{"id":20055,"date":"2019-05-06T08:20:07","date_gmt":"2019-05-06T08:20:07","guid":{"rendered":"https:\/\/developer.kore.ai\/v10-1\/?p=20055"},"modified":"2023-01-23T06:38:22","modified_gmt":"2023-01-23T06:38:22","slug":"traits","status":"publish","type":"post","link":"https:\/\/developer.kore.ai\/v10-1\/docs\/bots\/nlp\/traits\/","title":{"rendered":"Traits"},"content":{"rendered":"
\r\n\t
\r\n\t\t
\r\n\t\t\t\r\n\t\t<\/div>\r\n\t<\/div>\r\n\n

In natural conversations, it is very common that a user provides background\/relevant information while describing a specific scenario. <\/span>Traits<\/strong> 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 are used in driving the intent detection and bot conversation flows.<\/span><\/p>\n

For example, the utterance: <\/span>My flight is late and I will miss my connection<\/span><\/em> because of it expresses two traits: <\/span>flight delay <\/span><\/em>and <\/span>emergency<\/span><\/em>. In this scenario, the utterance does not convey any direct intent. However, the presence of the <\/span>emergency<\/span><\/em> trait is used to directly assign the conversation to a human agent.<\/span><\/p>\n

The <\/span>Traits <\/strong>feature of the XO Platform is aimed at identifying such characteristics present in user utterances and use them for intent detection and in customizing the VA definition using these characteristics.<\/span><\/p>\n

<\/div><\/div>\n

How Traits work<\/span><\/span><\/h1>\n

Traits are entities that can be extracted from user input, before intent recognition. They can be used in multiple scenarios<\/span><\/p>\n