ESOFT METRO CAMPUS

ARTIFICIAL INTELLIGENCE
COURSEWORK 2

ICC Cricket Tournament Chatbot

Team Members

1.Rajapaksha Kumaraunnehelage Hasitha Irshika Alponsu -

22086593

2.Dikhena Vidanalage Chathuranga Lankathilaka - 22086551

3. Yumal Kasun Jayamina Liyanapathirana - 22086483

4. Nanayakkara Nagahawaththage Hiruni Nimeshika - 22086559

Date Submitted: 25th May, 2023

CU6051ES Artificial intelligence - COURSEWORK 2 1

ESOFT METRO CAMPUS

Acknowledgment

We would like to express our gratitude and thanks to ESOFT Metro Campus for providing us
guidance to complete this project.
A special thanks must be, made to our Lecturer Ms. Umaya Balagalla for her assistance and
guidance.
Finally, we would like to thank our colleagues and all those who supported us in various
ways to complete this project successfully.

Thank you!

CU6051ES Artificial intelligence - COURSEWORK 2 2

ESOFT METRO CAMPUS

CU6051ES Artificial intelligence - COURSEWORK 2 3

ESOFT METRO CAMPUS
Introduction
At its most basic level, a chatbot is a computer program that simulates and processes human
conversation (written or spoken), allowing people to interact with a digital device as if they
were talking to a real person. Despite the lack of human interaction, these robots can save
money, reduce the workload of customer service agents, provide quick responses and more.
Chatbot applications can increase customer loyalty by streamlining communication between
people and tools. At the same time, they offer new ways to increase customer loyalty.

Problem Description

Aim
What is a Chatbot?
A chatbot can be defined as an AI-based computer program that imitates human conversation.
They are also called digital assistants that understand human capabilities. Bots interpret user
intent, process their questions, and provide quick and relevant answers. The bot can
communicate with both voice and text and can be used on websites, apps and messaging
channels such as Facebook Messenger, Twitter or WhatsApp.
Chatbots are typically used to perform specific tasks or provide information based on user
requests. They use natural language processing (NLP) and machine learning techniques to
understand and interpret user input, so they can generate relevant and context-appropriate
responses.

CU6051ES Artificial intelligence - COURSEWORK 2 1

ESOFT METRO CAMPUS
Types of Chatbots
Rule-based chatbots
Also called decision tree bots, these chatbots work based on predefined rules and patterns.
They follow a predetermined set of instructions to understand user input and generate
appropriate responses. Rule-based chatbots tend to be less flexible and require extensive
programming to handle different user requests.

AI-powered chatbots
Conversational chatbots combine the power of machine learning and NLP to understand the
context and purpose of a question before formulating an answer. They are guided by chatbot
scripts and generate their own answers to more complex questions using natural language
responses. The more you use and train these robots, the more they learn and work better with
users.
(Author’s BioSnigdha PatelSnigdha Patel is a customer experience researcher (2023) )
After analyzing various types of chatbots, we decided to develop an AI based chatbot to get
detailed information about ICC cricket tournament.
Advantages of chatbots
• High-speed resolution of queries
• Reduced operational costs
• Reduced human error
• 24/7 multi-user support
• Automation of certain tasks
Chatbot testing : A beginner’s guide (2022)
2.2 Research and Challenges Faced
Artificial Intelligence (AI), Natural Language Processing (NLP) and Machine Learning (ML)
are the main AI-based chatbot technologies. In addition to them, we need other technologies
for data storage and interaction with users.

CU6051ES Artificial intelligence - COURSEWORK 2 2

ESOFT METRO CAMPUS
Tool and techniques of create chatbot
Layer Analyzed Selected Justification for Selection
Technologies
Presentation Web application, Web Team members are capable of front-
Layer Messenger, application end development. Therefore, we
WhatsApp, Slack. decided to create a special website for
chatbot integration.

Bot Layer Microsoft Bot RASA Initially, we looked at the Microsoft

Framework, Bot Framework and Google
Dialogflow, IBM Dialogflow as frameworks for bot
Watson, Botkit, development. After serious obstacles,
RASA, ChatterBot we decided to adopt RASA. Rasa is a
popular open-source platform for
building AI-powered chatbots. These
are powerful NLU components,
flexible dialog systems, machine
learning model integration, etc.

Data Layer Oracle Database, Microsoft The entire team has previous
MySQL Database, SQL Server experience with Microsoft SQL
MongoDB, MS Server. In addition, Microsoft SQL
Access, Microsoft Server is a powerful and feature-rich
SQL Server RDBMS. It provides a structured and
organized way to store data, process
large data volumes and large
transaction loads, simple tools

A, H. (2022)
Artificial Intelligence (AI) Traits
The chatbot developed for the ICC Cricket Tournament includes the following Artificial
Intelligence (AI) features.

Cricket Chatbot
This intelligent virtual assistant has been designed to fulfill all your queries about cricket
world cup tournaments. If you are interested in searching for history of cricket world cup
tournaments, our chatbot is here to provide you with all the required information

When you ask a question, it will quickly retrieve relevant data, including tournament
statistics, match results, player records, team performances and more. Furthermore, the

CU6051ES Artificial intelligence - COURSEWORK 2 3

ESOFT METRO CAMPUS
chatbot's interface ensures a seamless user experience, helping cricket fans engage in
interactive conversations and easily explore the history of World Cup cricket.

P.E.A.S
PEAS is a representation system for AI agents that facilitates performance measurement with
respect to environment, sensors, and actuators. To design an agent, we need to know its
working environment. The PEAS system helps to specify the work environment. PEAS is an
acronym for Performance, Environment, Actuators and Sensors. Identifying PEAS helps in
writing optimal algorithms for AI

1. Performance Measure: Performance measure is the unit to define the success of an

agent. Performance varies with agents based on their different precepts.
2. Environment: Environment is the surrounding of an agent at every instant. It keeps
changing with time if the agent is set in motion. There are 5 major types of
environments:
o Fully Observable & Partially Observable
o Episodic & Sequential
o Static & Dynamic
o Discrete & Continuous
o Deterministic & Stochastic
3. Actuator: An actuator is a part of the agent that delivers the output of action to the
environment.
4. Sensor: Sensors are the receptive parts of an agent that takes in the input for the
agent.
Pandey, N. (2022)

PEAS identified for Cricket Chatbot

CU6051ES Artificial intelligence - COURSEWORK 2 4

ESOFT METRO CAMPUS
Performance Speed, Accuracy, Efficiency

Environment Multi platform accessibility, Device compatibility

Actuators Availability of UI components such as buttons

Sensors Natural Language Processing,

Database Diagram

CU6051ES Artificial intelligence - COURSEWORK 2 5

ESOFT METRO CAMPUS
Decision Tree for CRICKGPT

State Transition Diagram for CRICKGPT

CU6051ES Artificial intelligence - COURSEWORK 2 1

ESOFT METRO CAMPUS
CRICKGPT
Tools
• VS Code
• Rasa
• Python
• Ms SQL Server -2016

Interface

CU6051ES Artificial intelligence - COURSEWORK 2 2

ESOFT METRO CAMPUS
Natural Language Understanding (NLU)
Code

CU6051ES Artificial intelligence - COURSEWORK 2 3

ESOFT METRO CAMPUS

CU6051ES Artificial intelligence - COURSEWORK 2 4

ESOFT METRO CAMPUS

CU6051ES Artificial intelligence - COURSEWORK 2 5

ESOFT METRO CAMPUS

CU6051ES Artificial intelligence - COURSEWORK 2 6

ESOFT METRO CAMPUS

CU6051ES Artificial intelligence - COURSEWORK 2 7

ESOFT METRO CAMPUS

CU6051ES Artificial intelligence - COURSEWORK 2 8

ESOFT METRO CAMPUS

CU6051ES Artificial intelligence - COURSEWORK 2 9

ESOFT METRO CAMPUS
Action

Database

CU6051ES Artificial intelligence - COURSEWORK 2 10

ESOFT METRO CAMPUS
Domain

CU6051ES Artificial intelligence - COURSEWORK 2 11

ESOFT METRO CAMPUS

CU6051ES Artificial intelligence - COURSEWORK 2 12

ESOFT METRO CAMPUS

Functions

CU6051ES Artificial intelligence - COURSEWORK 2 13

ESOFT METRO CAMPUS
Rules

CU6051ES Artificial intelligence - COURSEWORK 2 14

ESOFT METRO CAMPUS

Stories

CU6051ES Artificial intelligence - COURSEWORK 2 15

ESOFT METRO CAMPUS

CU6051ES Artificial intelligence - COURSEWORK 2 16

ESOFT METRO CAMPUS

CU6051ES Artificial intelligence - COURSEWORK 2 17

ESOFT METRO CAMPUS
Testing

Test Case ID 1

Date 24/05/2023

Tester Dikhena Vidanalage Chathuranga Lankathilaka

Description Check Bot catch the Format

Pre-Conditions

Test Steps Ask a question on Cricket world cup tournament history

Expected Result Display the answer

Actual Result As Expected

Status Pass

Test Case ID 2

Date 24/05/2023

Tester Dikhena Vidanalage Chathuranga Lankathilaka

Description Check the bot catch the Tournament

Pre-Conditions

Test Steps Ask a question on Cricket world cup tournament history

Expected Result Display the answer

Actual Result As Expected

Status Pass

CU6051ES Artificial intelligence - COURSEWORK 2 18

ESOFT METRO CAMPUS
Test Case ID 3

Date 24/05/2023

Tester Yumal Kasun Jayamina Liyanapathirana

Description Check the bot save the year and tournament

Pre-Conditions

Test Steps Ask a question on Cricket world cup tournament history

Expected Result Display the answer

Actual Result As Expected

Status Pass

Test Case ID 4

Date 24/05/2023

Tester Yumal Kasun Jayamina Liyanapathirana

Description Check the bot answers to the correct tournament details

Pre-Conditions

Test Steps Ask a question on Cricket world cup tournament history

Expected Result Display the answer

Actual Result As Expected

Status Pass

CU6051ES Artificial intelligence - COURSEWORK 2 19

ESOFT METRO CAMPUS
Test Case ID 5

Date 24/05/2023

Tester

Description Check the bot reset the slots

Pre-Conditions Rajapaksha Kumaraunnehelage Hasitha Irshika Alponsu

Test Steps Ask a question on Cricket world cup tournament history

Expected Result Display the answer

Actual Result As Expected

Status Pass

Test Case ID 6

Date 24/05/2023

Tester Rajapaksha Kumaraunnehelage Hasitha Irshika Alponsu

Description Check the bot go back to the year section

Pre-Conditions

Test Steps Ask a question on Cricket world cup tournament history

Expected Result Display the answer

Actual Result As Expected

Status Pass

CU6051ES Artificial intelligence - COURSEWORK 2 20

ESOFT METRO CAMPUS
Test Case ID 7

Date 24/05/2023

Tester Nanayakkara Nagahawaththage Hiruni Nimeshika

Description Check the bot go back to the format type section

Pre-Conditions

Test Steps Ask a question on Cricket world cup tournament history

Expected Result Display the answer

Actual Result As Expected

Status Pass

Test Case ID 8

Date 24/05/2023

Tester Nanayakkara Nagahawaththage Hiruni Nimeshika

Description check the bot follow fallback classifier

Pre-Conditions

Test Steps Ask a question on Cricket world cup tournament history

Expected Result Display the answer

Actual Result As Expected

Status Pass

CU6051ES Artificial intelligence - COURSEWORK 2 21

ESOFT METRO CAMPUS

Reference
• What is chatbot? why are chatbots important?, REVE Chat. Available at:
https://www.revechat.com/blog/what-is-a-chatbot/ (Accessed: 24 May 2023).
• BrowserStack. Available at: https://www.browserstack.com/guide/what-is-chatbot-
testing (Accessed: 25 May 2023).
• Which are the best tools used for chatbot development, Perfomatix. Available at:
https://www.perfomatix.com/best-tools-for-chatbot-development/ (Accessed: 24 May
2023).
• Simplifying AI models with the peas representation system, Analytics Vidhya.
Available at: https://www.analyticsvidhya.com/blog/2022/08/simplifying-ai-models-
with-the-peas-representation-system/ (Accessed: 25 May 2023).

CU6051ES Artificial intelligence - COURSEWORK 2 22