SmartMeet: An AI-powered Meeting Scheduler with Email Automation

References

[1] J. Cranshaw et al., “Calendar.help: Designing a Workflow-Based Scheduling Agent with Humans in the Loop,” in Proc. CHI Conf. Human Factors in Computing Systems, Denver, CO, May 2017, pp. 2382–2393.

[2] S. Busemann, T. Declerck, et al., “Natural Language Dialogue Service for Appointment Scheduling Agents,” in Proc. 5th Conf. Applied Natural Language Processing, Washington, DC, 1997, pp. 25–32.

[3] D. Vishwanath and L. Vig, “Meeting Bot: Reinforcement Learning for Dialogue Based Meeting Scheduling,” in AAAI Conf. Artificial Intelligence, New Orleans, LA, Feb. 2018, pp. 8135–8136.

[4] K. Yang and N. Pattan, “Multi-Agent Meeting Scheduling Using Mobile Context,” in IEEE/WIC/ACM Int. Conf. Intelligent Agent Technology, Compiegne, France, Sept. 2005, pp. 488–491.

[5] E. Shakshuki, H. Koo, and D. Benoit, “A Distributed Multi-Agent Meeting Scheduler,” J. Computer Science and Technology, vol. 18, no. 3, pp. 295–304, May 2003.

[6] S. D. Gopalan and D. A. Sontag, “Learning to Schedule Meetings with a Calendar Virtual Assistant,” arXiv:2109.04596, Sept. 2021.

[7] M. G. Lee et al., “TaskMining: A Task-Centric Meeting Assistant,” Proc. ACM on Human-Computer Interaction, vol. 4, no. CSCW2, pp. 1–26, Oct. 2020.

[8] Y. K. Thang et al., “A Context-Aware Personal Assistant for Managing Social Events,” in 24th Int. Conf. Intelligent User Interfaces, Marina del Ray, CA, Mar. 2019, pp. 423–434.

[9] B. A. Plummer et al., “Dialogue Learning with Human-in-the-Loop,” in Proc. 34th Int. Conf. Machine Learning, vol. 70, Sydney, Australia, Aug. 2017, pp. 2832–2841.

[10] A. Rastogi et al., “Schema-Guided Dialogue State Tracking for Virtual Assistant Scheduling,” in Proc. 21st Annual SIGdial Meeting on Discourse and Dialogue, Virtual, July 2020, pp. 1–11.

[11] L. P. Willcocks, M. Lacity, and A. Craig, “The IT Function and Robotic Process Automation,” LSE Outsourcing Unit Working Paper Series, Rep. 15/05, 2015.

[12] A. Vaswani et al., “Attention Is All You Need,” in Advances in Neural Information Processing Systems 30, Long Beach, CA, Dec. 2017, pp. 5998–6008.

[13] T. B. Brown et al., “Language Models are Few-Shot Learners,” in Advances in Neural Information Processing Systems 33, Virtual, Dec. 2020, pp. 1877–1901.

[14] A. Radford et al., “Robust Speech Recognition via Large-Scale Weak Supervision,” arXiv:2212.04356, Dec. 2022.

[15] D. Jurafsky and J. H. Martin, Speech and Language Processing, 3rd ed. Stanford, CA: Stanford University, 2023.

[16] D. Xiao, M. Chen, and J. Zhang, “Enterprise Calendar Integration Patterns Using RESTful APIs,” IEEE Trans. Services Computing, vol. 12, no. 4, pp. 654–667, July–Aug. 2019.

[17] A. Cambria and B. White, “Jumping NLP Curves: A Review of Natural Language Processing Research,” IEEE Computational Intelligence Magazine, vol. 9, no. 2, pp. 48–57, May 2014.

[18] M. Henderson, B. Thomson, and S. Young, “Deep Neural Network Approach to Dialogue State Tracking Challenge,” in Proc. SIGDIAL 2013 Conf., Metz, France, Aug. 2013, pp. 467–471.

[19] S. J. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 4th ed. Hoboken, NJ: Pearson, 2020.

[20] P. Lison and C. Kennington, “OpenDial: A Toolkit for Developing Spoken Dialogue Systems with Probabilistic Rules,” in Proc. ACL 2016 System Demonstrations, Berlin, Germany, Aug. 2016, pp. 67–72.

@article{1713229,
      author = {Rahul Yadav, Shiwam Maddhesiya, Rohan Prasad, Ali Abdullah, Harvendra Kumar Patel},
      title = {SmartMeet: An AI-powered Meeting Scheduler with Email Automation},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {9},
      number = {7},
      pages = {2671-2680},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1713229.pdf},
      abstract = {Modern organizational workflows have been progressively dependent on sophisticated approaches to meeting coordination between people. However, traditional scheduling methods are still annoyingly inefficient, require heavy manual work, and are vulnerable to human error. We present SmartMeet, an intelligent automation framework that manages the entire meeting life cycle via natural conversational interfaces. Our multiple AI capabilities automatic speech recognition, transformer-based language understanding, large language model reasoning, and robotic process automation allow the system to execute the account action from a voice scheduling request without any human intervention.Different from currently available semi-automated tools which still require structured input or human verification at certain points, SmartMeet enables freeform speech, gets scheduling details by semantic parsing, resolves time conflicts algorithmically, makes calendar entries across systems, creates meeting links, and personalized notification emails, etc. all by itself. Through this research, we demonstrate that speech-to-intent pipelines are capable of handling real-world enterprise scheduling scenarios, invent new ways for detecting conflicts and suggesting alternatives, and present that cognitive AI components can be seamlessly integrated with deterministic RPA execution layers. Our design concepts have functionalities that complement the gaps of meeting automation research. It is a fully autonomous and natural language based solution that, in a measurable manner, assists in the reduction of the delayed scheduling cases, the elimination of the booking conflicts occurrences, and the improvement of the organizational productivity.},
      keywords = {Automated Meeting Coordination, Natural Language Understanding, Large Language Models, Calendar Integration, Email Automation, Conflict Resolution Algorithms},
      month = {January},
      doi = {https://doi.org/10.64388/IREV9I7-1713229}
  }