Third Review Chatbot
Third Review Chatbot
VII SEMESTER
• Chatbots, also known as conversational agents, are designed with the help of AI (Artificial Intelligence)
software. They simulate a conversation (or a chat) with users in a natural language via messaging
applications, websites, mobile apps, or phone.
• Web-based applications
• Standalone applications
• Chatbots represent a potential shift in how people interact with data and services online. While there is
currently a surge of interest in chatbot design and development, we lack knowledge about why people
use chatbots.
• Chatbots allow businesses to connect with customers in a personal way without the expense of
human representatives. For example, many of the questions or issues customers have are
common and easily answered. That's why companies create FAQs and troubleshooting guides.
• The multiple sources of information become more and more accessible. However, the
availability of a wide range of e-learning offers makes it difficult for learners to find the right
content for their training needs. In this context, our paper aims to design an e-learning AI-
powered Chatbot allowing interaction with learners and suggesting the e-learning content
adapted to their needs. In order to achieve these objectives, we first analysed the e-learning
multimedia content to extract the maximum amount of information. Then, using Natural
Language Processing (NLP) techniques, we introduced a new approach to extract keywords.
After that, we suggest a new approach for multimedia indexing based on extracted keywords.
Finally, the Chatbot architecture is realized based on the multimedia indexing and deployed on
online messaging platforms.
LITERATURE SURVEY
S.NO BASE PAPER YEAR PURPOSES
• Limited understanding of natural language: chatbots are still under development, and their ability
to understand and respond to natural language is limited. This can lead to misunderstandings and
frustration for users.
• Lack of personalization: Adaptive chatbots are often trained on a large dataset of conversations,
but they may not be able to personalize their responses to individual users. This can make the
experience feel less engaging and helpful.
• Bias: Adaptive chatbots can be biased, reflecting the biases in the data that they are trained on. This
can lead to unfair or discriminatory treatment of certain users.
• Privacy concerns: Adaptive chatbots collect a lot of data about their users. This data can be used to
track users' activities and preferences, which raises privacy concerns.
Proposed Work
Adaptive chatbots is to develop chatbots that can learn and adapt to their users over time.
This will allow chatbots to learn the patterns of human language and behavior, and to generate more natural and engaging responses.
Reinforcement learning is a type of machine learning approach that can be used to train chatbots to learn how to interact with users in a way that is
helpful and informative.
Here are some specific examples of the proposed work of adaptive chatbots:
• Personalized customer service: Adaptive chatbots can be used to provide personalized customer service experiences. For example, a chatbot
could learn a customer's preferences and needs over time, and then use t/hat information to provide more relevant and helpful recommendations.
• Personalized education: Adaptive chatbots can be used to provide personalized education experiences. For example, a chatbot could tailor its
patient to track their symptoms, manage their medications, and schedule appointments.
Adaptive chatbots are still under development, but they have the potential to have a significant impact on our lives. By developing chatbots that can
learn and adapt to their users, we can create more personalized and engaging experiences for everyone.
MODULES
• Data collection: The first step is to collect a large dataset of conversations. This dataset can be collected from
customer service logs, social media conversations, or other sources.
• Data preprocessing: Once the dataset has been collected, it needs to be preprocessed to clean it and make it
suitable for machine learning. This may involve removing noise, correcting spelling errors, and normalizing
the text.
• Model training: The next step is to train a machine learning model on the preprocessed dataset. This model
can be trained using a variety of different techniques, such as supervised learning, unsupervised learning, or
reinforcement learning.
• Model evaluation: Once the model has been trained, it needs to be evaluated on a held-out test set. This will
help to assess the accuracy and performance of the model.
• Deployment: Once the model has been evaluated and found to be satisfactory, it can be deployed to
production. This means making the model available to users so that they can interact with it.
• Monitoring and improvement: Once the model is deployed, it is important to monitor its performance and
make improvements as needed. This may involve collecting feedback from users, identifying areas where the
model is struggling, and retraining the model on new data.
ARCHITECTURE DIAGRAM
ARCHITECTURE FLOW
ARCHITECTURE LAYERS
• Presentation layer: The presentation layer is responsible for interacting with the user. This may include a
graphical user interface (GUI), a command-line interface (CLI), or a voice interface.
• Application layer: The application layer is responsible for processing the user's input and generating
responses. This layer may include modules for natural language understanding (NLU), natural language
generation (NLG), dialogue management, and user modeling.
• Data access layer: The data access layer is responsible for storing and retrieving data from the knowledge
base. This layer may include a database, a rule base, or a combination of both.
• Data processing layer: The data processing layer is responsible for pre-processing and cleaning the data
before it is stored in the knowledge base. This layer may include modules for tokenization, stemming, and
lemmatization.
Methodology
Natural language understanding (NLU) module: This module is responsible for understanding the user's input.
It does this by breaking the input down into tokens, such as words and phrases, and then identifying the
meaning of those tokens. The NLU module may also use natural language processing (NLP) techniques to
identify the intent and sentiment of the user's input.
Natural language generation (NLG) module: This module is responsible for generating responses to the user's
input. It does this by selecting a response from a set of pre-generated responses, or by generating a new
response on the fly. The NLG module may also use NLP techniques to ensure that the responses are natural
and fluent.
Dialogue management module: This module is responsible for managing the conversation between the user and
the chatbot. It does this by keeping track of the conversation state, such as the topic of conversation and the
current user goal. The dialogue management module may also use decision trees or other techniques to
determine the next best action to take.
• Learning module: This module is responsible for learning from the user's interactions with the chatbot.
It does this by collecting data about those interactions and using it to improve the chatbot's
performance. The learning module may also use machine learning techniques to identify patterns in the
data.
• Knowledge base module: This module stores the chatbot's knowledge. It can be a database, a rule
base, or a combination of both. The knowledge base is used by the NLU and NLG modules to answer
the user's questions and generate responses.
• User modeling module: This module is responsible for modeling the user's behavior. It does this by
collecting data about the user, such as their conversation history and their preferences. The
user modeling module may also use machine learning techniques to identify patterns in the user's behavior.
Demo Screenshot
Frontend Interface
LOGIN AND SIGNUP
DEMO CONVERSATION
SOFTWARE AND HARDWARE REQUIREMENTS
SOFTWARE REQUIREMENTS:
• Python (3.7.4)
• IDE (Jupyter)
• Numpy (version 1.16.5)
• Skimage.
• TKinter.
• VS code
HARDWARE REQUIREMENTS:
• SSD
• 16GB RAM
REFERENCES
• 1] M. Akhtar, J. Neidhardt, and H. Werthner, ‘‘The potential of chatbots:Analysis of chatbot
conversations,’’ in Proc. IEEE 21st Conf. Bus. Informat. (CBI), Jul. 2019, pp. 397–404.
• [2] M. T. Zemčík, ‘‘A brief history of chatbots,’’ DEStech Trans. Comput. Sci.Eng., vol. 2019, pp.
14–18, Oct. 2019.[3] E. Adamopoulou and L. Moussiades, ‘‘An overview of chatbot technology,’’
in Artificial Intelligence Applications and Innovatio(IFIP Advances in Information and
Communication Technology),I. Maglogiannis, L. Iliadis, and E. Pimenidis, Eds. Cham,
Switzerland:Springer, 2020, pp. 373–383.