SYSTEM AND METHOD FOR CARE SUPPORT AT HOME

• US 20180357760A1
• Filed: 06/09/2017
• Published: 12/13/2018
• Est. Priority Date: 06/09/2017
• Status: Active Grant

• Current Assignee: Midea Group Co., Ltd
• Original Assignee: Midea Group Co., Ltd
• Inventors: WANG, DONGYAN, GU, HAISONG
• Granted Patent: US 10,438,136 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 18/217 Validation; Performance evaluation; Active pattern learning techniques
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06V 10/776 Validation; Performance evaluation
• CPC Class Codes: G06V 40/25 Recognition of walking or running movements, e.g. gait recognition

Abstract

Systems and methods are provided for fall prediction. Such system may comprise one or more sensors configured to obtain at least gait information of a person, and one or more processors coupled to the one or more sensors. The one or more processors may be configured to receive the gait information of the person, obtain gait dynamic features based at least in part on the obtained gait information, and apply the obtained gait dynamic features to a learning model to predict at least a fall movement of the person.

Claims

1. A system for fall prediction, comprising:

one or more sensors configured to obtain at least gait information of a person;

one or more processors coupled to the one or more sensors and configured to;

receive the gait information of the person;

obtain gait dynamic features based at least in part on the obtained gait information; and

apply the obtained gait dynamic features to a learning model to predict at least a fall movement of the person.

2. The system of claim 1, wherein:

to apply the obtained gait dynamic features to the learning model to predict at least the fall movement of the person, the one or more processors are configured to;

obtain an environment condition, the environment condition comprising at least one of a temperature or a humidity of an environment of the person;

obtain a health condition of the person; and

apply the obtained gait dynamic features, the obtained health condition, and the obtained environment condition to the learning model to predict at least the fall movement of the person.

3. The system of claim 1, wherein:

the one or more sensors comprise one or more optical sensors; and

the optical sensors comprise at least one of a camera, an infrared sensor, a motion sensor, a temperature sensor, or a gesture sensor.

4. The system of claim 1, wherein:

the one or more sensors and the one or more processors are disposed in a household appliance.

5. The system of claim 1, wherein:

the one or more processors are coupled to the one or more sensors through a network.

6. The system of claim 1, wherein:

the gait dynamic features include at least one of cadence, left step length, right step length, base of support left step, base of support right step, left stride length, or right stride length.

7. The system of claim 1, wherein:

the learning model comprises a Dynamic Bayesian Network (DBN) model;

to apply the obtained gait dynamic features to the learning model to predict at least the fall movement of the person, the one or more processors are configured to;

obtain training data comprising fall movements of various people with associated gait dynamic features;

obtain the gait information of the person as incremental data;

train the learning model with at least one of the training data or the incremental data to obtain a trained learning model configured to obtain a fall movement probability based on at least one of;

one or more gait dynamic features in a current time or one or more gait dynamic features in a previous time; and

apply the obtained gait dynamic features to the trained learning model to predict at least the fall movement of the person.

8. The system of claim 1, wherein:

the prediction of the fall movement comprises a probability of the fall during a current or future time period.

9. The system of claim 1, wherein:

the one or more processors are further configured to control a device to at least mitigate the predicted fall movement; and

to control the device, the one or more processors are further configured to cause a change in at least one of a temperature or humidity control setting of an air-conditioner.

10. The system of claim 1, wherein:

the one or more processors are further configured to trigger a notification of the prediction.

11. A method for fall prediction, comprising:

obtaining at least gait information of a person;

obtaining gait dynamic features based at least in part on the gait information; and

applying the obtained gait dynamic features to a learning model to predict at least a fall movement of the person.

12. The method of claim 11, wherein:

applying the obtained gait dynamic features to the learning model to predict at least the fall movement of the person comprises;

obtaining an environment condition comprising at least one of a temperature or a humidity of an environment of the person;

obtaining a health condition of the person; and

applying the obtained gait dynamic features, the obtained health condition, and the obtained environment condition to the learning model to predict at least the fall movement of the person.

13. The method of claim 11, wherein:

the gait dynamic features include at least one of cadence, left step length, right step length, base of support left step, base of support right step, left stride length, or right stride length.

14. The method of claim 11, wherein:

the learning model comprises a Dynamic Bayesian Network (DBN) model; and

applying the obtained gait dynamic features to the learning model to predict at least the fall movement of the person comprises;

obtaining training data comprising fall movements of various people with associated gait dynamic features;

obtaining the gait information of the person as incremental data;

training the learning model with at least one of the training data or the incremental data to obtain a trained learning model configured to obtain a fall movement probability based on at least one of;

one or more gait dynamic features in a current time or one or more gait dynamic features in a previous time; and

applying the obtained gait dynamic features to the trained learning model to predict at least the fall movement of the person.

15. The method of claim 11, further comprising:

controlling a device to at least mitigate the predicted fall movement, wherein controlling the device comprises causing a change in at least one of a temperature or humidity control setting of an air-conditioner.

16. A non-transitory computer-readable medium for fall prediction, comprising instructions stored therein, wherein the instructions, when executed by one or more processors, perform the steps of:

obtaining at least gait information of a person;

obtaining gait dynamic features based at least in part on the gait information; and

applying the obtained gait dynamic features to a learning model to predict at least a fall movement of the person.

17. The medium of claim 16, wherein:

applying the obtained gait dynamic features to the learning model to predict at least the fall movement of the person comprises;

obtaining an environment condition comprising at least one of a temperature or a humidity of an environment of the person;

obtaining a health condition of the person; and

applying the obtained gait dynamic features, the obtained health condition, and the obtained environment condition to the learning model to predict at least the fall movement of the person.

18. The medium of claim 16, wherein:

the gait dynamic features include at least one of cadence, left step length, right step length, base of support left step, base of support right step, left stride length, or right stride length.

19. The medium of claim 16, wherein:

the learning model comprises a Dynamic Bayesian Network (DBN) model; and

applying the obtained gait dynamic features to the trained learning model to predict at least the fall movement of the person comprises;

obtaining training data comprising fall movements of various people with associated gait dynamic features;

obtaining the gait information of the person as incremental data;

training the learning model with at least one of the training data or the incremental data to obtain a trained learning model configured to obtain a fall movement probability based on at least one of;

one or more gait dynamic features in a current time or one or more gait dynamic features in a previous time; and

applying the obtained gait dynamic features to the trained learning model to predict at least a fall movement of the person.

20. The medium of claim 16, wherein the instructions, when executed by one or more processors, further perform the step of:

controlling a device to at least mitigate the predicted fall movement, wherein controlling the device comprises causing a change in at least one of a temperature or humidity control setting of an air-conditioner.