How do I manage my conversation entities, slots, synonyms?
To view your assistant's entities, navigate to the Entities tab in the Model Quickview or NLU Manager.
Creating Entites
To create a New Entity, hit the + icon in the Search Entities bar. You’ll see a New Entity creation screen that’s ready to be populated.
When creating a new entity, you’ll need to enter:
- Entity Name - you will notice the curly-braced {} in a colored box populate as you input a name; this will be how you invoke/input the entity in Intent utterances or any other applicable part of your assistant
- Entity Type - the type of data the entity is capturing
- Entity Values - its potential values (available when using Custom Entities)
- Entity Synonyms (optional) - the alternative slot values/variations of the entity values that can classify the Entity slot
- Entity Color - this does not affect your end-user experience, it helps organize your Model Manager experience
Entity Type
Entity types indicate the type of data the entity is capturing. Depending on your assistant type, you will notice a dropdown of various entity types available for your building experience.
In Voiceflow, there are two ways to categorize entities:
Custom Entities: These are the entities that can be defined by the conversation designer as per their use case.
System-Defined Entities: The system entities are commonly used entities that are pre-defined in the system, dependant on channel/assistant-type.
Channels like Alexa may have existing-defined Entity types like "FirstName". These channel-specific and/or assistant-type entities will have thousands of built-in examples - saves you from having to enter thousands of names.
System-Defined Entities In Voiceflow
In Voiceflow, there are a 14 pre-defined entity types for English based projects.
- NAME: Describes the name of a person, including first names, last names, or full names. For example, when asking for a user's name, they might reply with "Louise" or "Jen Zhong."
- EMAIL: Represents an email address. Useful in scenarios where you need to contact the user or send them information. An example response might be "bob@voiceflow.com."
- PHONENUMBER: Captures phone numbers. It's applicable in situations where the user needs to provide a contact number, such as "(650) 253-0000"
- PERCENTAGE: Recognizes percentages, whether written in symbols or words. This could be used when discussing completion rates, like "8 percent" of a task being done.
- GEOGRAPHY: Relates to geographical locations such as cities, countries, continents. A user may mention they are located in "South America."
- NUMBER: Identifies numerical values, which can range from integers to more complex numbers like "259223723" or phrases such as "four hundred and twenty one."
- TEMPERATURE: Deals with temperature values, which could be used for setting or querying climate control settings, like "18 below" Celsius.
- DIMENSION: Pertains to measurements including length, volume, area, etc. It could be used in logistics, for instance, when a user says a package is "86 square feet."
- DATETIME: Captures dates and times in various formats. If a user is making an appointment, they might say "21/02/2018" or "Today."
- CURRENCY: Refers to monetary amounts in various currencies. This would be useful in transactions, like when a user states their budget is "5 pounds."
- AGE: Indicates the age of a person. It could be used in any context where age is relevant, like a user stating "I am 54."
- KEY_PHRASE: Deprecated: A concept or subject to capture. Best to use a custom entity.
- URL: Captures web addresses. When asking for a source of information, a user might provide "https://en.wikipedia.org/."
- ORDINAL: Recognizes ordinal numbers that denote position or sequence, like "first" in a race or "23rd" in a series.
Extending System Defined Entities
If you have a specific pattern that you are expecting, you can extend the entity.
- For example if you are looking for 5 digit numbers, you can either create a number intent and add examples of 5 digit numbers, or use a custom intent.
- If your entity is surrounded by certain terms like “Hi my name is Bob”, adding example utterances to the capture or intent step are helpful.
Custom Entities
If there isn't an existing built-in Entity type for your use case, you will have to build a Custom Entity type. When building a Custom Entity type, you will manually or bulk-import the values you want your Entities to be able to capture.
Entity Synonyms
Entity synonyms let you enter variations of what a user could say to incite the value of a particular Entity.
Bulk Import Entities
Similarly to bulk importing Intent utterances, you are also able to bulk-import Entities and its synonyms.
You can also do so by clicking the cloud icon next to the Entity Type. You can also import your data via the in-line editor or as a (.csv) file.
Comments
0 comments
Please sign in to leave a comment.