Set Up Entities

Entities are pieces of specific information in contact messages, such as names, addresses, phone numbers, order numbers, and item numbers. You can extract the information to use in bot conversations.

After you create entities, you need to label examples of them in stories and rules, intent training data, or NLU Inbox messages. Labeling identifies words or phrases as entities, which tells the bot they're important for the intent of the message where you label them.

Concept Definition Example What the Bot Does
Message envelope icon

Utterance

Anything a contact says in an interaction. Sometimes called a message.

"I lost my password."

"What is my balance?"

"Are you a bot?"

 The bot uses Natural Language Understanding (NLU) to analyze each contact utterance to determine its meaning, or intent.
Magnifying glass icon

Intent

What the contact wants to communicate or accomplish. Every message the contact sends has an intent.

"I lost my password" has the intent of "reset password".

"Hello" has the intent of "greeting".

The bot analyzes a contact's message using NLUClosed This process expands on Natural Language Processing (NLP) to make decisions or take action based on what it understands. to determine the intent. Once it knows that, it can respond with a message of its own. You configure the response you want the bot to use for each intent.
Information icon

Entity

A defined piece of information in a contact's message. Person or product name, phone number, account number, location, and so on. The bot uses NLU to identify entities in a contact's message. Entities help the bot understand what the contact's message means.
Slot icon

Slot

An entity extracted from a contact's message and saved for use in bot responses. Similar to a variable. Creating a slot for contact name lets the bot use that name in responses during an interaction, making it more personal. When configured to do so, the bot extracts an entity from a contact message and saves it in a slot. You can have the bot use this information later in the conversation.
Rule icon

Rule

Defines a bot's response to messages that don't change meaning with context.
  • Single-turn interactions with fixed responses: What are your hours? What is your address?
  • Conversation building blocks: Greetings, good-byes, thank yous and transitions; simple yes/no questions; and acknowledgments. CXone Bot Builder comes with default intents and rules for several of these, including greetings, handoverClosed Any contact message that should trigger transfer to a live agent requests, and more.
  • FAQs
  • Insults and classic bot challenges
Rules are one of two ways you can configure how the bot responds to an intent. Rules are useful for certain kinds of intents, but not all intents.
Story icon

Story

Trains a bot to handle an interaction based on message intent and conversational context. In an interaction about a forgotten password, the bot would respond to, "How do I do that?" in one way. If the interaction were about creating a new account, the response would be quite different even though in both cases the contact is using the same words with the same intent – to get more information. Stories are the second of two ways you can configure how the bot responds to an intent. Stories teach the bot how to use the context of the conversation to respond appropriately.
Action icon, notated by three cogs

Bot Action

Anything a bot says or does while handling an interaction.

In an interaction about a forgotten password, the bot responds by sending the link to the password reset FAQ on the website.

When a contact expresses frustration, such as "I don't understand! It's not working!!!" the bot responds with "I'm sorry. Would you like me to transfer you to a human agent?" When the contact says yes, the bot initiates the transfer.

Actions are the options you have when defining how you want the bot to respond to each intent. They give you the flexibility to configure each response to achieve the outcome that meets the contact's needs.

Create Lookup Table Entities

This task describes one way to create lookup table entities. You can also create them on the Intents tab or in the NLU Inbox.

Akela Wolf already has a working bot to help her users with password resets. She wants to enable her bot to start asking for the user's location. She adjusts her happy pathClosed Story that produces the correct outcome for the intent to look like this:

Customer: Hello.

Bot: Hello. How can I help you?

Customer: I forgot my password.

Bot: I'm sorry to hear that. First, which office location are you at?

Customer: I'm at the Columbus office.

Bot: Thanks.

Based on this revision, Akela decides to create an entity called Location.

  1. In CXone, click the app selector and select Bot Builder.

  2. Click the bot you want to work with.
  3. Click NLU icon, which looks like a gear inside a head silhouette. in the left icon menu.

  4. Click the Entities tab.

  5. Locate the folder your new entity should go in. You can also click New Folder icon, indicated by a plus sign inside a circle., enter a name, and press Enter.

  6. Hover over the folder name and click New Entity > Lookup.

    Screenshot showing entry of a new plain text entity
  7. Enter a name and press Enter. Changes are saved automatically.
  8. On your new entity, click Add Example . Enter a value for the example and press Enter. Changes are saved automatically. Repeat this step for as many examples as you need. Add examples that you bot needs to be able to recognize. For example, if your bot collects a Location entity, add examples for every office location your organization has.

  9. On an example, you can click Add Synonym to add similar words to the example value. Do this when one of your entities could be called something else. For example, New York City is sometimes called NY and the Big Apple. When you label entities in stories and rules, intent training data, or NLU Inbox messages, be sure to label synonyms too.

    List of entity examples, with one showing synonyms

Create a Regex Entity

A regular expression (regex) is a sequence of characters that specifies a search pattern. Creating a regular expression to extract entities teaches your botClosed A software application that handles customer interactions in place of a live human agent. a pattern to look for to identify the correct information for that entityClosed Keyword or phrase defined in your company profile in Interaction Analytics. Related to an entity type. Can include variants.. You should have at least two intentClosed The meaning or purpose behind what a contact says/types; 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.

You can learn about working with regular expressions at https://regexr.com/ A square with an arrow pointing from the center to the upper right corner..

Akela Wolf noticed that a lot of her bot's conversations included a customer's invoice number. She wants to create a custom regular expression pattern to enable her bot to extract an entity for invoice number.

The invoice numbers for Akela's customers always start with #IN, followed by exactly eight digits. So, she writes a custom regex pattern that reads:

#IN\d{8,8}\b

Now, whenever a user message contains a sequence that starts with "#IN" and contains exactly 8 digits, it will be extracted as an invoice number entity.

  1. In CXone, click the app selector and select Bot Builder.

  2. Click the bot you want to work with.
  3. Click NLU icon, which looks like a gear inside a head silhouette. in the left icon menu.

  4. Click the Entities tab.

  5. Locate the folder your new entity should go in. You can also click New Folder icon, indicated by a plus sign inside a circle., enter a name, and press Enter.

  6. Hover over the folder name and click New Entity > Regex.

    Screenshot showing entry of a new regex entity
  7. Enter a name and press Enter. Changes are saved automatically.
  8. On your new entity:
    1. Choose the Pattern type from the drop-down.
    2. Enter your Regular Expression. Learn more about regular expressions at https://regexr.com/ A square with an arrow pointing from the center to the upper right corner..
    3. Enter several Test phrases. Any that match the pattern of your expression are highlighted in green.
    Screenshot of the fields to create a regex entity
  9. Label the entity in at least two intent examples so the NLU model can correctly register the association.

Create a New Entity from an Intent or the NLU Inbox

You can create new entitiesClosed A piece of information gathered from the contact's messages during conversations with a bot. from the Intent tab or the NLU inbox in Bot Builder. This allows you to create entities on the fly when working with intentsClosed The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish or reviewing contact utterancesClosed What a contact says or types..

  1. In CXone, click the app selector and select Bot Builder.

  2. Click the bot you want to work with.
  3. Click NLU icon, which looks like a gear inside a head silhouette. in the left icon menu.
  4. Do one of the following:
    • To create an entity from an intent: Click the Intent tab, then select the intent you want to work with.
    • To create an entity from the NLU Inbox: Click Inbox, then locate the message you want to work with.
  5. Select the word or phrase in the intent example or inbox message that represents the entity. For example, for a phone number entity, select the phone number. If the entity example is made up of more than one word, click each word. Bot Builder highlights the words.

  6. Click an entity type in the pop-up menu.

    Option Details
    Lookup Icon of three stacked horizontal lines.

    Select this option if you're adding an example of a lookup entity.

    Lookup tables establish patterns for identifying similar entities. They're useful for categories of things, such as products or ice cream flavors.

    Regex Icon of a dot and an asterisk next to each other.

    Select this option if you're adding an example of a regex entity.

    Use this option for entities that follow specific patterns that identify them, such as email addresses or account numbers.

    Synonym Icon of a filled-in circle with a curved line next to it.

    Select this option if you're adding a synonym of an existing lookup entity.

    Synonyms are other ways a contact might refer to an existing entity. For example, New York City has synonyms such as NYC and the Big Apple.

  7. Enter the name of the entity in the Type entity name field.

  8. Click Create Entity "[name]".

  9. If you want to add the word or phrase you selected at the beginning of this task as an example of your new entity, you must follow the steps to add an entity example from an intent or from the NLU Inbox.

Label and Add Entity Examples or Synonyms in Intent Training Data

Intent training data consists of all the examples you've added to your intentsClosed The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish. Labeling entityClosed A piece of information gathered from the contact's messages during conversations with a bot. examples adds them to the associated entity if they're not already present. It also teaches your bot that the entity is important for the intent associated with the message containing the entity.

  1. In CXone, click the app selector and select Bot Builder.

  2. Click the bot you want to work with.
  3. Click NLU icon, which looks like a gear inside a head silhouette. in the left icon menu.

  4. On the Intents tab, click the intent you want to work with.

  5. In an intent example, click the word or phrase that makes up the entity.

  6. Select an option from the pop-up menu for the type of entity you're working with.

    An entity selected in a training data example.
    Option Details
    Lookup Icon of three stacked horizontal lines.

    Select this option if you're adding an example of a lookup entity.

    Lookup tables establish patterns for identifying similar entities. They're useful for categories of things, such as products or ice cream flavors.

    Regex Icon of a dot and an asterisk next to each other.

    Select this option if you're adding an example of a regex entity.

    Use this option for entities that follow specific patterns that identify them, such as email addresses or account numbers.

    Synonym Icon of a filled-in circle with a curved line next to it.

    Select this option if you're adding a synonym of an existing lookup entity.

    Synonyms are other ways a contact might refer to an existing entity. For example, New York City has synonyms such as NYC and the Big Apple.

  7. If you're adding thes selected word or phrase as an example of a lookup or regex entity, follow these steps: 
    1. Enter the name of the entity in the search bar on the pop-up menu. For example, if you're adding a contact's office location as an entity example, enter the name of the entity for office location, such as Location.

    2. Click the matching entity name in the search results. Bot Builder adds the selected word or phrase as an entity example.

      Image shows adding an example to the Location entity from an intent example.

    3. If the entity you want doesn't exist, click Create Entity "[name]" to create an entity with the name you entered. Reselect the entity example and repeat the steps in this task to add it to the new entity.

  8.  If you're adding a synonym of an existing entity example, follow these steps: 
    1. Enter the name of the entity in the search bar. For example, location.

    2. Click the name of the entity example in the search results. For example, if you're adding NYC as a synonym for the New York, click New York City under the Location entity.

      Image showing adding NYC as a synonym of New York City.

Label and Add Entity Examples or Synonyms from the NLU Inbox

The NLU Inbox displays all new contact utterancesClosed What a contact says or types.. You can add entity examples from utterance messages viewed in the NLU Inbox.

Labeling entityClosed A piece of information gathered from the contact's messages during conversations with a bot. examples adds them to the associated entity if they're not already present. It also teaches your bot that the entity is important for the intent associated with the message containing the entity.

  1. In CXone, click the app selector and select Bot Builder.

  2. Click the bot you want to work with.
  3. Click NLU icon, which looks like a gear inside a head silhouette. in the left icon menu.

  4. On the Intents tab, click Inbox.

  5. In a message, click the word or phrase that makes up the entity.

  6. Select an option from the pop-up menu for the type of entity you're working with.

    An entity selected in an NLU Inbox message.
    Option Details
    Lookup Icon of three stacked horizontal lines.

    Select this option if you're adding an example of a lookup entity.

    Lookup tables establish patterns for identifying similar entities. They're useful for categories of things, such as products or ice cream flavors.

    Regex Icon of a dot and an asterisk next to each other.

    Select this option if you're adding an example of a regex entity.

    Use this option for entities that follow specific patterns that identify them, such as email addresses or account numbers.

    Synonym Icon of a filled-in circle with a curved line next to it.

    Select this option if you're adding a synonym of an existing lookup entity.

    Synonyms are other ways a contact might refer to an existing entity. For example, New York City has synonyms such as NYC and the Big Apple.

  7. If you're adding thes selected word or phrase as an example of a lookup or regex entity, follow these steps: 
    1. Enter the name of the entity in the search bar on the pop-up menu. For example, if you're adding a contact's office location as an entity example, enter the name of the entity for office location, such as Location.

    2. Click the matching entity name in the search results. Bot Builder adds the selected word or phrase as an entity example.

      Image shows adding an example to the Location entity from an NLU Inbox message

    3. If the entity you want doesn't exist, click Create Entity "[name]" to create an entity with the name you entered. Reselect the entity example and repeat the steps in this task to add it to the new entity.

  8.  If you're adding a synonym of an existing entity example, follow these steps: 
    1. Enter the name of the entity in the search bar. For example, location.

    2. Click the name of the entity example in the search results. For example, if you're adding NYC as a synonym for the New York, click New York City under the Location entity.

      Image showing adding NYC as a synonym of New York City.