Create New Dialog

Chatbots are known for their human-like conversational abilities. To generate better user experiences, you can use dialogue flow to make human-chatbot conversations more human. In 3Dolphins, dialog flow is the crucial aspect that makes chatbots conduct contextual communication.

The dialogue flow defines the actual dialogue context. For example, a user might say "find the nearest ATM in Central Jakarta", then in the middle of that conversation the user might say "find a hotel in Central Jakarta", the dialogue flow allows us to do that.

In the upper right corner, click the '+New Dialog' button. Then, you will see a page to create a new dialog, such image below.

Component Explanation:


Dialog Fallback

To display failed responses from bots that are in the dialog if there is a fallback

Term and Synonym

To set the word similarity level or the similarity of words from the user response to the FAQ or dialog understood by the bot

Transition Response

Trigger to save the session dialog to be asked again when the user calls another dialog, after another dialog that is called is finished, the Bot will resume the previous dialog session

Clone Dialog

Used to duplicate the selected dialog's intentions and entities.

Reminder Dialog

Trigger that encourages the customer to respond to the bot's dialogue.

  • Reminder Timeout: Enter the time in seconds to launch the reminder dialog. If you configure the bot timeout, the value entered in this field must be less than the timeout time.

  • Reminder Prompt: The bot will provide sentences or quick responses if the user does not respond to the bot's dialog within the specified time in the reminder timeout field.

  • Reminder Payload: Trigger that the system will interpret to deliver the reminder prompt.

Dialog Flow consists of 4 steps that must be completed, that is:

  1. Intention and Entity: Determine the intention and entity needed in a dialog.

  2. Prompt Response: Set the response of bots to each predetermined entity.

  3. Integration: Entity from user response can be used to query (get data) through SDK integration web service.

  4. Configuration: Set the confidence level of each entity, success response, failed response, until unrecognized response before the save process is performed for the build model.

Last updated