MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202621049011 A) filed by Prof. Ganesh Jadhav; Pranav Ganorkar; Pranay Meshram; Prasheel Kaushik; Prashik Upare; Pratham Taikar; and Pragati Sahu on April 17, 2026, for Desktop Ai Assistant - Task & App Launcher With Voice Control..
Inventors include Prof. Ganesh Jadhav; Pranav Ganorkar; Pranay Meshram; Prasheel Kaushik; Prashik Upare; Pratham Taikar; and Pragati Sahu.
The application for the patent was published on July 03, 2026, under issue no. 27/2026.
Abstract: With the rise of artificial intelligence technology and voice recognition systems, communicating with computers is easier for all. There has been an increase in the need for digital assistants that can complete tasks without using hands. This paper describes the creation of an intelligent, multifunctional desktop-based voice assistant named 'E.D.I.' that uses natural voice commands (speech) to perform multiple functions simultaneously. The E.D.I, voice assistant is composed of speech-to-text processing (STT), text-to-speech synthesis (TTS), and AI-based intent classification. This system has a single, efficient architecture that provides real-time interactions and accurate task completion by performing many functions simultaneously across multiple subject areas. The E.D.I, voice assistant will be able to perform tasks related to four functional areas: system automation; educational assistance; health and fitness monitoring; and entertainment. The education module will enable the user to interactively participate in quiz-based learning and to receive feedback regarding his/her performance. The health and fitness monitoring module will provide functionality that includes activity monitoring, hydration reminders, and guided wellness. The entertainment module will allow for greater interaction and engagement among users via various types of interactive games and trivia activities. As noted above, the total architecture of the proposed voice assistant will allow the different modules to work together as a complete and integrated solution from the user's perspective. Acknowledging the performance of the system, experimental testing has demonstrated that the E.D.I, voice assistant performs well in terms of recognition accuracy; response speed; and multi-module performance. Ultimately, by incorporating effective error-handling capabilities with each module into a total voice assistant architecture will provide a significant benefit to the user by increasing the reliability and stability of the overall system. This leads to considerable scalability due to the amount of modularity present in the individual modules.
Disclaimer: Curated by HT Syndication.
