{"id":17952,"date":"2016-12-06T23:41:55","date_gmt":"2016-12-06T23:41:55","guid":{"rendered":"https:\/\/developer.kore.com\/?post_type=docs&p=9158"},"modified":"2023-11-20T06:06:30","modified_gmt":"2023-11-20T06:06:30","slug":"working-with-the-entity-node","status":"publish","type":"post","link":"https:\/\/developer.kore.ai\/v10-1\/docs\/bots\/bot-builder-tool\/dialog-task\/working-with-the-entity-node\/","title":{"rendered":"Entity Node"},"content":{"rendered":"
\r\n\t
\r\n\t\t
\r\n\t\t\t

Virtual Assistants need to extract relevant information from the user utterance to fulfill the intent.<\/span><\/p>\n

Take a look at this sample utterance: <\/span>Book me a flight from LA to NYC on Sunday<\/span><\/em>. To act on this user intent, which is to book a flight ticket, the bot should extract the entities such as the <\/span>source city<\/span><\/em> (LA), <\/span>destination city<\/span><\/em> (NYC), and <\/span>departure date<\/span><\/em> (Sunday).<\/span><\/p>\n

So, in a Dialog Task, for every critical data you want to get from a user utterance, you should create a corresponding entity node. You can add prompt messages to these nodes for users to input the required values.<\/span><\/p>\n

The Kore.ai XO Platform supports ~30 <\/span>entity types<\/span><\/a> such as Address, Airport, Quantity, and so on. You can also define the entities as a selection from a list, free-form entry, file or image attachment from a user, or as regex expressions. You can also create custom regex and use these regex expressions as patterns to enable the masking of sensitive data contextually.<\/span><\/p>\n

Note:<\/b> You need to follow one entity node with several other entity nodes to collect a series of user inputs to complete a transaction, such as a username, location, amount, and due date, followed by a Webhook node to process a request to an API to complete an online transaction.<\/div>\n

Add the Node<\/span><\/span><\/h1>\n

Setting up an entity node in a dialog task involves the following steps:<\/span><\/p>\n

    \n
  1. Open the dialog task to add the <\/span>Entity <\/strong>node.<\/span><\/li>\n
  2. Add the entity node in the designated place. For information on adding nodes, <\/span>refer here<\/span><\/a>.<\/span><\/li>\n
  3. The Entity window is displayed with the <\/span>Component Properties<\/strong> tab selected by default.<\/span>
    \n    \"\"<\/a><\/li>\n<\/ol>\n
    Entity and Multilingual Bots:<\/b> If you add a new entity to a multilingual bot, the platform adds the entity for all languages, as it follows a consistent flow definition across all languages. The flow definition includes the list of nodes, transitions between the nodes, and some essential properties of nodes like node id, node type, entity type, etc. However, language-specific properties, such as prompts, error messages, lists of synonyms, etc., must have separate values for each language.<\/div>\n

    Configure the Node<\/span><\/span><\/h1>\n

    Component Properties<\/span><\/span><\/h2>\n

    The Entity window allows you to configure the General Settings, User, and Error Prompts.<\/span><\/p>\n

    Note:<\/b> The configurations you set up or modify in this section are reflected in all other dialog tasks that use this node.<\/div>\n
      \n
    1. On the <\/span>Component Properties<\/strong> tab, under the <\/span>General Settings <\/strong>section, enter a <\/span>Name<\/strong> and <\/span>Display Name<\/strong> for the entity node. Entity names cannot include spaces.<\/span><\/li>\n
    2. From the <\/span>Type <\/strong>drop-down list, select an entity type depending on the expected user input. For example, if you want the user to type the departure date, select <\/span>Date <\/strong>from the drop-down. The platform does the basic validation based upon the Type selected.<\/span>
      \n<\/span>The <\/span>Entity Type<\/strong> provides the NLP Interpreter with the expected type of data from a user utterance to enhance recognition and system performance. For more information, refer to <\/span>      Entity Types<\/span><\/a><\/li>\n
    3. Based on the Type selected, you have an option to set the Entity as <\/span>Multi-item<\/strong> thereby allowing the user multiple selections. If enabled, the VA should expect multiple items for this entity from the user.<\/span><\/li>\n
    4. Under the <\/span>User Prompt<\/strong> section, enter the prompt message that you want the user to see for this entity. For example, <\/span>Enter the Departure Date<\/span><\/em>.<\/span>\n
        \n
      1. You can enter channel-specific messages for user prompts using the <\/span>Manage<\/strong> link. For more information, refer to <\/span>Using the Prompt Editor<\/span><\/a>.<\/span><\/li>\n
      2. You can override the user prompt for this particular instance.<\/span>
        \n<\/span>To override,<\/span><\/p>\n