Define topics in Pega Email Bot so that the system determines the best response by
analyzing an email through natural language processing (NLP) and adaptive analytics text
analysis models. Defined topics help the email bot detect and organize suggested responses
and suggested cases in the system.
You can configure multiple languages for the email bot by setting up text analysis
for each language separately. This ensures that the system performs text analysis of
email in the correct language that is detected. For more information, see Selecting languages for an Email channel.
Note: All suggested cases that you define in the system are topics.
-
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.
- Optional:
To enable the advanced configuration mode, in the Text
Analyzer section, select the Use advanced
configuration check box.
In the advanced configuration mode, you configure the advanced text analyzers
in the system 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, click Edit
topics for the text analyzer that you want to edit.
-
In the Edit topics window, click Add
topic.
A topic is the general subject, the intent of an email that the system detects
using text analysis.
-
If you configure multiple languages for the email bot, in the section in the
Edit topics window, click a language.
The supported languages are displayed on a vertical tab. When you add a new
topic or edit an existing topic, you can switch between the languages by
clicking the name of a language.
-
In the table columns, specify a topic and matching criteria:
- In the Topic field, enter the natural language
processing topic for the email bot to use as the response. The NLP text
analyzer determines the topic based on criteria that matches exactly,
matches approximately, and or never matches the user input.
- In the Approximate match field, to configure the
email bot to look for approximate matches in the user input, enter words and
phrases that you want to use, and then separate them with commas. For
example, for an initial greeting responses, enter:
hello, good morning.
- In the Must match field, to configure the email
bot to look for specific items in the email, enter words and phrases that
you want to exactly match in the topic, and separate them with commas. For
example, for initial greeting response, enter
hi.
- In the Never match field, enter comma-separated
words or phrases to always ignore when matching for the topic. For example,
for an initial greeting response to never match a goodbye greeting, enter
bye.
- Optional:
To configure additional languages for the topic, repeat steps 7
through 8.
- Optional:
To add more topics for text analysis, repeat steps 6
through 9.
-
Click Submit.
-
Click Save.
Result: The email bot uses text analysis to match content in the email body or attachments
to a topic, a suggested case or a suggested response.