Skip to main content

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

Applying changes to a text analytics model for an IVA

Updated on February 10, 2023

To update Pega Intelligent Virtual Assistant™ (IVA) with training records that you have reviewed, so that the system extracts the correct information from a chat conversation, apply the modified records to the text analytics model. By applying these changes, you rebuild the model with the additional training data, which improves the accuracy of IVA detection of topics and entities in user input.

The IVA records training data from a chat conversation when you enable the recording of training data, or when you create data records manually for the system.
Note: You can apply changes to the text analytics model only if training data exists for the IVA channel.
Before you begin: Prepare some sample training data for the text analytics model. For more information, see Enabling training data recording for an IVA.
  1. In the navigation pane of App Studio, click Channels.
  2. In the Current channel interfaces section, click the icon that represents your existing Digital Messaging or Legacy Webchat channel.
  3. In the channel, click the Training data tab.
  4. In the list of training records, select the checkboxes for the records that you want to add to the model, and then click Mark reviewed.
  5. Click the More icon next to the Add records button, and then click Build model.
What to do next: Verify the text analytics model for the IVA by using the preview console to test how the system responds, and what it detects from the input. For more information, see Simulating a conversation and building a chatbot.
  • Previous topic Transferring training data to another IVA
  • Next topic Best practices when training model-based entities in an IVA

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

Close Deprecation Notice
Contact us