Sunteți pe pagina 1din 3

See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/313315555

Online Shopping Management System with Customer Multi-Language


Supported Query handling AIML Chatbot

Poster · February 2017


DOI: 10.13140/RG.2.2.10508.10885

CITATIONS READS

5 2,512

3 authors:

Md. Shahriare Satu Tajim Md. Niamat Ullah Akhund


Noakhali Science & Technology University Jahangirnagar University
22 PUBLICATIONS   47 CITATIONS    11 PUBLICATIONS   25 CITATIONS   

SEE PROFILE SEE PROFILE

Mohammad Abu Yousuf


Jahangirnagar University
26 PUBLICATIONS   134 CITATIONS   

SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Mining of Heart Disease data View project

Remote Temperature Sensing Line Following Robot with Bluetooth Data Sending Capability View project

All content following this page was uploaded by Md. Shahriare Satu on 04 February 2017.

The user has requested enhancement of the downloaded file.


Online Shopping Management System with Customer
Multi-Language Supported Query handling AIML
Chatbot
Md. Shahriare Satu1, Tajim Md. Niamat Ullah Akhund2 , Mohammad Abu Yousuf3
Institute of Information Technology, Jahangirnagar University
1shahriar.setu@gmail.com

2tajim.mohammad.3@gmail.com

3yousuf@juniv.edu

II. PROPOSED SYSTEM


Abstract—In the e-commerce sites, there are deal with
many kind of products throughout the world. Our proposed There are occurred many chatbot implementation in
shopping system contains different services to make user different field [4,5]. Our proposed system is consisted of
feasible in e-shopping time. When user want to buy anything
interactive e-commerce site of products with intelligent
from these sites, he needs guideline about product and other
things in this system just like make shopping in a store. To shopping assistant called AIML chatbot. AIML is
provide this kind of things in online, we integrate an derivation of Extensible Markup Language (XML)
artificial chatting system with e-commerce site which gives [2,3,4,6,7]. Now we will discuss some following steps that
unlimited chatting services. When user first get into the e- how-to user can access and manipulate the site and chat
commerce site, he can ask queries to know in the system. E- with an intelligent shopping chatbot briefly.
commerce system sends customer query to the AIML  There are two type of users which are administrator
Knowledge Base System to get answer by applying pattern (admin) and customer.
matching algorithm. Then this answer return back to the  Admin contains to maintain total system. He is
system and then back to the user. Besides, We try to develop responsible to add new product, update product
Bangla supported shopping assistant to show multi-lingual information and delete irrelevant or outdated product.
properties of chatting system. He can view and justify customer’s information whose
are registered in this system. Besides, he can notice
Keywords—AIML, chatbot, KBS viewer’s feedback about e-commerce site and product
to help authority further improvement.
I. INTRODUCTION  Customer can visit the site and view the product and
information of product. He can purchase desired
Online Shopping is the process where clients purchase their
products to add them to his order list. Besides, he can
goods and services from the vendor over the internet. Since the give feedback to the admin about products and e-
emergence of World Wide Web (WWW), vendor can easily sell commerce site.
their products to the people on the internet. Many people prefer  To ask query to know about products and services, our
online shopping because of its different kinds of convenience. e-commerce site is provided artificial chatting system
They can find a specific product by searching various online instead of human.
stores which is less time consuming and tedious process rather  E-commerce site send asking query to Knowledge
than searching this product in various store in the market. To Base System (KBS) to get answer this query.
know about the products and other things a buyer wants to meet Knowledge Base System is consisted of AIML based
and discuss about product with vendor. But for time and files. To find response of following query of customer,
distance, customer cannot meet to the vendor. Sometimes, applying pattern matching algorithm to those files.
human agents are recruited to give this service in online but he  The response of query return back to the e-commerce
does not provide much better services all time. Sometimes, he site and then back to the user.
felt annoyed, could not understand customer requirements and  In this way, user can ask more queries and otherwise
not available all times. In this case, we develop an integrated close conversation.
online shopping system with artificial chatting service that can
fulfill this requirement. Besides, to support multi-lingual III. RESULT AND DISCUSSION
capacities, we try to develop Bangla conversational agent that
can chat user with Bangla. ASP.NET MVC 4 (Model View Controller) and Entity
Framework 5 are required framework for developing this
ecommerce system Fig 1. We use photocopier machines of
different categories as the product of this site. Besides, this site
is represented different options to fulfill viewer requirement. To Translator checks the input, if it contains English alphabet then
manage customer online we introduce an intelligent shopping directly through it to the system and otherwise convert it to
assistant instead of human. It is developed by AIML files. Its English sentence and pass it this to the knowledge base system
category file developed over several years about 50,000 files [1] for further process. But, for response there is no need translator.
where all these categories are taken from different domain. With So, <template> is forwarded particular response for matching
the generic AIML files of knowledge base system, we have to pattern in the Bangla. Fig 3 shows the multi-language support
add more 860 new categories of products. Each file is accessed of AIML chatbot.
once to response a given question. So, time complexity is order
of n, where n is the number of words and space complexity is
depending on its memory location whose memory it use and
memory capacity. Fig 2 is showed the general representation of
AIML chatbot. It is a desktop version application that integrated
with main web application.

Fig. 3. Bangla supported of AIML chatbot

IV. CONCLUSION AND FUTURE WORK

In this work, we develop a model of e-commerce site that is


interactive to its users with different services to build a reliable
intelligent chatbot (assistant) which will responsible regular
customer service. But it has faced some limitations. One of
Fig. 1. Online Shopping System
them, it has lack of mining outcome as requirement. Besides, it
cannot contain sufficient natural language characteristics. So,
We are also integrated multi-language support capability that
in future we enrich our chatting system that can make
makes this application more interactive with user. In this case,
conversation using natural language with its user more
we use Bangla to support find result of this experiment. AIML
interactively with different medium.
supported Avro keyboard layout, Unicode and ANSI. When
chatbot get input data from user, we have to add a translator
REFERENCES
program.
[1] Md Shahriare Satu, and Md Hasnat Parvez. "Review of integrated
applications with AIML based chatbot." 2015 International Conference on
Computer and Information Engineering (ICCIE). IEEE, 2015.
[2] Bayan Abu Shawar and Eric Atwell. A chatbot as a novel corpus
visualization tool. In LREC, 2004.
[3] Bayan Abu Shawar and Eric Atwell. A comparison between alice and
elizabeth chatbot systems. Raport instytutowy, University of Leeds, 2002.
[4] Bayan Abu Shawar and Eric Atwell. Chatbots: are they really useful?
In LDV Forum, volume 22, pages 29–49, 2007.
[5] Hameedullah Kazi, BS Chowdhry, and Zeesha Memon. Medchatbot:
An umls based chatbot for medical students. International Journal of
Computer Applications, 55(17):1–5, 2012.
[6] Bayan Abu Shawar and Eric Steven Atwell. Using corpora in machine
learning chatbot systems. International journal of corpus linguistics,
10(4):489–516, 2005.
[7] Bayan Abu Shawar and Eric Atwell. A chatbot system as a tool to
animate a corpus. ICAME J, 29:5–24, 2005.

Fig. 2. AIML chatbot

View publication stats

S-ar putea să vă placă și