American Journal of Neural Networks and Applications

2017; 3(1): 1-4

http://www.sciencepublishinggroup.com/j/ajnna
doi: 10.11648/j.ajnna.20170301.11
ISSN: 2469-7400 (Print); ISSN: 2469-7419 (Online)

Proposal of Chat Based Automated System for Online

Shopping
Hemin Joshi, Vidhi Agarwal, Amol Ghodke, Dolly Gupta, Sharmila Gaikwad
Department of Computer Engineering, University of Mumbai, Mumbai, India

Email address:
[email protected] (H. Joshi), [email protected] (V. Agarwal), [email protected] (A. Ghodke),
[email protected] (D. Gupta), [email protected] (S. Gaikwad)

To cite this article:

Hemin Joshi, Vidhi Agarwal, Amol Ghodke, Dolly Gupta, Sharmila Gaikwad. Proposal of Chat Based Automated System for Online
Shopping. American Journal of Neural Networks and Applications. Vol. 3, No. 1, 2017, pp. 1-4. doi: 10.11648/j.ajnna.20170301.11

Received: October 26, 2016; Accepted: January 25, 2017; Published: March 1, 2017

Abstract: Chatbots have the potential to save any individual’s time, hassle, and tedium by automating mundane tasks. The
idea about this application is that it will help the user to interact with the Ecommerce engine through an Intelligent Assistant.
The application offers the exhilarating experience of placing orders on the Ecommerce site according to his/her needs and
viewing the previously placed orders anytime the user wants. CartBot will turn into a customized personal assistant that knows
your online likes and preferences and serves as a magical tool to deliver the products on time and in the most convenient
manner. An account has to be linked to the device, thus allowing you to back up your history in case of device malfunction or
any other unfortunate activity. This paper is based on the research work that has been done for the project.

Keywords: Chatbots, Artificial Intelligence, Ecommerce, Intelligent Agent, Human-Computer Interaction,

Dialogue Management

This paper is divided into various sections. Section 2 talks

1. Introduction briefly about the existing work done on chatbots. Section 3
It’s a rare moment when it becomes clear that a presents the idea of the project, and what it entails for an end
technological revolution is upon us. We believe that we are in user. Section 4 describes briefly about the flow of the project
midst of one of the biggest revolutions right now. If you and how it will work, Section 5 describes the plan that has
haven’t realized it, bots are everywhere. Your interaction been set by the team for the project’s implementation.
with Siri, scheduling an appointment over email with Section 6 discusses the future scope of the project. Section 7
someone named Raj Singh, or set up a team meeting with an concludes the paper. This is followed by references.
interestedly helpful associate in Slack, you’ve already had a
close interaction with a bot! Bots have the potential to save 2. Related Work
us time, stress, and tediousness by automating boring tasks,
like gathering your team’s lunch preferences or building a ALICE: ALICE [1] was implemented by Richard Wallace
travel itinerary, which could typically vex up hours of your in 1995. It uses pattern matching and stores the information
time. Brands are catching on too, as evidenced by the throngs in Artificial Intelligence Markup Language, or else known as
of businesses developing their self-designed mechanized AIML, files. An AIML file is similar to an XML file that was
messengers. With the rise in Machine Learning, chatbots or developed to store pattern knowledge for chatbots. There are
bots in general are termed to be precocious. three types of AIML categories, atomic categories, default
Having a chatbot on one’s e-commerce, it website will categories and recursive categories, which are described
certainly add to the company’s popularity, public relations below.
and will retain current users by turning them into even more Atomic categories: Is a type of AIML category where
proactive content consumers. One can use them from there is an exact match.
answering customer’s questions all the way to the delivery of <category>
the products. <pattern>What is your age</pattern>
2 Hemin Joshi et al.: Proposal of Chat Based Automated System for Online Shopping

<template>My age is 25</template> In Google Allo you’ll also be introduced to a preview

</category> edition of the Google Assistant. With your Assistant in
In the above example if the user submits “What is your Allo, you can have a conversation with Google. One
age” then the chatbot will reply with “My age is 25”. can ask questions and it will help get things done
Default categories: Is a type of AIML category where the directly in the chats.
use of a wild character such as * is used to match any input.
<category> 3. Trend Analysis
<pattern>What is *</pattern>
<template>It is my age</template> Companies like Slack, AirBnB, Facebook (Messenger
</category> Platform with Bot M), Tesla are increasingly relying on
If ALICE does not find a solution using the first category Artificially Intelligent Bots. Google has reportedly
it will proceed to the second. In this case if a user submits developing its own Chatbot ‘Allo’ which helps the user with
“What is a age” then ALICE will do a check until the wild mundane tasks. So it can be inferred that there is a growth in
char and if there is a match it will come with the answer. chatbot adoption rate. The graph in figure 1 shows increasing
Recursive categories: Is a type of an AIML category where interest in messenger bots recently according to Google
special tags are used to refer to a recursion to convince the trends [6].
user to be more specific.
<category>
<pattern>Do you know what the * is</pattern>
<template>It is my age
<srai>What is <star/></srai>
</template>
</category>
In this case the wild character * is used to reduce the input
submitted by the user. If the user submits “Do you know
what the time is” then this becomes “What is the time”.
ALICE is the most-awarded AI chatbots [2].
Slackbot: Slackbot [3] is very own friendly, built-in bot — Fig. 1. Trend Analysis.
part-time programmer and full-time assistant. It helps to keep
things in order. There are lots of things Slackbot can help Although chatbots are at a relatively early stage of
with. commercial exploitation we are already seeing some major
A few of them to list are: organisations in the USA deploy this technology.
1. Jump to any conversation in a second. Companies already deploying avatar based chatbots
2. Search for messages using search modifiers. technology include: Coca-Cola, L'Oriel, McDonalds, Cisco,
3. Organize important messages and tasks using stars Xerox and Dell.
4. Create custom emojis. UK operations already deploying chatbots include: Ikea,
5. Get back to important conversations by marking them Newcastle Building Society, Trainline [7].
as unread. While the chatbots market is still in the nascent stage of
6. Easily edit your most recent message with the up-arrow development, the race for leading enterprise chatbot platform
key guarantees to be exciting. In the current scenario, three
7. Integrate apps you use frequently. participants are in a position to offer enterprise chatbot
8. The forward slash opens up a whole new world of solutions include messaging platform vendors, voice
commands. platform vendors, and chatbot platform start-ups. The global
Google Allo: Allo [4] is an instant messaging mobile app chatbots market is driven by technology developments and
that is developed by Google that includes a virtual assistant innovation. The competitive conflict among current market
and provides a "smart reply" function that allows users to players is comparatively high as every player is seeking to
reply without typing. It was announced at Google I/O on gain first movers advantage in the market [8].
May 18, 2016 and launched on September 21, 2016. The app
is available on Android and iOS. 4. Concept Propagation
Some of the features [5] of Allo are:
Google Allo makes it easier for the user to respond Today E-Commerce websites contains a wide range of
quickly and keep the conversation going, even when products in each of its category which results in a huge and
you’re on the go. With Smart Reply, one can respond to complex database. These products are spread across
messages with just a tap, so one can send a quick numerous amount of web pages and categorized according to
response to a friend. their type. Navigating through these web pages to locate
Chat is more than just text, so they’ve created a rich relevant results, according to the user specifications, can be
canvas for users to express themselves in Google Allo. non-resulting, time consuming and annoy at times.
 American Journal of Neural Networks and Applications 2017; 3(1): 1-4 3

A user visiting an E-commerce may look for a specific after the payment has been made by the user will also be
product, or generally browse the website. The search tools reported by the bot.
use keyword matching to display multiple results to the The bot can give suggestions based on previous purchases,
user’s query. Out of these results, some might be relevant to give information about any product that user wishes to know
the user or the results might be not come with the output. about or ask questions to bring out further information about
This could be bad experience for user. Also in case a user the required product depending on the user interaction.
does not have clear knowledge about the product he/she
intends to buy, systems will not be able to give appropriate 4.2. Interaction with the User
results to such a user. The user can access the website through his/her android
4.1. Proposed System device and it will have a chat system with the bot. Any
requirement of the user can be directly entered into the
To demonstrate the concept of the project we will design message window. The chatbot takes this input and matches it
an E-Commerce Engine that has a catalogue of products that with the pattern matching programmed and it will give out
can be browsed by chatbot through an android app. responses. If the response that is returned is matching the
The website is self-designed so it can be integrated easily needs of the user, he/she can click on ‘YES’ and the product
with the chatbot. The depth of the “selection and ordering” will be added to cart. After this point, payment for the same
will be extremely flexible and hence will allow the user can be made.
which is the chosen product. The database of the agent
though not apparent to the user, will form the backbone of 5. Implementation Plan
data availability and storage. Forming a bot takes the load
from the user’s devices onto our servers, thus saving the The Implementation Plan of the entire system is divided
users from unnecessary thoughts about storage difficulties. into 3 tiers, which are to be done sequentially. The
The user will have the pleasure of being notified about the architecture of the system is as shown in the figure 2.
placement of the orders. The shipping status of the product

Fig. 2. Three-Tier Architecture System for Cartbot.

The 3 tiers are explained as follows: input controls or other widgets that draw some part of the UI.
(1). Android Skin This hierarchy tree can be as simple or complex as you need
All user interface elements in an Android app are built it to be but simplicity is best for performance [9].
using View and ViewGroup objects. A View is an object that
draws something on the screen that the user can interact with.
A ViewGroup is an object that holds other View (and
ViewGroup) objects in order to define the layout of the
interface.
Android provides a collection of both View and
ViewGroup subclasses that offer you common input controls
(such as buttons and text fields) and various layout models
(such as a linear or relative layout).
The user interface for each component of the app is
defined using a hierarchy of View and ViewGroup objects, as
shown in figure 3. Each view group is an invisible container
that organizes child views, while the child views may be Fig. 3. Illustration of a View Hierarchy defining UI Layout.
4 Hemin Joshi et al.: Proposal of Chat Based Automated System for Online Shopping

(2). Intelligent Agent learn the responses of the users resulting in increasing
An agent will gather information and perform the efficiency. Cartbot will have the ability to respond like
necessary services without your immediate presence and on human being hence it will ease the efforts that are required to
some regular schedule. Typically, the agent program will use be done by human.
the parameters you have provided, will search all or some Thus, in this paper, we have planned to implement an
part of the engine, gather information you're interested in, Ecommerce engine based Cartbot which will attempt to
and present it to you when you ask for it. A simplified improve the interaction of the user with E-Commerce engine.
architecture and working of the agent that will be used is as Cartbot will store a set of responses, but also will take
shown in figure 4. dynamic user input into account and thus tend to provide
relevant responses and product suggestions.

References
[1] Chatbot For Admissions. pdf [Online] Available:
https://Arxiv.Org/Ftp/Arxiv/Papers/1408/1408.6762.Pdf.

[2] Artificial Intelligence Foundation. A. L. I. C. E. [Online]

Available: http://alice.pandorabots.com/.

[3] Marc Knoll (2015, March 23). 10 Great Slack hacks and tips
that make you more productive by Marc Knoll [Online]
Fig. 4. Architecture of the Intelligent Agent. Available: http://trendblog.net/10-great-slack-hacksand-tips-
that-make-you-more-productive/.
Problem generator part of the agent will process the user
input to generate a problem statement. This will be parsed [4] Google Allo [Online] Available:
https://en.wikipedia.org/wiki/Google_Allo.
internally and results are sorted. Performance element will be
responsible for performing all external actions. Learning [5] Amit Fulay (2016, September 21). Say Hello to Google Allo:
element of the agent will take the feedback from the critics A Smarter Messaging App [Online] Available:
about the agent and decide on how performance element will https://googleblog.blogspot.in/2016/09/google-allo-smarter-
messaging-app.html.
have to be modified when it will be used in the future.
(3). Ecommerce Engine [6] Robert Allen (2016, June 29). The Rise of the Bots – What
Modules: marketers need to know about chatbots [Online] Available:
Catalogue and Product Management http://www.smartinsights.com/managing-digital-
marketing/managing-marketing-technology/the-rise-of-the-bots.
Order Management
Checkout, Payment & Processing [7] Deploying Chatbots to Customer Advantage, A White Paper,
Recommendation system [10]. November 2011 [Online] Available:
https://connect.innovateuk.org/c/document_library/get_file?gr
oupId=152301&folderId=3931510&title=Chatbots+for+Custo
6. Future Scope mer+Advantage.pdf.

The Cartbot will have pre-defined set of rules that [8] Admin (2016, June 14). Chatbots Market Size, Share, Trends,
transform the input sentence into an output. However, the Growth, Analysis and Forecast to 2022: Credence Research
[Online]. Available:
future of Cartbot can be based on using neural networks. The
http://www.getnews.info/555023/chatbots-market-size-share-
neural network model learns associations between the word trends-growth-analysis-and-forecast-to-2022-credence-
sequences that make up input and output sentences. It will be research.html.
an attempt of implementing Sequence to Sequence Learning
[9] UI Overview [Online]. Available:
with neural networks and reproducing results in
https://developer.android.com/guide/topics/ui/overview.html.
conversational model. It will not always be perfect but it will
be exciting. Cartbot advanced with neural network will learn [10] Magento Feature List, February 2014 [Online] Available:
in many notable ways, although act odd at times. But the user http://info2.magento.com/rs/magentosoftware/images/Magent
o%20Full%20Features%20List%20052714.pdf.
can sure have some good time shopping! [11].
[11] Jamie Condliffe (2015, February 02). Google's Neural
Network Chatbot Can Discuss Philosophy and IT Troubles
7. Conclusion [Online]. Available: http://gizmodo.com/googles-neural-
network-chatbot-can-discuss-philosophy-a-1715347859.
The Cartbot will use artificial intelligence and hence will