Links may not function; however, this content may be relevant to outdated versions of the product.
Creating entities for an IVA
Ensure that Pega Intelligent Virtual Assistant™ (IVA) detects the correct information in chat sessions by creating entities. Entities enable the IVA to extract pieces of data from within a chat message, such as a location, date, or postal code. For example, if you want the system to detect vehicle makes in user input, you can create the CarMake entity. At run time, your IVA then uses the detected information and maps it to case type properties, to provide the correct response to user requests and save time for the users handing the case.
- In the header of Dev Studio, click the name of the application, and then click Channels and interfaces.
- In the Current channel interfaces section, click the icon that represents your existing Alexa, Unified Messaging, or Web Chatbot channel.
- In the channel, click the Behavior tab.
- At the top of the preview console, turn on the Show analysis switch.
- In the preview console, in the right panel input field, enter a sample
For example: For car insurance quote, enter: I would like to request a car insurance quote for my Ford Mustang GT.. Result: The analysis in the preview console shows the sentiment of the user input (positive, negative, neutral), the detected topic, the confidence in the detected topic (as a percentage), and the detected entities.
- In the displayed text for the question that you entered in the previous step,
in the create case section, highlight and right-click the text that you want to
map to the new entity, and then click New entity.
For example: To select a car make in the user input, highlight the word Ford.
- In the Create new entity window, in the Entity
name field, enter a name for the entity, and then click
For example: To create an entity for a car make, enter Car Make.
- To create more entities for detection in user input, repeat steps 6 through 7.
- Click Save.
Previous topic Modifying chatbot response questions Next topic Mapping entities in conversation text