Department of Computer Science and Engineering

Nitte Meenakshi Institute of Technology

College Enquiry Chatbot

Cloud Computing-17CS72

Presented by:
Krishna Sampath Gudimani- 1NT17CS096
Prasad Patil- 1NT17CS128
Naveen Kumar Y R- 1NT17CS112
Joshwan M J- 1NT18CS412

Guided by: Mrs. Sharmila Sequeira

 Overview
 Introduction
 Background Study
 Requirements
 Design
 Architecture diagram
 Technology
 Future Works
 Conclusions
 References
 INTRODUCTION
 This project is focusing on creating a chatbot to be used by students to get their queries responded
easily from the college website. A chatbot is a program which can do real conversations with
textual and auditory methods. Using AI chatbots can simulate human conversion.

 There are two categories of chatbots. One category is command based chatbots where chatbots
rely on a databank of replies. The user must be very specific while asking the questions so that the
bot can answer. Hence, these bots can answer limited set of questions and cannot perform
function outside of the code.

 The other category is chatbots based on AI or machine learning algorithms, these bots can answer
ambiguous questions which means the user do not have to be specific while asking questions.
Thus, these bots create replies for the user’s queries using Natural Language Processing.

 Before implementing College Enquiry Chatbot, various existing chatbots are been reviewed such
as Amazon Shopping App, Alexa, Bank of America (Erica bot) and CNN news bot. In order to
understand the requirement of a chatbot.
 BACKGROUND STUDY
 In the olden days students had to visit the college to enquire about details and other
information about the college ,which is a time consuming process as well as lengthy procedure
for both parents as well as students. now a days there are many changes occurred in the
Education system with help of advanced technological improvements.

 Eliza and the Doctor Script: Many program and applications have been developed based on
this concept. One of first chatbot called Eliza. It is famous because it is an open source
program. Eliza makes the use of NLP. It provided a basic human-like interaction with almost
no information about human thought or emotion. It was written at MIT between 1964 and
1966.

 ELIZA uses simple pattern matching techniques, but was in talks when the creator explained
how it actually works. It was one of the first chatterbots in existence. It comprised of many
scripts, each of which processed the responses of the users by simple parsing and by the
substitution of them into premade templates and also there were hardcore phrases to as to
continue conversations.
 Cont…
 Cleverbot: Cleverbot is also a web application which converses with humans and uses artificial
intelligence algorithms. It was created be British scientist Rollo Carpenter. The difference
between Eliza and Cleverbot is that its unique algorithm learns from humans and remembers
words within its AI.

 Because of its complex algorithm structure, it is constantly learning. It’s data size is also
increasing. Due to this it appears to display a degree of “intelligence”. It’s software updates are
constantly checked and in 2014 it was upgraded to use GPU serving techniques.

 Cleverbot also participated in a Turing Test in 2011 organized by IIT Guwahati. Cleverbot was
judged to be 59.3% human. The software which participated in the test had to process 1 or 2
simultaneous requests, but it was noted that Cleverbot handled 80000 people at once.

 Problems with Cleverbot: It doesn’t take anyone too many sentences for it to fail a Turing test,
and figure out it was saying things that had been said to it many times.
 REQUIREMENTS

 Hardware Requirements:
 2 GB Space Disk
 4 GB RAM
 Processor Dual Core

 Software Requirements:
 Windows 7 and above
 SQL database servers
DESIGN

Chat

Add
Information

View
Information

Update
Information

Delete
Information
ARCHITECTURE DIAGRAM
Cont…
 TECHNOLOGY
 Context Identification:
Here pre-processing has been applied to the input text so as to standardize the
input. This is done keeping the system’s requirements in mind. The recognition of the
appropriate context is based on the keywords used in the text.

 Personal Query Response System:

 Log File:
A log file is also maintained which store those queries which the chatbot was
not able to answer. It is the work of the admin to view the log file and the responses
of the sentences. All this is done 32 into the knowledge base. This is a very
important method to improve the overall functioning of the chatbot.
 Cont…
Query Analysis and Response System:
 This technology provides information regarding the proceedings of the college. It is
known that the answer will be given to the user if the input matches a pattern in the
AIML files. In a case where the input does not match with the data in AIML files,
keywords are fetched.
 An algorithm to check the sentence similarity is applied to the modified input so that
its similarity can be checked. If a sentence is retrieved with confidence>0.5, the
query’s answer is given.

Context Reset:
After the queries of the user are over and the he/she wants to exit the portal, then they
have to just enter “bye” or simple exit the portal. When the user exits the application, all
the input parameters are reset.
 FUTURE WORKS
 To improve the current functionalities of College Enquiry Chatbot, in the future,
the scope of the chatbot can be increased by inserting data for all the
departments, training the bot with varied data, testing it on live website, and
based on that feedback inserting more training data to the bot.

 Some of the new features which can be added to the bot are:
 Speech recognition feature through which students can ask their queries
verbally and get the answers from the bot.
 Adding a capability for the bot to perform analytics based on user’s
sentiment based on which the bot can be re-trained on human emotions so
that more empathy can be added to the bot.
 Integration with multiple channels such as phone call, SMS, and various
social media platforms like Skype, Facebook and Twitter.
 Integration with services such as password reset and course.
 CONCLUSIONS
 College Enquiry Chatbot is helpful in guiding students with correct and most up
to date sources of information. It is advantageous for international applicants
for queries such as fee payment and academic matters. Students can get the
information at their fingertips rather than visiting college office. It improves
efficiency by taking over tasks for which humans are not essential.

 College Enquiry Chatbot correctly recognizes the user’s query such as positive,
negative, and neutral by storing all the conversations in the database. And reply
with appropriate result.
 REFERENCES
 Mauldin Michael (1994) ,”ChatterBots , TinyMuds, ” and that tureing test:
entering the loebner prize competition “, proceedings of the eleventh national
conference on artificial intelligence.

 Bayu Setiaji, Ferri Wahu Wibawo, “Chatbot Using A Knowledge in the Database
”, on 2016 7th International Conference on the Intelligent Systems, Modelling
and Simulation.

 E. Haller and T. Rebedea, "Designing a Chat-bot that Simulates an Historical

 S. J. du Preez, M. Lall and S. Sinha, "An intelligent web based voice chat bot,"
EUROCON 2009, EUROCON '09. IEEE, St. - Petersburg, 2009.