<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Dilane3 on Medium]]></title>
        <description><![CDATA[Stories by Dilane3 on Medium]]></description>
        <link>https://medium.com/@DilaneKombou?source=rss-ea80385386fe------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/0*EgMJAT4yu07dicpI.jpg</url>
            <title>Stories by Dilane3 on Medium</title>
            <link>https://medium.com/@DilaneKombou?source=rss-ea80385386fe------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Fri, 20 Nov 2026 11:19:04 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@DilaneKombou/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Understand how a single Artificial Neural works]]></title>
            <link>https://medium.com/@DilaneKombou/understand-how-a-single-artificial-neural-works-94dc4046b42c?source=rss-ea80385386fe------2</link>
            <guid isPermaLink="false">https://medium.com/p/94dc4046b42c</guid>
            <category><![CDATA[artificial-neural-network]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[neural-networks]]></category>
            <category><![CDATA[deep-learning]]></category>
            <dc:creator><![CDATA[Dilane3]]></dc:creator>
            <pubDate>Tue, 31 Aug 2021 12:07:55 GMT</pubDate>
            <atom:updated>2021-08-31T12:07:55.116Z</atom:updated>
            <content:encoded><![CDATA[<p>An Artificial Neural Network (ANN) is a computer system that works like a human’s neural brain. This concept is used in the Deep Learning, a subsection of Machine learning, for resolving complex problem of classification or multi class classification and other kind of problem. In this article, we will see elements which turn around one neural, after that we will know the basic concepts about a fundamental concept of the neural networks, <strong>the Neural</strong>. Let’s discover it…</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/597/1*bZ1C7wsWY_j6j5HE87nKfg.png" /><figcaption>Artificial Neural Network (ANN)</figcaption></figure><p>Artificial Neural Network contains several neural interconnected, we can see this in the picture above. A neural is a mathematical function that takes some value in the input and returns a value in the output. Understand how a specific neural works is important to know how the entire neural network works.</p><p>Firstly, I will present to you the different parts of a Neural.</p><ol><li><strong>Anatomy</strong></li></ol><figure><img alt="" src="https://cdn-images-1.medium.com/max/600/1*7LBCmULLnfi05CGBFk-3cA.png" /><figcaption>Parts of a Neural</figcaption></figure><p><strong>a. Inputs</strong></p><p>Inputs are primitives values, these values are used to train our neural networks.</p><p><strong>b. Weights</strong></p><p>These are parameters that the machine should learn (produce) for having a good neural network which resolves correctly the problem that we have. Each connection (link) is assigned to a specific weight (see on the picture).</p><p><strong>c. Linear Function</strong></p><p>This function depend of inputs and weights, and permit to compute the predictive value. Below is the representation of this function.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/336/1*RTrJ6CFPpeR-yV4artZfcQ.png" /><figcaption>Linear function expression</figcaption></figure><p><strong>d. Activation function</strong></p><p>The activation function is an important part of a neural, it’s used to classified the output. The outcome depend of the kind of activation function that we chosen.</p><p>There are several kind of activation function, such as:</p><ul><li><strong>Sigmoid Function</strong></li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/358/1*vnmtEN83vZ-TaiVNQtRyqA.png" /><figcaption>Sigmoid function representation</figcaption></figure><p>This function is defined from IR to ]0, 1[</p><ul><li><strong>Softmax Function</strong></li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/393/1*e4vTh3inAqxm41GHRblDdw.png" /><figcaption>Softmax function expression</figcaption></figure><p>This function is applied on a set of value, here we consider only zi. If we have N classes, then the sum of the softmax of all N expression is equal to 1.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/452/1*9qHY3OmFLPqhG5Z0R7IF4w.png" /></figure><ul><li><strong>Hyperbolic Tangent Function</strong></li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/254/1*vTGVEFwWKaDoCgp1V3eEpA.png" /><figcaption>Hyperbolic tangent expression</figcaption></figure><p>This function is defined from IR to ]-1, 1[.</p><ul><li><strong>ReLu Function</strong></li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/387/1*W8yNz9QX397yfSuafiYcGg.png" /><figcaption>ReLu expression</figcaption></figure><p><strong>e. Ouput:</strong> It’s the final value returned by our activation function.</p><p>2. <strong>Functioning</strong></p><p>At the beginning, we have inputs, these input are combined to theirs weight using a Linear Function and produced a value. This value is passed into an activation function (one function amongs these presented below) and it will produce the definitive value that will be passed to the second Neural. Too simple…</p><p>Now You know how a single Neural works, you are ready the learn how an Artificial Neural Network works.</p><p>Thank for reading this article, follow me and stay connected…</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=94dc4046b42c" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Presentation of MSE (Mean Squared Error)]]></title>
            <link>https://medium.com/@DilaneKombou/presentation-of-mse-mean-squared-error-a4ee9b6cff49?source=rss-ea80385386fe------2</link>
            <guid isPermaLink="false">https://medium.com/p/a4ee9b6cff49</guid>
            <category><![CDATA[mean-squared-error]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[linear-regression]]></category>
            <category><![CDATA[ai]]></category>
            <dc:creator><![CDATA[Dilane3]]></dc:creator>
            <pubDate>Thu, 12 Aug 2021 11:15:47 GMT</pubDate>
            <atom:updated>2021-08-12T11:15:47.927Z</atom:updated>
            <content:encoded><![CDATA[<p>In machine learning, when we are resolving a problem, we should choose a model which can match our cloud of points. Now, the problem is that, the model that we have chosen, can generated many errors and then it will not be optimized. What we should do is to minimize the error for having a good model.</p><p>One of the most Error sanctioning that we have in machine learning is MSE (Mean Squared Error). This type of error sanctioning is very useful when we implement a linear regression problem, logistic regression problem an so on.</p><p>Formula:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/473/1*wOtaeC2YkkWfj57n5kV_tg.png" /><figcaption>MSE formula</figcaption></figure><p>Assuming that <strong>fi = axi + b</strong>, which is the linear regression model at a specific position i. We could have the following representation of our model in the cloud of points.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/611/1*m147bKzSgHG4afwzi1YKnQ.png" /><figcaption>Error</figcaption></figure><p>In this picture, we can see that fi - yi represents the error at a specific point of coordinate xi and yi, and the MSE function covers all the errors that we have.<br>Our concern is to minimize error. Looking at the previous expression, we notice that the MSE function is a quadratic function because of the presence of the power of 2 in the expression, so we can have this type of representation …</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/576/1*WfVDoLsarrM5HpO9sh_ZQQ.png" /><figcaption>MSE graph</figcaption></figure><p>looking to this picture, we clearly see that the minimum point is located to this red point. Now, what we must do is to determine the values of <strong>a</strong> and <strong>b</strong> that give us the minimum error. For do this we can used <a href="https://builtin.com/data-science/gradient-descent"><strong>Gradient descent Algorithm.</strong></a></p><p>Thanks for reading…</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=a4ee9b6cff49" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[How should we choose our model of machine learning]]></title>
            <link>https://medium.com/@DilaneKombou/how-should-we-choose-our-model-of-machine-learning-d51cf3c16cf0?source=rss-ea80385386fe------2</link>
            <guid isPermaLink="false">https://medium.com/p/d51cf3c16cf0</guid>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[mathematics]]></category>
            <dc:creator><![CDATA[Dilane3]]></dc:creator>
            <pubDate>Wed, 11 Aug 2021 10:08:24 GMT</pubDate>
            <atom:updated>2021-08-11T10:08:24.019Z</atom:updated>
            <content:encoded><![CDATA[<p>Hello there, in this article i will show you how you can choose a model for your machine learning problem depending on the behavior of your data set after drwan it, let’s go.</p><p>Before make choice of which model you must use to resolve your machine learning problem, you need to draw the cloud of points of your data set. This step is necessary because, it should present to you the behavior of yours data.</p><p>Depending of the behavior of yours data, you can make different choice of model to resolve your problem.</p><p>Note: I assume that your data set contains only one feature (x variable, which affect the value of the output y).</p><ol><li><strong>Linear Model</strong></li></ol><figure><img alt="" src="https://cdn-images-1.medium.com/max/330/1*yNCFletmnWH0vVLlsaK2OA.png" /><figcaption>Linear model</figcaption></figure><p>After draw the cloud of points, if you see that yours points follow a linear direction like on this image above, the model that you should choose is a linear model. This model is represent by <strong>f(x) = ax + b</strong> where <strong>a</strong> and <strong>b</strong> are the parameters of the function, <strong>x</strong> is a feature contained in our data set and <strong>f(x)</strong> is the predicted value. The red line in the image representes your model.</p><p>2. Quadratic Model</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/427/1*ohHTMvXWiE6F8mihyhV7-A.png" /><figcaption>Quadratic model</figcaption></figure><p>In many cases, ours points doesn’t follow the linear direction, and we can not use the linear function. if we see that ours points follow the parabolic direction, we should use the quadratic function. It’s represent by <strong>f(x) = ax² + bx + c</strong> where <strong>a, b, c</strong> are the parameters of the model, <strong>x</strong> is the feature, and <strong>f(x) </strong>the predicted value.</p><p>3. Logistic Regression Model</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/251/1*39Okm9gsJiGl-LzPxOcogA.png" /><figcaption>logistic regression model</figcaption></figure><p>We see that, the linear of quadratic function didn’t match correctly our data set, that’s why in that case we use a sigmoid function which is represent by</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/124/1*hCMRhzHWivEjZLr7xUoVCg.png" /><figcaption>sigmoid function</figcaption></figure><p>where <strong>z = ax + b</strong> (linear function). This function is defined from <strong>IR to ]0, 1[.</strong> This model is used in the classification problem when we want for example to predict if an input value belongs to a specific class or not. It also used in Deep learning with Neural Network.</p><p><a href="https://deepai.org/machine-learning-glossary-and-terms/sigmoid-function">learn more about sigmoid function here</a></p><p>I have presented models that you must know when you start learning about machine learning.</p><p>Thank you for reading…</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=d51cf3c16cf0" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Understand how Rasa Framework works]]></title>
            <link>https://blog.chatbotslife.com/understand-how-rasa-framework-works-81d5a9afeb22?source=rss-ea80385386fe------2</link>
            <guid isPermaLink="false">https://medium.com/p/81d5a9afeb22</guid>
            <category><![CDATA[python3]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[chatbots]]></category>
            <dc:creator><![CDATA[Dilane3]]></dc:creator>
            <pubDate>Wed, 28 Jul 2021 20:56:15 GMT</pubDate>
            <atom:updated>2021-08-11T13:31:49.152Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/936/1*BV7F0OhmAjgMCeaoJzIi1g.png" /><figcaption>rasa framework.</figcaption></figure><p><strong>Rasa</strong> is a python framework that helps us to build any kind of Chatbot easily. It based on NLU (Natural Language Processing) which offer the possibility to understand what the user want. Let’s discover it.</p><p>Firstly you must know how the Chatbot works. The Chatbot is a conversational agent which talk with a client or user and provide answers to the users’ requests independantly of the human intervention.</p><p>The Chatbot is composed by some specifics terms that we will discover:</p><p><strong>Intents:</strong> It represent intentions that the user want to express when he submit his message to the Chatbot. Inside the intents, we provides somes phrases that the user may ask and we also provide some responses that the Chatbot must use to answer to the user. It’s the work of the Developper here.</p><figure><a href="https://chatbotslife.com/chatbot-conference-online-2021-7161960c2817"><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*lwlUzb2E7V5ZAsT4.png" /></a></figure><p><strong>Entities</strong>: Entities are <strong>keywords</strong> that represent some specifics datas that the Chatbot may use to perform the discussion with the user. Entities are used to extract some values inside the user input (message).</p><p>Now, we know how Chatbot works, we can switch to the Rasa Framework.</p><p><strong>Rasa</strong> is split into two python librairies like <strong>Rasa NLU</strong> and <strong>Rasa Core.</strong> The first one is the <strong>Natural Language Understanding </strong>and use the intents to understand what the user want and entities to extract some specifics values to make the conversation more interesting, after Rasa NLU have understood what the user want and extracted somes values, it send it to the next one. <strong>Rasa Core </strong>receives the data sended by Rasa NLU and process it to find the correct answer that it should send to the user as output, For having a response, it will look for the responses that the Developper provided to him inside the intents.</p><h3>Trending Bot Articles:</h3><blockquote><a href="https://chatbotslife.com/how-conversational-ai-can-automate-customer-service-ce1e6e330902">1. How Conversational AI can Automate Customer Service</a></blockquote><blockquote><a href="https://chatbotslife.com/automated-vs-live-chats-what-will-the-future-of-customer-service-look-like-69c90432c8f4">2. Automated vs Live Chats: What will the Future of Customer Service Look Like?</a></blockquote><blockquote><a href="https://chatbotslife.com/chatbots-as-medical-assistants-in-covid-19-pandemic-3d2731b85128">3. Chatbots As Medical Assistants In COVID-19 Pandemic</a></blockquote><blockquote><a href="https://chatbotslife.com/chatbot-vs-intelligent-virtual-assistant-whats-the-difference-why-care-180aebde9358">4. Chatbot Vs. Intelligent Virtual Assistant — What’s the difference &amp; Why Care?</a></blockquote><figure><img alt="" src="https://cdn-images-1.medium.com/max/604/1*Roc9Jbj1ojUTgkFpCc60Nw.png" /><figcaption>Functioning of Rasa</figcaption></figure><p><strong>Explanation</strong>:</p><ol><li>The User submit the <strong>request</strong> (a message is sended to the <strong>Interpreter</strong>)</li><li>In the <strong>Interpreter</strong> section, we have <strong>Rasa NLU</strong> which capture the request, and extract <strong>intents</strong> to understand what the user want, and in the same time it extract some specifics keywords (<strong>entities</strong>) which represent the important data. Then it send the result to the <strong>Tracker</strong>. The rest of the elements below is contained inside <strong>Rasa Core</strong>.</li><li>The <strong>Tracker</strong> here, is used to store the conversation history in memory. By this fact, the Chatbot should know in where level the conversation is, it maintains the conversation state.</li><li>After that, the <strong>Policy</strong> comes; it choose the action which will be execute at every step in the dialogue, regarding the history of the conversation.</li><li>The <strong>Action</strong> here, look inside the history for consulting the state of the conversation. This step can trigge another action.</li><li>The action is executed and an <strong>ouput</strong> is generated (message from the Chatbot) to the user.</li></ol><p>Now you have a brief understanding on how Rasa Framework works, you can now decided to learn about how you can build your own chatbot using this framework.</p><p>just check out the documentation of Rasa.</p><p>for more explanation: <a href="https://rasa.com/docs/rasa/playground">https://rasa.com/docs/rasa/playground</a></p><p>Thank to you reading.</p><h3>Don’t forget to give us your 👏 !</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/780/0*ZxaGcKC3UQEydQIX" /></figure><iframe src="https://cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fupscri.be%2F3e59ef%3Fas_embed%3Dtrue&amp;dntp=1&amp;url=https%3A%2F%2Fupscri.be%2F3e59ef&amp;image=http%3A%2F%2Fapi.screenshotlayer.com%2Fapi%2Fcapture%3Faccess_key%3Dfe59908dad3baab69ffab249a2224b03%26viewport%3D1024x612%26width%3D1000%26url%3Dhttps%253A%252F%252Fupscri.be%252F3e59ef%253Fscreenshot&amp;key=a19fcc184b9711e1b4764040d3dc5c07&amp;type=text%2Fhtml&amp;schema=upscri" width="800" height="400" frameborder="0" scrolling="no"><a href="https://medium.com/media/7078d8ad19192c4c53d3bf199468e4ab/href">https://medium.com/media/7078d8ad19192c4c53d3bf199468e4ab/href</a></iframe><figure><a href="https://chatbotslife.com/bot-communities-mastermind-group-d2dae9876709#.53x0py6ou"><img alt="" src="https://cdn-images-1.medium.com/max/255/1*6XUspT9JOSq0w0Fi35HIaA.png" /></a></figure><figure><a href="https://m.me/ChatbotsLife"><img alt="" src="https://cdn-images-1.medium.com/max/255/1*c1LDMH5vbnIz9rmAka8Hwg.png" /></a></figure><figure><a href="https://chatbotslife.com/chatbot-development-hire-top-ai-chatbot-developers-c8b45ef7f207"><img alt="" src="https://cdn-images-1.medium.com/max/255/1*D0Jf3dI6ZThtqcfwDYY7mg.png" /></a></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=81d5a9afeb22" width="1" height="1" alt=""><hr><p><a href="https://blog.chatbotslife.com/understand-how-rasa-framework-works-81d5a9afeb22">Understand how Rasa Framework works</a> was originally published in <a href="https://blog.chatbotslife.com/">Chatbots Life</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[How to create ChatBot using DialogFlow ?]]></title>
            <link>https://blog.chatbotslife.com/how-to-create-chatbot-using-dialogflow-66e6ea6bb67d?source=rss-ea80385386fe------2</link>
            <guid isPermaLink="false">https://medium.com/p/66e6ea6bb67d</guid>
            <category><![CDATA[chatbots]]></category>
            <category><![CDATA[dialogflow]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[chatbot-development]]></category>
            <category><![CDATA[bots]]></category>
            <dc:creator><![CDATA[Dilane3]]></dc:creator>
            <pubDate>Thu, 22 Jul 2021 14:40:46 GMT</pubDate>
            <atom:updated>2021-07-29T13:58:29.214Z</atom:updated>
            <content:encoded><![CDATA[<h3>How to Create a Chatbot Using DialogFlow ?</h3><h4>What is DialogFlow ?</h4><p>DialogFlow is a development platform created by Google that can help us to create Chatbots. It’s based on NLP (Natural Language Processing) which offers our chatbots the possibility to be very powerful.</p><h4>What is the ChatBot ?</h4><p>A chatBot is an intelligent program that can interact with people like a human and serves them in the specific domain where it has been created. The chatbot analyzes the intention of the client and researches the response that will be more adapted.</p><p>Now you know what DialogFlow and chatbot are, let’s see how we can create a chatbot using Dialogflow.</p><p><strong>Note:</strong> You should have a google account and login in to the Dialogflow platform before following these steps.</p><p>In this article, we will create a chatbot that can serve clients who will want to do a <em>reservation</em> for a bedroom in a Hotel.</p><figure><a href="https://chatbotslife.com/chatbot-conference-online-2021-7161960c2817"><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*lwlUzb2E7V5ZAsT4.png" /></a></figure><p><strong>Step 1. Create an Agent</strong></p><p>An Agent is an intelligent program inside the chatbot, it’s that program that interacts with the clients or users.</p><p>To create an Agent, go to the left section of your screen and click on the first button below the <strong>Dialogflow logo</strong> and go down to the <strong>create new agent </strong>button.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*dTN6-InijC_aTvE6qX_lrg.png" /></figure><p>After that, the new screen will be loaded, and you will be ask to specify the name of the Agent, the language that it should be speak and the time zone. For me, I type <strong>reservation-bot</strong> for the name and the rest, i leave the default values. After that, you must click on the <strong>CREATE</strong> button and DialogFlow will create an agent for your chatbot.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*1pRChIhZlSybfRz_CZpkow.png" /></figure><p><strong>Step 2. Create intents</strong></p><p>Intents is use by the chatbot to understand what the clients or users want. It’s inside the intents that we should provide to the chatbot the examples of phrases that the clients may ask and some responses that the chatbot should use to answer to the clients. Let’s show how we can do it.</p><p><strong>Note:</strong> When we create a new agent, it comes with two defaults intents named <strong>Default Fallback Intent</strong> and <strong>Default Welcome Intent</strong></p><p>For create a new Intent, click on the <strong>Create Intent</strong> button</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*ur2-cDsqyl84abm43yoWlQ.png" /></figure><p>After that, you must give the name of your intent. Then go to the <strong>Training Phrases</strong> section and click on <strong>add training phrases. </strong>This section concerns the way where you should give the example of the phrase which represents the different questions that clients may ask to the chatbot. we recommend giving many examples to make your chatbot very powerful.</p><p>For this example, you could take the same phrases as me.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/648/1*TZ4hOVLQ76GKXp6nGY3FRw.png" /></figure><p>We have added some phrases that clients may ask to our chatbot, for your own chatbot, feel free to add another phrase to improve the power of your chatbot</p><p>In this image, we can see that two expressions are overlined. In fact, DialogFlow has identified these expressions as an entity<strong>.</strong> DialogFlow recognizes three types of entities such as <strong>systems entities</strong>, <strong>developer entities,</strong> and <strong>session entities</strong>. <strong>this night </strong>and<strong> today</strong> are recognized as systems entities, it refers to the <strong>date</strong> or <strong>period of time</strong>, this type of entity is already set in Dialogflow. Later we will create our own entities which will recognize by DialogFlow as <strong>Developer entities</strong>. For more information, check out this <a href="https://cloud.google.com/dialogflow/es/docs/entities-overview">documentation</a></p><p>Now, let’s define some Responses that the agent may use to answer to clients. Go down to the <strong>Response</strong> section and click on the <strong>Add response</strong> button, and add some responses statements.</p><h3>Trending Bot Articles:</h3><blockquote><a href="https://chatbotslife.com/how-conversational-ai-can-automate-customer-service-ce1e6e330902">1. How Conversational AI can Automate Customer Service</a></blockquote><blockquote><a href="https://chatbotslife.com/automated-vs-live-chats-what-will-the-future-of-customer-service-look-like-69c90432c8f4">2. Automated vs Live Chats: What will the Future of Customer Service Look Like?</a></blockquote><blockquote><a href="https://chatbotslife.com/chatbots-as-medical-assistants-in-covid-19-pandemic-3d2731b85128">3. Chatbots As Medical Assistants In COVID-19 Pandemic</a></blockquote><blockquote><a href="https://chatbotslife.com/chatbot-vs-intelligent-virtual-assistant-whats-the-difference-why-care-180aebde9358">4. Chatbot Vs. Intelligent Virtual Assistant — What’s the difference &amp; Why Care?</a></blockquote><figure><img alt="" src="https://cdn-images-1.medium.com/max/650/1*x8h-EKuX6mUBC9mag9Fqvg.png" /></figure><p>You can see that inside these responses examples there are some expressions that start with<strong> the $ </strong>symbol, these expressions are considered as variables that will contain the values that clients will mention in their questions, and that DialogFlow will have recognized as a certain entity. On the image above, we have three variables such as <strong>$time-period</strong>, <strong>$date-time,</strong> and <strong>$reservation-type.</strong> $time-period and $date-time are systems entities variables and $reservation-type is a Developer entity variable, which means $reservation-type should be created by the developer, before that DialogFLow may recognize it. After added some responses that the agent should use, click on the <strong>Save</strong> button, we will come back hereafter.</p><p><strong>Step 3. Creation of entities</strong></p><p>In reality, entities are keywords that help the Agent to recognize what the client wants. To create it, just follow me.</p><p>Click on the Entities button</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/261/1*qIKzdFxfOH57G18mxPnF8Q.png" /><figcaption>creation of entities</figcaption></figure><p>After click on the <strong>Create Entity</strong> button</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/659/1*6JK6E5Nj5-TjUwTp3JiPag.png" /><figcaption>creation of entity</figcaption></figure><p>After, specify the name of the entity (you should give <strong>reservation-type</strong> as name of your entity, because you have use it as variable when you gave some responses to the agent). Then, add an entity <strong>bed-room </strong>and some synonyms like below.</p><p>make sure to check the case <strong>Define synonyms</strong> before, and then click on <strong>Save</strong> button.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/658/1*0sklBjpSrkhfQ32RBJbZhQ.png" /></figure><p>The role of synonyms is that, when clients should talk about bed-room, bed or room, all of this should refer to the bed-room.</p><p>Do the same with the entity <strong>reservation-action </strong>and save it.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/654/1*tfsrbamzLRR9FInTm7BOcA.png" /><figcaption>creation of reservation-action entity</figcaption></figure><p>Now, we have two entities ready to be used.</p><p><strong>Step 4. add our entities inside training phrases expressions</strong></p><p>back to the <strong>reservation intent</strong> interface and go to the training phrases section.</p><p>When you are there, select an expression, and inside this expression select the word <strong>bed-room</strong> like this</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/645/1*pPr5ipfulmjAQ78JntG3Ew.png" /></figure><p>Then, research for <strong>@reservation-type</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/613/1*mObHiQJIe5wuXIHVv2aX4A.png" /></figure><p>And click on this, and the color of bed-room will change.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/588/1*o44DxCtd4geK_9lzOHhqbg.png" /></figure><p>Do the same thing to all the bed-room inside all expressions.</p><p>For the words booking, reservation, and reserve, do the same things but instead of research <strong>@reservation-type</strong> you will research <strong>@reservation-action.</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/645/1*xwGjTQTwltRuJ-c6tZY_4g.png" /><figcaption>adding developper entities inside our training phrase expressions</figcaption></figure><p><strong>Step 5. Definition of parameters and actions</strong></p><p>It’s not required, but in some cases, it will be very important to obligate the user to give to the chatbot, some information.</p><p>Go down to the <strong>Actions and parameters</strong> section, always inside the reservation intent interface. you should have this image below.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/637/1*8SwyDP78al73w8YBPTdCTw.png" /><figcaption>action and parameters</figcaption></figure><p>For our chatbot, we want that clients provide the <strong>reservation type</strong> and the <strong>date</strong> of the reservation. Make sure to check it.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/644/1*dUKyyufsCVx2Dm3nL5oFRQ.png" /><figcaption>actions and parameters</figcaption></figure><p>After that, we should specify the prompt text that the Agent should display to the client when they haven’t specified the required parameters. You need to click on the <strong>Define prompts…</strong> space on the right place of this section, after defining prompt text, close the box dialog.</p><p>for the date-time parameter</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/841/1*Bg7PDL51cZ4bxoW16vX0XQ.png" /><figcaption>define prompt text for date time parameter</figcaption></figure><p>for the reservation type parameter</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/827/1*YCaY4NrncfIXrm2v0y7H_g.png" /></figure><p>After this, save the intent.</p><p>Now you can test your chatbot.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/366/1*hrl6tJaLDzURdcbmt7Zqdw.png" /><figcaption>test section</figcaption></figure><p>You can test your chatbot here.</p><p><strong>Step 6. Integration on the web platform</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/262/1*A9skOEXALSB-L5MwXrO2Zw.png" /><figcaption>integration</figcaption></figure><p>Click on the integrations button</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/649/1*_A2oGKXrbqetzZXG7iaimQ.png" /></figure><p>You can integrate your chatbot inside of many platforms, like Facebook messenger, WhatsApp, telegram, and so on.</p><p>For this article, we are going to choose the <strong>Web Demo</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/830/1*BqAxrDBKJ7Iuyg9huDq0PQ.png" /><figcaption>integration demo</figcaption></figure><p>click on the link, and test it again.</p><p><strong>My Demo on my phone.</strong></p><p><a href="https://drive.google.com/file/d/18OfWKBuWRQ-vIhwAhg7CL9K-3F6sA1-_/view?usp=sharing">reservation-bot-dialogflow.mp4</a></p><p>Thank you for reading…</p><h3>Don’t forget to give us your 👏 !</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/780/0*ZxaGcKC3UQEydQIX" /></figure><iframe src="https://cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fupscri.be%2F3e59ef%3Fas_embed%3Dtrue&amp;dntp=1&amp;url=https%3A%2F%2Fupscri.be%2F3e59ef&amp;image=http%3A%2F%2Fapi.screenshotlayer.com%2Fapi%2Fcapture%3Faccess_key%3Dfe59908dad3baab69ffab249a2224b03%26viewport%3D1024x612%26width%3D1000%26url%3Dhttps%253A%252F%252Fupscri.be%252F3e59ef%253Fscreenshot&amp;key=a19fcc184b9711e1b4764040d3dc5c07&amp;type=text%2Fhtml&amp;schema=upscri" width="800" height="400" frameborder="0" scrolling="no"><a href="https://medium.com/media/7078d8ad19192c4c53d3bf199468e4ab/href">https://medium.com/media/7078d8ad19192c4c53d3bf199468e4ab/href</a></iframe><figure><a href="https://chatbotslife.com/bot-communities-mastermind-group-d2dae9876709#.53x0py6ou"><img alt="" src="https://cdn-images-1.medium.com/max/255/1*6XUspT9JOSq0w0Fi35HIaA.png" /></a></figure><figure><a href="https://m.me/ChatbotsLife"><img alt="" src="https://cdn-images-1.medium.com/max/255/1*c1LDMH5vbnIz9rmAka8Hwg.png" /></a></figure><figure><a href="https://chatbotslife.com/chatbot-development-hire-top-ai-chatbot-developers-c8b45ef7f207"><img alt="" src="https://cdn-images-1.medium.com/max/255/1*D0Jf3dI6ZThtqcfwDYY7mg.png" /></a></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=66e6ea6bb67d" width="1" height="1" alt=""><hr><p><a href="https://blog.chatbotslife.com/how-to-create-chatbot-using-dialogflow-66e6ea6bb67d">How to create ChatBot using DialogFlow ?</a> was originally published in <a href="https://blog.chatbotslife.com/">Chatbots Life</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>