Skip to main content

Suggested cases

In Pega Customer Service™, natural language processing (NLP) analyzes the customer conversation and suggests cases based on topics that are identified in the conversation. For example, a customer calls U+ Bank support and says, "I want to add my newborn as a dependent." NLP detects newborn and dependent and suggests the Add child dependent case to the CSR. The CSR sees the suggestion in the Interaction Portal.

suggested case in Interaction Portal

You configure the topics that identify a case in the Voice AI channel. To associate topics with a suggested case, you need to:

  • Add the case type to the Voice AI channel.
  • Associate the case type with a topic by adding a create case command.
  • Associate an NLP topic model with the channel.
  • Optionally, add keywords to the topic to "feed" the NLP model and help detect the topic.

Case types

A case type guides the CSR on how to resolve a customer request. The case types that are available to your channel are displayed on the Cases & Data tab of the Application rule form. To view the case types, in Dev Studio, click Application > Definition > Cases & Data.

Application definition, available case types

How Voice AI identifies a topic and suggests a case

Topics are predefined categories Voice AI uses to associate a customer conversation with a case.

To configure a suggested case, you create a Response configuration. On the Response tab, you add a topic, and then associate the topic with a case type. For example, for the Account address change case type, we created a topic named Address change. To associate the case type with the topic, add the topic as the Create case command. If you add a new Create case command, Customer Service adds the command as a topic.

response configuration, suggested case

On the Text analysis tab of the Response configuration dialog box, you add keywords that a customer might say when calling about an address change, for example, address, moving, and moved. These keywords become part of the topic model for the channel.

A data scientist defines an NLP topic model for each channel. The topic model analyzes the live conversation and identifies which topic (Claims inquiry, Add newborn, Update my address) to suggest to the CSR. The words you add on the Text Analysis tab seed the model. The topic model learns new words to associate with the case from each customer conversation. A data scientist can view and make changes to the model in the Prediction Studio.

Prediction Studio for Voice AI channel

This Topic is available in the following Modules:

If you are having problems with your training, please review the Pega Academy Support FAQs.

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 Academy has detected you are using a browser which may prevent you from experiencing the site as intended. To improve your experience, please update your browser.

Close Deprecation Notice