Entities

Entities are pieces of specific information in contact messages, such as names, addresses, phone numbers, order numbers, and item numbers. You can use them to train your Mpower Agent A virtual agent created with CXone Mpower Agent Builder that can handle voice or chat interactions. to extract information from contact utterances What a contact says or types.. Extracted information can be saved to use in Mpower Agent responses. It can also be passed to CXone Mpower, or to third-party databases or applications via integrations.

Contact The person interacting with an agent, IVR, or bot in your contact center. utterances can contain a lot of information. You don't need entities for all of the information. You should only create entities for information that your Mpower Agent needs to accomplish its goals. For example, contacts may provide their first and last name during an interaction. If the goal is simply to enable your Mpower Agent to call the contact by their first name, there's no need to create an entity for the last name or the contact's full name.

When you create an entity, Agent Builder automatically creates a corresponding slot Entity extracted from contact's message and saved for use in bot responses. Similar to a variable. to hold the extracted information. Automatically-created slots must be modified to change the default settings.

Entities are closely related to slots. Slots hold information during an interaction until it's needed. An entity identifies and extracts information from an utterance and stores it in a slot. You can use the slot as a variable to use the information it holds.

Glossary

Concept	Definition	Example	What the Mpower Agent Does
Utterance	Anything a contact The person interacting with an agent, IVR, or bot in your contact center. says in an interaction The full conversation with an agent through a channel. For example, an interaction can be a voice call, email, chat, or social media conversation.. Sometimes called a message.	"I lost my password." "What is my balance?" "Are you a bot?"	The Mpower Agent uses Natural Language Understanding (NLU) to analyze each contact utterance to determine its meaning, or intent.
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 Mpower Agent analyzes a contact's message using NLU 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 your Mpower Agent to use for each intent.
Entity	A defined piece of information in a contact's message.	Person or product name, phone number, account number, location, and so on.	The Mpower Agent uses NLU to identify entities in a contact's message. Entities help the Mpower Agent understand what the contact's message means.
Slot	An entity extracted from a contact's message and saved for use in Mpower Agent responses. Similar to a variable.	Creating a slot for contact name lets the Mpower Agent use that name in responses during an interaction, making it more personal.	When configured to do so, the Mpower Agent extracts an entity from a contact message and saves it in a slot. You can have your Mpower Agent use this information later in the conversation.
Rule	Defines Mpower Agent responses 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. Mpower Agents come with default intents and rules for several of these, including greetings, handover The transfer of a contact from a virtual agent to a live agent. requests, and more. FAQs Insults and classic bot challenges	Rules are one of two ways you can configure how your Mpower Agent responds to an intent. Rules are useful for certain kinds of intents, but not all intents.
Story	Trains an Mpower Agent to handle an interaction based on message intent and conversational context.	In an interaction about a forgotten password, the Mpower Agent 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 your Mpower Agent responds to an intent. Stories teach the Mpower Agent how to use the context of the conversation to respond appropriately.
Mpower Agent Action	Anything an Mpower Agent says or does while handling an interaction.	In an interaction about a forgotten password, the Mpower Agent 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 Mpower Agent responds with "I'm sorry. Would you like me to transfer you to a human agent?" When the contact says yes, the Mpower Agent initiates the transfer.	Mpower Agent actions are the options you have when defining how you want your Mpower Agent to respond to each intent. They give you the flexibility to configure each response to achieve the outcome that meets the contact's needs.

Entity Types

There are two types of entities A piece of information gathered from the contact's messages during conversations with an Mpower Agent. in Agent Builder:

Regular expression (regex): Entities that follow regular patterns, such as phone numbers, order numbers, or email addresses.
Lookup table: Entities that don't follow a pattern, such as ice cream flavors, report titles, sock styles, or colors.

Regular Expression Entities

A regular expression (regex) is a sequence of characters that specifies a search pattern. Creating a regex to extract entities teaches your Mpower Agent a pattern to look for to identify the correct information for that entity. This is useful for data that has similar, regular patterns, such as email addresses, phone numbers, and account or invoice numbers.

You can add a regex entity from either tab in the NLU section in Agent Builder:

Lookup Table Entities

Lookup entities are categories of information. In Agent Builder, they're lists of words, where every word is one member of the category. The list must contain every member of the category that your Mpower Agent needs to know about. For example, if you create an entity for ice cream flavors, you need to provide every flavor that your company offers. You may also want to add flavors that your company doesn't offer but that are frequently requested, so your Mpower Agent can respond to those requests with an out-of-scope path.

You can add a lookup table entity from the NLU section in Agent Builder:

Entities tab
Inbox, when viewing messages
Intents tab, when working with intent examples

Lookup entities are not case-sensitive.

How Entities Work

To have your Mpower Agent extract an entity Keyword or phrase defined in your company profile in Interaction Analytics. Related to an entity type. Can include variants. from an utterance What a contact says or types., you must label it in the appropriate intent The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish. examples and in the dialogues Mpower Agent stories, rules, and flows in Agent Builder. for that intent. Labeling in both places trains your Mpower Agent when to extract an entity, which entity to extract, and to associate the entity with the intent. Labeling is required for regex entities, but not for lookup table entities. However, it's still helpful for lookup table entities.

To label an entity, you must select it in the utterance and then choose the kind of entity that the word or phrase represents. You can do this from the NLU Inbox, in intent examples, and from a story or rule.

During an interaction, the Mpower Agent predicts an intent for an utterance. If the intent contains a labeled entity, the Mpower Agent checks the utterance for a string that matches the pattern established in a regex entity or for one of the examples in a lookup table entity. If it finds a match, the Mpower Agent extracts the value and stores it in the entity's corresponding slot Entity extracted from contact's message and saved for use in bot responses. Similar to a variable.. That information is then available to use during the interaction.

You must configure when and how it's used by utilizing the slot as a variable. You can:

Use it in future Mpower Agent messages sent to the contact.
Use it as a condition to determine the path that the Mpower Agent takes the conversation.
Use it with script and API integrations.

Entities are always extracted and saved in the corresponding slot when the Mpower Agent recognizes them. If the Mpower Agentrecognizes an entity but doesn't have a story Used to train an Mpower Agent for interaction handling based on intent and context. or rule Used to define an Mpower Agent's response to messages that don't change with context. that shows it what to do with the information, it will ignore it. However, the presence of the entity it doesn't know what to do with can lower the Mpower Agent's confidence in predicting the correct intent The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish..

There may be times when you only want your Mpower Agent to fill an entity's slot in certain circumstances. You can configure restrictions on when the Mpower Agent can fill each slot. Restrictions can be based on the intent, a form, or both. Not every slot filling method supports both kinds of restrictions.

Entity Examples and Synonyms

After creating an entity, you must provide examples to help your Mpower Agent learn to recognize it. Examples are different for each type of entity:

For regex entities, examples should be real-world representations of the type of data the Mpower Agent will encounter during interactions. For example, for a phone number entity, use real phone numbers.
For lookup table entities, the examples must be members of the category that the entity represents. For example, the iceCreamFlavors entity might have examples such as chocolate, vanilla, and strawberry. The examples list must contain every member of the category that your Mpower Agent needs to know about. You may want to include members of the category that your organization doesn't use but that contacts may mention.

For lookup table entities, you can also identify synonyms for each example. Synonyms allow you to teach the Mpower Agent the various ways contacts might refer to the same entity value. For example, New York City can also be called NYC, NY, New York, and the Big Apple.

Classic Ice Cream Parlor, a subsidiary of Classics, Inc., sells 10 flavors of ice cream. The Agent Builder administrator, Christopher Robin, lists those flavors as entity examples. There are six other flavors that contacts often request, so , then Christopher adds those as well. Then he creates stories that teach his Mpower Agent how to respond to requests for flavors they don't carry.

Next, Christopher knows that some contacts use other names for the 10 flavors the company stocks, such as calling the Grape Ice flavor Icy Grape. Christopher adds those common synonyms as additional entity examples, then builds stories to teach the Mpower Agent which inventory flavor each synonym goes with.

You can add entity examples and synonyms in the following places in Agent Builder:

The Intents tab, when adding examples to an intent.
The Stories and Rules tabs, when creating a dialogue Mpower Agent stories, rules, and flows in Agent Builder..
The NLU Inbox, when reviewing messages sent to the Mpower Agent.

Label Entities to Teach the Mpower Agent to Use Them

After you create entities A piece of information gathered from the contact's messages during conversations with an Mpower Agent., you need to select and label them in the stories Used to train an Mpower Agent for interaction handling based on intent and context., rules Used to define an Mpower Agent's response to messages that don't change with context., intent The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish. training data, and NLU Inbox messages where they appear. Labeling teaches your Mpower Agent that an entity is important in the context of the intent of the messages where it's labeled. Labeling also:

Adds the highlighted text as an example of the entity you select. If the example already exists, nothing new is added.
Instructs the Mpower Agent to extract that entity from the utterance. You can then use or store the entity's value, such as updating a customer record or configuring the Mpower Agent to use the contact's name in an Mpower Agent response.

Both regex and lookup entities need to be labeled. For regex entities, this is required to teach your Mpower Agent to recognize the regex pattern. For lookup entities, it teaches your Mpower Agent that the entity is an important part of the intent.

You can label entities in stories and rules, intent training data, or NLU Inbox messages.