rasa NLU as a base library to build interactions between computers and humans using artificial intelligence. Rasa NLU is responsible for making interaction much real, like direct interaction with humans. Rasa core is a base library to regulate the interaction dialogue between chatbots and users. The Rasa Framework is also open source, so it has high adaptability to be modified to suit existing business needs. This supporting information system help to adjust the configuration chatbot in responding to questions, so that the operational can be easily carried out by the admin without IT background. The results of this research are the system requirements represented in use case diagrams and flowcharts and the selection of NLU pipeline for chatbots, the system architecture, the database design in the form of physical data models, and the interface design (mockup) for the chatbot framework support system RASA.</em></p>
30
Vinarti, Retno Aulia, Nisfu Asrul Sani, Rizki Amalia, Endang Sulistyani, Adistha Eka Noveyani, Edward Suryaputra e Muhammad Azhar Arwan. "KIA-CHAT: A QnA Chatbot for Postnatal and Newborn Care". Jurnal Promkes 12, SI 1 (26 de janeiro de 2024): 97–101. http://dx.doi.org/10.20473/jpk.v12.isi1.2024.97-101.
Texto completo da fonteResumo:
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.
31
Permatasari, Dinda Ayu, e Devira Anggi Maharani. "Combination of Natural Language Understanding and Reinforcement Learning for Booking Bot". Journal of Electrical, Electronic, Information, and Communication Technology 3, n.º 1 (30 de abril de 2021): 12. http://dx.doi.org/10.20961/jeeict.3.1.49818.
Texto completo da fonteResumo:
At present, some popular messaging applications have evolved specifically with bots starting to emerge into development. One of the developments of chatbots is to help humans booking flight with Named Entity Recognition in the text, trace sentences to detect user intentions, and respond even though the context of the conversation domain is limited. This study proposes to conduct analysis and design chatbot interactions using NLU (Natural Language Understanding) with the aim that the bot understands what is meant by the user and provides the best and right response. Classification using Support Vector Machine (SVM) method with (erm Frequency-Inverse Document Frequency (TF-IDF) feature extraction is suitable combination methods that produce the highest accuracy value up to 97.5%. Conversation dialogue on chatbots developed using NLU which consists of NER and intent classification then dialog manager using Reinforcement Learning could make a low cost for computing in chatbots.
32
Arkodeep Biswas and Ajay Kaushik. "Depression Therapy Using Chatbot". International Journal for Modern Trends in Science and Technology 6, n.º 12 (15 de dezembro de 2020): 323–27. http://dx.doi.org/10.46501/ijmtst061260.
Texto completo da fonteResumo:
The objective of this paper is to build a Web Application based on Virtual voice and chat Assistant. The current study focuses on development of voice and text/chat bot specifically. It is specially being built for people who feel depressed and insists them to talk open mindedly which in turn pacifies them. As the name of the application suggests, App: An application to pacify people and make them as happy as a cat would be with his or her mother (the reason why a cat purrs). We will be using Dialog flow for the application design and Machine Learning as a part of Artificial Intelligence for Natural Language Processing (NLP), an easiest way to use Machine Learning libraries. At the back-end we will be using a database to store the communication history between the user and the bot. This application will only work on devices with Web operating system version-5.0 and above.
33
Aini, Aliviya Nur, Risal Rinofah e Alfiatul Maulida. "Efektifitas Pengembangan Artificial Intelligence (AI) pada Chatbot MbakPia". JIIP - Jurnal Ilmiah Ilmu Pendidikan 6, n.º 10 (3 de outubro de 2023): 8224–28. http://dx.doi.org/10.54371/jiip.v6i10.3047.
Texto completo da fonteResumo:
Chatbot merupakan salah satu cabang kecerdasan buatan yang diprogram melalui komputer sehingga dapat melakukan dialog dengan manusia pada umumnya melalui pesan teks. Saat ini chatbot telah banyak digunakan untuk berbagai sektor kehidupan, salah satunya pada sektor ekonomi. Chatbot MbakPia merupakan salah satu pengembangan kecerdasan buatan untuk membantu pengembangan UMKM Bakpai Fadila Jogja. Banyak manfaat dan juga keuntungan dari chatbot diantaranya adalah efisiensi biaya dan juga mampu membalas pesan selama 24 jam. Tujuan dari penelitian ini adalah untuk mengetahui seberapa efektifkah pengembangan Chatbot MbakPia untuk UMKM BakPia Fadila Jogja. Indikator penelitian ini menggunakan indikator dari Kettner, Moroney dan Martin (2008:262) yaitu Effort, Cost-Efficiency, Result, Cost-Effectiviness, Impact. Data diperoleh melalui wawancara yang dilakukan dengan pemilik UMKM Bakpia Fadila. Setelah diperoleh data, maka peneliti memberikan kesimpulan dari hasil wawancara. Hasil peneitian menunjukkan bahwa Effort yang dilakukan tidak efektif, sosialisasi program yang dilakukan kurang maksimal. Cost-Efficiency yang dilakukan tidak maksimal, UMKM Bakpia Fadila Jogja tidak menganggarkan biaya pengembangan Chatbot MbakPia. Result yang diperoleh UMKM Bakpia Fadila Jogja tidak sesuai dengan harapan. Cost-Effectiviness yang diperoleh juga tidak efektif, karena tidak adanya anggaran biaya sehingga biaya yang dikeluarkan tidak bisa dianggap efektif. Impact dari Chatbot MbakPia tidak ada, proses penjualan masih berjalan seperti biasa dan tidak ada perubahan antara sebelum dan setelah pengembangan Chatbot MbakPia.
34
Kamber, Manoj, e Divyakumar Shah. "The Use of Conversational Natural Language Processing Chatbots For Simulated Intelligence in Home Cooking While Integrating with Meta Messenger". International Journal for Research in Applied Science and Engineering Technology 10, n.º 12 (31 de dezembro de 2022): 1081–85. http://dx.doi.org/10.22214/ijraset.2022.48127.
Texto completo da fonteResumo:
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.
35
Queudot, Marc, Éric Charton e Marie-Jean Meurs. "Improving Access to Justice with Legal Chatbots". Stats 3, n.º 3 (4 de setembro de 2020): 356–75. http://dx.doi.org/10.3390/stats3030023.
Texto completo da fonteResumo:
On average, one in three Canadians will be affected by a legal problem over a three-year period. Unfortunately, whether it is legal representation or legal advice, the very high cost of these services excludes disadvantaged and most vulnerable people, forcing them to represent themselves. For these people, accessing legal information is therefore critical. In this work, we attempt to tackle this problem by embedding legal data in a conversational interface. We introduce two dialog systems (chatbots) created to provide legal information. The first one, based on data from the Government of Canada, deals with immigration issues, while the second one informs bank employees about legal issues related to their job tasks. Both chatbots rely on various representations and classification algorithms, from mature techniques to novel advances in the field. The chatbot dedicated to immigration issues is shared with the research community as an open resource project.
36
Sysoyev, Pavel V., e Evgeny M. Filatov. "Chatbots in teaching a foreign language: advantages and controversial issues". Tambov University Review. Series: Humanities, n.º 1 (2023): 66–72. http://dx.doi.org/10.20310/1810-0201-2023-28-1-66-72.
Texto completo da fonteResumo:
The current stage of technological development of the world community is characterized by the dynamic introduction of artificial intelligence technologies into various spheres of human life. Informatization of education contributed to the integration of new innovative technologies in the teaching of certain subjects, including a foreign language. Chatbots are one of the modern programs that operate on the basis of natural language processing and machine learning technologies, which can be used in the development of students’ foreign language speech skills. By chatbots from the standpoint of the methodology of teaching foreign languages, we propose to understand a dialog training program capable of developing foreign-language oral and written speech skills of a student based on the algorithms of human speech behavior embedded in it by maintaining a dialogue with him and imitating human speech. In this work, based on the analysis of methodological research, we highlight the advantages of chatbots in teaching a foreign language and the controversial issues of using this program in the educational process. The advantages include the following: 1) increasing students' motivation to learn a foreign language based on innovative artificial intelligence technology; 2) the opportunity for students to improve foreign language speech skills; 3) the availability of chatbots for the development of students' speech skills, regardless of their location and time; 4) reducing the level of anxiety of students when interacting with the machine. The controversial issues include: 1) students are not always ready to replace the teacher with a chatbot; 2) most of the conversational chatbots are aimed at students with a level of foreign language proficiency A2-B1; 3) stereotyped and limited set of phrases used by the chatbot.
37
Chuma, Euclides Lourenco, e Gabriel Gomes De Oliveira. "Generative AI for Business Decision-Making: A Case of ChatGPT". Management Science and Business Decisions 3, n.º 1 (1 de julho de 2023): 5–11. http://dx.doi.org/10.52812/msbd.63.
Texto completo da fonteResumo:
ChatGPT (Generative Pretrained Transformer) is a chatbot using artificial intelligence (AI) launched by OpenAI, which is an AI research and deployment company. The ChatGPT has taken the technology world by storm. The ChatGPT is a trained AI model that can chat almost like a human. The dialog format allows the ChatGPT to answer follow-up questions, admit mistakes, challenge incorrect premises, and reject inappropriate requests. The ChatGPT can be utilized for compiling research, drafting marketing content, brainstorming ideas, delivering aftercare services, increasing customer engagement, and many others. The ChatGPT can provide enormous opportunities for companies leveraging this breakthrough technology strategically. Thus, we evaluate ChatGPT as a tool in common business decision-making cases in the current study. For example, the ChatGPT was asked about the impacts of a hypothetical merging of two supermarket chains in Sweden. In another example, the ChatGPT was asked about recommendations for investment in a Brazilian oil company. Finally, it was asked about the factors that influence online shopping behavior. The results are significant and demonstrate the tremendous potential of the ChatGPT in revolutionizing the corporate world.
38
Sumit. "AI Health Care Chatbot". International Journal for Modern Trends in Science and Technology 6, n.º 12 (13 de dezembro de 2020): 219–24. http://dx.doi.org/10.46501/ijmtst061241.
Texto completo da fonteResumo:
Healthcare bot is a technology that makes interaction between man and machine possible by using Artificial Intelligence with the support of dialog flow. Now a day people tend to seek knowledge or information from internet that concern with health through online healthcare services. To lead a good life healthcare is very much important. But it is very difficult to obtain the consultation with the doctor in case of any health issues. The basic aim of this system is to bridge the vocabulary gap between the doctors by giving self-diagnosis from the comfort of one’s place. The proposed idea is to create a medical chatbot using Artificial Intelligence that can diagnose the disease and provide basic details about the disease before consulting a doctor. To reduce the healthcare costs and improve accessibility to medical knowledge the medical bot is built. Certain bots act as a medical reference books, which helps the patient know more about their disease and helps to improve their health. The user can achieve the real benefit of a bot only when it can diagnose all kind of disease and provide necessary information. Hence, people will have an idea about their health and have the right protection.
39
Aquino, Andrea G., Katherine R. Bayona, Kimberly D. Gonzales, Gabrielle D. Reyes e Ria A. Sagum. "Interbot: A Credential Verification Chatbot Using an Enhanced Example Based Dialog Model". International Journal of Future Computer and Communication 3, n.º 4 (2014): 252–57. http://dx.doi.org/10.7763/ijfcc.2014.v3.306.
Texto completo da fonte
40
Artamonova, Maria Valerievna, Akbar Azamatovich Mambetov e Ekaterina Valer'evna Tulina. "Chatbot as a translation tool". Litera, n.º 8 (agosto de 2023): 235–53. http://dx.doi.org/10.25136/2409-8698.2023.8.43875.
Texto completo da fonteResumo:
This article is devoted to the study and analysis of modern technologies, namely artificial intelligence as an auxiliary tool in the work of a translator. The purpose of the study is to find out whether chatbots based on GPT–3.5 technology can be used in translation activities. The article compares the capabilities of chatbots and online text corpora, as well as checks their analytical abilities and ability to rhyme. Dialog assistants are given a task to find information or analyze it based on a query given to them. At the same time, it is checked whether chatbots developed by different companies provide the same information. The scientific novelty of the work lies in the attempt to find a universal tool that can automate the routine work of the translator. A special contribution of the authors of the study is an attempt for the first time to compare and analyze the rapidly developing functionality of chatbots in the context of translation activities and to identify key problems that do not allow the effective use of this technology in translation. As a result, it was determined that the modern GPT language model has many limitations and disadvantages that stop chatbots from becoming a reliable source of information and an efficient translation tool. Problems were identified, the solution of which would make it possible to use Chat GPT and other chatbots in translation activities.
41
Herrera, Kevin, Juan Miranda e David Mauricio. "Milchbot: App to Support the Process of Feeding and Caring for Dairy Cows in Peru". Agris on-line Papers in Economics and Informatics 14, n.º 4 (30 de dezembro de 2022): 27–37. http://dx.doi.org/10.7160/aol.2022.140403.
Texto completo da fonteResumo:
At present, Peru's agricultural sector has a shortfall of professionals, so livestock producers cannot be provided with relevant and reliable information to ensure good nutrition and care for dairy cows, which affects productivity. Milchbot is a chatbot that answers queries about the feeding and care of dairy cows based on reliable documentation. To do so, a chatbot model was designed to cover the topics of feeding, care, news and frequently asked questions for the planning, feeding and care processes about dairy cows. The model consists of a friendly interface, a dialog engine and a search engine that allows you to find and provide information from a document storage. This model was implemented employing Watson Assistant and Discovery. Milchbot was used and evaluated by 6 livestock producers and 7 zootechnicians. The results of the usability and satisfaction surveys show a high rating for both livestock producers and zootechnicians, and it should be noted that zootechnicians gave very high ratings on satisfaction.
42
Chu, Edward T. H., e Zi-Zhe Huang. "DBOS: A Dialog-Based Object Query System for Hospital Nurses". Sensors 20, n.º 22 (19 de novembro de 2020): 6639. http://dx.doi.org/10.3390/s20226639.
Texto completo da fonteResumo:
Due to the advance of indoor positioning technology, it is now possible to trace mobile medical equipment (such as electrocardiography machines, patient monitors, and so on) being moved around a hospital ward. With the support of an object tracking system, nurses can easily locate and find a device, especially when they prepare for a shift change or a medical treatment. As nurses usually face high workloads, it is highly desirable to provide nurses with a user-friendly search interface integrated into a popular mobile app that they use daily. For this, DBOS, a dialog-based object query system, is proposed, which simulates a real conversation with users via the Line messaging app’s chatbot interface. A hybrid method that combines cosine similarity (CS) and term frequency–inverse document frequency (TF-IDF) is used to determine user intent. The result is returned to the user through Line’s interface. To evaluate the applicability of DBOS, 70 search queries given by a head nurse were tested. DBOS was compared with CS, TF-IDF, and Facebook Wit.ai respectively. The experiment results show that DBOS outperforms the abovementioned methods and can achieve a 92.8% accuracy in identifying user intent.
43
Maulidiyah, Ismi Wafda, Zaqiatul Mardiah e Dikri Dirwatul Ghozali. "Pelanggaran Maksim dan Strategi Pelanggaran yang Terjadi pada Dialog Aplikasi Chatbot Simsimi Bahasa Arab dan Inggris". Jurnal Alfazuna : Jurnal Pembelajaran Bahasa Arab dan Kebahasaaraban 4, n.º 2 (19 de junho de 2020): 189–211. http://dx.doi.org/10.15642/alfazuna.v4i02.593.
Texto completo da fonteResumo:
In the era of technology that continues to develop, the way to communicate also develops. One of them is the chatbot as a friend of human communication. This research examines a chatbot that can make users laugh or upset because of the uniqueness of its responses. That is SimSimi, an artificial intelligence. This research examines the extent of SimSimi can communicate effectively and efficiently. In answering this matter, this research analyzes in what topics the flouting maxims are mostly committed by SimSimi. The analysis process relies on the principle of cooperation Grice (1975). Further, each flouting maxims is explored about the strategy of violations that occur, by referring to the idea of Cutting (2002) about the maxim violation strategy. In addition, with SimSimi's multilingual expertise, this research also compares the differences in the frequency of flouting maxims by SimSimi in Arabic and English. Therefore, this research utilizes comparative studies using qualitative methods. The conversations analyzed were 40 conversations containing 4 topics. Based on 20 Arabic conversations, there were 32 flouting maxims. As for the 20 conversations in English, there were 30 flouting maxims. This shows the comparison of the frequency of flouting maxims in Arabic and English dialogue at 16:15. As for the strategies of flouting maxims that occurred, there are 10 kinds of strategies in Arabic dialogue and 6 kinds of strategies in English dialogue. In Arabic dialogues, the topic that contains the most violations of the maxims is the topic of religion. So it is with English dialogue. The results of the research show that SimSimi in English can communicate more effectively and efficiently compared to its use in Arabic.
44
Zain Ahmad Taufik e Supriyanto Supriyanto. "Implementasi Chatbot untuk Layanan Frequently Asked Question Akademik dengan Penggunaan Dialogflow". Jurnal SAINTEKOM 13, n.º 1 (31 de março de 2023): 1–10. http://dx.doi.org/10.33020/saintekom.v13i1.337.
Texto completo da fonteResumo:
Academic Frequently Asked Questions (FAQ) service is a service designed to answer academic questions that are often asked by students. A survey conducted on April 12, 2022, to 33 students of the Ahmad Dahlan University Informatics study program showed that 39.4% of students rarely open the FAQ menu on the portal application. Students more often ask questions to administrators and lecturers, but 30.3% of students receive answers that last more than 10 minutes. Chatbot is an artificial intelligence system used to interact with users in real-time to provide information. The use of dialog flow in the system helps manage information and can provide an answer quickly and precisely to users. This research uses the waterfall method, which is a simple classic model with a linear flow system. The User Experience Questionnaire (UEQ) survey results get a score of 1,536 for attractiveness, 1,714 for clarity, 1,375 for efficiency, 1,357 for fixity, 1,536 for stimulation, and 0.964 for novelty. Based on these results, it shows that the application level is above average on the UEQ scale.
45
Lutfiani, Ninda, Sutarto Wijono, Untung Rahardja, Ade Iriani, Qurotul Aini e Rafly Ananda Dwi Septian. "A Bibliometric Study : Recommendation based on Artificial Intelligence for iLearning Education". Aptisi Transactions on Technopreneurship (ATT) 5, n.º 2 (30 de novembro de 2022): 112–19. http://dx.doi.org/10.34306/att.v5i2.279.
Texto completo da fonteResumo:
Since most students begin their studies online, the LMS platform is frequently used. Universities and colleges play a crucial role in adopting many of its LMS platforms. A web-based application software package called Bibliometrics is used to design, test, and evaluate specific learning processes. LMS will be the dominant artificial intelligence-based solution for managing eLearning starting in early 2021. The principal objective of this project is to develop an artificial intelligence-powered LMS portal that enables students to continue studying and receive the most recent lessons from their teachers. Using the Communicate cloud software and Dialog Flow, a chatbot plugin system connected to the Google platform, and based on current needs, research bibliometrics was developed as an LMS project system. Students can interact with the chatbot anytime to satisfy their learning needs as long as they have an internet connection and a student ID card to access the dashboard. The LMS Platform, which was developed utilizing Bibliometrics and Artificial Intelligence approaches to help students access resources and complete teacher tasks, is a novelty in this work, according to earlier publications that have been evaluated.
46
Shilowaras, Mahendran, e Nor Amizam Jusoh. "Implementing Artificial Intelligence Chatbot in Moodle Learning Management System". Engineering, Agriculture, Science and Technology Journal (EAST-J) 1, n.º 1 (2 de agosto de 2022): 70–75. http://dx.doi.org/10.37698/eastj.v1i1.122.
Texto completo da fonteResumo:
Learning Management System (LMS) is a software application or web-based technology that is used to develop, implement, and evaluate a specific learning process. KYP has implemented an e-Learning Management System (e-LMS) using Moodle since early 2021. The main features already implemented in this e-LMS is course details and it should also support the communication process between lecturers and students where currently, the KYP e-LMS lack of. Usually, students will ask the same question to their lecturer in person and cause the lecturer to have to give the same answers repeatedly. This results in a waste of time for both parties in answering and receiving answers. To overcome the problem, there is a need to replace the manual way of getting answers to any kind of academic or course related questions repeatedly. The main objective of the project is to develop an intelligence Chatbot which can help students finding academic related information without the need to ask their instructors or spent more time browsing menus in e-LMS. E-LMS has been developed based on Rational Unified Process (RUP) approach. In this project, the Moodle system is fully implemented by integrating with Kommunicate, one of the Cloud software and Dialog Flow, which is a chatbot plugin system connected with Google Could Platform. An AI Chatbot able to interact with students and can provide answer to students' queries instantly despite of the place, date and time zone of the student as well as enhances interaction which provides a feel of support to the students.
47
Villa, Laura, David Carneros-Prado, Cosmin C. Dobrescu, Adrián Sánchez-Miguel, Guillermo Cubero e Ramón Hervás. "Comparative Analysis of Generic and Fine-Tuned Large Language Models for Conversational Agent Systems". Robotics 13, n.º 5 (29 de abril de 2024): 68. http://dx.doi.org/10.3390/robotics13050068.
Texto completo da fonteResumo:
In the rapidly evolving domain of conversational agents, the integration of Large Language Models (LLMs) into Chatbot Development Platforms (CDPs) is a significant innovation. This study compares the efficacy of employing generic and fine-tuned GPT-3.5-turbo models for designing dialog flows, focusing on the intent and entity recognition crucial for dynamic conversational interactions. Two distinct approaches are introduced: a generic GPT-based system (G-GPT) leveraging the pre-trained model with complex prompts for intent and entity detection, and a fine-tuned GPT-based system (FT-GPT) employing customized models for enhanced specificity and efficiency. The evaluation encompassed the systems’ ability to accurately classify intents and recognize named entities, contrasting their adaptability, operational efficiency, and customization capabilities. The results revealed that, while the G-GPT system offers ease of deployment and versatility across various contexts, the FT-GPT system demonstrates superior precision, efficiency, and customization, although it requires initial training and dataset preparation. This research highlights the versatility of LLMs in enriching conversational features for talking assistants, from social robots to interactive chatbots. By tailoring these advanced models, the fluidity and responsiveness of conversational agents can be enhanced, making them more adaptable and effective in a variety of settings, from customer service to interactive learning environments.
48
Kumar, Sunil, Dr Shivani Dubey, Prof Vikas Singhal, Dr Ajay Kumar Sahu e Dr Pankaj Gupta. "Career Counselling Chatbot on Facebook Messenger using AI". International Journal of Innovative Research in Advanced Engineering 11, n.º 01 (27 de janeiro de 2024): 08–15. http://dx.doi.org/10.26562/ijirae.2024.v1101.02.
Texto completo da fonteResumo:
Work instructions have always been necessary, but in recent times they have only gained the respect they deserve and now that they are in high demand and available worldwide, it is important to have a simple understanding of the various tasks that need to be done. Career counsellors are responsible for providing high school students with the experience and skills they need to make informed career decisions, education, and long-term goals. Music; It is a social event that unites people regardless of market, age, history, language, interests, political affiliation and income. Music and streaming apps are in demand because they are versatile and compatible with daily life, travel, sports and other activities. The rise of mobile phones and digital multimedia technology has made digital music a consumer favourite for many young people. Although career orientation has always been important, it has recently become widely recognized as a key element in today's career change research. High school students, in particular, need early and sustained exposure to many popular careers around the world. This information allows them to make decisions that patiently pursue their educational preferences. Music is a unifying force that transcends borders and barriers and plays a special role in this field. Music and streaming services are integrated into daily life, travel and entertainment, resulting in a universal love of music. The growth of mobile phones and digital technology has brought digital music even more to the forefront of youth content. However, many students do not have enough guidance to bridge the gap between their education, passions, and future career goals. This often leads to frustration and inability to take action. To meet this need, our web career counselling program, based on the ASP.NET Framework, provides students with career planning tools, skills development and opportunity guidance through a Google Dialog flow-powered counselling chatbot. By exploring music as a potential career path and leveraging its global appeal, we aim to inspire and guide students into a successful and rewarding career.
49
Roca, Surya, Sophie Rosset, José García e Álvaro Alesanco. "A Study on the Impacts of Slot Types and Training Data on Joint Natural Language Understanding in a Spanish Medication Management Assistant Scenario". Sensors 22, n.º 6 (18 de março de 2022): 2364. http://dx.doi.org/10.3390/s22062364.
Texto completo da fonteResumo:
This study evaluates the impacts of slot tagging and training data length on joint natural language understanding (NLU) models for medication management scenarios using chatbots in Spanish. In this study, we define the intents (purposes of the sentences) for medication management scenarios and two types of slot tags. For training the model, we generated four datasets, combining long/short sentences with long/short slots, while for testing, we collect the data from real interactions of users with a chatbot. For the comparative analysis, we chose six joint NLU models (SlotRefine, stack-propagation framework, SF-ID network, capsule-NLU, slot-gated modeling, and a joint SLU-LM model) from the literature. The results show that the best performance (with a sentence-level semantic accuracy of 68.6%, an F1-score of 76.4% for slot filling, and an accuracy of 79.3% for intent detection) is achieved using short sentences and short slots. Our results suggest that joint NLU models trained with short slots yield better results than those trained with long slots for the slot filling task. The results also indicate that short slots could be a better choice for the dialog system because of their simplicity. Importantly, the work demonstrates that the performance of the joint NLU models can be improved by selecting the correct slot configuration according to the usage scenario.
50
Knaus, Thomas, e Gerhard Tulodziecki. "Thomas Knaus im Gespräch mit Gerhard Tulodziecki". Ludwigsburger Beiträge zur Medienpädagogik 23 (10 de outubro de 2023): 1–23. http://dx.doi.org/10.21240/lbzm/23/22.
Texto completo da fonteResumo:
Es ist Mai. Das Sommersemester ist in vollem Gange. Gerhard Tulodziecki hat vor wenigen Tagen ein neues Buch veröffentlicht: Es geht um individuelles Handeln, Gemeinwohl, Verantwortung und Künstliche Intelligenz (KI). Thomas Knaus kommt gerade aus seiner Einführungsvorlesung: In der heutigen Veranstaltung ging es um Medienentwicklung und deren gesellschaftlich-kulturelle Bedeutung. Auf den Folien zu KI-Expertensystemen und Machine Learning, die sich schon viele Jahre in seinem Foliensatz befinden, hat er für dieses Semester den Zusatz „Ausblick“ entfernt – die ursprünglichen Aussichten wurden inzwischen Realität: KI-basierte Dialog- sowie text- und bildgenerierende Systeme sind in unserem Alltag angekommen. In der Sitzung der Institutsleiter*innen in der vorletzten Woche ging es um „ChatGPT in Lehre und Prüfungen“. Einige Lehrende befürchten, dass sie eine ‚Künstliche Intelligenz‘ ersetzen könnte; der Geschichtsprofessor sorgt sich in Anbetracht textgenerierender KI um seine Studierenden, die die Kulturtechnik des Schreibens verlernen würden und andere Kolleg*innen berichten, wie sie text- und bildgenerative KI in der Lehre thematisieren, kontrovers mit Studierenden diskutieren und kreativ in Prüfungen einbinden. Auf Nachfrage einiger Kolleg*innen entstand am letzten Wochenende ein kurzes Video zu einer praktischen prüfungsrechtlichen Frage in der kleinen YouTube-Serie Medienpädagogik im Schaukelstuhl – eigentlich ein Format für Studierende.Alle Welt spricht derzeit von KI – konkreter von text- und bildgenerierenden Systemen – und noch konkreter von einem Chatbot, der auf einem large language model, dem Textgenerator GPT, basiert und vom US-amerikanischen Unternehmen OpenAI öffentlichkeitswirksam vorgestellt wurde. In dem hier verschriftlichten Gespräch begegnen sich zwei Medienpädagogen, die sich bereits seit vielen Jahren auch mit technischen und informatischen Fragen – und daher auch mit KI und ihrer gesellschaftlichen Bedeutung – befassen. Es gibt viel zu erzählen.