Adding a text analyzer for an email bot

To provide better responses by Pega Email Bot, you can configure one or more advanced text analyzers for an application. In this case, the text analyzers examine user input one by one, until the system finds a response.

Before you begin: To configure the Dialogflow text analyzer, first obtain and install the Dialogflow text analyzer component from Pega Marketplace. For more information, see Installing the Dialogflow component.

You can configure each text analyzer to serve a different purpose to help the email bot respond correctly. For example, you can configure the first text analyzer to detect only entities or topics in the email body, another one to detect only entities or topics in the email attachments, and a third one to detect entities or topics in both the email body and attachments.

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 Email channel.
In the Email channel, click the Behavior tab.
In the Text Analyzer section, select the Use advanced configuration check box.
In the advanced configuration mode, you configure the advanced text analyzers that use NLP and adaptive analytics. If you do not use advanced configuration, you configure the default text analyzer that exactly matches user input to a response. For more information, see Exploring text analyzers.
In the Text Analyzer section, select a method for configuring a text analyzer:
- To create a text analyzer, click Add text analyzer.
- To edit an existing text analyzer, click the Switch to edit mode icon next to the text analyzer that you want to edit.

In the Text analyzer type list, select and configure a text analyzer:

Choices	Actions
Pega NLP	Configure an advanced text analyzer that uses the best approximate match by using advanced natural language processing (NLP) and artificial intelligence: Select whether to detect entities or topics in the context of the email body, attachments, or both. In the Text analyzer rule field, select or enter a text analyzer rule. To modify the text analyzer rule settings, click the Open text analyzer rule field.
iNLP	Configure an advanced intelligent NLP text analyzer that uses adaptive analytics text analysis: Select whether to detect entities or topics in the context of the email body, attachments, or both. To modify the text analyzer rule settings, click the Open text analyzer rule field. This type of analysis integrates text analytics with strategies, propositions, and interaction history to provide the context for making better next-best-action decisions. For more information, see Customizable Interaction API for text analytics.
Dialogflow	Configure an external NLP and entity extraction solution from Google: Select whether to detect entities or topics in the context of the email body, attachments, or both. In the Dialogflow client access token field, enter the client access token API key for the Dialogflow agent. In the Dialogflow developer access token field, enter the developer access token API key for the Dialogflow agent.

Choices

Actions

Pega NLP

Configure an advanced text analyzer that uses the best approximate match by using advanced natural language processing (NLP) and artificial intelligence:

Select whether to detect entities or topics in the context of the email body, attachments, or both.
In the Text analyzer rule field, select or enter a text analyzer rule.
To modify the text analyzer rule settings, click the Open text analyzer rule field.

iNLP

Configure an advanced intelligent NLP text analyzer that uses adaptive analytics text analysis:

Select whether to detect entities or topics in the context of the email body, attachments, or both.
To modify the text analyzer rule settings, click the Open text analyzer rule field.

This type of analysis integrates text analytics with strategies, propositions, and interaction history to provide the context for making better next-best-action decisions. For more information, see Customizable Interaction API for text analytics.

Dialogflow

Configure an external NLP and entity extraction solution from Google:

Select whether to detect entities or topics in the context of the email body, attachments, or both.
In the Dialogflow client access token field, enter the client access token API key for the Dialogflow agent.
In the Dialogflow developer access token field, enter the developer access token API key for the Dialogflow agent.

Optional: To enable subject analysis in email, select the Enable subject analysis check box.
For more information, see Enabling subject analysis in email.
Optional: To enable email attachments analysis in email, in the Analyze email attachments list, specify how you want to analyze email attachments:
- To always analyze email attachments, click Always.
- To analyze email attachments based on a when rule, click When, and then in the adjacent field select or define a when rule.
For more information, see Enabling email attachments analysis during email triage.
Click Submit.
Optional: To add or configure more text analyzers for the email bot, repeat steps 5 through 9.
Click Save.

What to do next: Define topics for text analysis in the email bot. For more information, see Defining topics for text analysis for an email bot.