Entities

Create Entities Using Lookup Table

Required permission: Chatbot (ACD > DFO > Roles > [choose one] > Core Modules)

Entities are defined pieces of information extracted from a message Anything a contact says in a bot interaction, whether question or statement, written or spoken.. You should only create entities that your bot Virtual agent designed to handle specific interactions needs to accomplish its goals. For example, contacts may provide their names and addresses during an interaction. If the goal is simply to enable the bot to call the customer by name, there's no need to create an entity for the address. Each entity you create also creates a corresponding slot.

This task describes one way to create entities. You can also create new entities as part of creating the intents that will use them.

1. In the Digital First Omnichannel portal, click Chatbot.
2. Click the bot you want to work with.
3. Click NLU in the left icon menu.
4. Click the Entities tab.
5. Click New Entity > Lookup.
   View image

   
6. Enter a name for your new entity and press Enter. Entries are saved automatically.
7. On your new entity, click Add Example. Enter a value for the example and press Enter. Entries are saved automatically. Repeat this step for as many examples as you need.
8. On an example, you can click Add Synonym to add similar words to the example value. Be sure to label them correctly in your intent training examples as well.
   Follow the Planning Example

   After creating the location entity, Akela notices that her customers from New York refer to their location in several different ways. She creates an entity example for New York under location, then adds the synonyms NY and Big Apple. Now, when customers use NY or Big Apple in a conversation, the bot will know to extract that to the value of New York.

   View image

   

Create Entities Using Regular Expressions

Required permission: Chatbot (ACD > DFO > Roles > [choose one] > Core Modules)

A regular expression (regex) is a sequence of characters that specifies a search pattern. Creating a regular expression to extract entities teaches your bot Virtual agent designed to handle specific interactions a pattern to look for to identify the correct information for that entity Defined keyword or phrase, with or without variants, in an interaction or message. You should have at least two intent What the contact wants to communicate or accomplish examples with the regex entity in your training data to help your bot learn the association.

There are three types of regexes you can create:

• Phone Number—This is a predefined regex pattern. You can use it without any additional configuration.
• Email—This is a predefined regex pattern. You can use it without any additional configuration.
• Custom—This pattern allows you to define your own regex. See the planning example below.

1. In the Digital First Omnichannel portal, click Chatbot.
2. Click the bot you want to work with.
3. Click NLU in the left icon menu.
4. Click the Entities tab.
5. Click New Entity > Regex.
   View image

   
6. Enter a name for your new entity and press Enter. Entries are saved automatically.
7. On your new entity:
   1. Choose the Pattern type from the drop-down.
   2. Enter your Regular Expression.
   3. Enter several Test phrases. Any that match the pattern of your expression are highlighted in green.
   View image

   
8. Include the entity in at least two intent examples so the NLU model can correctly register the association.

Create Intents to Extract Entities

Required permission: Chatbot (ACD > DFO > Roles > [choose one] > Core Modules)

When you create an intent What the contact wants to communicate or accomplish for extracting entities, your examples teach your bot Virtual agent designed to handle specific interactions how to identify the correct information for that entity Defined keyword or phrase, with or without variants, in an interaction or message.

1. In the Digital First Omnichannel portal, click Chatbot.
2. Click the bot you want to work with.
3. Click NLU in the left icon menu.
4. Click New Intent.
   View image

   
5. Enter a name for your new intent and press Enter.
6. Beneath the new intent, begin entering phrases that the bot should recognize for that intent. Separate phrases by pressing Enter. Entries are saved automatically.
   View image

   
7. Once you have entered all your phrase examples, right-click on the location in the first example. Then click the words in the phrase that match the entity you want to use. You can hold Shift and click if you need to select multiple words. In the pop-up dialog, click the correct entity. If the correct entity doesn't exist yet, you can enter it in the Type entity name field and then click Create entity "..." to create it.
   View image

   In the following image, Akela has selected Salt Lake City as matching her location entity. In the preceding image, you can see the result when she followed this step for the Columbus location.