Abstract: A method for controlling a response utterance being reproduced and predicting a user intention includes: a voice signal analysis step of, when a second voice signal is received from a user while a first response utterance for responding to a first voice signal is output, starting analysis on the second voice signal; an utterance control step of, when one of preset keywords is identified to be included in a first sentence corresponding to the second voice signal, controlling the first response utterance being output to correspond to the identified keyword; an intention prediction step of, when a third voice signal is received in a state where the first response utterance is controlled, analyzing the third voice signal to predict an intention of the user, which is reflected in a second sentence corresponding to the third voice signal; and a response utterance output step of outputting a response utterance.

Abstract: This application relates to a user-customized question-answering system based on a knowledge graph that can answer questions accurately. In one aspect, the system includes a user interface configured to receive a question or a reply in the form of a natural language from a user and transmit an answer or reverse question to the user, through a network, and a natural language understanding unit configured to perform natural language analysis and question classification. The system may also include an integrated knowledge graph configured to store or manage a knowledge graph including multi-order relationship triples and a knowledge graph management unit configured to generate a context knowledge graph having entity knowledge graphs and select at least one entity knowledge graph from among the entity knowledge graphs. The system may further include a question target ranking unit configured to generate the answer or the reverse question for the question.

Abstract: A knowledge base correction system includes a question generator configured to detect incomplete knowledge data of a knowledge base, and to generate a question, an answer to which is used to correct the incomplete knowledge data; a user information storage configured to store level information about a plurality of users; and a question selector configured to determine a number of questions and questions to be assigned to each of the plurality of users, based on the level information of the plurality of users.