Risk estimation apparatus, risk estimation system, risk estimation method, and non-transitory computer readable recording medium

Patent metadata

Field	Value
Publication number	US-12357241-B2
Application number	US-202418413446-A
Country	US
Kind code	B2
Filing date	Jan 16, 2024
Priority date	Jul 3, 2020
Publication date	Jul 15, 2025
Grant date	Jul 15, 2025

Abstract

A risk estimation apparatus includes a data acquisition unit that acquires measured data of foot pressures of the left foot and the right foot obtained by sensors that are provided in shoes and measure the foot pressures, a stance phase identification unit that identifies a starting timing and an ending timing of a stance phase of each of the left foot and the right foot from the measured data of the foot pressures, and a risk estimation unit that estimates a risk of abnormality of a lower limb on the basis of asymmetry between the foot pressures of the left foot and the right foot during the stance phase.

First claim

What is claimed is:

1. A risk estimation apparatus comprising:
sensors measuring foot pressures of a left foot and a right foot, and provided in a right insole of shoes and a left insole of the shoes of a user;
at least one memory storing instructions; and
at least one processor configured to execute the instructions to:
acquire, from the sensors, the measured data of the foot pressures of the left foot and the right foot, the measured data indicating a time variation of the foot pressures of the left foot and the right foot;
attach a time stamp to the measured data of the foot pressures of the left foot and the right foot;
identify a starting timing and an ending timing of a stance phase of each of the left foot and the right foot from the measured data of the foot pressures on the basis of the attached time stamp;
estimate asymmetry between the foot pressures of the left foot and the right foot on the basis of a local maximum value and a local minimum value of the measured data of the time variation of the foot pressures collected during a corresponding stance phase; and
estimate, by using a machine learned model, a risk of abnormality of a lower limb on the basis of the asymmetry between the foot pressures of the left foot and the right foot during the stance phase of each of the left foot and the right foot in which parts of measurement periods temporally overlap each other,

wherein a risk level is used for making a decision related to improving a gait to reduce asymmetry between the foot pressures of the left foot and the right foot.

2. The risk estimation apparatus according to claim 1 , wherein the at least one processor is further configured to execute the instructions to:
acquire the measured data of the foot pressures on a heel side and a toe side of each of the left foot and the right foot; and
estimate the risk of the abnormality of the lower limb on the basis of the asymmetry between the foot pressures on the heel side and the toe side of the left foot and the right foot during the stance phase.

3. The risk estimation apparatus according to claim 1 , wherein two sensors are provided in the left shoe and two sensors are provided in the right shoe.

4. The risk estimation apparatus according to claim 3 , wherein one sensor of the two sensors provided in the left shoe is installed on a toe side of the left shoe, and another sensor of the two sensors provided in the left shoe is installed on a heel side of the left shoe, and
wherein one sensor of the two sensors provided in the right shoe is installed on a toe side of the right shoe, and another sensor of the two sensors provided in the right shoe is installed on a heel side of the right shoe.

5. The risk estimation apparatus according to claim 1 , wherein the sensors provided in the left shoe and the right shoe are installed in a bilaterally symmetrical manner with respect to each other.

6. A risk estimation method performed by a computer and comprising:
acquiring, from sensors measuring foot pressures of a left foot and a right foot, and provided in a right insole of shoes and a left insole of the shoes of a user, the measured data of the foot pressures of the left foot and the right foot, the measured data indicating a time variation of the foot pressures of the left foot and the right foot;
attaching a time stamp to the measured data of the foot pressures of the left foot and the right foot;
identifying a starting timing and an ending timing of a stance phase of each of the left foot and the right foot from the measured data of the foot pressures on the basis of the attached time stamp;
estimating asymmetry between the foot pressures of the left foot and the right foot on the basis of a local maximum value and a local minimum value of the measured data of the time variation of the foot pressures collected during a corresponding stance phase; and
estimating, by using a machine learned model, a risk of the abnormality of a lower limb on the basis of the asymmetry between the foot pressures of the left foot and the right foot during the stance phase of each of the left foot and the right foot in which parts of measurement periods temporally overlap each other,
wherein a risk level is used for making a decision related to improving a gait to reduce asymmetry between the foot pressures of the left foot and the right foot.

7. The risk estimation method according to claim 6 , further comprising:
acquiring the measured data of the foot pressures on a heel side and a toe side of each of the left foot and the right foot; and
estimating the risk of the abnormality of the lower limb on the basis of the asymmetry between the foot pressures on the heel side and the toe side of the left foot and the right foot during the stance phase.

8. The risk estimation method according to claim 6 , wherein two sensors are provided in the left shoe and two sensors are provided in the right shoe.

9. The risk estimation method according to claim 8 , wherein one sensor of the two sensors provided in the left shoe is installed on a toe side of the left shoe, and another sensor of the two sensors provided in the left shoe is installed on a heel side of the left shoe, and
wherein one sensor of the two sensors provided in the right shoe is installed on a toe side of the right shoe, and another sensor of the two sensors provided in the right shoe is installed on a heel side of the right shoe.

10. The risk estimation method according to claim 6 , wherein the sensors provided in the left shoe and the right shoe are installed in a bilaterally symmetrical manner with respect to each other.

11. A non-transitory storage medium storing a program executable by a computer to perform a risk estimation method comprising:
acquiring, from sensors measuring foot pressures of a left foot and a right foot, and provided in a right insole of shoes and a left insole of the shoes of a user, the measured data of the foot pressures of the left foot and the right foot, the measured data indicating a time variation of the foot pressures of the left foot and the right foot;
attaching a time stamp to the measured data of the foot pressures of the left foot and the right foot;
identifying a starting timing and an ending timing of a stance phase of each of the left foot and the right foot from the measured data of the foot pressures on the basis of the attached time stamp;
estimating asymmetry between the foot pressures of the left foot and the right foot on the basis of a local maximum value and a local minimum value of the measured data of the time variation of the foot pressures collected during a corresponding stance phase; and
estimating, by using a machine learned model, a risk of the abnormality of a lower limb on the basis of the asymmetry between the foot pressures of the left foot and the right foot during the stance phase of each of the left foot and the right foot in which parts of measurement periods temporally overlap each other,
wherein a risk level is used for making a decision related to improving a gait to reduce asymmetry between the foot pressures of the left foot and the right foot.

12. The non-transitory storage medium according to claim 11 , wherein the risk estimation method further comprises:
acquiring the measured data of the foot pressures on a heel side and a toe side of each of the left foot and the right foot; and
estimating the risk of the abnormality of the lower limb on the basis of the asymmetry between the foot pressures on the heel side and the toe side of the left foot and the right foot during the stance phase.

13. The non-transitory storage medium according to claim 11 , wherein two sen

Assignees

• Nec Corp

Inventors

• Huang Chenhui
• Fukushi Kenichiro
• Sekiguchi Yusuke
• Yaguchi Haruki
• Honda Keita
• Izumi Shinichi
• Owaki Dai

Classifications

• G16H40/67

  for remote operation · CPC title

• A61B2562/0247

  Pressure sensors · CPC title

• G16H50/30 Primary

  for calculating health indices; for individual health risk assessment · CPC title

• A61B2562/04

  Arrangements of multiple sensors of the same type · CPC title

• A61B5/6807

  Footwear · CPC title