Electronic device and control method therefor

Patent metadata

Field	Value
Publication number	US-11270565-B2
Application number	US-201917049847-A
Country	US
Kind code	B2
Filing date	May 13, 2019
Priority date	May 11, 2018
Publication date	Mar 8, 2022
Grant date	Mar 8, 2022

Abstract

An electronic device and a control method therefor are disclosed. A control method for an electronic device, according to the present disclosure, enables relearning of an artificial intelligence model for: receiving fall information acquired by a plurality of sensors of an external device when a fall event of a user is sensed by one of the plurality of sensors included in the external device; determining whether the user has fallen by using the fall information acquired by the plurality of sensors; determining a sensor, having erroneously determined that a fall has occurred, from among the plurality of sensors on the basis of whether the user has fallen; and determining that a fall has occurred by using a sensing value acquired by the sensor having erroneously determined that a fall has occurred. In particular, at least one part of a method for acquiring fall information by using a sensing value acquired through a sensor enables the user of artificial intelligence model having learned according at least one of machine learning, a neural network, and a deep-learning algorithm.

First claim

What is claimed is:

1. A control method of an electronic device, the method comprising:
based on a fall event of a user being detected by one from among a plurality of sensors comprised in an external device, receiving fall information obtained by a plurality of sensors in the external device;
identifying whether or not a fall of the user has occurred by using fall information obtained by the plurality of sensors;
identifying a sensor that erroneously identified whether or not a fall has occurred from among the plurality of sensors based on whether or not a fall of the user has occurred; and
retraining an artificial intelligence model that identifies whether or not a fall has occurred by using a sensing value obtained by the sensor which erroneously identified whether or not a fall has occurred.

2. The method of claim 1 , wherein the external device comprises a first sensor and a second sensor, and
wherein the receiving comprises,
based on a fall event being detected based on at least one from among a first fall information obtained by inputting a sensing value obtained by the first sensor to a first artificial intelligence model and a second fall information obtained by inputting a sensing value obtained by the second sensor to a second artificial intelligence model, receiving the first fall information and the second fall information through the communicator.

3. The method of claim 2 , wherein the identifying whether or not a fall of the user has occurred comprises identifying whether or not a fall of the user has occurred by using fall information obtained by a sensor with high accuracy from among the first sensor and the second sensor.

4. The method of claim 2 , wherein the identifying whether or not a fall of the user has occurred comprises:
obtaining information on whether or not an electronic device is in operation in a space the user is located; and
identifying whether or not a fall of the user has occurred based on the first fall information, the second fall information and information on whether or not the electronic device is in operation.

5. The method of claim 2 , wherein the retraining comprises:
based on the first sensor being identified as the sensor that erroneously identified whether or not a fall has occurred, retraining the first artificial intelligence model; and
based on the second sensor being identified as the sensor that erroneously identified whether or not a fall has occurred, retraining the second artificial intelligence model.

6. The method of claim 1 , further comprising:
transmitting the retrained artificial intelligence model to the external device.

7. The method of claim 1 , comprising:
transmitting the retrained artificial intelligence model to another external device which includes the sensor that erroneously identified whether or not the fall has occurred.

8. The method of claim 1 , wherein the plurality of sensors comprises at least one from among a video sensor, an ultra-wide band (UWB) radar sensor, an infrared (IR) sensor, and a microphone.

9. An electronic device, comprising:
a communicator;
a memory comprising at least one instruction;
a processor coupled with the communicator and the memory and configured to control the electronic device,
wherein the processor, by executing the at least one instruction, is configured to:
based on a fall event of a user being detected by one from among a plurality of sensors comprised in an external device, receive fall information obtained by a plurality of sensors in the external device through the communicator;
identify whether or not a fall of the user has occurred by using fall information obtained by the plurality of sensors;
identify a sensor that erroneously identified whether or not a fall has occurred from among the plurality of sensors based on whether or not a fall of the user has occurred; and
retrain an artificial intelligence model that identifies whether or not a fall has occurred by using a sensing value obtained by the sensor which erroneously identified whether or not a fall has occurred.

10. The electronic device of claim 9 , wherein the external device comprises a first sensor and a second sensor, and
wherein the processor is configured to,
based on a fall event being detected based on at least one from among a first fall information obtained by inputting a sensing value obtained by the first sensor to a first artificial intelligence model and a second fall information obtained by inputting a sensing value obtained by the second sensor to a second artificial intelligence model, receive the first fall information and the second fall information through the communicator.

11. The electronic device of claim 10 , wherein the processor is configured to identify whether or not a fall of the user has occurred by using fall information obtained by a sensor with high accuracy from among the first sensor and the second sensor.

12. The electronic device of claim 10 , wherein the processor is configured to:
obtain information on whether or not an electronic device is in operation in a space the user is located; and
identify whether or not a fall of the user has occurred based on the first fall information, the second fall information and information on whether or not the electronic device is in operation.

13. The electronic device of claim 10 , wherein the processor is configured to:
based on the first sensor being identified as a sensor that erroneously identified whether or not a fall has occurred, retrain the first artificial intelligence model; and
based on the second sensor being identified as a sensor that erroneously identified whether or not a fall has occurred, retrain the second artificial intelligence model.

14. The electronic device of claim 9 , wherein the processor is configured to control the communicator to transmit the retrained artificial intelligence model to the external device.

15. A non-transitory computer readable recording medium comprising a program for executing a control method of an electronic device, the method comprising:
based on a fall event of a user being detected by one from among a plurality of sensors comprised in an external device, receiving fall information obtained by a plurality of sensors in the external device;
identifying whether or not a fall of the user has occurred by using fall information obtained by the plurality of sensors;
identifying a sensor that erroneously identified whether or not a fall has occurred from among the plurality of sensors based on whether or not a fall of the user has occurred; and
retraining an artificial intelligence model that identifies whether or not a fall has occurred by using a sensing value obtained by the sensor which erroneously identified whether or not a fall has occurred.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Han Jonghee
• Kim Joonho
• Baek Hyunjae
• Yang Dojun

Classifications

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/092

  Reinforcement learning · CPC title

• G08B29/186

  Fuzzy logic; neural networks · CPC title

• G08B21/043 Primary

  detecting an emergency event, e.g. a fall · CPC title