IP Library › Granted Patent US 11,557,387
Granted Patent B2
US 11,557,387 · App. 16/490,336 · Granted Jan 17, 2023

Artificial intelligence robot and method of controlling the same

Inventor: Wonhee Lee (Seoul, KR)
Assignee: LG ELECTRONICS INC.
G16H20/13A61J7/0076G05D1/0221G05D1/0246G06K9/6201G06N5/02G06V20/10G06V40/20G08B21/24G16H40/67A61B5/02055A61B5/02438A61J2200/30A61J2200/70G05D2201/0206
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,557,387
App. No.
16/490,336
Granted
Jan 17, 2023
Kind
B2
Abstract

An artificial intelligence (AI) robot includes a body for defining an exterior appearance and containing a medicine to be discharged according to a medication schedule, a support, an image capture unit for capturing an image within a traveling zone to create image information, and a controller for discharging the medicine to a user according to the medication schedule, reading image data of the user to determine whether the user has taken the medicine, and reading image data and biometric data of the user after the medicine-taking to determine whether there is abnormality in the user. The AI robot identifies a user and discharges a medicine matched with the user, so as to prevent errors. The AI robot detects a user's reaction after medicine-taking through a sensor, and performs deep learning, etc. to learn the user's reaction, to determine an emergency situation, etc. and cope with a result of the determination.

Claims (46)

1. A method of controlling an artificial intelligence (AI) robot, the method comprising:

matching, by the AI robot, a user with a medication target according to a medication schedule;

discharging a medicine set for the user;

acquiring first image data including a medicine-taking action of the user after the discharging of the medicine;

comparing the first image data with previous image data including a previous medicine-taking action of the user from a previous cycle through deep learning to generate a first determination result indicating whether the user has taken the medicine correctly;

acquiring second image data of the user after the medicine-taking;

acquiring a sense signal including biometric data of the user after the medicine-taking;

generating a second determination result indicating whether there is an abnormality in the user based on the second image data and the sense signal including the biometric data; and

in response to the second determination result indicating that there is the abnormality in the user, performing an emergency measure.

2. The method according to claim 1 , wherein the AI robot comprises a body comprising a medicine container formed inside thereof, the medicine container having a space defined to contain the medicine, and an inlet/outlet port formed on an outer surface thereof, the inlet/outlet port injecting or discharging the medicine therethrough.

3. The method according to claim 2 , comprising:

analyzing an action pattern of the user based on the first image data through the deep learning; and

combining the sense signal and the action pattern of the user to determine whether there is the abnormality in the user.

4. The method according to claim 3 , wherein the biometric data comprises information about a heart rate of the user and a temperature of the user.

5. The method according to claim 4 , wherein the matching the user with the medication target comprises:

searching for the user while the AI robot moves; and

matching image data of the searched user with information about the medication target upon acquiring the image data of the searched user.

6. The method according to claim 5 , further comprising estimating a location where the user is located and moving to the estimated location.

7. The method according to claim 6 , wherein the AI robot receives medication command information from a server according to the medication schedule.

8. The method according to claim 6 , wherein the AI robot receives information about the medication schedule directly from the user and searches for the medication target according to the medication schedule stored therein.

9. The method according to claim 4 , wherein the matching a user with a medication target comprises calling a surrounding user through notification thereto according to the medication schedule and reading image data of the surrounding user to determine whether the surrounding user is the medication target.

10. An artificial intelligence (AI) robot comprising:

a body for defining an exterior appearance of the AI robot and configured to contain a medicine to be discharged according to a medication schedule;

a support for supporting the body;

an image sensor configured to capture an image within a traveling zone of the AI robot; and

a controller configured to:

discharge the medicine to a user according to the medication schedule,

acquire first image data including a medicine-taking action of the user after the discharging of the medicine,

compare the first image data with previous image data including a previous medicine-taking action of the user from a previous cycle through deep learning to generate a first determination result indicating whether the user has taken the medicine,

acquire second image data of the user after the medicine-taking,

acquire biometric data of the user after the medicine-taking, and

generate a second determination result indicating whether there is an abnormality in the user based on the second image data and the biometric data.

11. The AI robot according to claim 10 , wherein the controller is further configured to:

in response to the second determination result indicating that there is the abnormality in the user, perform an emergency measure.

12. The AI robot according to claim 10 , further comprising an inlet/outlet port formed on an outer surface of the body to inject or discharge the medicine therethrough.

13. The AI robot according to claim 10 , wherein the controller is further configured to:

analyze an action pattern of the user based on the first image data through the deep learning, and

combine the biometric data and the action pattern of the user to determine whether there is the abnormality in the user.

14. The AI robot according to claim 13 , wherein the biometric data comprises information about a heart rate of the user and a temperature of the user.

15. The AI robot according to claim 10 , wherein the support comprises a traveling part for moving the AI robot,

wherein the controller drives the traveling part such that the AI robot searches for the user while moving.

16. The AI robot according to claim 15 , wherein the controller is further configured to estimate a location where the user is located and drive the traveling part to move the AI robot to the estimated location.

17. The AI robot according to claim 16 , wherein the AI robot receives medication command information from a server according to the medication schedule.

18. The AI robot according to claim 16 , further comprising an interface configured to receive information about the medication schedule directly from the user,

wherein the storage part is configured to search for a medication target according to the medication schedule stored therein.

19. The AI robot according to claim 10 , wherein the AI robot is configured to call a surrounding user through notification thereto according to the medication schedule and read image data of the surrounding user to determine whether the surrounding user is a medication target.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 9, 2020
From: LEE, WONHEE
To: LG ELECTRONICS INC.
Reel/Frame 051460/0399 →
Continuity (1)
Related Publication 20200411154A1 · Dec 31, 2020