Introducing DialogFlow

Bleak chat box for your Web application or website is all the rage nowadays in this course. We'll see how to use one of the cutting edge platforms in chequebooks. We'll see how we can use Dialogflow. This course has very little utility. It's completely hands on, which is why it's called hands on chat bots the Google Dialogflow. In order to keep learning engaging at the beginning of every video bill, ask you a question at the end of this video, you should be able to confidently answer what the two categories of chat watch are and how they're different. If you can't, it might help you to go back and revise the video. Any other it would have been impossible to believe that any developer of a website or a web app can build a chat bot, which we conducted intelligent conversation in a very normal manner with a human being. But with the advances made in machine learning over the recent years and the development of cutting edge platforms which allow you to harness this machine learning have made possible these intelligent bots, which can conduct intelligent conversations mimicking a human being. Advances need in machine learning. Allow speech recognition, making it possible to understand words in different languages and in different accents. Machine learning also enables natural language processing, enabling a machine to understand what exactly a human being said. But really, this isn't enough. If you had to write your own machine learning algorithm in order to build your chat bot didn't really track bots would not be as accessible as they are today. The development of these platforms, which abstract the way the complex technologies underlying bots are, what make building these bots simple. And one such platform is Google's Dialogflow. Google's Dialogflow was formerly known as episode not easy. In fact, it changed very recently, and you find that several of the screenshots in this course still reference API. This is an amazing platform, with machine learning algorithms powered by Google's technologies and an easy, intuitive, very simple UI, allowing you to build sophisticated track bots. If you're taking this course, you probably already understand why chat bots are needed or where they might be used. We'll cover that anyway, briefly. But first, we'll start off by understanding what exactly a chat bot. If it's basically a computer program which is capable of conducting an intelligent conversation about a set to be intelligent, it can simulate human behavior and past what is called the building best. The plodding past was developed by the scientist Alan Turing back in 1950, and it basically says that if you can interact or have a conversation with a bot and be unable to distinguish between the bots responses and the responses of an actual human being, then that bot has passed the Turing test. Now, this seems like a big ask. Back in 1950, but all the chatbot technologies that are available nowadays will help you build bots that pass the building test. Let's see some of the simple use cases where you might need a chat bot. Let's say you're run a very complex site. It might be an e-commerce site, a matrimonial site, a hookup site, and you have some trouble navigating it. If you spend enough time on the site and you seem to be aimlessly browsing, you might have noticed that the chat window often pops up and asks you to just ask questions. Ask him questions about what you are looking for. What is it that you hope to achieve and so on? This chat is usually powered by a book. There is no real human behind this chat window. Using the chat window is an easy, natural and conversational way for you to achieve your objective on that website or web application. Chat bots can also be used to debug or troubleshoot issues. Let's say you've placed an order for a pair of shoes from your favourite e-commerce site, but the order hasn't arrived yet and you haven't received status updates before chat bots became ubiquitous. What you typically do is to call up the customer support agent on the phone and see that you're looking to track down your order. This proves to be very expensive for the e-commerce site because having these thousands of customer support agents and having them on the phone is an expensive setup. If you are in charge of building and running this e-commerce site, you might figure that a good way to cut down on costs would be encourage your customer to use a chat window for this query rather than calling up a customer support agent directly. This chat can be powered by a bot which is capable of asking the right questions in a friendly manner and directing the user to the right place. Tracking down the status of his or her order, and in general, being helpful. And really, there are many, many examples of how bots can be useful. These are just a few business use cases, but you can have chat bot, which help you track down the weather the weather bot. It can help you with your groceries, give you the latest news, help you with your personal finances, and also help you shop. What we spoke about so far was about Chatterbox in general. Now let's talk about Dialogflow specifically, Dialogflow is Google's offering for you to configure and chat, watch very, very easily and be able to harness Google's underlying machine learning technologies in order to have Natural Intelligent Board, which passes the Turing test. No chat bots can be divided in two broad categories. The first of these is the rule based chat bot. You can think of rule based chat bots as belonging to the machine learning era. These boards would basically look for standard patterns in the user requests like or did the user mention all those tactics? Maybe I should look through all of the user's previous orders. At the very basic level, you can think of a rule based chat bot as working with a bunch of pre-programmed rules, a bunch of if then else statements. If you find it easier to imagine it that way, it can't learn or understand new concepts. These books tend to be static and can change only when they are pre-programmed. Rule based chatbots are a thing of the past. What we work on nowadays are artificial intelligence based chat bot. These are intelligent. They understand what the user to seeing while natural language processing. They also learn from previous conversations that users have had such that a chat bot, which has been running for a long time, say for two or three months, will be more intelligent than the bot, which existed at the very beginning. These bots are dynamic, and because they constantly learn from human conversations, they get better over time. Google's Dialogflow is an artificial intelligence based chat bot. There are a variety of modes in which Dialogflow operates. We see that in a little bit, but it's primarily driven by machine learning algorithms to learn from the data. Let's take a little walk through time and understand how dialogue looking to be back in 2011. A company named Speak to It developed an intelligent personal assistant for mobile phones. This personal assistant worked on Windows Android as well as iPhone devices. Now, this personal assistant was popular and based on the cutting edge machine learning technologies and in 2014, speak to. It made it possible for third party developers who use these technologies as well. They released an SDK or basically the API dot EIA, I believe, to third party developers. This allowed anyone to plug in to the natural language processing and other modules to build conversational apps. Because its technology was cool, Google in 2016 realized that speak to it could be used to power Google Assistant. You might be familiar with this assistant on your phone, which is enabled when you say, OK, Google. This is if you have an Android phone, the API SDK. The libraries are still available for third party developers to use. Now this is how it continued until very recently, that is October 2017. This is when API it was renamed to Dialogflow. This was purely a name change. None of the functionality that API today offered was changed. In fact, new functionality is being added at a very fast clip. Now, this name change turned out to be a bit of a portal for us because it happened right when we were recording the demos for this course. So you'll find within the demos, the UI says Episode III. But when you log in at this date, the UI will see Dialogflow. Don't worry, it's the exact same setup. A few things might have changed because Google is constantly adding new features every 15 days or so, but the underlying code remains the theme. Dialogflow is essentially API air. With the new name. So what will Dialogflow help us with? It'll allow us to build natural rich conversations using a very intuitive UI. The UI, I must say, is amazing. The UI for Dialogflow is so simple that you just need to use it once before you've mastered it. I've also used Amazon's Alexa UI, and I must say that Dialogflow is generations ahead. We mentioned earlier that Dialogflow is an artificial intelligence based a lot, which means it uses machine learning to understand what does it and the users are seeing it figures out the intent of the user conversation by using natural language and other machine learning techniques. What sets Dialogflow aside from other chat bot platforms that might exist is that every machine learning model that it builds for an agent that you configure is unique to that individual user's bot. That machine learning model learns from conversations that your users of your website or app have with the bot, resulting in a bot that's tailored for your unique purpose. What are the other capabilities that Dialogflow possesses? It supports 40+ languages, including French, German, Spanish, etc. You can have the very same board set up to understand multiple languages if you have users from different countries. You can use 16 different programming languages in order to configure the bot, including Python, C, Sharp Java, JavaScript, all the common ones. Dialogflow offers the same ethics that Episode III did, which allow you to be bought for your own application, whether it's a mobile application on its website, Dialogflow also offers SD cards, which work with variables, so it's Internet of Things enabled. Or if you want to build a jackpot app, which integrates with an existing messaging platform like Facebook, Viber, Twilio, Cortana, Alexa or Slack, there are one click integrations available with all of these platforms. You'll see how easy it is to setup what's the very end of this course? And this is a good time to revisit this question. The two broad categories of Jackpot are Rule-Based chat bots and artificial intelligence based attack bots. Rule based chatbot are all in that you have two pre-programmed rules, which they understand the look for specific words or patterns within the user expression and then try to give their responses. They are static and do not change over time. They don't learn from user conversations. Artificial intelligence based chatbot to use machine learning and natural language processing in order to understand what the user said. They are more intelligent. They are dynamic. The longer you have the chat bot introduction, the more intelligent it will get. The Dialogflow platform helps you build a AI based checkbox.