On the Kore.ai Bots Platform, natural language engine attempts to identify a user input and match that user input to a task. You can modify additional advanced settings to enable negative patterns for intent detection.
This will be useful in filtering matched-intents which are part of user utterance but should not trigger that intent.
Use Case: For example, a user says “I was trying to Book a Flight when I faced an issue“. Based on the training data, the model may identify the intent as “Book a Flight“, but that is not what the user wants to do. In such a case, defining “faced an issue” as a negative pattern would ensure that the matched intent “Book a Flight” is ignored.
Negative patterns can be used to eliminate intents detected by the Fundamental Meaning or Machine Learning models. To enable Negative Patterns:
- Go to Natural Language > Training
- Select Advanced Settings
- Enable Negative Patterns, by default this option is disabled.
- You will see Negative Patterns section added, in this section:
- For each of the intent in your Bot you can define negative patterns similar to how you define intent patterns.
- Any intents identified by FM or ML engines, if identified as one of the configured negative patterns, will be ignored and not sent to Ranking & Resolver.
- Once added, these patterns can be reordered, edited, and deleted.