Detect information with entities

Chatlayer has 4 types of entities: match, contextual, system, and composite.

Entities are pieces of information that can be extracted from something that the user says.

When an entity is detected, it is saved as a variable, which means that you can re-use that piece of information later.

Access your entities under the Entities tab.

Detect information from what the user says by using entities.

On Chatlayer text fields, entities are noted with an@sign in front of them.

All entities are only detected after you've trained your NLP at least once. Every time you change, add, or delete an entity, you should train the NLP again.

Entity types

Chatlayer offers 4 types of entities;

Match entities

If the user states something that is part of a predefined list or matches a certain pattern, it will be detected as a match entity.

E.g.: I want to know more about the Premium pack → @product: Premium

Contextual entities

Train your NLP so it can recognise entities that depend on the context of an expression.

E.g.: Book a train ticket from Brussels to Amsterdam → @origin: Brussels, @destination: Amsterdam

Composite entities

A combination of different, but related entities.

E.g.: Two fries please → @order consists of @sys.number (2) and @foodItem (fries)

System entities

Entities that are pre-built on Chatlayer and that match a certain widely used pattern, like email or phone number.

E.g.: My email address is [e-mail] → @sys.email: [e-mail]

How to choose an entity

Decision tree on when to use which entities.

Entities should only be used if their value is needed in bot conversations. For example, if your bot helps users find information about a specific product, you should use entities to get the product name for database queries. However, if your bot merely redirects users to a webpage with all products, entities are unnecessary.