What is Dialogflow?
Dialogflow, formerly known as api.ai is a tool by Google to make conversational AI chatbots. The unique thing about it is that with only basic programming or coding knowledge, one can build a good conversational bot. It works on natural language processing and backed by Machine Learning.
But before you start making a conversational bot in Dialogflow, you should understand some basic terminologies or sections used in it. To understand these terminologies, you need to create agent, i.e. identity of your bot. If you already have an account, then just go to create new agent, and after selecting required parameters, click on create agent. If you don’t have Dialogflow account, you need to sign up. Now you are ready to learn the terminologies.
1) Invocation – The phrases or the keywords which invokes your bot or make it available to start the conversation is known as invocation.
2) Intents – As the name suggests, it is related to the “intentions” i.e. what user wants to know and with respect to it, how your bot will respond. It maps the users query with the “response” you feed in the respective intent. It has different sections for contexts, training phrases (user says), events, actions and parameters, and response.The intents get triggered on the basis of matched user’s queries and provide responses according to the triggered intents.
3) Entities – They are predefined collection or knowledge bags of Dialogflow which catches the parameters or details which user provides, using which our bot will respond to the user. It helps the bot to get and give “exact information”, as bot understands which particular or specific thing (e.g. – dates, time, city etc) user wants to know about. Apart from prebuilt entities, you can also create entities by your own.
4) Contexts – The very powerful method to keep user engaged and give a direction to the conversation to create a meaningful interaction. From user’s perspective also, it is very useful as bot don’t need to annoy user by asking him to specify details again and again.
In simple words, it can be explained by this example – Suppose user says to turn on red light, in response of which bot says “ok, turning on the red light.” Now when user says “turn it off”, the bot will understand by itself that user is talking in context with “red light” only and not blue or green light.
5) Events – Apart from triggering the intents through what user says, it can also be triggered by particular event. Suppose in Facebook messenger or Google assistant, you want to invoke “welcome intent”, then you can do it by assigning welcome event to the welcome intent in the events section.
6) Actions and parameters – Actions can be defined as the step your bot will take after the intent got triggered. It also extracts the important information from the whole conversation through parameters which user provides, and show it in the JSON response, which can be fetched to maintain databases easily, instead of going through whole conversations.
7) Responses – The output which user will get when he will ask any query to the bot is known as response. In the response section of the intents, we feed the output response which user should get if the query matches the keywords, phrases or the queries we fed in the intent’s “user says” section. This is where we can make our bots intelligent, by using some rich messages, webhook and fulfillment.
Rich Messages: In the Response section, you can add tabs for some of our supported integrations. This allows you to define default or integration-specific responses. In each tab, you can add multiple message types.The integration tabs allow you to add images, cards, and quick replies.
8) Fulfillment: Making bot is simple until you are providing text messages in the response and the queries are matching…What if they aren’t??
At this point, Dialogflow has the request from the user , so it now needs to request the information to fulfil the user’s request. The data is to be sent to the web-hook so that the required information can be fetched. Once the web-hook has fetched required information it will send it back to Dialogflow so that it can be presented to the user in the desired manner.
9) Webhook: Setting up a webhook allows you to pass information from a matched intent into a web service and get a result from it. Your web service receives a POST request from Dialogflow. This is in the form of the response to a user query, matched by intents with webhook enabled. Be sure that your web service meets all the webhook requirements specific to the API version enabled in this agent.If a request is sent from one of the messaging platforms, the original Request field is added to the response to a query.This format is chosen in order to simplify the response parsing on the service side with the help of Dialogflow SDKs.
10) Integration: Deploying the bot to the platform where we want to see it is known as integration. By default, Dialogflow provides 1-click integrations for 16 different platforms with all the necessary procedures and analytics, which makes it the best and easiest platform for making a bot.
- On any platform — Dialogflow support more than 16 platforms from Google home to Twitter
- Across devices — Dialogflow supports all the devices from wearables, to phones to devices.
- Around the world — Dialogflow supports more than 14+ languages worldwide & more support is coming.
Why choose us?
We as a Chatbot development company in Raipur is committed to helping its clients reach their goals, to personalizing their event experiences, to providing an innovative environment, and to make a difference.
Our strong sense of identification with client projects means that we are constantly striving to provide solutions, even for issues they aren’t yet aware of. To this end, we adopt a progressive approach to technology and marketing techniques, and having a highly experienced team working on Chatbot makes it more easier.
For pricing and quotations NB Digital Technologies