Creating training data manually for an email bot
To ensure that Pega Email Bot™ interprets emails in the correct way, manually create training records in the system. Training records provide valuable information for the email bot that strengthens the artificial intelligence algorithms and improves the accuracy of your text analytics model.For example, you can add a training record that specifies a request for an insurance quote for a 1968 Ford Mustang GT. If you connect that record to a car insurance topic, the system learns to associate this information with a car insurance case.
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.
- In the navigation pane of App Studio, click Channels.
- 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.
- In the toolbar, click Add records.
- If you configure multiple languages for the email bot, in the Creating new training record window, in the Language list, select the language for the training record, for example, English.
- In the Topic field, press the Down arrow key, and then select a name of a topic to which the training record relates, for example, Car insurance.
- In the field area below the Topic field, enter the text
for the training record.The text must be a good representation of sample user input from which the email bot can learn to respond to emails.
For example: Hi, I would like to obtain a car insurance quote for my 1968 Ford Mustang GT. Thank you for your help, Andrew.
- Click Create record.
Result: The system displays the training record in the list on the Training data tab. The Review training data section displays the training record contents with the detected entities highlighted. The NLP analysis section displays the detected language, topic, and entity types that are used in the training data.
- Optional: To add more training records for the email bot, repeat steps 4 through 8.
- Click Save.
The following video demonstrates how to add sample training data from the Training data tab:
Previous topic Enabling the training data recording for an email bot Next topic Correcting training data in an email bot