Traits are characteristics or specific attributes that can be identified and extracted from the search user’s input. They give you deeper insights into the search user’s intent. In natural conversations, it is very common that a user provides background/relevant information while describing a specific scenario.
You can also identify traits in jargons i.e., usages popular in a particular trade or profession. Example: pax in the travel industry, checkout in hospitality, discharge summary in health care etc.
Traits are specific entities, attributes, or details that the users express in their conversations. The utterance may not directly convey any specific intent, but the traits present in the utterance lead to the intent detection and drive bot conversation flows.
You can extract traits from given documents and the SearchAssist can map those traits to user queries that help to increase the relevance score. You can use the traits added to the search app in fine tuning index workbench and business rules configurations.
For example, instead of a simple query “How do I pay my bill”, the user might say something like “I was wondering if it would be possible to make payments.” For the SearchAssist app to result in the same response for both the preceding queries or utterances, manually define a common trait for these two utterances. Tag the corresponding content source or answer with that trait to respond with when the trait is identified.