AI METHOD AND COMPUTER READABLE RECORDING MEDIUM FOR PROVIDING ANSWERS BASED ON HYBRID HIERARCHICAL CONVERSATION FLOW MODEL WITH CONVERSATION MANAGEMENT MODEL USING MACHINE LEARNING

摘要

Provided is a method for providing an answer based on a hybrid hierarchical conversation flow model in which machine learning is applied to a conversation management technology, which is performed by a conversation comprehension AI service server. The present method may comprise: a step that a hybrid hierarchical conversation flow model is generated; a step that a natural language input of a user is received from a user terminal; a step that an intent of the user corresponding to the received natural language input is determined; a step that a current intent group on the hybrid hierarchical conversation flow model is determined; a step that a matching rate of the intent of the user is calculated with respect to each of the current intent group and a sub-intent group of the current intent group; a step that it is determined whether the highest matching rate exceeds a predetermined critical value; a step that, in the case that the highest matching rate exceeds the predetermined critical value, an answer with respect to the user input is selected from the current intent group having the highest matching rate; and a step that, in the case that the highest matching rate does not exceed the predetermined critical value, conversion into a deep learning mode is performed such that the answer with respect to the user input is selected.