Skip to main content


         This documentation site is for previous versions. Visit our new documentation site for current releases.      
 

Creating training data

Updated on March 16, 2021

Ensure that the natural language processing (NLP) engine provides helpful suggestions to your CSRs by adding training records to your Voice AI configuration. Each training record is a combination of a topic and an associated word or phrase that is relevant to your organization.

Pega Customer Service Implementation Guide

You can configure the Voice AI channel to collect training data from live interactions and automatically add training records based on that data. For more information, see Configuring text prediction.

  1. In the navigation pane of App Studio, click Channels.
  2. In the Current channel interfaces section, select the Voice AI channel interface for which you want to create training data.
  3. On the channel configuration page, select the Training data tab.
  4. Click Add records.
  5. In the Create new training record dialog box, select a topic, and then enter the keywords that you want to associate with the topic.
  6. Click Create record.
  7. Optional: To add additional records, repeat steps 5 and 6.
  8. Close the Create new training record dialog box.
    Result: The Training data landing page displays the new training records.
  9. Build the training records that you created into your NLP model by selecting the records, and then clicking Mark reviewed:
    Note: Only reviewed records trigger case and knowledge suggestions to CSRs.
    • To select specific records, select the individual records.
    • To select all records, use the Select all checkbox.
    Result: The Training data landing page no longer displays the records, which wait in the queue to be built into your NLP model.
  10. To update the NLP model, click the ellipses icon beside the Add records button, and then select Build Model.
  11. Save your updates to the channel configuration by clicking Save.

Have a question? Get answers now.

Visit the Support Center to ask questions, engage in discussions, share ideas, and help others.

Did you find this content helpful?

Want to help us improve this content?

We'd prefer it if you saw us at our best.

Pega.com is not optimized for Internet Explorer. For the optimal experience, please use:

Close Deprecation Notice
Contact us