KNOWLEDGE GRAPH CREATION AND USER QUERYING ON HOSPITAL DATA: AN ONTOLOGICAL APPROACH Shruti Srivatsan 1 , Rahul Singhal 2 , Priyabrata Panda 3 1 Department of Mathematics, University of Waterloo, Canada shrutisrisvce@gmail.com 2 Department of Computer Science and Engineering, Jaypee Institute of Information Technology, Noida, India rahulsinghal1904@gmail.com 3 Department of Electrical Engineering, Maulana Abul Kalam Azad University of Technology, Kolkata, India priyabratapanda20000@gmail.com ABSTRACT Every hospital has a large number of staff including doctors, nurses, ward clerks and patients. For the enhanced functioning of the hospital, it is essential to have a system which can efficiently store records of hospital personnel in a robust manner. It is difficult to maintain a system which can update the records regularly and establish the relationships among the various classes clearly. By having such a system, it is easier to process user queries in an automated manner apart from storing records. This project involves creating a robust system for storing large amounts of data in a graph database and retrieving information based on user queries. The first step involves devising an ontology for the hospital use case followed by addition of data to a graph database and performing Natural Language Processing (NLP) techniques on user queries. The ontology is devised after gaining domain knowledge about the working of the hospital. Using the ontology, the graph nodes are created using Cypher Query Language (CQL) on the Neo4J platform. NLP techniques such as keyword extraction are applied to user queries to retrieve the necessary information from the graph database. KEYWORDS Hospital Ontology, Knowledge Graph, Natural Language Processing, User query 1. INTRODUCTION A hospital comprises various personnel including doctors, patients and other staff. A graph- based database system would be efficient for storing large amounts of records and is easier to retrieve user queries. The objective of this work is to develop an ontology for hospital use case followed by a graph database to store records and perform querying. There are a lot of people involved in the smooth functioning of a hospital and they can roughly be categorized into the following: • Doctors • Allied Health Professionals • Nurses • House Keeper • Ward Clerk • Lab Assistant • Cashier • Patient