Create a pattern entity
Create a pattern entity from a word or phrase with repeatable patterns, such as email addresses and phone numbers. These patterns help the system to recognize similar utterances based on the patterns.
시작하기 전에
- Make sure that the NLU Workbench plugin, NLU Workbench - Core plugin, NLU Common Model plugin, and Predictive Intelligence plugin are all installed and activated on your instance.
- Create or use an existing NLU model for Virtual Agent or AI Search.
- Create or use an existing intent.
- Role required: nlu_editor, nlu_admin, or admin. The nlu_editor must be assigned to the model.
이 태스크 정보
Pattern entities help your model identify, contextualize, and govern similar types of
content. Inputs such as phone numbers and email address follow the same pattern. By
creating a pattern entity, you can train the model to recognize all variations of
those inputs.
주:
Pattern entities use regular expressions (regex). The regex field
value is a Java regular expression. For more information on how to use regex,
see Using regular
expressions in entities.
In this example scenario, you've created an intent that's titled #CheckITTicketStatus. In this example procedure, you're creating a pattern entity for incident record numbers.
프로시저
-
Select one of the words of an utterance.
In this scenario, you click INC1234567.
-
In the Create a new entity window, configure the fields.
For this example procedure, use these configurations:
- Entity Name: Enter incidentnumber
- Type: Select Pattern
- Model Availability: Select this box if you want this entity to be included in all intents in your model
- Regex: Enter INC\d{7}