Dialogue system, and dialogue processing method

1. A dialogue system comprising:

a storage configured to store context information including at least one of vehicle state information indicating a vehicle state, user information indicating a driver of the vehicle, or driving environment information indicating a driving environment of the vehicle; and

at least one processor configured to:

determine whether a context of the vehicle is a pre-utterance context, in which the dialogue system firstly outputs an utterance, based on the stored context information, determine whether a task related to the pre-utterance context is a duplicate task which has already processed or is currently processing when the context of the vehicle is the pre-utterance context, and obtain at least one of an action corresponding to the pre-utterance context or a pre-utterance message to be output by the dialogue system when the task related to the pre-utterance context is not a duplicate task;

obtain, from the storage, a parameter value of an action parameter used to perform the action corresponding to the pre-utterance context when the at least one processor obtains the action corresponding to the pre-utterance context; and

generate a dialogue response,

wherein the generated dialogue response corresponds to a response for performing the action corresponding to the pre-utterance context using the obtained parameter value of the action parameter when the at least one processor obtains the action corresponding to the pre-utterance context, and the generated dialogue response corresponds to the pre-utterance message when the at least one processor obtains the pre-utterance message to be output by the dialogue system.

2. The dialogue system of claim 1 , wherein

the storage stores a pre-utterance condition related to the context information, and

the at least one processor determines whether the pre-utterance condition is satisfied based on the context information, and determines that the context of the vehicle is the pre-utterance context when the pre-utterance condition is satisfied.

3. The dialogue system of claim 1 , wherein

the storage stores the action corresponding to the pre-utterance context for each of a plurality of pre-utterance context types, and

the at least one processor extracts, from the storage, an action corresponding to one of the plurality of pre-utterance context types.

4. The dialogue system of claim 1 , wherein

the at least one processor generates the action corresponding to the pre-utterance context according to rules stored in the storage.

5. The dialogue system of claim 1 , wherein

the storage stores, in the text form, a virtual user utterance corresponding to the pre-utterance context for each of a plurality of pre-utterance context types.

6. The dialogue system of claim 5 , wherein

the at least one processor extracts an action corresponding to the pre-utterance context by applying a natural language understanding algorithm to the virtual user utterance.

7. The dialogue system of claim 1 , further comprising

a communicator configured to perform wireless communication with an external device,

wherein the communicator transmits the generated dialogue response to the vehicle or a mobile device connected to the vehicle.

8. The dialogue system of claim 7 , wherein

the communicator receives the context information from the vehicle or the mobile device.

9. The dialogue system of claim 7 , wherein

the communicator receives, from the vehicle or the mobile device, a virtual user utterance corresponding to the pre-utterance context.

10. The dialogue system of claim 9 , wherein

the at least one processor extracts an action corresponding to the pre-utterance context by applying a natural language understanding algorithm to the virtual user utterance.

11. The dialogue system of claim 1 , wherein

the at least one processor generates a pre-utterance trigger signal when the context of the vehicle is the pre-utterance context, and transmits the trigger signal to the result processor.

12. The dialogue system of claim 11 , wherein

the at least one processor generates the dialogue response when the trigger signal is transmitted.

13. The dialogue system of claim 1 , wherein

the at least one processor terminates the pre-utterance context when the at least one processor determines that the task related to the pre-utterance context is a duplicate task.

14. A dialogue processing method comprising:

collecting context information including at least one of vehicle state information indicating a vehicle state, user information indicating a driver of the vehicle, or driving environment information indicating a driving environment of the vehicle;

determining whether a context of the vehicle is a pre-utterance context, in which a dialogue system of the vehicle firstly outputs an utterance, based on the collected context information;

determining whether a task related to the pre-utterance context is a duplicate task which has already processed or is currently processing when the context of the vehicle is the pre-utterance context;

obtaining at least one of an action corresponding to the pre-utterance context or a pre-utterance message to be output by the dialogue system when the task related to the pre-utterance context is not a duplicate task;

obtaining, from the storage, a parameter value of an action parameter used to perform the action corresponding to the pre-utterance context when the input processor obtains the action corresponding to the pre-utterance context; and

generating a dialogue response,

wherein the generated dialogue response corresponds to a response for performing the action corresponding to the pre-utterance context using the obtained parameter value of the action parameter when the input processor obtains the action corresponding to the pre-utterance context, and the generated dialogue response corresponds to the pre-utterance message when the input processor obtains the pre-utterance message to be output by the dialogue system.

15. The dialogue processing method of claim 14 , further comprising:

storing a pre-utterance condition related to the context information;

determining whether the pre-utterance condition is satisfied based on the context information; and

determining that the context of the vehicle is the pre-utterance context when the pre-utterance condition is satisfied.

16. The dialogue processing method of claim 14 , further comprising:

storing, in the text form, a virtual user utterance corresponding to the pre-utterance context for each of a plurality of pre-utterance context types.

17. The dialogue processing method of claim 16 , further comprising:

extracting an action corresponding to the pre-utterance context by applying a natural language understanding algorithm to the virtual user utterance.

18. The dialogue processing method of claim 14 , further comprising:

transmitting the generated dialogue response to the vehicle or a mobile device connected to the vehicle via a communicator configured to perform wireless communication with an external device.

19. The dialogue processing method of claim 18 , further comprising:

receiving, from the vehicle or the mobile device, the context information via the communicator.

20. The dialogue processing method of claim 19 , further comprising:

receiving a virtual user utterance corresponding to the pre-utterance context from the vehicle or the mobile device.

21. The dialogue processing method of claim 14 , further comprising:

terminating the pre-utterance context when it is determined that the task related to the pre-utterance context is a duplicate task.