Project Abstract

While databases are crucial to almost any business and its operations, users often need training, make mistakes, and may feel uncomfortable using a particular database, as databases are not all created equal nor are intuitively navigable and/or well-designed. Arguably, the internet is a database, and the browser is a user interface to a database; while internet browsing has become intuitive, other databases and their interfaces are not. Designing a Database Management System (DBMS) that is intuitive to use and user-friendly may not be easily achieved in specialised fields, i.e. healthcare.Integrating an Artificial Intelligence aid into the user experience may limit and/or eliminate the user?��s interaction with newly created or poorly designed databases in the first place. A predefined set of instructions triggered by a written or dictated command from the user can help load, navigate, validate, visualise, and manipulate the data. The solution is envisioned as a search field interface, allowing users to type or dictate queries in their natural language. These queries are then translated into instructions to be applied to multiple databases. As a result, the user does not have to interact directly with poorly designed or newly created databases.Advanced solutions harnessing the power of machine learning are to be explored to automate the process while respecting the research’s available time frame.

Keywords: DBMS, AI, NLP

 Conference Details

Session: Presentation Stream 8 at Presentation Slot 9

Location: GH037 at Tuesday 7th 13:30 – 17:00

Markers: Galileo Sator (GTA), Ulrich Berger

Course: MSc Computer Science 2yr PT, Masters PG

Future Plans: I’m undecided