Skip to main content


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

Enabling training data recording for an IVA

Updated on February 10, 2023

To help Pega Intelligent Virtual Assistant™ (IVA) make better predictions when responding to users, enable the recording of training data in the system. You can then modify and classify the training data by reviewing the data and applying changes to the text analytics model. As a result, you ensure that the IVA correctly detects the topics and entities in chat conversations with users.

Before you begin: Build an IVA, for example, for Digital Messaging. For more information, see Creating a Digital Messaging channel.
  1. In the navigation pane of App Studio, click Channels.
  2. In the Current channel interfaces section, click the icon that represents your existing Alexa, Digital Messaging, or Legacy Webchat channel.
  3. In the channel, click the Behavior tab.
  4. In the Text Analyzer section, activate the recording of training data:
    ChoicesAction
    For the default text analyzer
    1. Select the Enable model training checkbox.
    For advanced configuration
    1. Select the Use advanced configuration checkbox.
    2. In the text analyzer list, click the Switch to edit mode icon for a text analyzer.
    3. In the Text analyzer configuration window, select the Enable model training checkbox.
    4. Click Submit.
  5. Click Save.
For example: The following figure shows the section with the default text analyzer configuration where you enable the training data recording for a chatbot:
The default text analyzer configuration for an IVA
The default text analyzer configuration on the Behavior tab for an IVA channel.

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