CHAT BOT SYSTEM

FOR COLLEGE
INFORMATION
Domain: machine learning

STUDENT NAME : K.SAMVEL

REG. NO : 832200340
DEPARTMENT : II M.Sc CS
GUIDE :Dr.D.BHUVANESWARI,M.SC.,M.PHIL.,ME., PH.D.
Assistant Professor,
Department of Computer Science.
 ABSTRACT
• A Chatbot is a computer program which conducts a conversation
via auditory or textual methods.
• The Chatbot has information stored in its database to identify the
sentences and making a decision itself as response to answer a given
question.
• The organization enquiry chat bot will be built using algorithms that
analyzes queries and understand user’s message.
• This System will be a web application which provides answer to the
query of the student very effectively.
• Students just have to put their query to the chat-bot which is used for
chatting.
• The system will use bigram and sentence similarity algorithms to
give appropriate answers to the user.
• If the answer is found invalid, then there is a system to declare the
answer as invalid. These invalid answers can be deleted or modified
by the administrator of the system.
 1.INTRODUCTION TO
PROJECT
• The chatbots have embedded knowledge which helps them to identify
the user’s query and give a response to it .
• The college enquiry chat-bot project is built using algorithms that
analyses user’s queries and understand user’s message. This system is
a web application which provides answer to the query of the student.
• Students just have to query through the bot which is used for
chatting. The user can query any college related activities through the
system. The user doesn’t have to personally go to the college for
enquiry. The system analyses the question and then answers to the
user.
• The system answers to the query as if it is answered by the person.
With the help of algorithms, the system answers the query asked by
the students. The system will also have an online notice board on
which any Text notices or PDF documents can be displayed.
• This will help the user to be updated with the important notices. Not
much time will be wasted by the user to search for the important
notices.
 2.INTRODUCTION TO
DOMAIN
Machine Learning
⚬ In the statistical context, Machine Learning is defined as an application
of artificial intelligence where available information is used through
algorithms to process or assist the processing of statistical data.
⚬ While Machine Learning involves concepts of automation, it requires
human guidance. Machine Learning involves a high level of
generalization in order to get a system that performs well on yet unseen
data instances.
⚬ Machine learning is a relatively new discipline within Computer Science
that provides a collection of data analysis techniques. Some of these
techniques are based on well established statistical methods (e.g. logistic
regression and principal component analysis) while many others are not.
⚬ Most statistical techniques follow the paradigm of determining a
particular probabilistic model that best describes observed data among a
class of related models.
⚬ Similarly, most machine learning techniques are designed to find models
that best fit data (i.e. they solve certain optimization problems), except
that these machine learning models are no longer restricted to
probabilistic ones.
 3.OBJECTIVE AND SCOPE

• To design a chatbot in efficient manner.

• Less time consumption.
• User friendly model.
• Should be applicable to all place of work.
 4.EXISTING SYSTEM

Direct Information Method:

⚬ In existing system the students has to get the information from the
college websites.

⚬ Sufficient informations will not be given for the students so they have
to contact the concerned person through phone call or meet directly.
4.1.EXISTING SYSTEM
DISADVANTAGES
• Problem with current scenario Traditionally, the chat bot system is not
known to people who are not more into the technology.
• Even if there exist a chat bot system, it is not much accurate in proving the
answer or solutions.
• Students need to manually visit to the college to get their queries answered
by the college help desk.
• This process consumes lot of time as well as money as the customer
needed to visit college if its miles away from home. Also, this process may
lead to communication gap between student and college.
5.PROPOSED SYSTEM
• The goal of the system is to help the students to stay updated with colleges to
improve their education activities.
• The main motive of the project is to reduce the work load on the college staff
and reduce the response time to a user’s query.
• The student when visits the website first registers him/herself and after which
he can visit the enquiries section for making queries to the AI Chatbot.
• The AI Chatbot has information in the form of pattern-template stored in the
database. Use of SQL is made for handling the database.
5.1.PROPOSED SYSTEM
ADVANTAGES
• Less time consumption.
• User friendly.
• Sufficient information's provided.
• Updates are possible at anytime.
6.SYSTEM REQUIREMENTS
HARDWARE REQUIREMENTS

• Processor : I3 Processor.
• Ram : 4GB
• Hard Disk : 500 G.B Hard Disk

SOFTWARE REQUIREMENTS
• Technology : Python
• Web Technologies : Html/CSS
• IDE :Jupiter Notebook
• Database : My SQL
7.ARCHITECTURE DIAGRAM

USER
8.UML DIAGRAM

LOGIN TEACHER

PARENT
DATABA LOGIN
SE
ADMI LOGIN
N LOGIN
STUDENT

LO
GI
N
ALUMINI
 9.MODULES

1. Training and Testing Subset

2. Applying algorithm
3. User Login and Complaint
4. Chat BOT Responding System:
5. Answer the Complaints
6. Predicting results
 9.1.MODULES DESCRIPTION
1.Training and Testing Subset: As the dataset is imbalanced, many
classifiers show bias for majority classes. The features of minority class are
treated as noise and are ignored. Hence it is proposed to select a sample dataset.

2. Applying algorithm: LSTM classification algorithms used to test the

sub-sample dataset.

3.User Login and Complaint: User registers himself/herself on Chat-

Bot application. Then submits his/her complaints and queries regarding the
college information’s.

4. Chat BOT Responding System:

a. NLP Processing and Sentiment Analysis for
Complaint: When user complaint is submitted to the system, NLP is
applied and sense of the complaint is detected. The sense of the words is found
using part of speech tagging and wordnet dictionary.

b. Search Questions in knowledge database: Once the

negation level of the question is detected, furthermore, the exact question in the
complaint is detected using WorldNet.
5. Answer the Complaints:
As described above whenever user submits a complaint, the negation
level and exact issue/question of the complaint are detected.
Then it is checked that is there such question registered in database. If the answer
is found then that answer is sent to that User.
If a particular question is not found in the database such questions are answered by
admin person. Once he answered the question the answer is sent to that user.
And that question along with answer is stored in database so that whenever such
questions will be asked so that they get answered directly from the database.
Due to this admin doesn’t need to answer same question manually anymore.

6. Predicting results: The test subset is applied on the trained model .

10.FORM
DESIGN
TESTING 1
TESTING 2
11.SAMPLE
OUTPUT
 12.CONCLUSION
• The main objectives of the project were to develop an algorithm that
will be used to identify answers related to user submitted questions.
• To develop a database were all the related data will be stored and to
develop a web interface. The web interface developed had two parts,
one for simple users and one for the administrator.
• A background research took place, which included an overview of
the conversation procedure and any relevant chat bots available.
• A database was developed, which stores information about
questions, answers, keywords, logs and feedback messages. A usable
system was designed, developed and deployed to the web server on
two occasions.
• An evaluation took place from data collected by potential students of
the University.
• Also after received feedback from the first deployment, extra
requirements were introduced and implemented.
13.FUTURE SCOPE
• In the future scope of this project, we can include voice based queries and
answers.
• The users will have to give voice input and the system will give the text
output and while giving it, it will give a voice output as well.
• By just adding text-to-speech and speech-to-text we can add the above
functionality to our project.
 14.REFERNCES
• Bayu Setiaji, Ferry Wahyu Wibowo, “AI Chatbot Using A Knowledge in
Database”, 2018 7th International Conference on Intelligent Systems,
Modelling and Simulation.
• C. Erdogan, H. Nusret Bulus, and B. Diri, “Analyzing The Performance
Differences Between Pattern Matching and Compressed Pattern Matching on
Texts,” Proc. IEEE of 2018 International Conference on Electronics,
Computer and Computation (ICECCO),2018, pp. 135-138,
doi:10.1109/ICECCO.2013.6718247.
• S. Ghose and J. J. Barua, “Toward The Implementation of A Topic Specific
Dialogue Based Natural Language AI Chatbot As An Undergraduate Advisor,”
Proc. IEEE of 2018 International Conference on Informatics, Electronics &
Vision (ICIEV), 2018, pp. 1-5,doi:10.1109/ICIEV.2013.6572650.
• Y. Bin, P. Cunlin, and L. Dan, “Chinese Text Feature Extraction Method
Based on Bigram,” Proc. IEEE of 2018 International Communications,
Circuits and Systems (ICCCAS), 2018, pp. 342- 346, doi:
10.1109/ICCCAS.2013.6765352.
• A. Augello, G. Pilato, A. Machi, and S. Gaglio, “An Approach to Enhance AI
Chatbot Semantic Power and Maintainability:Experinces Within The FRASI
Project,” Proc. of 2012 IEEE Sixth International Conference on Semantic
Computing, 2012, pp. 186-193.
THANK YOU