Create a model to detect case language
Edit and test the pre-trained model to detect the language used to create customer service cases.
- Before you begin
- Role required: ti_admin
- About this task
- The language detection model is a pre-trained model. You select a set of records to test
the model and then view the results before deploying.
Using the language detection model automatically enables the Task Intelligence Case Language Detection flow and the sn_csm_ml_task.case.language.mlpredictor.enabled property.
- Prerequisite
- Activate the I18N: Internationalization plugin
- Enable the ServiceNow translator.
Set up your model
- Navigate to to access the Task Intelligence Admin Console.
- Select Edit model on this model: Predict case language to
improve assignments.
This opens the model and displays the first of four pages. Each page in the model asks you questions and helps you select the information you need to build an effective model.
Test your model
Choose the cases to use to test the model.
- Use conditions to choose a set of records for testing.
- Select Launch testing.
Assess your model
Assess the results from the testing and view sample results for past cases.
- Select View all test results to see a list of results.
- Select Save & continue.
Set your preferences
Tell the model how you want to use the language predictions.
- Use predictions in new cases.
- Add the predicted language in the Language field in cases.
- Use the language prediction as a skill to assist with case routing (add the language skill to the Task Skills table for the case record).
- If desired, you can run the model in the background only.
With this option, the system makes the language predictions and stores the information in the Predictions History but does not add any information to the case records.
- Select Save & continue.
Deploy your model
Review your selections from the previous pages. Then you can select Deploy to deploy the model.