Dialogue system and dialogue processing method

Patent metadata

Field	Value
Publication number	US-10991368-B2
Application number	US-201816191095-A
Country	US
Kind code	B2
Filing date	Nov 14, 2018
Priority date	Jun 25, 2018
Publication date	Apr 27, 2021
Grant date	Apr 27, 2021

Abstract

A dialogue system for a vehicle may include: an input processor configured to receive a user's utterance, to acquire an utterance text by recognizing the user's utterance, to recognize a dialogue subject based on the acquired utterance text, and to identify the user; and a dialogue manager including a memory storing program instructions and a processor configured to execute the stored program instructions, the dialogue manager configured to verify whether a chat room related to the dialogue subject is present, and to determine whether to add the identified user as a participant of the chat room based on a result of the verification.

First claim

What is claimed is:

1. A dialogue system for a vehicle comprising:
an input processor configured to receive a user's utterance, to acquire an utterance text by recognizing the user's utterance, to recognize a dialogue subject based on the acquired utterance text, and to identify the user; and
a dialogue manager including a memory storing program instructions and a processor configured to execute the stored program instructions, the dialogue manager configured to verify whether a chat room related to the dialogue subject is present, and to determine whether to add the identified user as a participant of the chat room based on a result of the verification,
wherein, when the identified user is a participant of the chat room, the dialogue manager is further configured to verity whether the dialogue subject is related to a dialogue subject of the corresponding chat room, and when the dialogue subject is not related to the dialogue subject of the chat room, the dialogue manager is further configured to delete the identified user from the participant of the chat room.

2. The dialogue system of claim 1 , wherein:
the dialogue manager is further configured to add the identified us as a participant of the chat room when the chat room is present.

3. The dialogue system of claim 1 , wherein,
when the chat room is not present, the dialogue manager is further configured to generate a chat room related to the dialogue subject and to add the identified user as a participant of the generated chat room.

4. The dialogue system of claim 1 , further comprising:
a context information processor configured to map an internal image of the vehicle acquired by a camera with an utterance input by a user, and to estimate a location of the user based on the mapped image,
wherein the input processor identifies the user based on the estimated location of the user.

5. The dialogue system of claim 1 , wherein,
when the dialogue subject is not related to a dialogue subject of the chat room, the dialogue manager is further configured to exclude the identified user from being a participant of the chat room.

6. The dialogue system of claim 5 , wherein,
when the identified user is excluded from being a participant of the chat room, the dialogue manager is further configured to disregard the user's utterance.

7. The dialogue system of claim 6 , wherein,
when an utterance of the excluded user is related to the dialogue subject of the chat room, the dialogue manager is further configured to add the user as a participant of the chat room.

8. The dialogue system of claim 7 , wherein:
the dialogue manager is further configured to count the utterance of the user added to the participant of the chat room in a dialogue performed in the chat room.

9. The dialogue system of claim 1 , further comprising:
a storage configured to store a dialogue subject of the chat room and a dialogue performed in the chat room,
wherein the dialogue manager is further configured to close a chat room in which a participant is not present, to store information of the closed chat room including a dialogue performed in the closed chat room and a dialogue subject of the closed chat room, and when the dialogue subject is related to the dialogue subject of the closed chat room, to generate a chat room based on the stored information of the closed chat room.

10. The dialogue processing method of claim 1 , further comprising:
when the dialogue subject is not related to a dialogue subject of the chat room, excluding, by the dialogue manager, the identified user from being a participant of the chat room.

11. The dialogue processing method of claim 10 , wherein
the exclusion of the identified user comprises disregarding, by the dialogue manager, the user's utterance.

12. The dialogue processing method of claim 11 , further comprising:
when an utterance of the excluded user is related to the dialogue subject of the chat room, adding, by the dialogue manager, the user as a participant of the chat room.

13. The dialogue processing method of claim 12 , wherein
the adding of the user as a participant of the chat room comprises counting, by the dialogue manager, an utterance of the user added to the participant of the chat room in a dialogue performed in the chat room.

14. A dialogue processing method for a vehicle comprising:
receiving, by an input processor, a user's utterance;
acquiring, by the input processor, an utterance text by recognizing the user's utterance;
recognizing, by the input processor, a dialogue subject based on the acquired utterance text;
identifying, by the input processor, the user;
verifying, by a dialogue manager including a memory storing program instructions and a processor configured to execute the stored program instructions, whether a chat room related to the dialogue subject is present;
determining, by the dialogue manager, whether to add the identified user as a participant of the chat room based on a result of the verification;
when the identified user is a participant of the chat room, verifying, the dialogue manager, whether the dialogue subject is related to a dialogue subject of the chat room; and
when the dialogue subject is not related to the dialogue subject of the chat room, deleting, by the dialogue manager, the identified user as a participant of the chat room.

15. The dialogue processing method of claim 14 , wherein:
the determination of whether to add the identified user as a participant of the chat room comprises adding, by the dialogue manager, the identified user as a participant of the chat room when the chat room is present.

16. The dialogue processing method of claim 14 , wherein:
the determination of whether to add the identified user as a participant of the chat room comprises, when the chat room is not present, generating, by the dialogue manager, a chat room related to the dialogue subject; and adding; by the dialogue manager, the identified user as a participant of the generated chat room.

17. The dialogue processing method of claim 14 , further comprising:
mapping, by the dialogue manager, an internal image of the vehicle acquired by a camera with an utterance input by a user; and
estimating, by the dialogue manager, a location of the user based on the mapped image,
wherein the identification of the user comprises identifying the user based on the estimated location of the user.

18. The dialogue processing method of claim 14 , further comprising:
closing, by the dialogue manager, a chat room in which a participant is not present;
storing, by the dialogue manager, information of the closed chat room including a dialogue performed in the closed chat room and a dialogue subject of the closed chat room; and
when the dialogue subject is related to the dialogue subject of the closed chat room, generating, by the dialogue manager, a chat room based on the stored information on the closed chat room.

Assignees

• Hyundai Motor Co Ltd
• Kia Motors Corp

Inventors

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

Classifications

• G06F3/167

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title

• G06V20/593

  Recognising seat occupancy · CPC title

• G06V20/59

  inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions · CPC title

• G06V40/10

  Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands · CPC title

• G10L15/22 Primary

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