Granted Patent B2

US 12,450,026 · App. 17/888,971 · Granted Oct 21, 2025

Inventor: Yoon A Cho (Gyeonggi-do, KR)

Assignees: HYUNDAI MOTOR COMPANY; KIA CORPORATION

G06F3/165G06F3/013G06V20/593G06V20/597

Abstract

Claims (33)

1. A method of suggesting a speech that provides a speech suggestion to a user inside a vehicle, the method comprising:

obtaining a user image where at least one user inside the vehicle is photographed;

detecting a user looking at a display inside the vehicle among the at least one user, based on the obtained user image;

determining, by a processor, a target user which is a target of the speech suggestion, based on a result of the detection; and

determining, by the processor, the speech suggestion corresponding to the target user, wherein the determining of the speech suggestion includes determining at least one of content, a way of speaking, or an output location of the speech suggestion to correspond to the target user.

2. The method of claim 1 , wherein the determining of the target user includes determining the user looking at the display inside the vehicle among the at least one user, as the target user.

3. The method of claim 2 , wherein the determining of the target user further includes determining a driver as the target user, when two or more users looking at the display inside the vehicle exist among the at least one user and the driver is included in the two or more users.

4. The method of claim 2 , wherein the determining of the target user further includes determining a driver as the target user, when the user looking at the display inside the vehicle does not exist.

5. The method of claim 2 , wherein, when a first user is determined as the target user among the at least one user, and then the user looking at the display is changed from the first user to a second user, the determining of the target user further includes changing the target user of the speech suggestion to the second user, when the second user keeps looking at the display for more than a predetermined time period.

6. The method of claim 1 , wherein the determining of the speech suggestion includes determining the output location of the speech suggestion to correspond to a seating location of the target user.

7. The method of claim 1 , wherein the determining of the speech suggestion includes determining at least one of the content and the way of speaking of the speech suggestion to correspond to at least one of an age and a gender of the target user.

8. The method of claim 1 , further including:

storing a preference related to at least one of the content and the way of speaking of the speech suggestion for each user,

wherein the determining of the speech suggestion further includes:

identifying the target user; and

determining the at least one of the content and the way of speaking of the speech suggestion, based on the stored preference of the identified target user.

9. The method of claim 1 , wherein the determining of the speech suggestion further includes:

identifying the target user; and

determining the content of the speech suggestion based on a vehicle-related knowledge level of the identified target user.

10. The method of claim 9 , further including:

storing a speech history or a driving history for each user; and

determining the vehicle-related knowledge level based on the stored speech history or the stored driving history.

11. A non-transitory computer-readable recording medium storing a program for implementing a method of suggesting a speech that provides a speech suggestion to a user inside a vehicle, the method comprising:

obtaining a user image where at least one user inside the vehicle is photographed;

detecting a user looking at a display inside the vehicle among the at least one user, based on the obtained user image;

determining, by a processor, a target user which is a target of the speech suggestion, based on a result of the detecting; and

determining the speech suggestion corresponding to the target user, wherein the determining of the speech suggestion includes determining at least one of content, a way of speaking, or an output location of the speech suggestion to correspond to the target user.

12. The non-transitory computer-readable recording medium of claim 11 , wherein the determining of the target user includes:

determining the user looking at the display inside the vehicle among the at least one user, as the target user.

13. The non-transitory computer-readable recording medium of claim 12 , wherein the determining of the target user includes:

determining a driver as the target user, when two or more users looking at the display inside the vehicle exist among the at least one user and the driver is provided in the two or more users.

14. The non-transitory computer-readable recording medium of claim 12 , wherein the determining of the target user includes:

determining a driver as the target user, when the user looking at the display inside the vehicle does not exist.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (16)