Information processing method and non-temporary storage medium for system to control at least one device through dialog with user

1. A method to be executed at least in part in a computer for controlling at least one device through dialog with a user, the method comprising:

acquiring first voice information, indicating a voice of a user input by the user, from a microphone;

generating first text string information from the first voice information;

referencing a first database via a bus and/or a first network, which is a private network, by the computer and determining whether the first text string information matches any piece of text string information registered in the first database;

outputting, to a server via a second network, the first text string information when it is determined that the first text string information does not match any piece of text string information registered in the first database;

when the first text string information matches a piece of text string information in a second database, acquiring, from the server via the second network, (i) first semantic information associated with the piece of text string information in the second database and/or a control command corresponding to the first semantic information, and (ii) one or more pieces of text string information associated with the first semantic information in the second database;

instructing the at least one device to execute an operation in accordance with the first semantic information and/or the control command;

retrieving, from the first database, second text string information that matches one of the one or more pieces of text string information acquired from the server; and

outputting, to a speaker, second voice information generated from the second text string information.

2. The method according to claim 1 , further comprising:

converting the second text string information to the second voice information.

3. The method according to claim 1 , further comprising:

generating a control command based on the first semantic information.

4. The method according to claim 1 , further comprising:

converting the first voice information to the first text string information.

5. The method according to claim 1 , wherein

the second network is the Internet, and

the first database is stored in a local server that is communicable with the at least one device without through the Internet.

6. The method according to claim 1 , further comprising:

instructing the at least one device to execute the operation without communicating with the server, when determining that the first text string information matches one of the plurality of pieces of text string information registered in the first database.

7. A non-transitory storage medium storing a program that causes the computer to execute the method according to claim 1 .

8. A method to be executed at least in part in a computer for controlling at least one device through dialog with a user, the method comprising:

acquiring first voice information, indicating a voice of a user input by the user, from a microphone;

generating first text string information from the first voice information;

referencing a first database via a bus and/or a first network, which is a private network, by the computer and determining whether the first text string information matches any piece of text string information registered in the first database;

outputting, to a server via a second network, the first text string information when it is determined that the first text string information does not match any piece of text string information registered in the first database;

when the first text string information matches a piece of text string information in a second database, acquiring, from the server via the second network, first semantic information associated with the piece of text string information in the second database;

instructing the at least one device to execute an operation in accordance with the first semantic information;

retrieving, from the first database, second text string information that matches the first semantic information; and

outputting, to a speaker, second voice information generated from the second text string information.

9. The method according to claim 8 , further comprising:

converting the second text string information to the second voice information.

10. The method according to claim 8 , further comprising:

generating a control command based on the first semantic information.

11. The method according to claim 8 , further comprising:

converting the first voice information to the first text string information.

12. The method according to claim 8 , wherein

the second network is the Internet, and

the first database is stored in a local server that is communicable with the at least one device without through the Internet.

13. The method according to claim 8 , further comprising:

instructing the at least one device to execute the operation without communicating with the server, when it i determined that the first text string information matches any piece of text string information registered in the first database.

14. The method according to claim 8 , wherein the server has no information indicating what text string information is registered in the first database.

15. A non-transitory storage medium storing a program that causes the computer to execute the method according to claim 8 .

16. The method according to claim 1 , wherein the server has no information indicating what text string information is registered in the first database.