AIML Basic College Enquiry Chat-bot

 

Hello Technotizers, this article is focusing on providing some information about a Machine Learning based project which is AIML Basic College Enquiry Chat-bot. This project will help you begin your career with Machine Learning by giving you certain insights about creating and training a chat-bot. 

Note: This project is only for education purpose and does not aim to promote any institution whatsoever.

1.    Introduction

 

This project is focusing on creating a simple chat-bot to be used by students to get information about the college without visiting the college website or actual college. A chat-bot is a program which can do real conversations with textual and/or auditory methods. Using Artificial Intelligence (AI), chat-bots can simulate human conversations. There are two categories of chat-bots. One category is command based chat-bots where chat-bots 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 chat-bots 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 (NLP). Making a AI based chat-bot s a tedious job and is difficult to understand the process as compared to a databank based chat-bot.Our project develops a databank based chat-bot as a part of learning to create basic chat-bots. It focuses on giving specific information about the college.  Figure 1: How a Chat-bot Works

Figure 1 shows how a chat-bot works. Whenever a user asks any query, the bot will first analyze the request, then identifies intents and entities, builds a response and sends it back to the user. Now, intents mean intention of the query and entity means details of that query. For example, if a student wants to know the fees of a course then the intent will be fees and entity will be name of the course in this case.

2.    Objectives:

·  With the help of Chat-Bot a student need not have to be physically present in college office for the enquiry and thus gaps the bridge between administration and the students.

· Helping students to get basic information about the college.

·  Creating an easy to use chat-bot for both staff and students which requires user to enter any option provided by the chat-bot.

· Students opting for admission in the college can have quick information about the college using this chat-bot.

3.    Limitations of existing system:

·         Time consuming and hectic

·         Needs personal attendance

·         Isn’t available 24/7

 

The existing system is not only tedious but also makes a gap between administration and students. Surfing the website for small information can be irritating sometimes. It is rather better to just enter your query and get information on your fingertip. Now-a - days there are many changes that occurred in the Education system with help of advanced technological improvements. Everything is happening over the internet without any difficulty. In previous days for submitting a small application we had to visit that place, but as the days are passing away it’s completely changing. Collecting the applications manually will be hectic procedure and it also needs a lot of manpower. For reducing that manpower and such difficulties many devices or systems were emerged day by day. One of them is a chat-bot which serves as an efficient communication tool between system and users. Chat-bot bridges the gap between traditional enquiry means and users that are particular about time.

 

4.    Architecture/ Framework

 

System Architecture:

 

Figure 2: System Architecture

According to the architectural diagram of College Enquiry Chat-Bot System, there are 6 modules which are explained as follows accordingly:

 

1. Data (AIML Files) – These are the main data files which are programmed in AIML language.

2.    Manage – In this module the admin performs the various tasks to fetch into the data various college information requirements like placement sheet, department information, timetable, etc. All this fetched information is then retrieved as a response to the user query accordingly. Admin only has the authority to manage data details.

3.    User – This module represents user entering into the system.

4.  Chat – In this, User types the query and the bot replies to the user query accordingly. Actual Chatting occurs in this phase only.

5.  Upload – In this section admin uploads the common/ general information like, faculty information, fee structures, event and seminar notices, etc. which user may query out during chatting phase. Information that is not available while chatting is uploaded.

6.  Exit – This is the phase where user after finishing his work closes the system.

5.    Algorithm and process      design:

Algorithm

  Step 1: START: IMPORT MODULES AND CREATE KERNEL OBJECT

Step 2: IF: BRAIN FILE EXISTS IN OS PATH

Load the brain file.

ELSE:

Learn files and save brain file.

Step 3: GET TEMPLATE FILE

Step 4: GET REQUEST FROM USER AND STORE IN THE VARIABLE QUERY.

IF: RESPONSE IS AVAILABLE IN BRAIN FILE

PRINT response

 ELSE:

PRINT Alternative statement

Step 5: STOP

Process Design

Figure 3: Process Design

1.      User adds a query to the chat-bot through the interface.

2.      The main python program extracts the data from the brain file.

3.      The system checks for availability of response in the data.

4. If response for the query is available it is extracted and passed on to the chat-bot interface with prints the response for the user.

5.      If response is not available then user is asked to visit the website and information is uploaded in the data by the admin.

6.      Brain file learns information from various AIML files that store information like fees, faculty, academics, infrastructure, etc.

Figure 4: Use case diagram

The above diagram shows the functions of the user and the admin. The user can only chat with the chat-bot, whereas the admin can add information, view information, update information and delete information.

6.    Details of hardware &  software

 HARDWARE REQUIREMENTS

·         Processor: Intel(R) Core(TM)i3-6100U CPU @2.30Ghz 2.30Ghz Installed.

·         RAM: 4.00GB.

·         System Type: 64-bit operating system,x64-based processor.

 

 SOFTWARE REQUIREMENTS

·         Python 3.8

·         AIML 1.0

·         HTML

·         Any browser

7.    Experiment and Results

 

1.     Running the program

 

·         The main python program runs on the command prompt.

·  If brain file is not present, the program loads all the files and creates the brain file.

·         This generates an address which indicates the running address of the chat-bot.

 

2.    Getting the interface

 

 

·         When the generated address is opened in a browser, we come to the man interface of the chat-bot.

·         It is designed for an ease of communication.

·         The user is given a menu to choose from.

3.    Implementing the chat-bot

 

§  Here when we enter option FEES from the main menu we get a detailed list that gives us the class options.

§  Same types of lists are available for every option entered by the user.

 

·         Next, FEES SE is entered and detailed information about the fees category wise is obtained. Link for the fee structure is also provided.

4.    Trying incorrect input

Here an incorrect input is given to the bot. For this the bot prints, “Information not found. Please check the website: https://phcet.ac.in/".

Hence, the chat-bot runs properly and gives result to every input.

8.    Conclusion and  future work

To conclude, College Enquiry Chat-bot is helpful in guiding students with correct and most up to date sources of information. We can conclude from the above situation and usage is that greater the data and more the models and use cases, the better is the reaction produced for the user.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 the college office. It improves efficiency by taking over tasks for which humans are not essential.

 

To improve the current functionalities of College Enquiry Chat-bot, in the future, the scope of the chat-bot 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

1)  Speech recognition feature through which students can ask their queries verbally and get the answers from the bot

2)  Integration with multiple channels such as phone call, SMS, and various social media platforms like Skype, Facebook and Twitter

3)  Handling context aware and interactive queries in which bot will be aware of the context of an ongoing conversation with a student

4)  Integration with services such as password reset and course enrollment

5)  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

• For source code and detailed information of the project visit AIML-Basic-College-Enquiry-Chatbot

With this we come to an end of this article. Hope it was helpful. Do provide your feedback and ideas through comments, it would be highly appreciated. See you soon!

Keep coding and exploring new techs!!