LUNA – AI BASED VIRTUAL ASSISTENT

A Major Project Report

Submitted in Partial fulfillment for the award of
Bachelor of Technology in Computer Science & Engineering

Submitted to
RAJIV GANDHI PROUDYOGIKI VISHWAVIDYALAYA
BHOPAL (M.P)

MAJOR PROJECT REPORT

Submitted by

Himanshu Tiwari[0301CS201019] Parnita Dwivedi[0301ME201033]

Isha Shukla[0301EE201028] Puneet Kulshrestha[0301CS201039]
Sumit Saurav Chodhary[0301CS2060]

Under the supervision of

Ashok Dohare & Sanjay Verma
Faculty of Dept. of computer science & engineering

Department of Computer Science & Engineering

Rewa Engineering College, Rewa (M.P.)
Session 2023
 REWA ENGINEERING COLLEGE, REWA (M.P.)

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING

CERTIFICATE

This is to certify that the work embodied in this Major/Minor Project work entitled “LUNA –
Virtual Assistent” has been satisfactorily completed by the Himanshu Tiwari [0301CS201019],
Parnita Dwivedi [0301ME201033], Isha Shukla [0301EE201028], Puneet Kulshrestha
[0301CS201039] and Sumit Saurav Chodhary [0301CS201060]. It is a bonafide piece of work,
carried out under the guidance from Department of Computer Science & Engineering, Rewa
Engineering College, Rewa (M.P.) for the partial fulfillment of the Bachelor of Technology
during the academic year 2023.

Sanjay Verma
Faculty of dept. of computer science & engineering
(GUIDE)

Approved By

Ashok Dohare
Prof. & Head
Department of Computer Science & Engineering

Forwarded by
PRINCIPAL

2|Page
 REWA ENGINEERING COLLEGE, REWA (M.P.)
DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING

ACKNOWLEDGEMENT

We express our deep sense of gratitude to Prof. Sanjay Verma (Guide) Department of
Computer Science & Engineering R.E.C., Rewa (M.P.), whose valuable guidance and timely help
encouraged me to complete this project.

A special thank goes to Ashok Dohare (Prof. & HOD) who helped me by providing timely
suggestions in completing this project work. He/she exchanged his/her interesting ideas &
thoughts which made this project work successful.

We would also thank our institution and all the faculty members without whom this project
work would have been a distant reality.

Himanshu Tiwari [0301CS201019]

Parnita Dwivedi [0301ME201033]
Isha Shukla [0301EE201028]
Puneet Kulshrestha [0301CS201039]
Sumit Saurav Chodhary[0301CS201060]

3|Page
Contents :
S.No. TOPICS Pages No.

1. Introduction 7

2. Literature Survey 10

3. Methodology 11

4. Hardware/Software platform environment 12

5. System Design (Use Case/ Component/ Sequence ) 16

6. Detailed Design (Modeling /Flowcharts ) 17

7. Result Analysis & Snapshots of Input & Output 21

8. Conclusion 24

9. Project limitation and Future scope. 25

10. References. (Books/ Research Papers/ Websites etc.) 27

4|Page
List of Figures :
S.No. Figures Pages No.

1. Figure 3.1 : System architecture 15

2. Figure 3.2 : Use Case Diagram 16

3. Figure 3.3 : Component Diagram 17

4. Figure 3.4 : Sequence Diagram 17

5. Figure 3.5 : Sequence Diagram(Answering the user) 18

6. Figure 3.6: Flow Chart 22

5|Page
 ABSTRACT
The Virtual Assistant with AI project is an intelligent system designed to enhance human-computer
interactions through Natural Language Processing (NLP) and Speech Recognition technologies. It
automates tasks, learns from user interactions, and offers personalized assistance, making it an
indispensable tool for streamlined productivity and satisfaction in users' daily lives. The project
prioritizes security and privacy, aiming to revolutionize the way users interact with technology by
providing an intuitive and contextually-aware virtual assistant. A Voice Assistant is one of the hot
topics in the current world that are programs that listens to human’s verbal command and respond
to them which makes it a human- computer/device interaction. In the current days, a voice
assistant is everywhere which is a lot useful in these busy days. Nowadays, almost everyone in the
current world is using voice assistant because it’s everywhere starting from Google smartphone
assistant which even 5 years old kids will know how to use because of the current world pandemic
which makes them use smartphones till Amazon's Alexa which will be very useful to do works
starting from entertaining the users till turning on and off the household products.

6|Page
 CHAPTER 1

INTRODUCTION

The very first voice activated product was released in 1922 as Radio Rex. This toy was very simple, wherein a
toy dog would stay inside a dog house until the user exclaimed its name, “Rex” at which point it would jump
out of the house. This was all done by an electromagnet tuned to the frequency similar to the vowel found in the
word Rex, and predated modern computers by over 20 years.

In the 21st century, human interaction is being replaced by automation very quickly. One of the main reasons
for this change is performance. There’s a drastic change in technology rather than advancement. In today’s
world, we train our machines to do their tasks by themselves or to think like humans using technologies like
Machine Learning, Neural Networks, etc. Now in the current era, we can talk to our machines with the help of
virtual assistants.

Virtual assistants are software programs that help you ease your day to day tasks, such as showing weather
reports, giving daily news, searching the internet etc. They can take commands by voice. Voice-based
intelligent assistants need an invoking word or wake word to activate the listener, followed by the command.
We have so many virtual assistants, such as Apple’s Siri, Amazon’s Alexa and Microsoft’s Cortana and
Amazon's Alexa and this has been an inspiration for us to do this as a project. This system is designed to be
used efficiently on desktops. Voice assistants are programs on digital devices that listen and respond to verbal
commands. A user can say, “What's the weather?” and the voice assistant will answer with the weather report
for that day and location.

1.1 OVERVIEW

A disease is a condition that affects the individual functioning of body totally. Diseases if neglected will lead to
the death of an individual. Diseases can be identified by the symptoms of the body of an individual. Health is
the most important in every human’s life. Weekly or monthly check up of one’s health is most important for the
prevention and also to stay healthy.

Healthcare is the most crucial parts of the human life. Nowadays, so many are not willing to go to hospital, due
to work overload and negligence of their health. The doctors and nurses are putting up maximum efforts to save
people’s lives without even considering their own loves. There are also some villages which lack medical
facilities.

Accurate and on-time analysis of any health-related problem is important for the prevention and treatment of the
illness. The traditional way of diagnosis may not be sufficient in the case of a serious ailment. In this situation,
where everything has turned virtual, the doctors and nurses are putting up maximum efforts to save people’s
lives even if they have to danger their own.

There are also some remote villages which lack medical facilities. The dataset was processed in ML models
Naive Bayes and Decision Tree. While processing the data, symptoms are given as input and the disease was
received as an output. This project helps to get the idea about the disease of an individual based on the
symptoms he/she have, and get the treatment easily by contacting the concern doctor.

1.2 DESIGN

7|Page
a) The voice assistant takes an input word which is called as "signal word" to be activated. so, it takes in
the signal word and starts operating for the user commands.

b) Converting the speech into text will be processed by the assistant.

c) The converted text is now processed to get the required results.

d) The text given by the user should contain one or two keywords that determine what query is to be
executed. If the keyword doesn’t match any of the queries in the code then the assistant asks the user to speak
again.

e) Finally, the output to the user's query will be given by converting speech to text.

1.3 VOICE ASSISTANT

Our assistant “LUNA” extends to helps us when working on a system in which it is installed. We can access by
calling the wake word "Hello LUNA".

1.3.1 WHAT IS VOICE ASSISTANT

A voice assistant, also known as an intelligent personal assistant or a connected speaker, is a new type of device
that is based on natural language speech recognition and is offered by popular companies like Apple, Amazon,
and Google. We got inspired by that and created one our self.

1.3.2 WHY DO WE NEED IT

Usually, typing out and searching or doing day-to-day tasks becomes hectic. But our life doesn’t need to be like
that. One can ask for help to voice assistants. They let the users to perform a task using a speech command, as
well as retrieve information via voice synthesis.

Following are the reasons to have a voice assistant.

• Minimal Effort
It’s easier to say a few words than type them on a small smartphone screen.

• Eyes Free
One can be as blind as a bat, but a voice assistant will always help you. Our ears are enough. One can
also ask the bot about something while cooking at the same time.

• Fast response
Imagine how much time you have to spend to find some information on a website? Or how many clicks
do you need to make before you find the thing you need in a mobile application? Voice assistants don’t generate
such difficulties. One can ask a question and you have the answer.

1.3.3 WHERE TO USE IT

8|Page
Voice search has been a hot topic of discussion. Voice visibility will undoubtedly be a challenge. This is due to
the lack of a visual interface for voice assistants. Users cannot see or interact with a voice interface unless it is
linked to the Alexa or Google Assistant app. Search behavior patterns will change dramatically as a result.

Brands are currently undergoing a transformation in which touchpoints are transforming into listening points,
and organic search will be the primary means of brand visibility. Advertising agencies are becoming more
popular as voice search grows in popularity. Voice assistants will also continue to offer more individualized
experiences as they get better at differentiating between voices. The number of people using voice assistants is
expected to grow. According to the Voice bot Smart Speaker Consumer Adoption Report 2018, almost ten
percent of people who do not own a smart speaker plan to purchase one. If this holds true, the user base of smart
speaker users will grow 50 percent, meaning a quarter of adults in the United States will own a smart speaker.

9|Page
 CHAPTER 2

LITERATURE SURVEY

2.1 RELATED WORK

This field of virtual assistants having speech recognition has seen some major advancements or innovations.
This is mainly because of its demand in devices like smartwatches or fitness bands, speakers, Bluetooth
earphones, mobile phones, laptop or desktop, television, etc. Almost all the digital devices which are coming
nowadays are coming with voice assistants which help to control the device with speech recognition only. A
new set of techniques is being developed constantly to improve the performance of voice automated search.

As the amount of data is increasing exponentially now known as Big Data the best way to improve the results of
virtual assistants is to incorporate our assistants with machine learning and train our devices according to their
uses. Other major techniques that are equally important are Artificial Intelligence, Internet of Things, Big Data
access and management, etc. With the use of voice assistants, we can automate the task easily, just give the
input to the machine in the speech form and all the tasks will be done by it from converting your speech into
text form to taking out keywords from that text and execute the query to give results to the user.

Machine Learning is just a subset of Artificial Intelligence. This has been one of the most helpful advancements
in technology. Before AI we were the ones who were upgrading technology to do a task but now the machine is
itself able to counter new tasks and solve it without need to involve the humans to evolve it.

This has been helpful in day-to-day lifestyle. From mobile phones to personal desktops to mechanical industries
these assistants are in very much demand for automating tasks.

10 | P a g e
 CHAPTER 3

METHODOLOGY

3.1 EXISTING SYSTEM

From the above literature survey, we have inferred that all the systemsexisting predict only particular diseases
namely lung disease, breast cancer, heartdisease, diabetes by implementing various algorithms on the particular
datasets.
After implementing various algorithms, the most accurate one is selected and it is used for prediction of disease.
Sometimes, we may get confused of what algorithm to use. Also, all the systems find only the particular disease
and not the disease based on the symptoms.

3.2 PROPOSED SYSTEM

We are proposing a system in an efficient way of implementing a Personal voice assistant, Speech Recognition
library has many in-built functions, that will let the assistant understand the command given by user and the
response will be sent back to user in voice, with Text to Speech functions. When assistant captures the voice
command given by user, the under lying algorithms will convert the voice into text. And according to the
keywords present in the text (command given by user), respective action will be performed by the assistant.
This is made possible with the functions present in different libraries. Also, the assistant was able to achieve all
the functionalities with help of some API’s. We had used these APIs for functionalities like performing
calculations, extracting news from web sources, and for telling the weather. We will be sending a request, and
through the API, we’re getting the respective output. API’s like WOLFRAMALPHA, are very helpful in
performing things like calculations, making small web searches. And for getting the data from web. In this way,
we are able to extract news from the web sources, and send them as input to a function for further purposes.
Also, we have libraries like Random and many other libraries, each corresponding to a different technology. We
used the library OS to implement Operating System related functionalities like Shutting down a system, or
restarting a system.

At the outset we make our program capable of using system voice with the help of sapi5 and pyttsx3. pyttsx3 is
a text-to-speech conversion library in Python. Unlike alternative libraries, it works offline, and is compatible
with both Python 2 and 3. The Speech Application Programming Interface or SAPI is an API developed by
Microsoft to allow the use of speech recognition and speech synthesis within Windows applications. Then we
define the speak function to enable the program to speak the outputs.
After that we will define a function to take voice commands using the system microphone. The main function is
then defined where all the capabilities of the program are defined.

• The proposed system will have the following functionality:

(a) The system will keep listening for commands and the time for listening is variable which can be changed
according to user requirements.
(b) If the system is not able to gather information from the user input it will keep asking again to repeat till the
desired number of times.
(c) The system can have both male and female voices according to user requirements.
(d) Features supported in the current version include playing music, texts, search on Wikipedia, or opening
system installed applications, opening anything on the web browser, etc.

3.3 OBJECTIVE OF PROJECT

11 | P a g e
Main objective of building personal assistant software (a virtual assistant) is using semantic data sources
available on the web, user generated content and providing knowledge from knowledge databases. The main
purpose of an intelligent virtual assistant is to answer questions that users may have. This may be done in a
business environment, for example, on the business website, with a chat interface. On the mobile platform, the
intelligent virtual assistant is available as a call-button operated service where a voice asks the user “What can I
do for you?” and then responds to verbal input. Virtual assistants can tremendously save you time. We spend
hours in online research and then making the report in our terms of understanding.

Provide a topic for research and continue with your tasks while the assistant does the research. Another difficult
task is to remember test dates, birthdates or anniversaries. It comes with a surprise when you enter the class and
realize it is class test today. Just tell assistant in advance about your tests and she reminds you well in advance
so you can prepare for the test. One of the main advantages of voice searches is their rapidity. In fact, voice is
reputed to be four times faster than a written search: whereas we can write about 40 words per minute, we are
capable of speaking around 150 during the same period of time. In this respect, the ability of personal assistants
to accurately recognize spoken words is a prerequisite for them to be adopted by consumers.

3.4 SOFTWARE AND HARDWARE REQUIREMENTS

3.4.1 Software Requirements:

Python 3.5 & Above

Windows 8 And Above

3.4.2 Hardware Requirements:

Processor: Intel Core i5

RAM: 4GB

OS: Windows / Mac

Microphone

ARDUINO UNO board

Relay

A Light Bulb

USB Cable

Electronics Wires

Plug Point & a Plug

3.4.3 Libraries:

12 | P a g e
 Pyttsx3- It is a text to speech conversion library in python which is used to convert the text given in the
parenthesis to speech. It is compatible with python 2 and 3. An application invokes the pyttsx3.init() factory
function to get a reference to a pyttsx3. it is a very easy to use tool which converts the entered text into speech.
The pyttsx3 module supports two voices first is female and the second is male which is provided by “sapi5” for
windows. Command to install: - pip install pyttsx3
It supports three TTS engines: - sapi5- To run on windows
nsss - NSSpeechSynthesizer on Mac OS X espeak – eSpeak on every other platform

Speech_recognition- It allows computers to understand human language. Speech recognition is a machine's

ability to listen to spoken words and identify them. We can then use speech recognition in Python to convert the
spoken words into text, make a query or give a reply. Python supports many speech recognition engines and
APIs, including Google Speech Engine, Google Cloud Speech API.
Command to install :- pip install SpeechRecognition

WolfarmAlpha- Wolfram Alpha is an API which can compute expert-level answers using Wolfram's
algorithms, knowledgebase and AI technology. It is made possible by the Wolfram Language. The
WolfarmAlpha API provide a web-based API allowing the computational and presentation capabilities of
WolframAlpha to be integrated into web, mobile and desktop applications.
Command to install :- pip install wolframalpha

Randfacts- Randfacts is a python library that generates random facts. We can use randfacts.get_fact() to
return a random fun fact.
Command to install :- pip install randfacts

Pyjokes- Pyjokes is a python library that is used to create one-line jokes for the users. Informally, it can also
be referred as a fun python library which is pretty simple to use.
Command to install :- pip install pyjokes

Datetime- This module is used to get the date and time for the user. This is a built-in module so there is no
need to install this module externally. Python Datetime module supplies classes to work with date and time.
Date and datetime are an object in Python, so when we manipulate them, we are actually manipulating objects
and not string or timestamps.

Random2- Python version 2 has a module named "random". This module provides a Python 3 ported version
of Python 2.7's random module. It has also been back-ported to work in Python 2.6. In Python 3, the
implementation of randrange() was changed, so that even with the same seed you get different sequences in
Python 2 and 3.

Math- This is a built-in module which is used to perform mathematical tasks. For example, math.cos() which
returns the cosine of a number or math.log() returns the natural logarithm of a number, or the logarithm of
number to base.

Warnings- The warning module is actually a subclass of Exception which is a built-in class in Python. A
warning in a program is distinct from an error. Conversely, a warning is not critical. It shows some message, but
the program runs.

OS- The os module is a built-in module which provides functions with which the user can interact with the os
when they are running the program. This module provides a portable way of using operating system-dependent

13 | P a g e
functionality. This module has functions with which the user can open the file which is mentioned in the
program.

Serial- This module encapsulates the access for the serial port. It provides backends for Python running on
Windows, OSX, Linux, BSD and Iron Python. The module named “serial” automatically selects the appropriate
backend.
Command to install :- pip install pyserial

Time- This module provides many ways of representing time in code, such as objects, numbers, and strings. It
also provides functionality other than representing time, like waiting during code execution and measuring the
efficiency of our code. This is a built-in module so the installation is not necessary.

Wikipedia :-This is a Python library that makes it easy to access and parse data from Wikipedia. Search
Wikipedia, get article summaries, get data like links and images from a page, and more. Wikipedia is a
multilingual online encyclopedia.
Command to install :- pip install wikipedia

Selenium Webdrive- The selenium module is used to automate web browser interaction from Python. Several
browsers/drivers are supported (Firefox, Chrome, Internet Explorer), as well as the Remote protocol. The
supported python versions are python 3.5 and above.
Command to install :- pip install selenium

Requests- The requests module allows you to send HTTP requests using Python. The HTTP request returns a
Response Object with all the response data. With it, we can add content like headers, form data, multipart files,
and parameters via simple Python libraries. It also allows you to access the response data of Python in the same
way.
Command to install :- pip install requests

Webbrowser- Webbrowser module is a convenient web browser controller. It provides a high-level interface
that allows displaying Web-based documents to users. webbrowser can also be used as a CLI tool. It accepts a
URL as the argument with the following optional parameters: -n opens the URL in a new browser window, if
possible, and -t opens the URL in a new browser tab. This is a built-in module so installation is not required.

3.5. PROGRAMMING LANGUAGES

3.5.1 PYTHON

Python is an OOPs (Object Oriented Programming) based, high level, interpreted programming language. It is a
robust, highly useful language focused on rapid application development (RAD). Python helps in easy writing
and execution of codes. Python can implement the same logic with as much as 1/5th code as compared to other

14 | P a g e
OOPs languages. Python provides a huge list of benefits to all. The usage of Python is such that it cannot be
limited to only one activity. Its growing popularity has allowed it to enter into some of the most popular and
complex processes like Artificial Intelligence (AI), Machine Learning (ML), natural language processing, data
science etc. Python has a lot of libraries for every need of this project. For this project, libraries used are speech
recognition to recognize voice, Pyttsx for text to speech, selenium for web automation etc.

It’s owing to the subsequent strengths that Python has –

Easy to be told and perceive- The syntax of Python is simpler; thence it's comparatively straightforward, even
for beginners conjointly, to be told and perceive the language.
Multi-purpose language − Python could be a multi-purpose programing language as a result of it supports
structured programming, object-oriented programming yet as practical programming.
Support of open supply community − As being open supply programing language, Python is supported by
awfully giant developer community. Because of this, the bugs square measure simply mounted by the Python
community. This characteristic makes Python terribly strong and adaptative.

3.6. SYSTEM ARCHITECTURE

Fig 3.1 System Architecture

3.7 ALGORITHMS USED

3.7.1 SPEECH RECOGNITION MODULE

The class which we are using is called Recognizer.

It converts the audio files into text and module is used to give the output in speech.
Energy threshold function represents the energy level threshold for sounds. Values below this threshold are
considered silence, and values above this threshold are considered speech.
Recognizer instance.adjust_for_ambient_noise(source, duration = 1), adjusts the energy threshold
dynamically using audio from source (an AudioSource instance) to account for ambient noise.

15 | P a g e
3.7.2 SPEECH TO TEXT & TEXT TO SPEECH CONVERSION

Pyttsx3 is a text-to-speech conversion library in Python. And can change the Voice, Rate and Volume by
specific commands.
Python provides an API called Speech Recognition to allow us to convert audio into text for further
processing converting large or long audio files into text using the Speech Recognition API in python.
We have Included sapi5 and espeak TTS Engines which can process the same.

3.7.3 PROCESS & EXECUTES THE REQUIRED COMMAND

The said command is converted into text via speech recognition module and further stored in a temp.
Then, Analyze the user’s text via temp and decide what the user needs based on input provided and runs the
while loop.
Then, Commands are executed.

3.8 SYSTEM DESIGN:

3.8.1 USE CASE DIAGRAM:

Fig 3.2 Use Case Diagram

In this project there is only one user. The user queries command to the system. System then interprets it and
fetches answer. The response is sent back to the user.

16 | P a g e
3.8.2 COMPONENT DIAGRAM:

Fig 3.3. Component Diagram

The main component here is the Virtual Assistant. It provides two specific service, executing Task or
Answering your question.

SEQUENCE DIAGRAM:

Fig 3.4. Sequence Diagram

The user sends command to virtual assistant in audio form. The command is passed to the interpreter. It
identifies what the user has asked and directs it to task executer. If the task is missing some info, the virtual

17 | P a g e
assistant asks user back about it. The received information is sent back to task and it is accomplished. After
execution feedback is sent back to user.

Fig 3.5. Sequence Diagram (Answering the user)

The above sequence diagram shows how an answer asked by the user is being fetched from internet. The
audio query is interpreted and sent to Web scraper. The web scraper searches and finds the answer. It is then
sent back to speaker, where it speaks the answer to user.

3.9 Feasibility Study

Feasibility study can help you determine whether or not you should proceed with your project. It is essential to
evaluate cost and benefit. It is essential to evaluate cost and benefit of the proposed system. Five types of
feasibility study are taken into consideration.

1. Technical feasibility: It includes finding out technologies for the project, both hardware and software.
For virtual assistant, user must have microphone to convey
their message and a speaker to listen when system speaks. These are very cheap now a days and everyone
generally possess them. Besides, system needs internet connection.
While using, make sure you have a steady internet connection. It is also not an issue in this era where almost
every home or office has Wi-Fi.

2. Operational feasibility: It is the ease and simplicity of operation of proposed system. System does not
require any special skill set for users to operate it. In fact, it is designed to be used by almost everyone.
Kids who still don’t know to write can read
out problems for system and get answers.

18 | P a g e
 3. Economic feasibility: Here, we find the total cost and benefit of the proposed system over current
system. For this project, the main cost is documentation cost. User also, would have to pay for
microphone and speakers. Again, they are cheap and available. As far as maintenance is concerned, it
won’t cost too much.

4. Organizational feasibility: This shows the management and organizational structure of the project.
This project is not built by a team. The management tasks are all to be carried out by a single person.
That won’t create any management issues and will increase the feasibility of the project.

5. Cultural feasibility: It deals with compatibility of the project with cultural environment. Virtual
assistant is built in accordance with the general culture. This project is technically feasible with no
external hardware requirements. Also, it is simple in operation and does not cost training or repairs.
Overall feasibility study of the project reveals that the goals of the proposed system are achievable.
Decision is taken to proceed with the project.

3.10. TYPES OF OPERATION

• Information:
If we ask for some information, it opens up wikipedia and asks us the topic on which we want the information,
then it clicks on the wikipedia search box using its xpath, searches the topic in the search box and clicks the
search button using the xpath of the button and reads a paragraph about that topic.
Keyword: information

• Plays the video which we ask:

If we ask it to play a video, it opens up YouTube and asks us the name of the video which it wants to play. After
that, it clicks on the search YouTube search box using its xpath, then it clicks on the search button using its
xpath and clicks the first result of the search using the xpath of the first video.
Keyword: Play and video or music

• News of the day:

If we ask for the news, it reads out the Indian news of the day on which it is asked.
Keyword: news

• Temperature and Weather:

If the user asks the temperature, it gives the current temperature.
Keyword: temperature

• Joke:
If the user asks for a joke, it tells a one liner joke to the user.
Keyword: funny or joke

• Fact:
If the user asks for some logical fact, it tells a fact to the user.
Keyword: fact

19 | P a g e
• Game:
The assistant can play the number guessing game with the user. First, it asks for the lower and the upper limit
between which the number should be. Then it initializes a random number between that upper and lower limit.
After that, it uses a formula to calculate the number of turns within which the user should guess the number.
Keyword: game

• Restart the system:

The assistant restarts the system if the user asks the assistant to restart the system.
Keyword: Restart the system or Reboot the system

• Open:
The assistant will open some of the folders and applications which the user asks the assistant to open.
Keyword: Open

• Date and Time:

If the user asks for the date or time, the assistant tells it.
Keyword: date or time or date and time

• Calculate:
The assistant will calculate the equations which the user tells it to calculate using wolframalpha API key.
Keyword : calculate (along with the equation)
Tells your name:
The assistant tells its name if the user asks it. The name of the assistant is LUNA.

• Exit:
The assistant will stop assisting the user if the user asks it to exit.
Keyword: exit or end or stop.

20 | P a g e
 CHAPTER 4

RESULTS AND DISCUSSION

The project work of the voice assistant has been clearly explained in this report, how useful it is and how we
can rely on a voice assistant for performing any/every task which the user needs to complete and how the
assistant is developing everyday which we can hope that it'll be one of the biggest technology in the current
technological world. Development of the software is almost completed form our side and it's working fine as
expected which was discussed for some extra development. So, maybe some advancement might come in the
near future where the assistant which we developed will be even more useful than it is now.

4.1. WORKING

It starts with a signal word. Users say the names of their voice assistants for the same reason. They might say,
“Hey Siri!” or simply, “Alexa!” Whatever the signal word is, it wakes up the device. It signals to the voice
assistant that it should begin paying attention. After the voice assistant hears its signal word, it starts to listen.
The device waits for a pause to know you’ve finished your request. The voice assistant then sends our request
over to its source code. Once in the source code, our request is compared to other requests. It’s split into
separate commands that our voice assistant can understand. The source code then sends these commands back
to the voice assistant. Once it receives the commands, the voice assistant knows what to do next. If it
understands, the voice assistant will carry out the task we asked for. For example, “Hey NOVA! What’s the
weather?” NOVA reports back to us in seconds. The more directions the devices receive, the better and faster
they get at fulfilling our requests. The user gives the voice input through microphone and the assistant is
triggered by the wake up word and performs the STT (Speech to Text) and converts it into a text and
understands the Voice input and further performs the task said by the user repeatedly and delivers it via TTS
(Text to Speech) module via AI Voice.

These are the important features of the voice assistant but other than this, we can do an plenty of things with the
assistant.

List of features that can be done with the assistant:

- Playing some video which, the user wants to see.
- Telling some random fact at the start of the day with which the user can do their work in an informative way
and the user will also learn something new.
- One of the features which will be there in every assistant is playing some game so that the user can spend their
free time in a fun way.
- Users might forget to turn off the system which might contain some useful data but with a voice assistant, we
can do that even after leaving the place where the system is just by commanding the assistant to turn the system
off.

As discussed about the mandatory features to be listed in voice assistant are implemented in this work, brief
explanation is given below.

API CALLS
We have used API keys for getting news information from newsapi and weather forecast from openweathermap
which can accurately fetch information and give results to the user.

SYSTEM CALLS

21 | P a g e
In this feature, we have used OS & Web Browser Module to access the desktop, calculator, task manager,
command prompt & user folder. This can also restart the pc and open the chrome application.

CONTENT EXTRATION
This can Perform content extraction from YouTube, Wikipedia and Chrome using the web driver module from
selenium which provides all the implementations for the webdrive like searching for a specific video to play, to
get a specific information in google or from Wikipedia.

Fig 4.1. Flowchart

1) Must provide the user any information which they ask for: -
The user might need any information which will be available on the internet but searching for that information
and reading that takes a lot of time but with the help of a voice assistant, we can complete that task of getting
the information sooner than searching and reading it. So, this is a small proof that a voice assistant helps the
user to save time

2) Telling the day's hot news in the user's location: -

In Common, watching a news channel just to know the important news in one’s location takes a lot of time and
the user might even want to listen to some news which is unnecessary to them or a news of some different
location before getting to know the news which they want needs a lot of patience to the user but having a voice
assistant makes all that nothing, it'll give the news of the location which the user wants to now or the news
which they want to know.

3) Telling some joke to chill up the moment: -

Now let's be honest, everyone would have had at least one moment in their life where they were so tensed up or
had an argument with their close people. So, these moments can be chilled up at least ten percentage with some
random joke which might cool us that moment or stop that fight. We even have a quote stating "Laughter is the
best medicine" which is relatable to the words mentioned here in this paragraph.

4) Opening the file/folder which the user wants: -

In the busy world, everything should do quick else, our schedule will get changed and sometimes we need
assistance of someone to complete that task quickly but, if we have a voice assistant, we can complete that task

22 | P a g e
in right away in a hustle freeway. For example, let's say the user is doing some documentation but after a while,
he needs some file for reference and he goes searching for that file which wastes a lot of time and he ends up
missing the deadline but, with a voice assistant we can do the searching part in a quick way by commanding the
assistant to open the folder. So, by this we can say that it is one of the important features of a voice assistant.

5) Telling the temperature/weather at the user's location: -

Let's start this with a question, why is it important for us to know the weather of the day? or why is it important
for us to monitor the weather every day? The answer is pretty simple it forewarns the users asking about the
weather telling that "it might rain today so carry an umbrella if you go out" or "It will be a sunny day so wear a
sun glass". So, by this we can say that this is also a must have feature.

6) Searching for what the user asks:

Today in the 20th century, we people often get doubts and we need to clear that doubt as soon as possible else
that one doubt will be multiplied and at the end, we'd have n doubts and to clear the doubts searching the
question in the internet will give us an answer and clear our doubts and asking that to the assistant will save a
lot of time. Other than clearing the doubts, we need to search a lot of questions or topics in the internet to keep
up with the trend and we can do this searching just by giving command to our assistant, asking it to search a
specific topic/question.

Snapshots

23 | P a g e
24 | P a g e
 CHAPTER 5

CONCLUSION

5.1.CONCLUSION

As stated before, "voice assistant is one of the biggest problem solver" and you can see that in the proposals
with the examples that it is in fact one of the biggest problem solver of the current world. We can see that voice
assistant is one of the major evolving artificial intelligence in the current world once again on seeing the
proposal examples because at the past, the best feature which a voice assistant had was telling the date and
searching the web and giving the results but now look at the functions that it can do so with this, we can say that
it is a evolving software in the current world. The main idea is to develop the assistant even more advanced than
it is now and make it the best ai in the world which will save an ample of time for its users. I would like to
conclude with the statement that we will try our best and give one of the best voice assistants which we are able
to.

5.2.FUTURE SCOPE

We are entering the era of implementing voice-activated technologies to remain relevant and competitive.
Voice-activation technology is vital not only for businesses to stay relevant with their target customers, but also
for internal operations. Technology may be utilized to automate human operations, saving time for everyone.
Routine operations, such as sending basic emails or scheduling appointments, can be completed more quickly,
with less effort, and without the use of a computer, just by employing a simple voice command. People can
multitask as a result, enhancing their productivity. Furthermore, relieving employees from hours of tedious
administrative tasks allows them to devote more time to strategy meetings, brainstorming sessions, and other
jobs that need creativity and human interaction.

1) Sending Emails with a voice assistant:

Emails, as we all know, are very crucial for communication because they can be used for any professional
contact, and the finest service for sending and receiving emails is, as we all know, GMAIL. Gmail is a Google-
created free email service. Gmail can be accessed over the web or using third-party apps that use the POP or
IMAP protocols to synchronize email content.

To integrate Gmail with Voice Assistant we have to utilize Gmail API. The Gmail API allows you to access and
control threads, messages, and labels in your Gmail mailbox.

2) Scheduling appointments using a voice assistant:

The demands on our time increase as our company grows. A growing number of people want to meet with us.
We have a growing number of people who rely on us. We must check in on certain projects or set aside time to
chat with possible business leads. There won't be enough hours in the day if we keep doing things the old way.

We need to get a better handle on our full-time schedule and devise a strategy for arranging appointments that
doesn't interfere with our most critical job. By working with a virtual scheduler or, in other words, a virtual
assistant, we let someone else worry about the organization and prioritize our schedule while we focus on the
work.

3) Improved Interface of a voice assistant (VUI):

25 | P a g e
Voice user interfaces (VUIs) allow users to interact with a system by speaking commands. VUIs include virtual
assistants like Amazon's Alexa and Apple's Siri. The real advantage of a VUI is that it allows users to interact
with a product without using their hands or their eyes while focusing on anything else.

-Other benefits of a Voice user interface (VUI):

Speed and Efficiency:

Hands-free interactions are possible with VUIs. This method of interaction eliminates the need to click buttons
or tap on the screen. The major means of human communication is speech. People have been using speech to
form relationships for ages. As a result, solutions that allow customers to do the same are extremely valuable.
Furthermore, even for experienced texters, dictating text messages has been demonstrated to be faster than
typing. Hands-free interactions, at least in some circumstances, save time and boost efficiency.

Intuitiveness and convenience:

Intuitive user flow is required of high-quality VUIs, and technical advancements are expected to continue to
improve the intuitiveness of voice interfaces. Compared to graphical UIs, VUIs require less cognitive effort
from the user. Furthermore, everyone – from a small child to your grandmother – can communicate. As a result,
VUI designers are in a better position than GUI designers, who run the danger of producing incomprehensible
menus and exposing users to the agony of poor interface design. Customers are unlikely to need to be instructed
on how to utilize the technology by VUI makers. People can instead ask their voice assistant for assistance.

26 | P a g e
 REFERENCES

[1] K. Noda, H. Arie, Y. Suga, T. Ogata, Multimodal integration learning of robot behavior using deep neural
networks, Elsevier: Robotics and Autonomous Systems, 2014.

[2] Artificial intelligence (AI), sometimes called machine intelligence.

https://en.wikipedia.org/wiki/Artificial_intelligence.

[3] Deepak Shende, RiaUmahiya, Monika Raghorte, AishwaryaBhisikar, AnupBhange, “AI Based Voice
Assistant Using Python”, Journal of Emerging Technologies and Innovative Research (JETIR), February 2019,
Volume 6, Issue 2.

[4] J. B. Allen, “From lord rayleigh to shannon: How do humans decode speech,” in International Conference
on Acoustics, Speech and Signal Processing, 2002.

[5] John Levis and Ruslan Suvorov, “Automatic Speech Recognition”.

[6] B.H. Juang and Lawrence R. Rabiner, “Automatic Speech Recognition - A Brief History of the Technology
Development”.

[7] AbhayDekate, ChaitanyaKulkarni, RohanKilledar, “Study of Voice Controlled Personal Assistant Device”,
International Journal of Computer
Trends and Technology (IJCTT) – Volume 42 Number 1 – December 2016.

27 | P a g e