Transferring training data to another IVA
Maintain the quality of text analysis in Pega Intelligent Virtual Assistant (IVA)
and in your application by copying training data from one IVA environment to another
environment. Transferring training data from one environment to another results in
greater accuracy of topic and entity detection, and makes the IVA easier to maintain and
build.
For example, you can copy training data from a production environment
to a development environment. To correct training data for an IVA to further improve
accuracy, modify the training data in the IVA. For more information, see Correcting training data in an IVA.
Before you begin: Before you can begin transferring data, start recording training data in the IVA.
For more information, see Enabling training data recording for an IVA.
Copying training data from one IVA environment to another involves first creating training data in a production environment, and then exporting the training data to a file. Next, you edit the IVA in a development or QA environment, and then import the saved training data from the file. You can export either only reviewed training data for an IVA, or all of the training data. The training data that you export includes entities that the system added to the text analyzer, but did not build in the model.