Duplicate an NLU model

  • 릴리스 버전: Australia
  • 업데이트 날짜 2026년 03월 12일
  • 소요 시간: 3분
  • Duplicate an existing Natural Language Understanding (NLU) model to create a new one. Duplicating a model copies the settings and contents of the original model, including its default test set.

    시작하기 전에

    • Make sure that the NLU Workbench plugin, NLU Workbench - Core plugin, and Predictive Intelligence plugin are all installed and activated on your instance.
    • Identify an existing NLU model to copy from. The source model should have the language and purpose you want for the new model. If a suitable model does not exist, create and train one.
    • Role required: nlu_admin or admin.

    이 태스크 정보

    In this example procedure, you've already created a model that's titled NLU for Access Requests. You want to customize it for another department. You duplicate the model to create a new, separate model. To customize the new model, you then add content related to the other department.

    프로시저

    1. Set your scope to the scope of the model you want to create.
      After creation, these model settings cannot be changed: language, purpose, scope.
    2. Navigate to All > NLU Workbench > Models.
    3. On the far right column of the model list, select the More options menu for the model you want to duplicate.

      More options menu with Duplicate this model selected.

    4. Select Duplicate this model.
    5. In the Duplicate this Model window, enter a name and description for the new model.

      Duplicate this Model window.

      In this example scenario, you enter NLU for Access Requests Copy1 for the description.
    6. Click Duplicate.
      The system duplicates the model. The Model details page loads for your new model.

    다음에 수행할 작업

    You can customize the new model by adding new content to it. Train, test, and publish the new model. For more information, see Build and train your model.

    To duplicate an entire model group, or one of the models in a group, see Multilingual model management.

    To transfer a model to a different instance, see Add an NLU model to an update set.