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.
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.
- In the navigation pane of
App Studio, click Channels.
- In the Current channel interfaces section, click the icon
that represents your existing Unified Messaging or Web Chatbot
- In the channel, click the Training data tab.
- In the list of training records, select the check boxes for the records that
you want to add to the model, and then click Mark
- Click the More icon next to the Add
records button, and then click Build