Defining advanced Facebook text analyzer configuration

Text analyzers process user input and look for matching responses. In the advanced text analyzer configuration for a Facebook channel, you can specify several text analyzer definitions to provide the best response to users. User input is analyzed by the first text analyzer definition in the list, and if no match is found, the second text analyzer definition in the list, and so on, until a response is found.

You can specify whether each text analyzer runs within the context of a case, outside of the context of a case, or both. For example, if you have a case that allows users to buy airline tickets, you can run a text analyzer definition within the context of a case so that when the chatbot asks the user about when to book the flight, the response is automatically converted to a specific date.

The Dialogflow text analyzer is available only if you install the Dialogflow Text Analyzer component from Pega Exchange. You first create a Diagflow agent separately on the Dialogflow developer portal to carry out natural language processing and entity extraction for the Facebook channel interface. When you select the Dialogflow text analyzer during configuration of a Facebook chatbot, you specify the client access token and developer access token API keys for the configured Dialogflow agent. For more information, see the Community Configuring the Dialogflow text analyzer for the Facebook channel article.

Note: To use Pega Intelligent Virtual Assistant for Facebook in your application, you must obtain and install the Facebook channel component from Pega Exchange.
  1. In a Facebook channel interface, click the Behavior tab.
  2. In the Text analyzer section, select the Use advanced configuration check box.
  3. Add a new text analyzer definition to the list:
    1. Click + Add text analyzer.
    2. In the Text Analyzer type list, click a text analyzer. For example, click iNLP or Pega NLP.
    3. Optional: If you select the Pega NLP text analyzer, in the Text Analyzer rule field select a text analyzer rule that contains an NLP definition to use.
    4. Optional: If you select the third-party Dialogflow text analyzer:
      1. In the Dialogflow client access token field, enter the client access token API key for the Dialogflow agent.
      2. In the Dialogflow developer access token field, enter the developer access token API key for the Dialogflow agent.
      3. Click Submit.
    5. Select the Apply in context of a case check box to specify that the text analyzer definition is to run during a process that is specified by a case.
    6. Select the Apply outside of case context check box to specify that the text analyzer definition is to run outside of a process that is specified by case.
    7. Click Submit.
  4. Optional: To configure a text analyzer definition, click the Switch to edit mode icon next to the text analyzer.