Artificial intelligence device for performing speech recognition

1. An artificial intelligence device for performing speech recognition, the artificial intelligence device comprising:

a database configured to store correction data replacing a predetermined speech command;

a microphone configured to receive a first speech command from a first user; and

a processor configured to store the first speech command in the database when operation to be performed with respect to the first speech command is not determined, acquire a second speech command or text data as correction data replacing the first speech command from a second user, and map and store the first speech command and the correction data in the database.

2. The artificial intelligence device according to claim 1 , wherein the processor retrieves a speech command having a pattern similar to that of the first speech command from the database and stores the first speech command in the database when the speech command having the pattern similar to that of the first speech command is not retrieved.

3. The artificial intelligence device according to claim 1 , wherein the processor acquires the second speech command from the second user and acquires the second speech command as the correction data replacing the first speech command when the second user is determined as a user authorized to correct data based on the second speech command.

4. The artificial intelligence device according to claim 1 , wherein the processor acquires the second speech command from the second user and acquires the second speech command as the correction data replacing the first speech command when operation to be performed with respect to the second speech command is determined.

5. The artificial intelligence device according to claim 1 , wherein the processor acquires the text data from the second user and acquires the text data as the correction data replacing the first speech command when operation to be performed with respect to the text data is determined.

6. The artificial intelligence device according to claim 1 , wherein the processor acquires correction data for modifying prestored correction data replacing the first speech command from the second user and acquires the modified prestored correction data as the correction data replacing the first speech command.

7. The artificial intelligence device according to claim 1 ,

wherein the microphone receives a third speech command from the first user, and

wherein the processor acquires correction data replacing the third speech command from the database and determines operation to be performed with respect to the correction data replacing the third speech command to perform speech recognition.

8. The artificial intelligence device according to claim 7 , wherein the processor retrieves a speech command having a pattern similar to that of the third speech command from the database and acquires correction data replacing the retrieved speech command having the similar pattern as the correction data replacing the third speech command.

9. The artificial intelligence device according to claim 7 , further comprising a communication unit configured to transmit the correction data replacing the third speech command to a natural language processing (NLP) server for performing intention analysis,

wherein the processor acquires intention analysis information from the NLP server to perform speech recognition.

10. A speech recognition method performed by an artificial intelligence device including a database for storing correction data replacing a predetermined speech command, the speech recognition method comprising:

receiving a first speech command from a first user;

storing the first speech command in the database when operation to be performed with respect to the first speech command is not determined;

acquiring a second speech command or text data as correction data replacing the first speech command from a second user; and

mapping and storing the first speech command and the acquired correction data in the database.

11. The speech recognition method according to claim 10 , wherein the storing of the first speech command in the database includes:

retrieving a speech command having a pattern similar to that of the first speech command from the database; and

storing the first speech command in the database when the speech command having the pattern similar to that of the first speech command is not retrieved.

12. The speech recognition method according to claim 10 , wherein the acquiring of the correction data replacing the first speech command includes:

acquiring the second speech command from the second user; and

acquiring the second speech command as the correction data replacing the first speech command when the second user is determined as a user authorized to correct data based on the second speech command.

13. The speech recognition method according to claim 10 , wherein the acquiring of the correction data replacing the first speech command includes:

acquiring the second speech command from the second user; and

acquiring the second speech command as the correction data replacing the first speech command when operation to be performed with respect to the second speech command is determined.

14. The speech recognition method according to claim 10 , wherein the acquiring of the correction data replacing the first speech command includes:

acquiring the text data from the second user; and

acquiring the text data as the correction data replacing the first speech command when operation to be performed with respect to the text data is determined.

15. The speech recognition method according to claim 10 , wherein the acquiring of the correction data replacing the first speech command includes:

acquiring correction data for modifying prestored correction data replacing the first speech command from the second user; and

acquiring the modified prestored correction data as the correction data replacing the first speech command.

16. The speech recognition method according to claim 10 , further comprising: receiving a third speech command from the first user;

acquiring correction data replacing the third speech command from the database; and

performing speech recognition by determining operation to be performed with respect to the correction data replacing the third speech command.

17. The speech recognition method according to claim 16 , wherein the acquiring of the correction data replacing the third speech command from the database includes:

retrieving a speech command having a pattern similar to that of the third speech command from the database; and

acquiring correction data replacing the retrieved speech command having the similar pattern as the correction data replacing the third speech command.

18. The speech recognition method according to claim 16 , wherein the performing of the speech recognition includes:

transmitting the correction data replacing the third speech command to a natural language processing (NLP) server for performing intention analysis; and

acquiring intention analysis information from the NLP server to perform speech recognition.

19. An artificial intelligence device for performing speech recognition, the artificial intelligence device comprising:

a database configured to store correction data replacing a predetermined speech command;

a microphone configured to receive a first speech command from a first user; and

a processor configured to store the first speech command in the database when operation to be performed with respect to the first speech command is not determined, acquire correction data replacing the first speech command from a second user, and map and store the first speech command and the correction data in the database,

wherein the processor acquires correction data for modifying prestored correction data replacing the first speech command from the second user and acquires the modified prestored correction data as the correction data replacing the first speech command.