To make your chatbot better, you need to train it to respond to situations where it did not understand what the user was trying to accomplish. Once you navigate to the Training section, you will see all the conversations that happened between a user and your chatbot, and also the conversations that your chatbot did not understand. But what will you do with all that information? It is also important to train your chatbot so that it can give better answers to customers, and this is where Training comes into the picture. The curved arrows indicate that the user session ended at that particular internet.Īs you can see, the Session Data can give you a lot of information on how your chatbot is used. If you hover the mouse over a particular Intent, it shows the metrics for that particular intent. Session Path: Session Paths tell you how people are starting their sessions with your chatbot.įor instance, in the current Ticket Booking bot that we created earlier, the Session Path looks something like this:Īs you can see, a few people went from the Default Welcome Intent to the Show Timings Intent, whereas others continued on in the Default Welcome Intent and then moved on to ending the conversation.Īs another example, here is the Session Path for a Dialogflow Chatbot developed by Google themselves. The Intent path shows the skeletal structure of your chatbot and is an important metric when it comes to Bot Analytics.ģ. The Intent Path should ideally be clear, and, if you observe that there are some strange connections in your intent path, then it’s time for you to see if you have assigned your Intents correctly. Intent Path View: The Intent Path view lets you know how people are interacting and engaging with your chatbot. If you see the example above, the Exit percentage is 50% for the intent Show Timings, which means that this is the intent where 50% of the users dropped off.Ģ. The Sessions feature tells you how many sessions the users had with that particular intent.Ī thing to note here is the Exit percentage. This is a great place to see how your bot’s various use cases, since it tells you about the number of Sessions, the number of Interactions, and the Exit percentage. Intents: Navigating to the Intents feature will give you the summarized stats by intent.Let us now look at some of the more interesting features in detail: There are other views too which Dialogflow provides that help you understand the behavior of your chatbot. In the given example, we had 1 interaction on 25th of February, and hence the flat line. The first view that Analytics provides is the Overall view, in which you can see the number of Sessions and number of Interactions within the stipulated time period. For the purposes of this tutorial, we have picked it for the month of February 2022: To begin with, let’s select the Date Range between which you want to see how the chatbot is functioning. We will use the same chatbot, albeit this time to learn more about Analytics. In one of our previous articles, we had created a Dialogflow chatbot that helped us book movie tickets. Dialogflow CX is the choice when you need to build complex agents for large enterprises. Beginners use Dialogflow ES to build a simple chatbots. Both Dialogflow ES and CX use intents, but in CX, the intents are simplified and reusable. Of Course, if you are just starting out building your chatbot, there is always Dialogflow ES which stands for Essentials. CX stands for Customer Experience, and with Dialogflow CX, you can use a visual builder to build and train your chatbot, without the need to write complex code. Dialogflow CX is a powerful tool that helps you engineer advanced virtual agents, aka chatbots. But before that: What is Dialogflow?ĭialogflow is the NLU engine developed by Google, that allows you to understand language in your chatbot. In this article, we talk primarily about Dialogflow Analytics and how to use Dialogflow training phrases to improve your chatbot. If you have built a chatbot, or are considering building a chatbot, the name Dialogflow would have appeared right at the top of your Google Search bar. Conversational experiences, where you talk to a system and the system talks back, can be difficult to build.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |