Open Access Open Access  Restricted Access Subscription Access

AI Desktop Assistant using Python [JARVIS]

Kajal Bhosale, Aparna Patil

Abstract


We are all aware of the connection between technology and artificial intelligence. Voice assistants driven by AI have become a necessary component of our daily life, integrating technology with everyday chores. With a personal virtual assistant, a user may ask questions or give commands just like they would with a human. They can even perform certain simple operations, such as playing music, opening programs, and searching Wikipedia without launching a browser. In this project, a Python personal desktop assistant is developed with the goal of helping users with their computer-related tasks by automating tasks and making their lives easier. To improve its usefulness and user experience, the assistant integrates technologies including speech recognition, natural language processing, and integration with external APIs. The assistant sets itself apart from other products by providing a platform that is extremely extendable and adaptable. In addition to gaining from connection with well-known tools and services, users can customize the assistant's behavior and functionality to suit their unique requirements. Both inexperienced and seasoned users will have a smooth experience thanks to the user interface's intuitive and user-friendly design. The objective of this project is to improve users' productivity and effectiveness in their daily computer work by developing a personal desktop assistant that blends automation, convenience, and customized features.


Full Text:

PDF

References


T. R. M., Vinoth Kumar, V., & Lim, S.-J. (2023). UsCoTc: Improved collaborative filtering (CFL) recommendation methodology using user confidence, time context with impact factors for performance enhancement. PLoS ONE, 18(3), e0282904. https://doi.org/10.1371/journal.pone.0282904.

Ramakrishna, M. T., Venkatesan, V. K., Bhardwaj, R., Bhatia, S., Rahmani, M. K. I., Lashari, S. A., & Alabdali, A. M. (2023). HCoF: Hybrid collaborative filtering using social and semantic suggestions for friend recommendation. Electronics, 12(1365). https://doi.org/10.3390/electronics12061365.

Gunasekaran, K., Vinoth Kumar, V., Kaladevi, A. C., Mahesh, T. R., Bhat, C. R., & Venkatesan, K. (2023). Smart decision-making and communication strategy in Industrial Internet of Things. IEEE Access. https://doi.org/10.1109/ACCESS.2023.3258407.

Venkatesan, V. K., Ramakrishna, M. T., Izonin, I., Tkachenko, R., & Havryliuk, M. (2023). Efficient data preprocessing with ensemble machine learning technique for the early detection of chronic kidney disease. Applied Sciences, 13(2885). https://doi.org/10.3390/app13052885.

Subashchandrabose, U., John, R., Anbazhagu, U. V., Venkatesan, V. K., & Thyluru Ramakrishna, M. (2023). Ensemble federated learning approach for diagnostics of multi-order lung cancer. Diagnostics, 13(19), 3053.

Alturki, N., Altamimi, A., Umer, M., Saidani, O., Alshardan, A., Alsubai, S., ... & Ashraf, I. (2024). Improving Prediction of Chronic Kidney Disease Using KNN Imputed SMOTE Features and TrioNet Model. CMES-Computer Modeling in Engineering & Sciences, 139(3).

Barmak, Oleksander, Iurii Krak, Sergiy Yakovlev, Eduard Manziuk, Pavlo Radiuk, and Vladislav Kuznetsov. "Toward explainable deep learning in healthcare through transition matrix and user-friendly features." Frontiers in Artificial Intelligence 7 (2024): 1482141.


Refbacks

  • There are currently no refbacks.