• Dr Sridevi Tumula
• Sai Vinitha Yeggadi
• V. Indira Priyadarshini

Scheduling a meeting manually is a low level but is a time-consuming task. It cannot be done in a single go; instead, it takes multiple emails with several backs and forth negotiations over the date and time. To solve this problem and make this process automated, this scheduler is introduced. By conversing with this virtual assistant, the user can initiate a meeting by specifying the dayparts/time and set of participants for the meeting. This system's main aim is to schedule a meeting efficiently, i.e., without conflicts and with minimum user interactions. The system interprets user utterance using Intent Classifier followed by Name Entity Recognizer. Multi-Label Classifier maps initiator's utterance (example afternoon) to multiple possible time slots. After estimating time slots, Reinforcement Learning is used to select an agreeable timeslot. Based on the prior experience of scheduling meetings with different users in the system, the reinforcement learning-based bot attempts to choose slots with the maximum probability of participants agreeing. The agent will automatically schedule an appointment and tag the conference details to the user's calendar.

Agent , Scheduling,Process Automation,Virtual Assistant,Classifier,Reinforcement Learning

"Pluto: AI-Based Meeting Scheduler ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 6, page no.d673-d682, June-2021, Available :http://www.jetir.org/papers/JETIR2106502.pdf

"Pluto: AI-Based Meeting Scheduler ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 6, page no. ppd673-d682, June-2021, Available at : http://www.jetir.org/papers/JETIR2106502.pdf