Images
|You can only have one image in one image component. Buttons are not available for images.
Caution: Since there are limits as to image sizes, images may be automatically cropped.
| | Carousels |Carousels, (Generic Template, also known as regular templates)
Maximum of 10 blocks of carousel per message. Each carousel block can have a maximum of 3 buttons.
| | Quick replies |After clicking a quick reply, the content of the quick reply will be pasted on the user’s input box.
Each Messenger message has a maximum of 11 quick replies. After clicking on a quick reply button, the button disappears in the conversation.
Quick replies are only allowed to appear after other components; in other words, they cannot appear at start of conversations. Quick replies cannot open WebViews.
| | Continuing Item | In each message content, you can use existing messages as a continuous response that follows other components in the message. A continuing item leads the conversation to another already made message, so that when the same content is needed in different messages, you don’t have to do it again. | | Random Component | Random Components are a set of components. The system will randomly pick one as response. | | JSON API | JSON API allows your chatbot to communicate with your backend server in order to achieve flexible responses and additional functions. | ### LINE Conversation Components | Component Names | Description | | ------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | |Text
| Plain text or plain text with buttons. Max of 3 buttons and the buttons can do tasks like dialing a number, opening a webview or triggering other messages. | | Image |You can only have 1 image in one image component. Buttons are not available for images.
Caution: Since there are limits as to image sizes, images may be automatically cropped.
| | Carousels | Maximum of 10 blocks of carousel per message. Each carousel block can have a maximum of 3 buttons. | | Imagemap |An Imagemap is made of multiple images combined as one. You can configure the style of your imagemap. You can also add an action for each section of the imagemap, such as opening a WebView or sending a message.
Notice: imagemaps are not the same as rich menus
A rich menu is a persistent menu below conversations that consists of options to pick from. To setup rich menus, please navigate to “Menu” under “Dialogue”
| | Quick replies |After clicking a quick reply, the content of the quick reply will be pasted on the user’s input box.
A LINE message can have a maximum of 13 quick replies. After clicking on a quick reply button, the button disappears in the conversation.
Quick replies are only allowed to appear after other components; in other words, they cannot be the start of conversations. Quick replies cannot open WebViews.
| | Continuing Item |In each message content, you can use existing messages as a continuous response that follows other components in the message.
A continuing item leads the conversation to another already made message, so that when the same content is needed in different messages, you don’t have to do it again.
| | Random Component | Random Components are a set of components. The system will randomly pick one as response. | | JSON API | JSON API allows your chatbot to communicate with your backend server in order to achieve flexible responses and additional functions. | # Intent Under “My Bot” on the left sidebar on YOCTOL.AI, **`Intent`** is where you tell the bot how to categorize users’ intentions. If you want to train your chatbot with its NLU engine on YOCTOL.AI, you need to have at least 2 intents. You can have a maximum of 25 intents. {% hint style="info" %} We suggest you design 2-3 intents at first for your chatbot with 3-5 [utterances](https://app.gitbook.com/@docs-en-yoctol-ai/s/yoctol/~/edit/drafts/-LnQJsTXatUDJ-slOjKr/v/master/term-translations/utterance) for each intent. An intent can have a maximum of 30 utterances. {% endhint %} ### Example Take a chatbot for a beverage shop as an example. It has to understand these three basic intents. * Products Inquiry * Delivery Request * Branches Inquiry There can be many ways to express the same intent. For example, when a customer asks about a new product of the shop, he/she could say “What brand is this? Is it good?” or “Do you have anything new?” With the NLU engine embedded in your chatbot, the bot would categorize these two messages as similar and respond with a product information message. # Utterance **Utterances** are various ways of expressions for the same [intent](https://app.gitbook.com/@docs-en-yoctol-ai/s/yoctol/~/edit/drafts/-LnQJsTXatUDJ-slOjKr/v/master/term-translations/intent) used by the chatbot to learn and categorize the intent. We recommend a number of 3-5 utterances for each intent with diverse and representative sentence structures. Each intent has a maximum of 30 utterances. You can utilize [“entities”](https://app.gitbook.com/@docs-en-yoctol-ai/s/yoctol/~/edit/drafts/-LnQJsTXatUDJ-slOjKr/v/master/term-translations/entity) and put various utterances with similar sentence structure in one utterance only. Each utterance can have a maximum of 3 entity values. ### Example Take a beverage shop chatbot as an example. If we want to train it to understand the intent of delivery request, the following would be possible utterances for this intent. In utterance 3, we can use an entity of “drink name” instead of using countless\ utterances to list out all the drinks. If there are entities used, you can use the symbols {{ }} to mark them. 1. I want to order many cups! 2. How many cups do I need to buy for delivery? 3. How long will it take to deliver 10 cups of {{drink name}} 4. … # Entity Under **`Intent`** on the left sidebar on YOCTOL.AI, an **`entity`** includes a group of entity values, which are normally nouns of the same category and can all be applied whenever the specific entity is used in any utterance. Common entities include: objects, names, time, locations or prices. Entities are under[ intents](https://app.gitbook.com/@docs-en-yoctol-ai/s/yoctol/~/edit/drafts/-LnQJsTXatUDJ-slOjKr/v/master/term-translations/intent). When a user sends in messages, the NLU model will first identify the message’s intent, then it will match the message with all the entity values listed. Same entity can be used in multiple intents, widening the range of knowledge a chatbot can learn from its [utterances](https://app.gitbook.com/@docs-en-yoctol-ai/s/yoctol/~/edit/drafts/-LnQJsTXatUDJ-slOjKr/v/master/term-translations/utterance). An entity can have multiple entity values. An entity value may have multiple synonyms. You can create entities when writing [utterances.](https://app.gitbook.com/@docs-en-yoctol-ai/s/yoctol/~/edit/drafts/-LnQJsTXatUDJ-slOjKr/v/master/term-translations/utterance) Entities should be marked with the symbols **{{ }}**. {% hint style="danger" %} The name of an entity cannot start with a number. {% endhint %} ### Example Take a beverage shop chatbot as an example. A possible entity for product inquiry may be the type of product. * Entity: Product * Entity Value: Boba, bubble green tea * Synonyms for Boba: bubble tea; bubble green tea: boba green tea  You can use the entity “Product” for the intent “Product inquiry as such: 1. **Expand utterances**: An example utterance for the intent “Product inquiry” would be “I want to learn more about {{product}}” * To the NLU engine, this utterance may be expanded into: * I want to learn more about the **bubble tea.** * I want to learn more about the **bubble green tea.** * I want to learn more about the **boba.** * I want to learn more about the **boba green tea.** * Imagine you have hundreds of products. It’s impossible to list all the products out as utterances. Therefore, replace the product names with a single entity to assist your chatbot’s NLU training. 2. **Dialogue design**: For the dialogue corresponding to the intent Product Inquiry, you can design a message that provides the menu of the shop or information about each beverage. * Basic answer: the “Product Introduction” message can be used for every single product on the menu. * You can even have a more specific response message for a certain entity. * Message “product\_intro\_bubble\_tea” gives information about bubble tea. * Message “product\_intro\_bubble\_green” gives information about bubble green tea. # Rule Each [message](https://app.gitbook.com/@docs-en-yoctol-ai/s/yoctol/~/edit/drafts/-LnQJsTXatUDJ-slOjKr/v/master/term-translations/message) on YOCTOL.AI has its own “rule”. Each rule defines a certain situation for the chatbot to react to the chatbot users’ input. **There can only be one message connected to each rule.** \ **However, a message can have multiple rules.** If you apply the same rule to multiple messages, the chatbot might not be able to reply correctly. ### Example Take the message “Order information” as an example. The following examples are possible rules for the message. 1. NLU: Select the intent for “Order Information” 2. Keyword matching: Select “When it matches any keyword: ‘place an order’, ‘order drinks’ or ‘order’ 3. Regular expression: write a regular expression such as “.\*(order|buy).\*$”. For more information about regular expressions, please visit [Regular Expression](https://app.gitbook.com/@docs-en-yoctol-ai/s/yoctol/~/edit/drafts/-LnQJsTXatUDJ-slOjKr/v/master/term-translations/regular-expression).Large
Medium
Small
|Coke
Sprite
Fanta
| With regular expressions, we can narrow these three sentences down to a rule as below: > (large|medium|small) cup of (coke|sprite|fanta) ### Common circumstances for regular expressions Regular expressions are often used for emails, phone numbers, birthdays, or any sort of structural character combinations. > Phone number: ^(\\+1)?d{10}$ > > Social Security Number: ^\d{3}-\d{2}-\d{4}$ > > Email (gmail for example): ^.\*@gmail.com$ > > Birthday: ^\d{4}-\d{2}-\d{2}$ ### When to use regular expressions When we build our chatbots, we sometimes hope that certain combinations of words in a customer’s message would normally lead them to a certain intent, which further triggers a response from the dialogue. These combinations may subtly display a certain kind of combination rule. This is where regular expressions come in handy. When encountering situations like this, you should sort the customers’ messages and use regular expressions to categorize, exclude, or set limitations to the messages. We will demonstrate an actual use case later. ### Symbols Basic rule: These symbols limit the number of occurrence of the character before it. We will introduce a couple common symbols below. For more symbols, there are many cheat sheets available online.