Dialogue system, dialogue processing method

1. A dialogue system comprising:

a Speech to Text (STT) engine configured to convert a user speech into a spoken text;

a learning-based dialogue engine configured to determine a user intention corresponding to the spoken text;

a storage configured to store learning data used for learning of the dialogue engine; and

a controller configured to determine an actual user intention based on at least one of context information or an additional user speech, to match the spoken text, by which the dialogue engine failed to determine the user intention, with the actual user intention when the dialogue engine fails to determine the user intention corresponding to the spoken text, and to store the spoken text and the actual user intention in the storage,

wherein the dialogue engine performs learning using the spoken text and the actual user intention that are stored in the storage,

wherein the dialogue engine generates a system speech to confirm the determined actual user intention, and

wherein the controller matches the spoken text, by which the dialogue engine failed to determine the user intention, with the actual user intention, and stores the spoken text and the actual user intention in the storage when a positive response from the user is input to the system speech.

2. The dialogue system of claim 1 , wherein

the dialogue engine performs the learning periodically or when a predetermined event occurs.

3. The dialogue system of claim 1 , further comprising:

a communicator configured to receive the context information from an electronic device registered in the dialogue system.

4. The dialogue system of claim 3 , wherein

the context information includes at least one of information on an operation of the electronic device executed after the user speech is input or information on a user's behavior.

5. The dialogue system of claim 3 , wherein the dialogue engine outputs the system speech to confirm the determined user intention when determining the user intention is successful.

6. The dialogue system of claim 5 , wherein the controller determines the actual intention of the user based on at least one of context information acquired before and after the user's speech is input or the additional user speech inputted after the system speech, and matches the spoken text with the actual user intention of the user and stores the spoken text in the storage when a negative user response is input to the determined user intention.

7. The dialogue system of claim 3 , wherein the controller generates a control command for performing an action corresponding to the determined user intention when the controller succeeds in determining the user intention.

8. The dialogue system of claim 7 , wherein the controller determines the actual user intention based on the received context information, matches the spoken text with the actual user intention, and stores the matched spoken text in the storage when the context information indicating the execution of an action opposite to the performed action and an additional action is received after the action corresponding to the determined user intention is performed.

9. The dialogue system of claim 8 , wherein the controller matches and stores the user speech, the spoken text, and the actual user intention in the storage, and

wherein the STT engine performs learning using the user speech, the spoken text, and the actual user intention stored in the storage.

10. A dialogue processing method, the method comprising:

converting a user speech into a spoken text in a Speech to Text (STT) engine;

determining a user intention corresponding to the spoken text based on learning in a dialogue engine;

determining an actual user intention based on at least one of context information or an additional user speech;

matching the spoken text, by which the dialogue engine failed to determine the user intention, with the actual user intention when the dialogue engine fails to determine user intention corresponding to the spoken text, and storing the spoken text and the actual user intention in a storage; and

performing learning of the dialogue engine using the spoken text and the actual user intention that are stored in the storage,

wherein the storing of the spoken text and the actual user intention comprising:

generating system speech to confirm the determined actual user intention;

matching the spoken text, by which the dialogue engine failed to determine the user intention, with the actual user intention, and storing the spoken text and the actual user intention in the storage when a positive response from the user is input to the system speech.

11. The method of claim 10 , further comprising

performing, by the dialogue engine, the learning periodically or when a predetermined event occurs.

12. The method of 11 , further comprising

receiving, by a communicator, the context information from an electronic device registered in a dialogue system.

13. The method of claim 12 , wherein the context information includes at least one of information on an operation of the electronic device executed after the user speech is input or information on a user's behavior.

14. The method of claim 12 , further comprising

outputting the system speech to confirm the determined user intention when determining the user intention is successful.

15. The method of claim 14 , further comprising:

determining the actual user intention based on at least one of the context information acquired before and after the user's speech is input or the additional user speech inputted after the system speech when a negative user response is input to the determined user intention; and

matching the spoken text with the actual user intention of the user and storing the spoken text in the storage.

16. The method of claim 12 , further comprising

generating a control command for performing an action corresponding to the determined user intention when the controller succeeds in determining the user intention.

17. The method of claim 16 , further comprising:

determining the actual user intention based on the received context information when the context information indicating the execution of an action opposite to the performed action and an additional action is received after the action corresponding to the determined user intention is performed; and

matching the spoken text with the actual user intention and storing the spoken text in the storage.

18. The method of claim 10 , further comprising:

matching and storing the user speech, the spoken text, and the actual user intention in the storage; and

performing learning using the user speech, the spoken text, and the actual user intention stored in the storage.