SYNOPSIS

on
CHATBOT ASSISTANT

DEVELOPED BY:
Ravi Kumar
Kanhaiya Verma
Prachi Bhardwaj
Ashok Kumar
Kurma Anil Kumar
Section: K18BY
LOVELY PROFESSIONAL
UNIVERSITY
What is a chatbot assistant?
An Intelligent Virtual Assistant (IVA) or Intelligent Personal Assistant
(IPA) is an artificial agent who can perform tasks or services based on
commands or questions for a person. The term "chatbot" is sometimes used to
refer to virtual assistants which are generally or directly accessed via online
chat. Internet chat services are in some cases solely intended for entertainment
purposes. Some virtual assistants can read human speech and react through
synthesized voices. Users can ask questions from their assistants, monitor home
automation systems and media playback through voice, and use verbal
(spoken?) commands to handle other basic tasks, such as email, to - do lists and
calendars.
As of 2017, virtual assistant functionality and use are rapidly expanding, with
new products entering the market and a strong emphasis on both email and
voice user interfaces. Apple and Google have large user bases built on their
smartphones. Microsoft has a wide installed base of personal computers,
smartphones and smart speakers running on Windows. Amazon has a broad
deployment base for smart speakers.

Method of interaction
Virtual assistants do work through:
 Text including: online chat (especially with an instant messaging app or
other device), text message, email or other text-based communication
channels.
 Voice with, for example, Amazon Alexa on an Amazon Echo app, Siri on an
iPhone, or Google Assistant on Google-enabled / Android mobile devices
 By taking and/or uploading photos, as in the case of Samsung devices.
Virtual assistants use natural language processing (NLP) to align executable
commands with user text or voice data. Many are constantly learning by using
techniques of artificial intelligence like machine learning.
To activate a virtual assistant using the voice, a wake word might be used. This
is a word or groups of words such as "Hey Siri", "OK Google" or "Hey
Google", "Alexa", and "Hey Microsoft".
Concepts on which virtual assistant works
 Algorithms: An algorithm is a finite sequence of well-defined,
computer instructions in mathematics and computer science,
usually to solve a class of problems or to perform a computation.
Algorithms are always unambiguous and are used to perform
calculations, data processing, automatic reasoning, and other tasks
as defined.

 Natural language processing (NLP) is a subfield of linguistics,

computer science, information processing, and artificial
intelligence concerned with computers-to-human (natural)
language interactions, in particular how computers are
programmed to process and interpret large amounts of natural
language data.

 Machine learning (ML) is a scientific study of algorithms and

statistical models used by computer systems to perform a particular
task without using explicit instructions, relying instead on patterns
and inferences. It is considered to be a branch of artificial
intelligence. Machine learning algorithms create a sample data-
based mathematical model, known as "training data," to make
predictions or decisions without the function being specifically
programmed to perform the task.

 Artificial Intelligence (AI), sometimes referred to as machine

intelligence, is the intelligence shown by machines, in contrast to
the natural intelligence shown by humans and animals. It is often
used to define machines (or computers) that replicate “cognitive"
functions that people associate with the human mind, such as
“learning” and “solving problems”.
Devices and objects where found
 In devices such as smart speakers such as Amazon Echo, Google Home and
Apple Home Pod
 Instant mobile and web-based messaging apps, for example. Facebook's M
(virtual assistant) on both Facebook and Facebook Messenger apps or via the
Web
 Built into a mobile operating system (OS) like Apple's Siri on iOS devices
and BlackBerry Assistant on BlackBerry 10 devices, or into a desktop OS
like Cortana on Microsoft Windows OS
 Built into an OS-independent smartphone like Bixby on Samsung devices.
 On Instant Messaging Platforms, assistants from specific organizations such
as Aero Mexico's Aerobot on Facebook Messenger or WeChat Secretary on
WeChat.
 Across specific companies and other organizations ' mobile apps, such as
Dom from Domino's Pizza
 In appliances, vehicles, and wearable technology.
 Previous generations of virtual assistants often worked on websites such as
Ask Jenn of Alaska Airlines or on interactive voice response (IVR) systems
such as Nuance's American Airlines IVR.

Services
 Provide data, such as weather, facts, e.g. Wikipedia or IMDb, set an alarm,
make to - do lists and shopping lists
 Stream music from streaming services including Spotify and Pandora; play
radio stations; read audiobooks
 Stream video, TV shows or movies on TV, streaming from e.g. Netflix
 Conversational trade: live chat on messaging apps such as WeChat,
Facebook Messenger and WhatsApp, and messaging app chatbots or
websites.
 Assistance in public government communications (see Artificial
Government Intelligence).
 Complementing and/or replacing customer service by humans. One report
estimated that an automated on-line assistant produced a 30 per cent
decrease in the workload for a human-provided call center.

Developer platforms
 In April 2017, Amazon Lex was opened to developers. It involves natural
language understanding technology combined with automatic speech
recognition and was brought in November 2016.
 Google provides Actions on Google and Dialogflow platforms for
developers to create "Gestures" for Google Assistant.
 Apple provides SiriKit to developers to create extensions for Siri
 Watson's IBM, while sometimes speaking as a virtual assistant is actually
an entire artificial intelligence platform and a community powered by some
virtual assistants, chatbots and many other types of solutions.
How voice assistant works?
 Say the interaction words like OK Google, Alexa or Siri or click
the voice assistant button.
 Speak the task to be done.
 Voice assistant implements the task.
1. OK Google
2. Alexa

3. Siri
 Concept behind how the voice assistant works
Alexa, Siri and Google Assistant all work in a similar way, but there are policy
and data privacy intricacies involved when switching from assistant to assistant.
When you activate one of the assistants, your request is immediately packed and
sent to the servers operated by your respective system service.

On arrival, the words and tone of your request are evaluated by an algorithm,
which is then matched to a command it believe you asked for. Essentially, it
means, "We're eighty-five percent sure you asked this question," which is why
you don't always get the answer you were looking for. If the algorithm isn't sure
enough, it might ask, "Did you mean blank?” and give you the best guess of
what you wanted or it might say, "I'm sorry I can't do that yet."

While the algorithm is evaluating the problem, your device is trying to figure
out if it can handle the command without requiring information from the sever.
For example, a demand like "Can you pause music?"" is easy; if you want an
assistant to translate a word from Italian to English, it's more complicated. If
your request is more complex than a local command your system can connect
back to the server and continue to cross-check your question to make sure it
knows what you're asking for.

Finally, the answer to your question is given. If you have asked your assistant to
answer a trivial question, it will search the answer from the web (Google, Bing,
etc.) and move the answer back to your device. When you ask your Echo to turn
on your smart lights, a wi-fi signal will be sent to them, and they will be turned
on. The difficulty is related to the pace of the job and the perception of what
you want in the first attempt. Once an assistant knows what to do, that's the
basic process of logging into a website, a third-party computer, or another
electronic device.

Creating a voice assistant using python implementation

As we know, Python is a language that suits script writers and developers.
Python may be used to create a Personal Voice Assistant. The assistant's query
may be modified according to the needs of the user.

The implemented assistant can open the application (if it is installed in the
system), check the query for Google, Wikipedia, and YouTube, measure any
mathematical problem, etc., by simply giving the voice command. We can
process the data as needed or add the features depending on how we code things
.
Packages that may be required to run the chatbot assistant successfully:
 Speech Recognition Package: When you voice a question, we're going to
need something to catch it. The Speech Recognition program allows Python
to access audio from the microphone of your system, to transcribe audio, to
save audio into an audio file, and other related tasks.
 Text to Speech Package: Our assistant will have to translate your spoken
question to one that is text And then, once the assistant looks up an online
answer, the response will need to be translated into a voiceable phrase To
this end, we will use the gTTS (Google Text-to-Speech) kit. This kit
interfaces with the Google Translate API.
 Audio Playback Package: All that’s left is to give voice to the answer. The
mpyg321 package allows for Python to play MP3 files.
 Selenium needed for web-based work from browser.
 Wolframalpha package will be needed for calculation given by user.
 pyaudio  will be required for voice engine in python.

After this, we have to get started with the coding the program. We will be
dividing each function as a single code for easy understanding.