RAIPUR INSTITUTE OF TECHNOLOGY, RAIPUR (C.G.

)
Department of Computer Science and Engineering
Chatauna, Mandir Hasaud, Raipur, (C.G.)

DECLARATION BY THE CANDIDATE

I the undersigned solemnly declare that the report of the thesis work entitled “JARVIS
DESKTOP AI ASSISTANT” is based my own work carried out during the course of my
study under the supervision of Mr. YOGESH RATHORE, Asst. Prof., Department of
CSE, RITEE, Raipur.

I assert that the statements made and conclusions drawn are an outcome of the project
work. I further declare that to the best of my knowledge and belief that the report does not
contain any part of any work which has been submitted for the award of any other
degree/diploma/certificate in this University /deemed University of India or any other country.

-----------------------------------
(Signature of the Candidate)

Name: GAURAV RAJ

Roll No.: 301202216011
Enrollment No.: BA3578

B.E. 7th semester (C.S.E)

I
 RAIPUR INSTITUTE OF TECHNOLOGY, RAIPUR (C.G.)
Department of Computer Science and Engineering
Chatauna, Mandir Hasaud, Raipur, (C.G.)

CERTIFICATE BY THE SUPERVISOR

This is to certify that the report of the thesis entitled “JARVIS DESKTOP AI ASSISSTANT” is
a record of research work carried out by bearing Roll No. 301202216011 & Enrollment No.:
BA3578 under my guidance and supervision for the award of Degree of Bachelor of Engineering
in Computer Science and Engineering of Chhattisgarh Swami Vivekanand Technical University,
Bhilai (C.G.), India.
To the best of my knowledge and belief the thesis
i) Embodies the work of the candidate herself/himself,
ii) Has duly been completed,
iii) Fulfills the requirement of the Ordinance relating to the B.E. degree of the
University and
iv) Is up to the desired standard both in respect of contents and language for being
referred to the examiners.

(Signature of the HOD) (Signature of the Supervisor)

Forwarded to Chhattisgarh Swami Vivekanand Technical University,Bhilai

----------------------------------------
(Signature of the Principal)

II
 RAIPUR INSTITUTE OF TECHNOLOGY, RAIPUR (C.G.)
Department of Computer Science and Engineering
Chatauna, Mandir Hasaud, Raipur, (C.G.)

CERTIFICATE BY THE EXAMINERS

The Thesis entitled “JARVIS DESKTOP AI ASSISSTANT” submitted by GAURAV RAJ

(Roll No.: 301202216011 Enrollment No.: BA3578 has been examined by the undersigned as a

part of the examination and is hereby recommended for the award of the degree of Bachelor of

Engineering in Computer Science and Engineering of Chhattisgarh Swami Vivekanand

Technical University, Bhilai.

------------------------------ -------------------------------
Internal Examiner External Examiner
Date: Date :

II
I
 ACKNOWLEDGEMENT

The pleasure, the achievement, the glory, the satisfaction, the reward appreciation and the
construction of my project cannot be thought of without the few, who apart from their regular
schedule spared their valuable time. A number of persons contribute either directly or indirectly in
shaping and achieving the desired outcome. I owe a debt of gratitude to Mr. AVINASH DHOLE
(HOD) for providing me with an opportunity to develop this project. Through her/his timely advice,
constructive criticism and supervision she was a real source of inspiration for me.
I express my sincere thanks to my guide, Mr. YOGESH RATHORE , ASSISSTANT
PROFESSOR, Department of Computer Science & Engineering, RAIPUR INSTITUTE OF
TECHNOLOGY for his valuable guidance, suggestions and help required for executing the project
work time to time. Without his direction and motivation, it would have been nearly impossible for
me to achieve the initial level of target planned.
I am also expressing my unending gratefulness towards Mr. ABHISHEK SAW for their
remarkable advice and unending support throughout, thus leading me to my objective. Also I
express cordial thanks to Dr SANJEEV SRIVASTAVA , Principal, Raipur Institute of
Technology, Raipur, for providing necessary infrastructural and moral support.
At the last but not the least I am really thankful to my parents for always encouraging me in my
studies and also to my friends who directly or indirectly help me in this work.

----------------------------------
(Signature of the Student)
Name: GAURAV RAJ,

RAIPUR INSTITUTE OF
TECHNOLOGY

I
V
 Abstract
Intelligent Personal Assistants (IPA) are implemented and used in Operating
Systems, Internet of Things (IOT), and a variety of other systems. Many im-
plementations of IPAs exists today and companies such as Apple, Google and
Microsoft all have their implementations as a major feature in their operating
systems and devices . With the use of Natural Language Processing (NLP),
Machine Learning (ML), Artificial Intelligence (AI) , and prediction models
from these fields in Computer Science (CS) , as well as theory and techniques
from Human - Computer Interaction (HCI) , IPAs are becoming more intelli-
gent and relevant . This paper aims to analyse and compare the current major
implementations of IPAs in order to determine which implementation is the
most developed at this moment in time and is contributing to the sustainable
future of AI.

V
 List of Tables

PAGE NO.

Table 1.1 Future Scope Of AI Assisstants 31

V
I
 List of Figures

PAGE NO.

Figure 1.1: Dataflow diagram of Jarvis 16

Figure 1.2: Speech Recognition Dataflow Diagram 17
Figure 1.3: ER Diagram of Jarvis 18
Figure 1.4: UML Diagram of Jarvis 19
Figure 1.5: Jarvis Implementation Diagram 31

V
II
 List of Abbreviations

1. RGB - Red-Green-Blue color space

2. ML - Machine Learning
3. gtts - Google text to speech
4. sr - SpeechRecognition
5. sklearn - Scikit Learn
6. th - Thaneau
7. pyttsx - Python text to speech
8. os - Operating System
9. sys - System
10. pyaudio - Python Audio

V
II
I
 Table of Contents

PAGE NO.

DECLARATION BY CANDIDATE …....……………………………………………. I

CERTIFICATE BY SUPERVISOR ……………………………………………….. II
CERTIFICATE BY EXAMINERS …………………………………………………. III
ACKNOWLEDGEMENT ………………………………………………………… IV
ABSTRACT ………………………………………………………………………… V
LIST OF TABLES ………………………………………………………………… VI
LIST OF FIGURES ……………………………………………………………. …. VII
LIST OF ABBREVIATIONS …………………………………………………VIII

Chapter1: Introduction ----------------------------------------------------------------- 1-10

1.1 Background
1.2 Limitation of existing system
1.3 Introduction to Project Work ------------------------------------------------------- 8
1.4 Introduction of software/ language used --------------------------------------------- 10

Chapter 2: Software Requirement Specification

2.1 Functional Requirement
2.2 Non functional Requirement
2.3 Software and Hardware Requirement

Chapter 3: Software Design Phase

3.1 Data flow diagram
3.1.1 zero level DFD
3.1.2 first level DFD
3.1.3 second level DFD
3.2 ER Diagram
3.3 UML diagrams
I
X
Chapter 4: Implementation and Results
4.1 Description of Modules
4.2 Output window with description
4.3 Implementation

Chapter 6 : Conclusion and scope of work

6.1 Conclusion
6.2 Future scope of work

Reference

X
 Chapter - 1
Intoduction
In the Modern Era of fast moving technology we can do things which we never
thought we could do before but, to achieve and accomplish these thoughts there is a
need for aplatform which can automate all our tasks with ease and comfort. Thus we
need to develop a Personal Assistant having brilliant powers of deduction and the
ability to interact with the surroundings just by one of the materialistic form of human
interaction i.e. HUMAN VOICE. The Hardware device captures the audio request
through microphone and processes the request so that the device can respond to the
individual using in-built speaker module. For Example, if you ask the device ’what’s
the weather?’ or ’how’s traffic?’ using its built-in skills, it looks up the weather and
traffic status respectively and then returns the response to the customer through
connected speaker.
1.1. Background :
In 21st century, everything is leaning towards automation, may it be your home or
car. There is an unbelievable change rather advancement in technology over the last
few years. Believe it or not, in today’s world you can interact with your machine. What
is interacting with a machine? Obviously giving it some input, but what if the input is
not in the conventional way of typing, rather it is your own Voice. What if you are
talking to the machine, giving it commands and wanting the machine to interact with
you like your assistant? What if the machine is not giving you answers just by
showing you the best results but also by advising you with a better alternative. An
easy access to machine with voice commands is the revolutionary way of human-
system interaction. To achieve this, we need to use speech to text API for
understanding the input. Many companies like Google, Amazon and Apple are trying
to achieve this in generalized form. Isn’t it amazing that you can set reminders by just
saying remind me to.... Or set alarm with wake me up at .. Understanding the
importance of this we have decided to make a system that can be placed anywhere
in vicinity and you can ask it to help you do anything for you just by speaking with it.In
addition to this, you can also connect two such devices through WiFi and make them
communicated with each other in future. This device can be very handy for day to day
X
I
use and it can help you function better by constantly giving you reminders and
updates. Why would we need it? Because your own voice is turning into a best input
device than a conventional enter key.
1.2. Limitation of Existing System :
 Voice recognition software won't always put your words on the screen
completely accurately. Programs cannot understand the context of language
the way that humans can, leading to errors that are often due to
misinterpretation.
 Voice recognition systems can have problems with accents. Even though
some may learn to decode your speech over time, you have to learn to talk
consistently and clearly at all times to minimize errors. If you mumble, talk too
fast or run words into each other, the software will not always be able to cope.
Programs may also have problems recognizing speech as normal if your voice
changes, say when you have a cold, cough, sinus or throat problem.
 To get the best out of voice recognition software, you need a quiet
environment. Systems don't work so well if there is a lot of background noise.
They may not be able to differentiate between your speech, other people
talking and other ambient noise, leading to transcription mix-ups and errors.
This can cause problems if you work in a busy office or noisy environment.
Wearing close-talking microphones or noise-canceling headsets can help the
system focus on your speech.
 If you use voice recognition technology frequently, you may experience some
physical discomfort and vocal problems. Talking for extended periods can
cause hoarseness, dry mouth, muscle fatigue, temporary loss of voice and
vocal strain. The fact that you aren't talking naturally may make this worse and
you may need to learn how to protect your voice if you'll use a program
regularly.

1.3. Introduction to Project Work :

Intelligent Voice Assistant system on android platform was developed as an android
application that demonstrate the use of natural language processing which helps to
X
II
send messages and even use the in-build mobile application by using voice
commands. This system was surveyed to use the mailing and calendar where user
were able to mail and also create their event using voice command. Home
Automation system[5] based on Internet of Things was proven to work satisfactorily
by connecting simple appliances to it and the application appliances were
successfully controlled remotely through internet. The designed system not only
monitors the sensor data like temperature, gas, light, motion sensors but also
actuates a process according to the requirement. For instance, switching on the lights
when it gets dark. It also stores the sensor parameters in the cloud in a timely
manner. This will help user to analyze the condition of various parameters in the
home anytime anywhere. Everyone must be familiar with Siri, Cortana, Google Nowor
Watson or with any of the countless fictional virtual assistant. These real-life virtual
assistants aren't as smart as Ironman's Jarvis, but their intended function is largely
the same, voice-activated computing powered by artificial intelligence. Ask a
question, get an answer. Give a command, get results. Here is the insight of some of
the Personal Assistant devices .Ivee Sleek is a voice-activated alarm clock by
Interactive Voice that makes setting an alarm, changing an alarm sound, and turning
an alarm on or off completely hands-free. Additionally, Ivee Sleek has a variety of
possible voice commands ranging from the current date and time to uncategorizable
inquiries. Homey is a voice-activated home automation hub created by Netherlands-
based startup Athom. It comes with multiplatform Smartphone app and it can still
communicate with a bunch of differently-configured gadgets at once. It's multi-lingual
and understands English, Dutch, Spanish, and French. It is compatible with a bunch
of app-enabled smart home products. Amazon's Alexa is a "Virtual-Assistant"
manages to set itself apart. Unlike mobile-based virtual assistants like Siri, Alexa is
centralized within dedicated, in-home Amazon devices --most notably the Amazon
Echo, an always-on, always-listening Internet-connected speaker. Here are some
features of Alexa. Stream music: Ask Alexa to play a song and it will stream it from
the Amazon Prime Music Library. Read the headlines: Alexa can read out headlines
from the news outlets .
1.4. Introduction of Software / Language Used :
X
II
I
1.4.1 PYTHON 3.6 :
 Python’s standard library is very extensive, offering a wide range of facilities as
indicated by the long table of contents listed below. The library contains built-in
modules (written in C) that provide access to system functionality such as file
I/O that would otherwise be inaccessible to Python programmers, as well as
modules written in Python that provide standardized solutions for many
problems that occur in everyday programming. Some of these modules are
explicitly designed to encourage and enhance the portability of Python
programs by abstracting away platform-specifics into platform-neutral APIs.
 The Python installers for the Windows platform usually include the entire
standard library and often also include many additional components. For Unix-
like operating systems Python is normally provided as a collection of packages,
so it may be necessary to use the packaging tools provided with the operating
system to obtain some or all of the optional components.
 It contains data types that would normally be considered part of the “core” of a
language, such as numbers and lists. For these types, the Python language
core defines the form of literals and places some constraints on their semantics,
but does not fully define the semantics. (On the other hand, the language core
does define syntactic properties like the spelling and priorities of operators) .
 The library also contains built-in functions and exceptions — objects that can be
used by all Python code without the need of an import statement. Some of
these are defined by the core language, but many are not essential for the core
semantics and are only described here.
 The bulk of the library, however, consists of a collection of modules. There are
many ways to dissect this collection. Some modules are written in C and built in
to the Python interpreter; others are written in Python and imported in source
form. Some modules provide interfaces that are highly specific to Python, like
printing a stack trace; some provide interfaces that are specific to particular
operating systems, such as access to specific hardware; others provide
interfaces that are specific to a particular application domain, like the World
Wide Web. Some modules are available in all versions and ports of Python;
X
I
V
 others are only available when the underlying system supports or requires them;
yet others are available only when a particular configuration option was chosen
at the time when Python was compiled and installed.

1.4.2 pyaudio :
pyAudioAnalysis is a Python library covering a wide range of audio analysis
tasks. Through pyAudioAnalysis you can:
 Extract audio features and representations (e.g. mfccs, spectrogram,
chromagram)
 Classify unknown sounds
 Train, parameter tune and evaluate classifiers of audio segments
 Detect audio events and exclude silence periods from long recordings
 Perform supervised segmentation (joint segmentation – classification)
 Perform unsupervised segmentation (e.g. speaker diarization)
 Extract audio thumbnails
 Train and use audio regression models (example application: emotion
recognition)
 Apply dimensionality reduction to visualize audio data and content similarities
1.4.3. pyttsx3 :
 An application invokes the pyttsx3.init() factory function to get a
reference to a pyttsx3.Engine instance. During construction, the
engine initializes a pyttsx3.driver.DriverProxy object responsible
for loading a speech engine driver implementation from the
pyttsx3.drivers module. After construction, an application uses the
engine object to register and unregister event callbacks; produce and
stop speech; get and set speech engine properties; and start and stop
event loops.
 pyttsx3.init([driverName : string, debug : bool]) →
pyttsx3.Engine
X
V
  Gets a reference to an engine instance that will use
the given driver. If the requested driver is already
in use by another engine instance, that engine is
returned. Otherwise, a new engine is created.

1.4.4.speech recognition :
 Speech Recognition is an important feature in several
applications used such as home automation, artificial
intelligence, etc. This article aims to provide an
introduction on how to make use of the
SpeechRecognition library of Python. This is useful
as it can be used on microcontrollers such as
Raspberri Pis with the help of an external
microphone.
 Speech recognition is the process of converting audio
into text. This is commonly used in voice assistants
like Alexa, Siri, etc. Python provides an API called
SpeechRecognition to allow us to convert audio into
text for further processing. In this article, we will
look at converting large or long audio files into
text using the SpeechRecognition API in python.
 One way to process the audio file is to split it into
chunks of constant size. For example, we can take an
audio file which is 10 minutes long and split it into
60 chunks each of length 10 seconds. We can then feed
these chunks to the API and convert speech to text by
concatenating the results of all these chunks. This
method is inaccurate. Splitting the audio file into
chunks of constant size might interrupt sentences in
between and we might lose some important words in the
process. This is because the audio file might end
X
V
I
 before a word is completely spoken and google will
not be able to recognize incomplete words.

 The other way is to split the audio file based on

silence. Humans pause for a short amount of time
between sentences. If we can split the audio file into
chunks based on these silences, then we can process
the file sentence by sentence and concatenate them to
get the result. This approach is more accurate than
the previous one because we do not cut sentences in
between and the audio chunk will contain the entire
sentence without any interruptions. This way, we don’t
need to split it into chunks of constant length.

 The disadvantage of this method is that it is

difficult to determine the length of silence to split
because different users speak differently and some
users might pause for 1 second in between sentences
whereas some may pause for just 0.5 seconds.
1.4.5. os module :

 The OS module in python provides functions for

interacting with the operating system. OS, comes under
Python's standard utility modules. This module
provides a portable way of using operating system
dependent functionality. The *os* and *os.path*
modules include many functions to interact with the
file system.

 The functions OS module provides allows us to operate

on underlying Operating System tasks, irrespective of
it being a Windows Platform, Macintosh or Linux. In
this lesson, we will review these functions and what
we can do with these.

X
V
II
  Python is one of the most frequently used languages in
recent times for various tasks such as data
processing, data analysis, and website building. In
this process, there are various tasks that are
operating system dependent. Python allows the
developer to use several OS-dependent functionalities
with the Python module os. This package abstracts the
functionalities of the platform and provides the
python functions to navigate, create, delete and
modify files and folders. In this tutorial one can
expect to learn how to import this package, its basic
functionalities and a sample project in python which
uses this library for a data merging task.

1.4.6. sys module :

 The value of sys.argv is a Python list of command line
arguments that were passed to the Python script. The
first argument, argv[0] is the name of the Python
script itself. Depending on the platform that you are
running on, the first argument may contain the full
path to the script or just the file name. You should
study the documentation for additional details.
 The sys module’s path value is a list of strings that
specifies the search path for modules. Basically this
tells Python what locations to look in when it tries
to import a module. According to the Python
documentation, sys.path is initialized from an
environment variable called PYTHONPATH, plus an
installation-dependent default.
 The stdin, stdout and stderr map to file objects that
correspond to the interpreter’s standard input,
X
V
II
I
 output and error streams, respectively. stdin is used
for all input given to the interpreter except for
scripts whereas stdout is used for the output of print
and expression statements. The primary reason I mention
this is that you will sometimes need to redirect
stdout or stderr or both to a file, such as a log or
to some kind of display in a custom GUI you have
created.

1.4.6 threading module:

 Python has a number of different concurrency
constructs such as threading, queues and
multiprocessing. The threading module used to be the
primary way of accomplishing concurrency. A few years
ago, the multiprocessing module was added to the
Python suite of standard libraries. This chapter will
be focused on how to use threads and queues.
 Thread class that can download files from the
internet. The U.S. Internal Revenue Service has lots
of PDF forms that it has its citizens use for taxes.
We will use this free resource for our demo.
 This is basically a complete rewrite of the first
script. In this one we import the os and urllib2
modules as well as the threading module. We will be
using urllib2 to do the actual downloading inside the
thread class. The os module is used to extract the
name of the file we’re downloading so we can use it
to create a file with the same name on our machine.
In the DownloadThread class, we set up the __init__
X
I
X
 to accept a url and a name for the thread. In the run
method, we open up the url, extract the filename and
then use that filename for naming / creating the file
on disk. Then we use a while loop to download the file
a kilobyte at a time and write it to disk. Once the
file is finished saving, we print out the name of the
thread and which url has finished downloading.
 The Python 3 version of the code is slightly
different. You have to import urllib instead of urllib2
and use urllib.request.urlopen instead of urllib2.urlopen.
 Now you know how to use threads and queues both in
theory and in a practical way. Threads are especially
useful when you are creating a user interface and you
want to keep your interface usable. Without threads,
the user interface would become unresponsive and
would appear to hang while you did a large file
download or a big query against a database. To keep
that from happening, you do the long running
processes in threads and then communicate back to
your interface when you are done.

X
X
 Chapter – 2

Software Requirement Specification

2.1. Functional Requirement :
 The main objective of the study is to define the metrics to measure the quality
of software in the architecture for an artificial intelligence system. The proposed
architecture for measurement consists of four components; Task specification
layer, problem solver layer, domain layer and an adapter layer. These four
components are hierarchically organized in a layered fashion. In this
architecture, the overall structure is decomposed into sub components, in a
layered way such that a new layer can be added to the existing layer that can
change the behavior of the system. The quality of components in the
architecture are measured with metrics such as source code, depth of
inheritance, number of paths, complexity level etc., These metrics are related to
software quality characteristics suggested by ISO. This study is organized in the
following way; Firstly, the study addresses the significance of software
architecture in a software intensive AI system, the importance of quality of the
X
X
I
 software in the architecture and a layered architecture for artificial intelligence
system. The secondly, the study addresses the relation ship between the quality
characteristics and the metrics used for measuring the quality. The performance
of the system with respect to functional requirement and non-functional
requirements are measured and discussed.
 Quality is a multi-dimensional construct comprising of various parameters,
which are reflected in quality modeling. Although, several quality attributes to
measure the software quality are specified in the literature, like FURPS,
McCall, Boehm, they are related to various aspects of the software such as
product revision, transition and operation. Hence it is necessary to select
appropriate attributes that are relevant to the software pertaining to Artificial
Intelligence systems. In this study, the quality attributes, which are relevant to
the software of Artificial Intelligence systems, are identified as testability
usability readability and self-descriptiveness. Metrics are related to these
attributes and measured for the software applicable to Artificial Intelligence
System. The attributes selected for measurement in this study is based on ISO
9126 model.
 Intelligence is the ability to process information in a properly complex
environment in a partial way; nevertheless this partial processing mechanism
yields maximally successful behavior. Even though AI is a sub field of
information processing, there are some important differences, in information
processing complete processing is a must, whereas in Artificial intelligence
processing in most cases complete processing is not possible. The illustrations
for the above is, in information processing, the algorithm for searching a data
must be complete, but in AI processing complex heuristics are used to reduce
the search and in some cases the best options may be missed occasionally.
Hence the AI systems should be architected in an evolutionary way not only to
fulfill the functional requirements or services that the system has to accomplish
but also to take in to account the quality of the service provided which are non-
X
X
II
 functional requirements such as portability, efficiency etc., Several constraints
like type of the platform, kind of network are also non-functional requirements,
which will have the impact on overall quality of the system.

2.2. Non functional Requirement :

 With the proliferation of vendor solutions in the Industrial Analytics marketplace,
it may be tempting to bypass the Business, Functional and Technical
Requirements phase of the purchase process. The danger of diverging from
standardized requirements and due diligence practices is that you become over-
dependent on the information provided by the solution vendors.
 The selection process for an IIoT Industrial Analytics solution is based on
industry, facility and solution-specific requirements. Although no two
requirements documents are identical, there are several functional and non-
functional requirements common for most analytics and maintenance scenarios.
 Below are key variables to consider when defining the requirements for an
Industrial Analytics solution for Predictive Maintenance. Use this checklist as a
starting point to develop your Requirements Document. For each variable, we
provided a Basic or Baseline Functionality and an Optimal or Best Practice
Functionality.
 Please note that our evaluations are high-level, and individual vendor solutions
will vary. We strongly recommend developing your own scorecard based on the
list of Functional and Non-Functional requirements identified by the internal
stakeholders of your industrial facility.
 At a facility level, technicians accessing the user-interface will not be trained in
Artificial Intelligence and Big Data. The key considerations when defining this
requirement are the visualization of machine behavior and the ability to depict the
health of machinery or the entire facility, and take specific action as a result.

X
X
II
I
  Analytics platform must be applicable to a machine or facility of any size. The
solution must be able to add assets without a need for any incremental investment
in hardware, software or dedicated labor hours.
2.3. Software and Hardware Requirement :
 Artificial Intelligence (AI) software is a reality, but only for limited classes of
problems. In general, AI problems are significantly different from those of
conventional software engineering. The differences suggest a different program
development methodology for AI problems: one that does not readily yield
programs with the desiderata of practical software (reliability, robustness, etc.).
In addition, the problem of machine learning must be solved (to some degree)
before the full potential of AI can be realized, but the resultant self-adaptive
software is likely to further aggravate the software crisis. Realization of the full
potential of AI in practical software awaits some prerequisite breakthroughs in
both basic AI problems and an appropriate AI software development
methodology.
 It is required to have a mother board which has on it, CPU, RAM, Video Card
and normally drives. This is necessary for the software to run and normally will
require an output device like monitors and speech recognition. The output
devices help the computer to recognize other information that it may have not
been able to recognize without it. This is important in some applicants such as a
robot which will react when you say words will be able to understand you if it
connected with a microphone and has the capability of using it.
 Hardware Requirement :
→ CPU: Core i5 / i7 or higher
→ RAM: 8 GB OR higher
→ Video Card: NVIDIA 7800 Series, ATI Radeon 1800 Series or better
→ Graphic Card: 512MB of Graphics Memory
→ Storage: 12GB
→ Sound Card: DirectX 9.0c Compatible
X
X
I
V
  Software synthesises data received from the hardware. Once the data has been
received and processed the AI system needs to make an intelligent response. To
create this software non-procedural languages are often used. These include
languages such as LISP and PROLOG. Both of these languages will actually
allow the system to learn and modify its responses to its environment. The
software requirements for a modeling and simulation of AI needed to do this
include:
 a fast CPU
 large amounts of RAM
 large storage capacity (i.e. large hard drive)
 a good graphics card
 you may also require specialized input output devices

Chapter – 3
Software Design Phase :
3.1. Dataflow Diagram :

X
X
V
1.1 dataflow diagram

X
X
V
I
1.2. Speech Recognition dataflow diagrams

X
X
V
II
3.2. ER Diagram :

1.3 ER Diagram of Jarvis

X
X
V
II
3.3. UML Diagram :

1.4. UML diagram of Speech Recognition of Jarvis

X
X
I
X
 Chapter – 4
Implementation and Results :
4.1. Description of Modules :
4.1.1 speech_recognition module :
 This module will record audio from your microphone, send it to the speech API
and return a Python string.
 The audio is recorded using the speech recognition module, the module will
include on top of the program. Secondly we send the record speech to the
Google speech recognition API which will then return the output.
4.1.2 text_to_speech module :
 Pyttsx3 is a cross-platform speech (Mac OSX, Windows, and Linux) library.
You can set voice metadata such as age, gender, id, language and name. Thee
speech engine comes with a large amount of voices.

4.2. Output Window :

 Custom Voice Commands – Its very easy to make custom voice commands in
English. Using this feature you can create your own commands and decide what
should Jarvis do when you say something. For example, you can create a
custom voice command such as open my sites which opens multiple websites
that you frequently use.
 Search Files and Folders – Search files and folders on your computer 10 times
faster!
 Weather Information – Get current weather condition report for any city/town
of the world.
 Open Programs, Files and Websites – Quickly open files and websites. You
can even create custom commands for the same.

X
X
X
  Text to Speech – You can make Jarvis read any text using text to speech. You
can make it read emails, e-books, stories or any website content just by
selecting text.
 Play/Search Songs and Videos – This is a super cool feature of this AI
program. Just say Play <song/artist name>, for eg. Play Hips don’t lie or Play
Akon and this app will start playing the song for you. Similarly, you can also
play videos on your computer by voice command.
 Window Control – Window control commands allows you to Minimize,
Maximize and Restore Windows. It also allows you to Scroll Up, Scroll Down
and even Switch Applications.

4.3 Implementation :

1.5. Jarvis Implementation Diagram

 Artificial Intelligence personal assistants have become plentiful over the last few
years. Applications such as Siri, Bixby, Ok Google and Cortana make mobile device
users’ daily routines that much easier. You may be asking yourself how these function.
Well, the assistants receive external data (such as movement, voice, light, GPS
readings, visually defined markers, etc.) via the hardware’s sensors for further
processing - and take it from there to function accordingly.
X
X
X
I
 In order to create a simple personal AI assistant, some programming abilities are
required. In particular, such languages as Python (being the most popular in this
regard) are used for the creation of AI-based apps.
 Python is used as a base for the most renowned AI-based software because of its
flexibility, simplicity and longstanding reputation.
 To successfully develop a virtual assistant, even an experienced Python developer
would need to advance the level of qualification from time to time, so topical literature
will come in handy. We can recommend several useful tools to make the stages of
AIA creation easier. Familiarize yourself with such libraries and tools as NumPy,
Matplotlib, Pandas, Scikit, Theano, AIMA, pyDatalog, SimpleAI, EasyAi, PyBrain,
MDP, scikit, PyML and others.
 It requires significant financial and time resources, which is why modern IT-
companies tend to choose ready-made platforms (described briefly above) in order to
create a unique product. As a result, the testing of general functionality of each
developed AI-based software consists of attempts to analyze the user interface, along
with quality and speed, with which it memorizes individual user interactions (route
optimizing, topics of general education, time management, informal conversations
with assistant, etc.) Monitoring will result in changes to further interaction
dependencies based on the influence of previous user experiences.
 The final step is to tie your application in the process(text) function. I left this function
empty. You can customize this portion as you wish and process the text to respond to
user queries.

X
X
X
II
 Chapter - 6
Conclusion and Scope of Work :
6.1. Conclusion :
 Project development and implementation → As it has been previous stated, the
program is mainly concerns with the techniques of Android development, Java
programming, Database management, Cloud computing, different APIs for Google
products, Bing translate and etc. The program is developed by two developers and
follows the extreme programming model. During the eight weeks development, the
developers did the same cycle in each phase of analyze requirements, construct design,
implement the solutions in pair programming mode and test the result. The
development is carried out as its primary planning which guide the work process of
how to work with the program, how much time should the each of the developers
spent in every week, the rescores needed for developing and how to handle the
problems while it came up. The project was efficiently completed under the
development model and the resources we found in early time were really useful when
implementing the program.
 Project usage & prospect, potential → The project is very useful and owns a large
potential use in different industries. Although the program primary concerns more
about how to do the personal assistant on Android phone using the voice, the concept
of voice recognition can be applied in different industries as in many situations it will
be more convenient, save a lot of time and helpful especially for those who have
difficulty in working with manual operations.

X
X
X
II
6.2. Future Scope of Work :
 No program has a perfect design without any flaws; it is the same here in this program.
Even though the program is completed with all the primary functions implemented and
work properly, there are still many things that can be done with this program. As the
future improvement, the potential work that can be implemented ranging from adding
more functions to offering the user a more comprehensive, convenient program,
refining the logic to make the program more humanized and easy to use, increase the
database capacity and add more possible keywords, responses and data in this
program, interface optimization and etc.
 Add more functions: although there have been 8 normal functions that are used really
often with the mobile phone, there can be more functions which simplify our daily life
and make it convenient to use. Functions as playing movies, checking stocks,
exchange rate, downloading and uploading, installing APPs and etc, these can be the
potential functions that make the program more comprehensive and people can enjoy
more services in this program.
 The more humanized the program is, more easier the user can use it. People should
accept that even if developers constantly try to add more predefined commands, more
responses to it, analyze and respond to the command more intelligently, the program
will never be completely comprehensive and contain all the possible circumstances
that the users meets. Nevertheless, the program will certainly be improved and be
more user-friendly if there can be more readable commands, more humanized structure
and more intelligent response.

X
X
X
I
Table 1.1 Future Scope

X
X
X
V
References :
 http://www.ai.sri.com/~nysmith/slides/aic-seminars/070322-wobcke.pdf
 www.youtube.com
 www.googlescholar.com
 https://codewithharry.com/videos/python-tutorials-for-absolute-beginners-120
 https://www.youtube.com/watch?v=9SqTJQGDJZ0&list=PLkb3p1b2TbNwHFsnLLb
6ovtm5_9VdOffD&index=12
 OpenAI, Blog, https://openai.com/blog/
 N. Bostrom, Superintelligence: Paths, dangers, strategies
 Microsoft, Cortana actions, https://msdn.microsoft.com
/en-us/cortana/actiontypeofaction,
 Apple,Introduction to sirikit,
https://developer.apple.com/library/prerelease/content/documentation/Intents/Concept
ual/SiriIntegrationGuide/index.html

X
X
X
V