Training the model 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 other issues. When you train the text analytics model for the email bot, the system learns from training records, which improves the artificial intelligence algorithms and provides better responses to user input.For example, you train the model for the email bot and apply the changes to the model. Based on the detected topic, entities, sentiment, language in emails, and intelligent email routing, the email bot then runs automated tasks, such as starting a business case and sending an automatic reply to the user.
To ensure that the email bot learns from the training records and detects the correct information, such as topics and entities, apply the training changes to the text analytics model for the system. You apply changes to the model after you enable the training data recording, and then create and review the training records.
The system generates training data when a CSR:
- Spins off a business case by selecting a case from the suggested case or other cases list. For more information, see Spinning off business cases for an email bot.
- Sends a reply by selecting a reply from the suggested reply or other replies list. For more information, see Replying to customers by email for an email bot.
For relevant training materials, see the Training the email bot module on Pega Academy.
- Enable training of your text analytics model for the email bot.For more information, see Enabling the training data recording for an email bot.
- Improve the email bot model by providing sample training records.For more information, see Creating training data manually for an email bot.
- Update the training data by ensuring that the email bot detects the right
information by using text analysis.For more information, see Correcting training data in an email bot.
- Optional: To move the training data to another email bot, export and import the training
records.This action makes the email bot easier to maintain and build in production, QA and development environments. For more information, see Transferring training data to another email bot.
- Make the email bot learn from the training data by building a text analytics
model.This action improves the artificial intelligence of the system. For more information, see Applying changes to a text analytics model for an email bot.
Note: For more information about NLP and machine learning in email bots, see Using email bots for natural language processing and machine learning. Previous topic Testing email routing conditions Next topic Enabling the training data recording for an email bot