A
SYNOPSIS REPORT
on
“VIRTUAL DESKTOP ASSISTANT”
Submitted in partial fulfilment of the requirements of the degree
of
BACHELOR OF SCIENCE
in
COMPUTER SCIENCE
Submitted by
Soniya Shah ()
DEPARTMENT OF COMPUTER SCIENCE
Seva Sadan's
R.K. TALREJA COLLEGE OF ARTS, SCIENCE &
COMMERCE, ULHASNAGAR-3
(SEM V)
(2025– 2026)
1. Name (Group Member) and Title of the Project
Group Members: (1) Soniya Shah
Project Title: “VIRTUAL DESKTOP ASSISTANT",
2. Objective and Scope of the Project
Objective:
1) To build personal assistant software using semantic data sources available on the web ,user generated content
and providing knowledge from knowledge databases.
2) To answer questions that users may have. This may be done in a business environment.
Scope:
The virtual assistants who might be presently available are speedy and responsive however we nevertheless
must go an extended manner. The assistants available these days are still no longer reliable in critical
eventualities. The destiny of these assistants may have the virtual assistants integrated with Artificial
Intelligence which incorporates Machine Learning, Neural Networks and IoT. With this technology, we are able
to gain new heights. What the digital assistants can attain is lots past what we have done till now. Most of us
have seen Jarvis, that is a digital assistant evolved through iron guy which is even though fictional but this has
set new requirements of what we will achieve using voice-activated digital assistants.
3. Methodology
I- Speech to Text Module user will ask the computer to run command by giving input as [Link] speech
processing includes a speech recognizer residing on a first computing device and a speech model server residing
on second computing [Link] speech recognizer receives speech training speech training data and processes
it into an intermediate representation of the speech training.
II- Command Execution: Based on command received from will executive the command. System accept various
command such as opening of specific applications writing a not and saving it opening web URL Search for
query or details and shutdown & Restart command.
III- Text to Speech once command is received, application speaks the command which makes user experience
more interactive with [Link] Converter has been complied in a liberal who provides an Application
Programming Interfaces(API) to the application.
4. Hardware and Software to be Used
Hardware Requirements:
• Pentium-pro processor or later.
• RAM 64MB or more.
Software Requirements:
• Windows 7(32-bit) or above.
• Python 2.7 or later
• Chrome Driver
• Selenium Web Automation
• SQLite
5. Project Timeline
"Phase 1 (Dates): 30/06/2025 – Research and Code Formulation
"Phase 2 (Dates): 7/07/2025 – Training and Testing the Modules and Error Handling
"Phase 3 (Dates): 14/07/2025 – Final Implementation
6. Modules
Pyttsx3 : To convert text into speech in python the pyttsx3 module is used. This is an offline module. The
module provides run and wait [Link] is used to allow how much time the system will wait for another
input of user. this is a module available in the python community for free that can be installed using the pip
command.
Datetime : The Date-Time module is imported to support the date and time. for example, the consumer wants to
recognize the modern- day date and time or the person desires to time table a venture at a sure time. In brief this
module helps instructions to manipulate date and time and carry out operations according to it handiest. This is a
critical module, mainly in tasks in which we need to keep a track of time.
Wikipedia : Wikipedia is an online library in python which it possible for the virtual assistant to process the
queries on Wikipedia and display it to the users. this library needs an internet connection. the number of lines
that the user wants to get as a result can be set manually.
Webbrowser : Web-browser module is imported to display information from web to users. If the user wants to
open browser and gives input as ‘Open Google’. Then input is processed using this module and the Google
browser is opened. The browser which is set in code will open.
7. Application and Future Scope of the Project
Applications:
The application of Virtual Assistants (VA) is providing the user shortcut way doing her work in place
of same work done by difficult ways in our growing fast personal and professional life. A virtual
assistant is an intelligent application that can perform tasks or provide services for a person
responding to orders or inquiries during our life. Some VAs can understand and respond to human
think using synthesized voices. Users may be using voice commands or written form request their VA
system to answer the question, its managed home appliances, and handle other essential activities.
Future Scope:
The most quickly adopted technology is the virtual assistant. From smartwatches to smart speakers, all
products now have a virtual voice recognition model built in. The future has numerous potential for voice
technology to advance. However, there are still adjustments and advancements to be made in this subject.
Virtual assistants using Artificial Intelligence, such as Machine Learning, Neural Networks, and IoT, will be the
future of these helpers. By adopting this technology, we will be able to achieve new heights.
We will be able to make our computers and cell phones smarter in the future by utilising these built-in virtual
assistants. We can make things smarter and better by employing artificial intelligence.
8. References
[1] Dr. Vivek Vishal Singh, “Virtual Assistant using Python with GUI.” IEEE Transactions on Speech
Recognition and Audio Processing. In a May 2022.
[2] R Belvin, R. Burns, and C. Hein, “Development of the HRL route navigation dialogue system,” in
Proceedings of ACL-HLT, 2001
[3] T.J. Hazen, and Hetherington, “JUPITER: A Telephone Based Conversational Interface for Weather
Information,” IEEE Transactions on Speech and Audio Processing, vol. 8, no. 1, pp. 85–96, 2000.