Artificial Intelligence Bot As Personal Assistant

ABSTRACT

An AI personal assistant is a piece of software that can perform tasks for a user based on verbal or written commands. This software can perform tasks such as providing online customer service, sales and marketing massages which would have been carried out by human assignment. This thesis presents a customer service chat application: online customer service application. Its purpose is to provide online chat with website visitors in real time, independent of the location. We examine the functional requirements of such an application. The requirements are: interactivity, enhancing customer relationships and satisfaction, good quality and fulfilling a need. There are different types of AI assistants such as Siri, Alexa, livezhat and Google Assistant, etc. but in this work we focusing on artificial intelligence assistant using chatbot.

The application is communicating with customers to provide notifications and enable information exchange. It was found to enhance customer relationships with its quality and interactivity. According to survey evaluation, the application was easy to use and appealing. Out of two customers who used the application during a test period, one used the application rather much. Other feedback from the evaluation provided us a chance to improve the application in the future.

The main aim of the work is to AI personal assistant to provide online customer service, sales and marketing messages [which would have been carried out by human beings] using chatbot. Chatbots are tiny programs that help simulate interactions with customers automatically based on a set of predefined conditions, triggers, and/or events.

ABBREVIATIONS

TABLE OF CONTENT

TITLE PAGE

APPROVAL PAGE

DEDICATION

ACKNOWLEDGEMENT

ABSTRACT.

TABLE OF CONTENT

CHAPTER ONE

INTRODUCTION

• BACKGROUND OF THE STUDY
• AIM OF THE STUDY
• OBJECTIVE OF THE STUDY
• SCOPE OF THE STUDY
• SIGNIFICANCE OF THE STUDY
• STATEMENT OF PROBLEM
• PURPOSE OF THE STUDY
• LIMITATION OF THE STUDY
• DEFINITION OF TERMS.

CHAPTER TWO

REVIEW OF RELATED LITERATURE

• CUSTOMER RELATIONSHIPS
• BENEFITS OF AUTOMATION CUSTOMER SERVICE, SALES AND MARKRTING MESSAGES
• OVERVIEW OF CHATBOT
• HISTORICAL BACKGROUND OF CHATBOT
• DEVELOPMENT OF CHATBOTS
• APPLICATION OF CHATBOTS
• TYPES OF CHATBOTS

CHAPTER THREE

METHODOLOGY

• CHAT BOT SOFTWARE APPLICATION
• DESIGN AND IMPLEMENTATION
• DESIGN PROCESS
• FINAL UI AND FUNCTIONALITY
• EVALUATION OF THE DESIGN
• EVALUATION

CHAPTER FOUR

RESULT ANALYSIS

4.1.     RESULT ANALYSIS

4.2      DISCUSSION

CHAPTER FIVE

CONCLUSION, FUTURE AND REFERENCES

• CONCLUSION
• SUMMARY
• FUTURE WORK
• REFERENCES

CHAPTER ONE

1.0                                              INTRODUCTION

Traditionally customer service people sit at their computers and answer to customers’ inquiries. For small company’s website, e.g., less than 10 employees, a website visitor may ask a question sporadically. In this scenario, it makes no sense to hire dedicated full-time customer service personnel to sit at a computer and wait for customers to pose a question. On the other hand, a mobile support application is ideal: when a notification on the mobile device is triggered, the support personnel may respond immediately and carry on to other work tasks when finished. Compared to email, for example, a live chat software handles the chats better, being synchronous, showing them individually in a list, and each chat can be closed after the customer’s needs are satisfied. For the customer (i.e., website visitor) it is far easier to use the chat box located directly on the bottom corner of the website than sending an email to support staff. All the basic functions such as listing chats, receiving visitor messages, sending message and getting visitor information can be easily implemented to the mobile application.

The fourth product, LiveChat, is the most closely related to this thesis and where the contributions of this thesis lie. LiveChat is a software that allows Customer Service Representatives (CSR) to chat in real time with their website visitors [7]. With the chat, CSR’s are able to select potential customers and help them in making a buying decision answer any questions they might have.

Before this thesis was made, Livechat was restricted to the browser, where customer service staff can answer to website visitors’ questions. The chat box, where website visitors ask their questions, is also restricted to the browser. To make CSR’s work more efficient, a mobile application is needed (Livechat Mobile app). This thesis’ goal is to reduce the drawbacks of a web-based only solution. The application implemented does all the basic functions that the browser version of Livechat does but adds one major addition into customer service experience: the aspect of mobility.

Another means of communicating with customers by providing service, sales and marketing messages to them is by using chatbot which is the latest technology for automated customer service software.

“Bots and chat make it easier for people to buy the way they want to, when they want to–and that should be the goal of any business.” – David Cancel, CEO of Drift

Chatbots are tiny programs that help simulate interactions with customers automatically based on a set of predefined conditions, triggers, and/or events.

There are several advantages to using chatbots:

1. They can be proactive or reactive.
2. Their responses are consistent every time.
3. They can respond to customers immediately.
4. They can help you collect important data and also learn from the data collected.
5. They can be used through a variety of different mediums like SMS, live chat, or even social media.

The concept of a chatbot itself is nothing new. In fact, they’ve been around since the 1960s.

However, applying chatbots to help businesses grow is only a recent phenomenon. Applying chatbots to business use cases is the result of democratized technology in recent years.

1.1                                           BACKGROUND OF THE STUDY

Automation means that system is controlled by computers, most usually some scripts to do the desired work. Automation robots at industry are handling many complex simultaneous tasks at rapid speed and very accurately. Most scripts of automated systems are doing one simple task very well and these scripts can be put to parallel or serial to work together. Main idea by using automated scripts is to reduce the need of human work during production and provide automated service for users.

During 20th and 21st centuries automation has been increasing in world economy but still technology is not able to automate all the desired tasks. Most commonly automation is used to increase quality of manufacturing process and do simple repeatable actions. Any system that is using automation is decreasing operational time and handling time. Operational time is period during which a system is working in a manner acceptable to its operator or user and handling time is a period needed to transport parts or materials to or from a work area. Also automation allows employees to concentrate more on other tasks such as development and maintenance of automation processes. (The Boston Globe. 2008-03-24)

1.2                                                     AIM OF THE STUDY

The main aim of the work is to provide an avenue where customer can visit company or organization website and get instant answer to their challenges or enquires without the intervention of the customer care.

1.3                                               OBJECTIVE OF THE STUDY

The objective of the study is to:

• Reach out to customers in real-time when they encounter an issue,
• Address more of your customer’s issues and concerns,
• Dramatically shorten your time to resolution,
• And create happier, more loyal customers who can’t help but evangelize your company’s support.
• To give an instant and automated support to help your customers

1.4                                                   SCOPE OF THE STUDY

Most companies can’t possibly give one-on-one attention to each customer. Some automation is helpful, if not vital, for customer satisfaction.

Automation strengths to enhance your customer’s support experience by encouraging and expediting communication with your company. There many softwares and means of communicating with customers, but in this work we are using chatbot

Chatbot will respond to your fans, automate your marketing and sales efforts and learn all the way to provide better and better results.

Chatbots work all day every day – starting conversations, asking valuable questions and delivering the most qualified leads right to you.

1.5                                           SIGNIFICANCE OF THE STUDY

• Deliver regular or promotional content, important news, special offers and collect your subscribers.
• Share / broadcast your content with scheduling: pics, GIFs, videos or PDF files with various targeting options, such as language.
• Reach out to your customers with different conversational content such as polls, cards and more.
• Automation can create a support experience that isn’t possible when our processes are constrained by human capability.
• Human support is (generally) passive or reactive — it relies on the customer taking the initiative to make the first contact or search through help documents.
• The advantage of automation — why it helps you provide better service— is it allows you to provide a degree of responsiveness that isn’t humanly possible.
• For instance, you can’t have someone monitoring all your site traffic or in-app activity for indicators of distress, but an automated system can “see” signs of trouble in a nearly unlimited amount of data and “react” in real-time.

1.6                                              STATEMENT OF PROBLEM

Automated customer service has a bad reputation. Perhaps it’s well-deserved. Most of us prefer to speak to a real person when we call support and we cringe when someone tries to pass off an automated email as if it were personally sent.

Automation and artificial intelligence can’t replace a real person manning a help desk, phone, or live chat. We are decades away from matching a human’s ability to perceive, judge, and react to complex situations in a caring, helpful way.

1.7                                  PURPOSE OF THE STUDY

• To Set up conversations for different events, such as new user onboarding.
• To define tasks to automate your sales and marketing process.
• Teach your bot to communicate with pre-defined content based on statements, keywords and other settings.
• To send the exact resource that walks the customer through tackling the specific problem they are dealing with.

1.9                                                              LIMITATIONS OF THE STUDY

The creation and implementation of chatbots is still a developing area, heavily related to artificial intelligence and machine learning, so the provided solutions, while possessing obvious advantages, have some important limitations in terms of functionalities and use cases. However this is changing over time.

The most common ones are listed below:

• As the database, used for output generation, is fixed and limited, chatbots can fail while dealing with an unsaved query.
• Chatbot’s efficiency highly depends on language processing and is limited because of irregularities, such as accents and mistakes that can create an important barrier for international and multi-cultural organisations
• Chatbots are unable to deal with multiple questions at the same time and so conversation opportunities are limited.
• As it happens usually with technology-led changes in existing services, some consumers, more often than not from the old generation, are uncomfortable with chatbots due to their limited understanding, making it obvious that their requests are being dealt machines.

1.8                                                  DEFINITION OF TERMS

Automated Customer Service: The process of using canned replies, email automation, and other techniques in order to scale the capacity of a customer service department to serve a business’ customer base.

Application programming interface (API) – A set of definitions, protocols and tools to build application software.

Artificial intelligence (AI) – AI is the creation of computer systems that can perform tasks that require human intelligence, such as speech recognition, understanding and translating language, and decision making. AI includes computer science, neuroscience, psychology and linguistics, which are all needed by a machine to duplicate a typical human response.

Bots (see Chatbots) – A short name for computer programs that interact intelligently with humans and the internet.

Broadcast – A message that is proactively sent to users, similar to a push message in a mobile app.

Channel – The medium for chatbot conversations. Channels include Your Website, Messenger, Slack, Skype, SMS, email and web chat windows.

Chat Logs – chat data of human bot conversions.

Chatbot – A chatbot is an intelligent computer program that interfaces among humans, computer systems, and the internet. The word is a contraction of chat and robot.

Cloud or cloud computing – Internet-connected computers that share computer processing resources and data with other computers on demand.

Context – Contextual data is information from the chatbot related to specific conversations and can have a relative importance.

Conversational UI – A user interface based on human speech or language.

Conversations – This is a decision tree or logic diagram of a scripted conversation. These conversations can be linear or they have branching logic with multiple answers to questions.

Deep Learning – Algorithms used in machine learning and artificial intelligence to gain insights.

Entity – An entity modifies an intent. For example, if a user types “show me yesterday’s financial news”, the entities are “yesterday” and “financial”. Entities are given a name, such as “dateTime” and “newsType”. Entities are sometimes referred to as slots.

Framework – A structure that provides building blocks and functionality to build a chatbot that also requires programming.

Human in the Loop – Chatbots learn by collecting and monitoring data from conversations. The AI system applies what it learns from each conversation. Human in the Loop is when a human has to monitor some of the AI responses to make sure the appropriate response is given.

Intent – An intent is the user’s intention to gather a specific piece of information, such as the daily weather forecast. The intent is usually a noun-verb word combination that tells the chatbot what the human wants it to do. For example, find an ATM, book an appointment, or order food.

Interaction – A verbal or written communication between a chatbot and a human.

Interface – A shared boundary where two or more parts of a computer system exchange information.

Machine Learning (ML) – Machine learning is the process where a computer learns from experience rather than from programming. The machine learns by gathering data and it can find insights from that data without being explicitly programmed.

Multiple intents – When a user makes a complex request to the chatbot and the chatbot has to process and prioritize two or more intents simultaneously.

Natural language processing (NLP) – Natural language processing is teaching a computer to understand language and the intent behind the language. NLP is based on artificial intelligence, computer science, and computer linguistics.

Natural language processing Engineer – a person that specializes in NLP, AI, ML and chatbots

Pilot – The development stage of a chatbot where it is deployed to small group of testers.

Rails, Guard Rails – When a user asks a question that stumps the chatbot or is beyond the scope of the chatbot, the conversation must be redirected to a human. This redirection is called a Rail or a Guard Rail.

Response – Any reply from a chatbot based on user input.

Structured data – Highly organized information that is searchable when put in a database.