Use the prebuilt Natural Language Understanding (NLU) models in the NLU Workbench to create a new one.
始める前に
Make sure that the NLU Workbench plugin, NLU Workbench - Core plugin, and Predictive Intelligence plugin are all installed and activated on your instance.
You can create NLU models for Virtual Agent
and AI Search.
Role required: nlu_admin or admin.
このタスクについて
In this example procedure, you're building an NLU model based on the prebuilt HR NLU for VA model. You base your model on the prebuilt model, then edit or add to the model content to meet your business requirements.
Your new model contains intents, entities, and vocabulary from the prebuilt model. The new model also contains an empty default test set, ready to be populated with test utterances.
手順
Set your scope to the application scope you want for your new model.
Navigate to All > NLU Workbench > Models.
The Virtual Agent tab opens by default.
Select the tab for the type of model you want to create, such as AI Search.
Select the Create new model button.
In the How do you want to create your model? window, select
Use prebuilt model.
On the Add some details window, fill in the
Name and Short description for
the model.
In this example scenario, you enter Human Resources VA
Model for the name and Virtual Agent Model for
responding to HR Requests for the short description.
Select the language and purpose from the drop-down lists.
In this example scenario, you select English and
Virtual Agent.
オプション: Select the business area for the model.
In this example scenario, you select HR.
Click Next.
Select the prebuilt model from the drop-down list.
In this example scenario, you select HR NLU for VA.
Select Next.
On the Select intents screen, select the prebuilt intents to add to your model.
In this example scenario, you select 10 intents from the list.
注:
You can select all the prebuilt intents by checking the Intent box at the top of the list.
Select Next.
Your model starts building. After completion, select View
model to open the Model details page for
your new model.
次のタスク
Add more intents and training utterances to continue building the
model. Update entities and vocabulary to help the model understand inputs from your
users. For more information, see Build and train your model.
Add test utterances and intents to build the model's default test set. For
more information, see Test set creation and management.