Applying changes to a text analytics model for an email bot
To add the reviewed training records to Pega Email Bot so that the system recognizes more information in emails, apply the modified records to the text analytics model. By applying these changes, you can build the model with additional classified training data, which improves how the email bot responds to emails topic, entity, and language detection in the user input.The email bot records training data with incoming email when you enable the recording of training data, or when you create data records manually for the system.
- Start the recording of training data in the email bot. For more information, see Enabling the training data recording for an email bot
- Modify training data in the email bot. For more information, see Correcting training data in an email bot.
- Add sample training data to the system. For more information, see Creating training data manually for an email bot.
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.
On the Email channel configuration page, click the Training data tab.
If you configure multiple languages for the email bot, to filter data records by a language, in the Language list, select a language.To display data records only detected in the English language, select English.
In the list of training records, select the check boxes for the records that you want to add to the model, and then click Mark reviewed.
Click the More icon next to the Add records button, and then click Build model.
- Training data for the Email channel
To use Pega Email Bot in your application to seamlessly respond to user problems, train the system to recognize different user input in emails, such as help requests or issues. When you train the data for the email bot, the system learns from training records, improves the artificial intelligence algorithms, and provides better responses to user input.