A Chatbot is a software application that replaces a live human agent to conduct a conversation via text or text to speech. It is designed to behave like a human would behave in that conversation. In this system, we demonstrate a chatbot that uses Artificial Intelligence to produce dynamic responses to online client enquiries. This web-based platform provides a vast intelligent base that can help humans to solve problems. The chatbot recognises the user's context, which prompts an intended response. Because this is a dynamic response, the user's desired response will be generated. This also uses a machine-learning algorithm to learn the chatbot by experiencing various requests and responses. Chatbots come to use in numerous fields of our daily life. Because AI enhances the human touch in every communication, chatbots are becoming increasingly robust.. It triggers accurate responses after understanding a user's query. Its objective is to reduce human dependency in every organisation and reduce the need for different systems for different processes.

Intelligent Chatbot

Unstructured data from the internet constitute large sources of information, which need to be formatted in a user-friendly way. This research develops a model that classifies unstructured data from data mining into labeled data, and builds an informational and decision-making support system (DMSS). We often have assortments of information collected by mining data from various sources, where the key challenge is to extract valuable information. We observe substantial classification accuracy enhancement for our datasets with both machine learning and deep learning algorithms. The highest classification accuracy (99% in training, 96% in testing) was achieved from a Covid corpus which is processed by using a long short-term memory (LSTM). Furthermore, we conducted tests on large datasets relevant to the Disaster corpus, with an LSTM classification accuracy of 98%. In addition, random forest (RF), a machine learning algorithm, provides a reasonable 84% accuracy. This research’s main objective is to increase the application’s robustness by integrating intelligence into the developed DMSS, which provides insight into the user’s intent, despite dealing with a noisy dataset. Our designed model selects the random forest and stochastic gradient descent (SGD) algorithms’ F1 score, where the RF method outperforms by improving accuracy by 2% (to 83% from 81%) compared with a conventional method.

Real-Time AI-Based Informational Decision-Making Support System Utilizing Dynamic Text Sources

A Chatbot is software that makes an interaction between user and machine where the automatic responses will be generated. Chatbot can make the user to think that he/she is chatting with another human by using these bots. The usage of a smart phone with many applications increased. The motive of the chatbot is to generate a quick response within less time to the user’s query and reduce the workload of the management system. Every year, there is a breakthrough in the field of artificial intelligence. Bots are now utilized for communication to provide required or predetermined acknowledgment. The Chatbot should be forthright and communicative. They assist us by providing distraction, saving time, and reducing stress. These are designed to simulate the behavior of a human to engage with the real-time conversations. A remarkable customer experience can be built by using chatbots. These can be utilized by a large number of people at the same time. Our concept of considering chatbot can help students in pandemic and socially distant situations. The proposed system is developed by using Multinomial Naive Bayes algorithm and will be able to act as user side and generate responses to the user queries accurately.

Information Chatbot for College Management System Using Multinomial Naive Bayes

Multi-vehicle coordinated motion planning has always been challenged to safely and efficiently resolve conflicts under non-holonomic dynamic constraints. Constructing spatial-temporal corridors for multi-vehicle can decouple the high-dimensional conflicts and further reduce the difficulty of obtaining feasible trajectories. Therefore, this paper proposes a novel hierarchical method based on interactive spatio-temporal corridors (ISTCs). In the first layer, based on the initial guidance trajectories, Mixed Integer Quadratic Programming is designed to construct ISTCs capable of resolving conflicts in generic multi-vehicle scenarios. And then in the second layer, Non-Linear Programming is settled to generate in-corridor trajectories that satisfy the vehicle dynamics. By introducing ISTCs, the multi-vehicle coordinated motion planning problem is able to be decoupled into single-vehicle trajectory optimization problems, which greatly decentralizes the computational pressure and has great potential for real-world applications. Besides, the proposed method searches for feasible solutions in the 3-D $(x,y,t)$ configuration space, preserving more possibilities than the traditional velocity-path decoupling method. Simulated experiments in unsignalized intersection and challenging dense scenarios have been conduced to verify the feasibility and adaptability of the proposed framework.

A Hierarchical Multi-Vehicle Coordinated Motion Planning Method based on Interactive Spatio-Temporal Corridors

Chat and Voice Bot Implementation for Cardio and ENT Queries Using NLP

A chatbot is an interactive AI tool that tries to imitate human behavior that interprets information provided and responds accordingly in either textual or audio format Nowadays chatbots are used to efficiently carry out digital communication Our concept introduces a new field of research in chatbot communication Nowadays most chatbots efficiently complete the required task, but there is one thing to notice Many of the conversations between a human and a chatbot are repetitive Technology has always been reducing human effort and hence a multi-agent system is proposed that has a chatbot as a middleware between the user and the outside world This chatbot has something unique, ie it understands the user and their requirements It is like having an assistant who understands the user & their requirements Now since it understands the user, it has the capability of making decisions on behalf of the user, thereby reducing the efforts of a user to carry out a task Our concept of considering one task that is done with the help of a chatbot is demonstrated The proposed system adapts and acts accordingly on behalf of the user

A Self Learning Chat-Bot From User Interactions and Preferences

Multi-Agent Pathfinding (MAPF) is the task of finding paths for more than one agent in a common environment such that each agent reaches its goal and does not collide. Multi-Agent Path Finding is a problem that is related to various applications ranging from robot movements, game simulations, self-driving vehicles, etc. Most of the existing solutions to these problems are providing paths to each agent which they shall follow. These paths are optimal but are calculated once for a certain fixed and known scenario. There might be collisions and time-based overlapping paths if another agent or an obstacle is dynamically added to the grid. Thus, there is a need to have a system that deals with such situations while providing the most possible optimal path. Hence, we propose a solution to this problem by using a Deep Learning Model trained on a dataset made using an A* pathfinding algorithm that can take decisions at run time for each agent while making sure it does not collide with any obstacle or any other agent and handles all sort of dynamic variations in the environment at any point of time while not relying on precomputation.

Manas Sinkar

Papers

A Self Learning Chat-Bot From User Interactions and Preferences

Multi-Agent Path Finding using Dynamic Distributed Deep Learning Model