How do we create a chatbot and a different integration platform using Dialogflow?

No matter how sophisticated or powerful our thinking machines become, there still will be two kinds of people: those who let the machines do their thinking for them, and those who tell the machines what to think about...!!!

What is conversational experience?

Conversational User Experience (CUX) is an experience composed of either chat or voice-based human-computer interaction that mimics human conversation.

Dialogflow can analyze multiple types of input from your customers, including text or audio inputs (like from a phone or voice recording). It can also respond to your customers in a couple of ways, either through text or with synthetic speech.

Synonyms:

Conversational interface,

Conversational UX,

Conversational app,

Voice bot,

Chatbot...!!!

What was the first chatbot?

ELIZA: It is considered to be the first chatbot in the history of Computer Science which was developed by Joseph Weizenbaum at the Massachusetts Institute of Technology (MIT). It was in 1994 that the term 'Chatterbot” was coined.

What are chatbots?

The chatbot is simply a chatting application in which the user/customer chats with an application/bot to get a solution for any specific task that the bot is designed for.

Two main types of chatbots:?

rule-based and AI chatbots: The latter has a much more complicated functionality and contextual awareness that require less training data and that can actually perform the task for the customer without any human assistance

Chatbots are based on Artificial Intelligence (AI) and Natural Language Processing (NLP). These bots are intelligent and can “learn” over time to respond as humans would to free-form user inputs.

Chatbots are designed for specific tasks i.e if the application is designed to order food, it can help with ordering food-related tasks. The more we train the application bot, the more it will understand the phrase given by the user and give the response more accurately. We will learn this as we go forward and create our first bot.

What are the different types of chatbots?

1. Simple chatbots: Simple chatbots have limited capabilities, and are usually called rule-based bots. They are task-specific.?

2. Smart chatbots: AI-enabled smart chatbots are designed to simulate near-human interactions with customers.?

3. Hybrid chatbots: They are a combination of simple and smart chatbots.

Chatbot as Dialogflow :

Pros:

1. Available 24*7

2. Automation of repetitive work

3. Personal assistance and customization

4. Faster Customer service

5. Lower Labor Costs

6. Push relevant content to end-users and test user engagement

7. No extra staffing during peak season

Cons:

1. Are not as intelligent as humans

2. Bad at improvisation

3. Limited responses could lead to frustration

4. Can’t interpret multiple questions asked at once

5. Not really that smart

There are several interfaces where we can connect our application bot like Messenger, Google Assistant, Slack, and much more. We can create our own custom interface as well. In this tutorial, we will cover the integration with Google Assistant.

Dialogflow:

Dialogflow is a natural language processing platform. For a chatbot, it is important to understand what the user is trying to say with as much variety as possible. For example, if the bot asks ‘what is your name?’, the user can answer it in several ways like "my name is John"/"John is my name"/" myself John"/"Name- John" etc.

To fulfill the given request, we only have to say the word "John" instead of factoring it in the entire sentence. This is where Dialogflow comes into play. It is made and maintained by Google.

We can pass an entire string to Dialogflow using REST APIs which in turn will return meaningful text so we can use it to interact with the application at a later time.

What's new in Dialogflow CX?

September 01, 2020. Beta launch of Dialogflow CX. Dialogflow CX provides a new way of designing agents, taking a state machine approach to agent design. This gives you clear and explicit control over a conversation, a better end-user experience, and a better development workflow.

The Dialogflow Essentials (ES) Edition is a pay-as-you-go edition that provides the standard ES agent type. The Essentials Edition offers production-ready quotas and support from Google Cloud support.

The Dialogflow Customer Experience (CX) Edition is a pay-as-you-go edition that provides the advanced CX agent type

72 % of people who own a voice-activated speaker say their devices are often used as part?of their daily routines.

60% of consumers want easier access to self-serve solutions for customer service.

91% of survey respondents would rather use a knowledge base if it were available and tailored to their needs.

There is a diverse set of use cases:

1. Connecting businesses to their customers:

Customer service, Commerce

2. Controlling IoT devices:

Home entertainment, Auto

3. Connecting businesses to their employees:

Organizational Knowledge, Surfacing data and insights.

What are the uses and benefits of Dialogflow?

1. Is user-friendly with an integrated code editor and serverless application structure.

2. Offers integrations in over 20 different languages, with differentiation in the types of services offered for each.

3.It is scalable in nature.

4. Software development kits (SDK) are offered for multiple different devices like cars, mobile devices, speakers, wearables, and other smart devices.

5. Contains Google features like machine learning and speech-to-text translation.

6. Multiple AI assistants, including Google Assistant, Alexa Cortana, and Facebook Messenger actions can be built.

Building conversational chatbot using AI?

Conversational AI is a type of artificial intelligence that enables consumers to interact with computer applications the way they would with other humans. Conversational AI has primarily taken the form of advanced chatbots, or AI chatbots that contrast with conventional chatbots.

Types of chatbots?

1. Dialogflow

2. Flow XO

3.ManyChat

4. Botsify

5. Chatfuel

6.LivePerson

7. Bold360

8. Octane AI?

and many more...!!!

How does the assistant work?

Task 1: search on google Dialogflow console.

1>In the GCP Console, on the Navigation menu (), click APIs & Services.

2>Click Enable APIs and Services.

3>Search for Dialogflow, and then select Dialogflow API.

4>Click Enable (if not already enabled).

Task 2: Getting started with Dialogflow

Dialogflow requires a Google account to sign in. You will use the qwiklabs account to sign in to complete this lab.

Start with the Dialogflow console at https://console.dialogflow.com

1. Click on Google to sign in.?

2. Allow Dialogflow to access your Google account.

Task 3: Create your first Dialogflow agent

To create a Dialogflow agent:

1. Click Create Agent in the left menu.

Alternatively, you can also click on the “Create Agent” button on the right of the screen.

1. Enter “pizza bot” for your agent’s name, English as the default language, and set the default time zone to your time zone. Under Google Project, ensure you are using the same project that you see in your GCP console (use the drop-down list to select). Then click the Create button.

The need for NLP/AI:

It involves the processing and understanding of human language by machines, and is a subfield of artificial intelligence (AI). Using NLP, machines are able to understand human language more accurately and efficiently.

Various repetitive tasks can be automated to achieve this. There are several applications of natural language processing, including ticket classification, machine translation, spell checks, and summarization.

With the development of NLP technology, today, it is able to perform sentiment analysis for human language. Conversing smartly is one of these great tools. One of the most widely used NLP applications by businesses is to detect brand sentiment on the internet (search engine reviews, social media reviews) by detecting emotions in the text.

By enabling brands to identify customer issues on the internet, businesses are in a better position to respond and take necessary rectifying actions for positive customer satisfaction.

Why Is Natural Language Processing Important?

1. Immediate Customer Support

2. Save time and money

3. Boost your conversion rate

Few terms to understand in Dialogflow:

Intents: In Dialogflow, intents are created to understand what the user is trying to say by providing multiple training phrases which may be written by the user. When an end-user writes a phrase, Dialogflow uses its NLP algorithm to find the best possible intent from a list of intents and returns meaningful data derived from it.

The ‘intent’ of a user is simply the intent of the user i.e., what the user wants. Let’s say the user says:

I would like to book a flight from Chennai to Bangalore.

The intent of the user here could be: book_flight

Entities: Entities are used to extract names, places, or things from a user's sentence. For example, we shall create an entity named states inside which we will store the list of states needed in the application. Now, when a user types something like, "I live in state XYZ", it is passed over to Dialogflow. In case the XYZ state is found in the state entity, Dialogflow will understand and return XYZ to the application, which the developer can use later on as needed.

Entities are data buckets used in conversations. They are the slots that you would like to send to the back-end and process later on. Entities consist of the information we would like to capture from the user.

I would like to book a flight from Chennai to Bangalore.

Here, the entities could be as follows:

- from_city: Chennai

- to_city: Bangalore

Dialogflow ES vs Dialogflow CX :

Using contexts, Dialogflow ES supported a flat structure of intents and implicit controls. For large, complex conversational agents, this approach did not scale well.

Conversation flow controls are provided in a more explicit and structured manner in Dialogflow CX. Conversation flows can be designed using a graphical structure in CX.

How Dialogflow works?

Training Data+ Proprietary Language Models by Dialogflow unique trained model?user query response.

Dialogflow benefits for users:

1. Build faster:

1. start training with only a few examples.

2.40+ pre-builts agents and "smart talk" features.

Prebuilt agents help you get a head start:

1. Food delivery

2. Hostel Booking

3. Language settings

4. Local services

5. Music

6. Maps

7. Radio

8. Navigation etc.

Integrations:

Actions on Google:

1. Google Home, Pixel...and more to come

External integrations:

1. Slack, Facebook Messenger,

2.Twitter,Twilio,Skype,Tropo,

3.Telegram,Kik,LINE,Cisco,Spark,

4. Alexa, Cortana.

Integrate seamlessly between surfaces with the actions SDK:

1. Google Home

2. Google Assistant

3. Dialogflow

.

.

.

Hope you like it...

Thank you so much...