Dialogue system, vehicle having the same and dialogue processing method

Patent metadata

Field	Value
Publication number	US-10839797-B2
Application number	US-201715855165-A
Country	US
Kind code	B2
Filing date	Dec 27, 2017
Priority date	Jan 23, 2017
Publication date	Nov 17, 2020
Grant date	Nov 17, 2020

Abstract

A dialogue system includes: an input processor extracting an action corresponding to a user's utterance; a storage storing information value of context information comprising at least one of vehicle state information related to a vehicle state, and driving environment information related to the driving environment of the vehicle; a dialogue managing processor acquiring a parameter value of a condition determination parameter used to determine whether the action corresponding to the user's utterance is executable, from the storage, the dialogue managing processor determining an action to be executed based on the parameter value of the condition determination parameter, the dialogue managing processor acquiring a parameter value of action parameter used to execute the determined action, from the storage; and a result processor generating a response to execute the determined action by using the acquired parameter value of action parameter.

First claim

What is claimed is:

1. A dialogue system comprising:
an input processor configured to extract an action corresponding to a user's utterance;
a storage configured to store information value of context information comprising at least one of vehicle state information related to a vehicle state or driving environment information related to a driving environment of a vehicle;
a dialogue managing processor configured to acquire a parameter value of a condition determination parameter, which is used to determine whether an action is executable, from the storage, determine whether the action is executable based on the parameter value of the condition determination parameter, and acquire a parameter value of an action parameter used to execute an action which is determined to be executed, from the storage; and
a result processor configured to generate a response to execute the action determined to be executed by using the parameter value of the action parameter,
wherein the dialogue managing processor is configured to:
acquire at least one action related to the action corresponding to the user's utterance;
determine a priority among the action corresponding to the user's utterance and the at least one related action; and
determine the action to be executed based on the priority.

2. The dialogue system of claim 1 , wherein the storage is configured to store the context information related to actions according to each action, and
wherein the input processor is configured to acquire the information value of the context information, which is related to the action corresponding to the user's utterance, from the storage and transmit the information value to the dialogue managing processor.

3. The dialogue system of claim 2 , wherein the input processor is configured to request the information value of the context information to the vehicle when the information value of the context information related to the action corresponding to the user's utterance is not stored in the storage.

4. The dialogue system of claim 2 , wherein the dialogue managing processor is configured to use the information value of the context information as the parameter value of the condition determination parameter or the parameter value of the action parameter.

5. The dialogue system of claim 1 , wherein the storage is configured to store a relationship between actions related to each other.

6. The dialogue system of claim 5 , wherein the dialogue managing processor is configured to acquire the at least one action related to the action corresponding to the user's utterance, from the storage.

7. The dialogue system of claim 1 , wherein the dialogue managing processor is configured to acquire the parameter value of the condition determination parameter used to determine whether the at least one action related to the action corresponding to the user's utterance is executable from the storage, and determine whether the at least one action related to the action corresponding to the user's utterance is executable based on the parameter value of the condition determination parameter.

8. The dialogue system of claim 7 , wherein the dialogue managing processor is configured to determine an action, which is executable and has a highest priority between the action corresponding to the user's utterance and the at least one action related to the action corresponding to the user's utterance, as the action to be executed.

9. The dialogue system of claim 1 , wherein, when the input processor cannot extract the action corresponding to the user's utterance, the dialogue managing processor is configured to estimate the action corresponding to the user's utterance based on at least one of the vehicle state information or the driving environment information.

10. The dialogue system of claim 9 , wherein the dialogue managing processor is configured to acquire the parameter value of the action parameter used to execute the estimated action corresponding to the user's utterance, from the storage.

11. The dialogue system of claim 9 , wherein the storage is configured to store a relationship between actions related to each other, and
wherein the dialogue managing processor is configured to acquire at least one action related to the estimated action corresponding to the user's utterance, from the storage.

12. The dialogue system of claim 1 , further comprising a communicator configured to communicate with an external server,
wherein the dialogue managing processor is configured to request the parameter value of the condition determination parameter or the parameter value of the action parameter from the external server when the dialogue managing processor cannot acquire the parameter value of the condition determination parameter or the parameter value of the action parameter from the storage.

13. The dialogue system of claim 1 , wherein the result processor is configured to generate a dialogue response to execute the action determined to be executed and a command for a vehicle control.

14. The dialogue system of claim 1 , further comprising a communicator configured to receive the information value of the context information from the vehicle and transmit the response to execute the determined action to the vehicle.

15. The dialogue system of claim 1 , further comprising a communicator configured to receive the information value of the context information from a mobile device connected to the vehicle and transmit the response to execute the determined action to the mobile device.

16. A dialogue processing method comprising:
storing, in a storage, information value of context information comprising at least one of vehicle state information related to a vehicle state or driving environment information related to a driving environment of a vehicle;
extracting, by an input processor, an action corresponding to a user's utterance;
acquiring, from the storage, at least one of a parameter value of a condition determination parameter used to determine whether at least one candidate action comprising the action corresponding to the user's utterance is executable or a parameter value of an action parameter used to execute the at least one candidate action;
determining, by a dialogue managing processor, whether the at least one candidate action is executable and determining an action to be executed in the at least one candidate action when the candidate action is determined to be executable; and
generating, by a result processor, a response to execute the determined action by using the parameter value of the action parameter,
wherein the determining an action to be executed comprises:
acquiring at least one action related to the action corresponding to the user's utterance;
determining a priority among the action corresponding to the user's utterance and the at least one related action; and
determining the action to be executed based on the priority,

wherein the at least one candidate action comprises the at least one related action.

17. The dialogue processing method of claim 16 , further comprising:
storing the context information related to actions according to each action in the storage; and
acquiring the information value of the context information related to the action corresponding to the user's utterance from the storage, and transmitting the information value to the dialogue managing processor.

18. The dialogue processing method of claim 17 , further comprising requesting the information value of the context information to the vehicle when the information value of the context information related to the

Assignees

• Hyundai Motor Co Ltd
• Kia Motors Corp

Inventors

• Shin Dongsoo
• Seok Donghee
• Joo Sihyun
• Lee Jeong-Eom
• Kim Ga Hee
• Kim Seona
• Park Jung Mi
• Ro Heejin
• Kim Kye Yoon

Classifications

• G10L15/04

  Segmentation; Word boundary detection · CPC title

• G10L2015/225

  Feedback of the input speech · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• B60R16/0315

  using multiplexing techniques (multiplexing for transmission of signals G08C15/00; multiplexing for electrical communication in general H04J) · CPC title

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title