AI-Assisted Intelligent Task Manager with ML- Based Priority Classification and Conversational AI

Abstract

Intoday\'sfastpacedprofessionalandacademicenvironments,effectivetaskmanagementisacriticalchallenge.Thispaperpresents the design and implementation of an AI-Assisted Intelligent Task Manager, a web-based application that leverages machine learning to automatically classify and prioritize user-submitted tasks. The system employs a multi-feature ML model trained on task metadata including deadlines, dependencies, estimated effort, and contextual keywords to generate a dynamic priority score for each task. A natural language chatbotinterface,poweredbyalargelanguagemodel (LLM),enablesuserstointeract conversationallywiththesystemqueryingtaskstatus,askingforpriorityexplanations,andreceivingintelligentschedulingsuggestions.Thesystemadditionallysupportssmartreminders,workloadforecasting,andintegrationwithcalendarAPIs.Evaluationresultsdemonstratehighclassificationaccuracyandstrongusersatisfaction,making the system a robust solution for intelligent personal and team productivity management.

Introduction

The text describes an AI-Assisted Intelligent Task Manager designed to improve task organization in fast-paced academic and professional environments. The system uses machine learning to automatically classify and prioritize tasks based on factors such as deadlines, dependencies, effort, and keywords, generating a dynamic priority score.

It also includes an LLM-powered chatbot interface that allows users to interact naturally with the system to check task status, understand priority decisions, and receive scheduling recommendations. Additional features include smart reminders, workload forecasting, and calendar integration.

Evaluation results show high accuracy and strong user satisfaction, indicating that the system is an effective solution for intelligent task and productivity management.

Conclusion

ThispaperhaspresentedacomprehensiveAIAssistedIntelligentTaskManagerthatcombinesmachinelearningbasedpriorityclassificationwithaconversationalAIinterfacetocreateanintelligent,explainable,anduser-friendlyproductivitytool. The proposed system addresses the critical limitations of existing task management solutions by automating priority scoring, providing natural-language explanations, and offering proactive workload management features. The experimental evaluation demonstrates that the system achieves state-of-the-art priority classification accuracy of 94.7% while maintaining low inference latency suitable for real-time use. The user study confirms practical utility, with participants reporting an average productivity improvement of 31% and high satisfaction with the chatbot\'s explanatory capabilities. Futureworkwillexplorefederatedlearningtoenablemodelpersonalizationwithoutcompromisinguserprivacy,multi- modal task input supporting voice and image attachments, and advanced multi-agent collaboration features for enterprise deployments.

References

[1] M. V. Mäntylä, B. Adams, F. Khomh, E. Engström, and K. Petersen, \"On rapid releases and software testing: a case study and a semi-systematic literaturereview,\" Empirical Software Engineering, vol. 20, no. 5, pp. 1384–1425, 2015. [2] K.Tian,M.Revelle,andD.Poshyvanyk,\"Usinglatentdirichletallocationforautomaticcategorizationofsoftware,\"inProc.6thIEEEInt.WorkingConf.onMining Software Repositories, 2009, pp. 163–166. [3] J.Devlin,M.Chang,K.Lee,andK.Toutanova,\"BERT:Pretrainingofdeepbidirectionaltransformersforlanguageunderstanding,\"inProc.NAACL-HLT,2019, pp. 4171–4186. [4] T.B.Brownetal.,\"Languagemodelsarefewshotlearners,\"inAdvancesinNeuralInformationProcessingSystems,vol.33,2020,pp.1877–1901. [5] T. Chen and C. Guestrin, \"XGBoost: A scalable tree boosting system,\" in Proc. 22nd ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining,2016, pp. 785–794. [6] S.M.LundbergandS.I.Lee,\"Aunifiedapproachtointerpretingmodelpredictions,\"inAdvancesinNeuralInformationProcessingSystems,vol.30,2017. [7] P.Lewisetal.,\"RetrievalaugmentedgenerationforknowledgeintensiveNLPtasks,\"inAdvancesinNeuralInformationProcessingSystems,vol.33,2020. [8] Google,FirebaseCloudMessagingDocumentation.[Online].Available:https://firebase.google.com/docs/cloud-messaging [9] OpenAI,\"GPT-4TechnicalReport,\"arXivpreprintarXiv:2303.08774, 2023. [10] A.Vaswanietal.,\"Attentionisallyouneed,\"inAdvancesinNeuralInformationProcessingSystems,vol.30,2017.

Copyright

Copyright © 2026 Manikandan ., Vishal SZ, AL Raafhath RK, Roselin Lourd. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.