DESKTOP AI ASSISTANT

Abstract

The present invention introduces a versatile voice assistant designed to enhance user interaction through direct, personal, and effective dialogue. Initially conceived as a voice command application, Sophy has evolved into a comprehensive smart assistant with an array of functionalities. Developed using Python, the system integrates Pyttsx3 for text-to-speech conversion, SpeechRecognition for voice input, and Psutil for system monitoring. Sophy’s capabilities extend from providing real-time information on weather, news, and entertainment to executing system tasks such as taking screenshots, managing open windows, and clearing the recycle bin. Equipped with a GUI, Sophy allows seamless interaction both graphically and verbally. Additionally, it offers system status updates and integrates with web services like YouTube, Google, and Amazon, enhancing multitasking and delivering personalized responses. This invention provides a practical solution for users seeking a powerful, flexible voice assistant capable of managing daily tasks and improving overall convenience.

Specification

Description:The invention is the fully flexible voice assistant that is capable to be multitasked, integrated with systematic operations and web related functions. Flexible voice choice, custom greetings that depend on the time of the day, and versatile commands which encompass playing of music, controlling local applications, web searching, and real time weather update. There is also an inherent error-checking mechanism to complement this system of interaction with the user.
The device, a customizable voice assistant named "Sophy," consists of multiple modules to support a wide range of functions. The Text-to-Speech Engine (TTS) uses Python's pyttsx3 library to convert text to speech, allowing Sophy to respond to users verbally. The Speech Recognition Module, powered by the speech_recognition library, enables Sophy to listen to voice commands through a microphone, interpret them, and process the spoken information. The assistant's Graphical User Interface (GUI), developed with Tkinter, includes a window with interactive buttons, labels, and message boxes for user engagement and message display.
Sophy is equipped with System Control Functions to perform essential tasks like launching applications, managing files, switching windows, and executing shutdown or reboot commands. The users can access Wikipedia, IMDb for movie information, and Google News for the latest headlines through Information Retrieval Components. External APIs enable the Weather and Calendar Module to provide real-time weather updates via the Weatherbit API and user-specific calendar information. The Multimedia and Entertainment Module offers additional features such as playing music, searching YouTube videos, and telling jokes with pyjokes.
The System Status Monitoring employs a python system and process utilities (psutil) to track CPU and battery health, ensuring users have up-to-date system information. Finally, Sophy supports Automated Web Interaction, enabling users to open web browsers for searches, shopping on Amazon, or locating places, enhancing the assistant's versatility and user convenience.
1. Customization Features:
The voice assistant offers personalized features to enhance user engagement. One such feature is Voice Selection, which allows users to select their preferred type of voice for the assistant, making interactions more personal. This is achieved by incorporating the pyttsx3 text-to-speech library and engine within the project, providing users with multiple voice options to choose from. Another feature, Greeting Customization, enables the assistant to greet users with a customized message depending on the time it is activated. This greeting is dynamically set through the wish_me function, which checks the current time and delivers an appropriate salutation, such as "Good Morning" or "Good Evening," ensuring a warm and timely welcome for the user.
2. Multitasking Capabilities:
The voice assistant supports Simultaneous Task Execution, enabling it to play music, conduct web searches, and open applications concurrently. This is managed through a while True: loop that continuously listens for new voice commands, allowing it to process commands without interrupting ongoing tasks. Additionally, the assistant offers System-Level Interaction, allowing it to perform advanced tasks such as launching local applications like MS Word and PowerPoint, capturing screenshots, shutting down, and restarting the computer. The assistant's Web Integration extends its functionality by using specific queries to retrieve information from platforms like Wikipedia, YouTube, and Google, along with API integration for real-time weather reports. Error Handling enhances user experience by prompting users to repeat unclear commands, thereby improving interaction and reducing frustration. This feature relies on conditional checks to identify unrecognized commands and request clarification, ensuring smoother communication and response accuracy. , Claims:1. A customizable and multitasking voice assistant system, comprising:
a Text-to-Speech (TTS) Engine configured to convert text into audible speech, enabling a user-responsive, spoken output;
a Speech Recognition Module operative to capture, interpret, and process voice commands via a microphone, thereby facilitating hands-free interaction; and
a Graphical User Interface (GUI) with interactive elements including buttons, labels, and message boxes, allowing user engagement and command visualization.
2. The system as claimed in claim 1, wherein the system dynamically executes simultaneous multitasking through concurrent operation of multiple processes, thereby supporting uninterrupted user commands and responses.
3. The system as claimed in claim 1, wherein the TTS Engine employs a Python-based text-to-speech library, such as pyttsx3, enabling customizable voice selection that allows users to choose from multiple voice options, enhancing personal interaction and user engagement.
4. The system as claimed in claim 1, wherein the System Status Monitoring Module utilizes system and process utilities, such as psutil, to monitor CPU and battery health, providing real-time feedback to the user on system performance and resource availability, thereby ensuring informed system usage and maintenance.
5. The system as claimed in claim 1, wherein the Simultaneous Task Execution is enabled through a control structure that continuously listens and processes sequential voice commands within a looped architecture, allowing parallel operation of tasks such as music playback, web search, and application control without user interruption.
6. The system as claimed in claim 1, wherein the Voice and Command Flexibility permits versatile command processing across various domains, including entertainment, system control, and information retrieval, whereby the system can interpret complex, multi-step instructions for streamlined user experience.
7. The system as claimed in claim 1, wherein the User-Friendly GUI Module developed using Tkinter, wherein interactive buttons, labels, and pop-up message boxes facilitate intuitive user navigation, command entry, and real-time response display, enhancing usability for users of diverse technical backgrounds.
8. The system as claimed in claim 1, wherein the Greeting Customization feature generates context-sensitive greetings based on the time of day, employing a time-checking function to set the greeting dynamically, thereby delivering a personalized welcome experience.

Documents