JP2018079220A - Body condition information estimation method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a body condition information estimation method which allows a user to get to know his or her own body composition customarily, without using a device of directly measuring the body composition.SOLUTION: The method comprises a body condition information estimation step S504 which estimates body condition information of a user by applying user's exercise information on an exercise done by the user and a time zone in which the exercise was done to body condition related information expressing correlation between at least subject exercise information on exercises done by plural subjects and time zones in which the exercises were done and subject body condition information on the bodies of the subject, which were acquired in advance.SELECTED DRAWING: Figure 6

Description

  The present invention relates to a body state information estimation method, a body state information estimation program, a body state information estimation device, and a body state information estimation system that estimate information about a body state from user motion information.

It is known that adult diseases such as hypertension, dyslipidemia, diabetes and the like progress without the consciousness of the person and cause arteriosclerosis to cause myocardial infarction or cerebral infarction if left untreated. Such a symptom is also called metabolic syndrome, and since it is related to obesity, the abdominal circumference and visceral fat area can be used as predictors. In addition, muscle mass decreases with age, and although it is not a disease, there may be problems with motor functions such as low back pain, knee pain, and falls. Such a malfunction of motor function is also called locomotive syndrome. In order to prevent and improve metabolic syndrome and locomotive syndrome, it is effective for the person to be aware of the body composition such as fat and muscle mass of his body.
Devices that measure body composition include DEXA (Dual-Energy X-ray Absormetry) and CT (Computed Tomography). However, since all such devices are only located in medical institutions, it is difficult to use them frequently by users to check body composition on a daily basis.

In addition, as a simpler configuration than DEXA and CT, a relatively small device that measures body composition by passing a weak current through a living body and measuring impedance is also commercially available. A known technique for measuring a body composition based on a measurement result using such a small device is described in Patent Document 1, for example.
Furthermore, Patent Document 2 describes a biological analysis device that detects a change in a subject's state by measuring the activity of the subject in a time series without using a device that measures the body composition.

JP 20042544741 A JP 2008-67892 A

However, the impedance measurement described in Patent Document 1 cannot be used for a person having a pacemaker in the heart or a pregnant woman. In addition, there are users who cannot make it a habit to measure body composition every day. Furthermore, the technique described in Patent Document 2 merely measures a user's state continuously and detects this change. Therefore, Patent Document 2 does not describe any association of data obtained by measurement with the body composition of the user.
The present invention provides a body state information estimation method, a body state information estimation program, a body state information estimation device, and a body state information estimation system that allow a user to habitually know the body including its own body composition. For the purpose.

The body state information estimation method of the present invention includes at least subject exercise information related to a motion acquired by a plurality of subjects acquired in advance and a time zone during which the exercise was performed, and subject body state information related to the subject's body. A body state information estimation step of estimating the user's body state information by applying the user's motion information related to the exercise performed by the user and the time zone during which the exercise was performed to the body state related information representing the relevance It is characterized by including.
The body state information estimation program of the present invention is based on at least the subject motion information related to the exercise performed by a plurality of subjects acquired in advance and the time zone during which the exercise was performed, and the subject's body state information. Including a body state information estimation method step of estimating the body state information of the user by applying to the body state related information to represent the user's motion information regarding the motion performed by the user and the time zone during which the motion was performed It is characterized by.

The body state information estimation device according to the present invention includes at least subject exercise information related to exercise performed by a plurality of subjects acquired in advance and a time zone during which the exercise was performed, and subject body state information related to the subject's body. A body state information estimation unit for estimating body state information of the user by applying the user motion information related to the exercise performed by the user and the time zone during which the exercise is performed to the body state related information representing the relevance It is characterized by including.
The body state information estimation system of the present invention includes an exercise information acquisition device that acquires user exercise information related to an exercise performed by a user and a time zone during which the exercise is performed, and the user exercise information from the exercise information acquisition device. And the body state information estimating apparatus for estimating body state information related to the user's body based on the user movement information.

  The present invention described above is a body state information estimation method, a body state information estimation program, a body state information estimation device, and a body that can know the body composition of the body habitually without using a device that directly measures the body composition. A state information estimation system can be provided.

It is a figure for demonstrating the body state information estimation apparatus of one Embodiment of this invention. 2A and 2B are diagrams illustrating the configuration of the body state information estimation system according to the embodiment of the present invention. It is the figure which showed the relationship between the measured value and estimated value of a visceral fat area among the body state information of one Embodiment of this invention. It is the figure which showed the relationship between the measured value and estimated value of a skeletal muscle index among the body state information of one Embodiment of this invention. It is the figure which illustrated the message of one Embodiment of this invention. It is a flowchart for demonstrating the body state information estimation method of one Embodiment of this invention.

  Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In all the drawings, the same constituent elements are denoted by the same reference numerals, and redundant description is omitted as appropriate.

[Physical condition information estimation device and physical condition information estimation system]
(Physical condition information estimation device)
FIG. 1 is a diagram for explaining a body state information estimation apparatus 10 according to the present embodiment. The body state information estimation device 10 is based on the exercise information about the exercise performed by the user of the body state information estimation device (hereinafter simply referred to as “user”) and the time zone during which this exercise was performed. A body state information estimation unit 132 that estimates state information is provided. The estimation of the body state information includes at least exercise information on a plurality of subjects acquired in advance (hereinafter simply referred to as “subjects”) and exercise information on a time zone in which the exercise was performed, This is performed by applying the user's exercise information to the body state related information representing the relevance of.

In the above description, “subject” means a person who has provided exercise information and body state information for creating body state related information, and a user is a body state information estimation method using this body state related information. A person who uses “Exercise” means that the subject and the user consciously move the body. The “time zone” is a time defined by the start time and end time of exercise. “Exercise information” is information that associates the amount and intensity of exercise performed by the subject with the time zone during which this exercise was performed.
The amount of exercise may be represented by, for example, the time during which the exercise is continuously performed, the number of movements of the body, the calorie consumption, and the like. The exercise intensity may be defined by, for example, oxygen intake or heart rate. As an expression of exercise intensity, “METs” based on oxygen intake and heart rate at rest are known, and directly measured parameters may be converted into METs and used.
“Physical condition information” is information indicating the state of a person's body, specifically, body composition information related to the composition of body fat, muscles, etc., and size related to the size of the body such as abdominal circumference and waist circumference. Information. “Physical state-related information” is information that associates the physical state information of the subject with the exercise information of the exercise performed by the subject.

The body state information estimation device 10 includes an acceleration sensor 11, a control unit 13, a display unit 15, a timer 17, a related information storage memory 19 and an input unit 21 that acquire user motion information in order to estimate body state information. I have.
(Acceleration sensor)
The acceleration sensor 11 is a sensor that detects acceleration in the x-axis direction, x-axis, y-axis, and z-axis directions, and detects the acceleration applied to the body state information estimation apparatus 10 and thus the user with the y-axis direction as the gravity direction. As such an acceleration sensor 11, for example, Suzuken Lifecoder (registered trademark) EX, Lifecoder PLUS, or the like is used. However, the acceleration sensor 11 may be a uniaxial sensor. In this embodiment in which exercise information is acquired using the acceleration sensor 11, the user's walking motion is measured as exercise. When measuring walking, the acceleration sensor 11 is mounted near the user's waist.
In the present embodiment, exercises other than walking may be employed for acquiring exercise information. As an exercise other than walking, for example, push-ups can be considered. When measuring the number and speed of push-ups, it can be considered that the acceleration sensor 11 is worn near the upper arm of the user.

(Control part)
The control unit 13 includes an exercise information creation unit 131, a body state information estimation unit 132, and a message creation unit 133. The exercise information creation unit 131 inputs acceleration data acquired by the acceleration sensor 11. Then, the number of steps taken by the user and the exercise intensity (hereinafter also referred to as “walking intensity”) are detected from the acceleration data. The walking intensity may be detected by, for example, the “speed” of walking.
Furthermore, exercise information is created by associating time information acquired from the timer 17 with the number of steps or walking intensity. Such a control unit 13 is a so-called computer, and has a known configuration such as a CPU (Central Processing Unit) (not shown), a memory for storing data, and a working memory. The exercise information creation unit 131, the body condition information estimation unit 132, and the message creation unit 133 are each configured by hardware that performs a predetermined function and a program that controls the hardware on the control unit 13.
The exercise information creation unit 131 reads the acceleration signal output from the acceleration sensor 11, and calculates the amount of exercise and the exercise intensity by various arithmetic processes as described below. In this embodiment, the number of steps taken as the amount of exercise is measured by the number of times acceleration is applied. In addition, the intensity of exercise is the walking intensity, and the measurement is performed based on the acceleration intensity including the walking intensity.

The motion information creation unit 131 may extract an acceleration component in the gravity direction from the acceleration signal acquired by the acceleration sensor 11. Various arithmetic processes for calculating the number of steps and the speed from the acceleration signal have been proposed so far and are not particularly limited. An example is shown below.
First, the motion information creation unit 131 converts acceleration signals sequentially output from the acceleration sensor 11 into voltage signals, performs digital conversion and noise removal, and performs processing such as synthesis of triaxial acceleration or extraction of gravity direction components. Generate acceleration data. In addition, in this embodiment, acceleration means what removed the influence of the gravity acceleration of the earth. That is, the user who is walking is loaded with an acceleration of 1 G or more (for example, 1.2 G) together with the gravitational acceleration. However, the motion information creation unit 131 may acquire a value (in this case, 0.2 G) obtained by appropriately excluding the influence of gravitational acceleration from the measured acceleration.

When measuring the number of steps, the exercise information creation unit 131 compares the acceleration data with a threshold value, and measures the user's walking when the acceleration value exceeds the threshold value. The number of times of walking is counted as the number of steps. Further, when measuring the exercise intensity of walking, the exercise information creation unit 131 determines the magnitude of acceleration by comparing the acceleration data with a threshold value, and calculates the exercise intensity based on the determination result. The threshold value is stored in advance in the exercise information creation unit 131. The exercise information creation unit 131 constantly measures acceleration from a user who is active with the acceleration sensor 11 mounted, and exercise intensity by walking and walking every predetermined time interval (hereinafter referred to as intensity determination interval). Is calculated.
In this embodiment, the exercise information creation unit 131 classifies the measured acceleration data into 11 levels of 0 to 9 and 0.5, for example, based on the magnitude. The classified acceleration data is stored in the data storage memory described above with data measured during the intensity determination interval as one unit.

The intensity determination interval can be 1 second or more and 10 seconds or less, for example, 4 seconds or 6 seconds. By setting the intensity determination interval to 10 seconds or less, the user's movement can be analyzed in detail.
The exercise information creation unit 131 generates one or a plurality of acceleration data based on the acceleration signal from the acceleration sensor 11 at each intensity determination interval, and determines the magnitude of the acceleration. Preferably, a plurality of acceleration data is generated at each intensity determination interval, and the magnitude of the acceleration is determined. In this case, the sampling interval at which the acceleration sensor 11 acquires the acceleration signal is set shorter than the intensity determination interval, and more preferably, the acceleration sensor 11 measures the acceleration signal a plurality of times within the time of the intensity determination interval. Set to For this reason, by setting the intensity determination interval to 1 second or more, many acceleration signals can be measured by the acceleration sensor 11 within the time of the intensity determination interval without excessively shortening the sampling interval of the acceleration sensor 11. .

The exercise information creation unit 131 determines the exercise intensity of the user within the time of the intensity determination interval based on the number of occurrences for each determined magnitude of acceleration. Thereby, it is suppressed that the exercise intensity is determined to be excessive due to instantaneously detecting a large acceleration. Also, even if the detected magnitudes of acceleration are equal, the exercise intensity can be distinguished into different intensity levels based on the magnitude of the acceleration occurrence frequency.
The exercise information creation unit 131 may determine the exercise intensity by averaging the accelerations counted within the intensity determination interval. This prevents an excessively high exercise intensity from being measured by a large acceleration recorded at the moment when the user stands up or falls. In this way, the exercise information creation unit 131 can generate one exercise intensity for each intensity determination interval based on a plurality of acceleration data acquired within the time of the intensity determination interval.

The body state information estimation unit 132 reads the body state related information from the related information storage memory 19. Then, the exercise information created by the exercise information creation unit 131 is applied to the body condition related information to estimate the user's body condition information. The body state related information will be described in detail later.
The message creation unit 133 compares the exercise information of the user with the physical condition information of the subject and the exercise information of the subject, and creates a message including advice information that suggests the exercise and the time zone for performing the exercise. . In creating the advice information, it is also possible to use a target value or condition previously input by the user via the input unit 21. Examples of the target value of the user include body state information on fat and muscle strength targeted by the user. Moreover, as conditions, the upper limit of the amount of exercises or exercise intensity which a user desires is mentioned. As the input unit 21, various types such as a keyboard, a pen tab, a touch panel, and a voice input device can be used.
The message creation unit 133 creates advice information for exercising so that the user's body state information approaches the target body state information and does not exceed the upper limit value. A message including the advice information created by the message creation unit 133 is output to the display unit 15 and displayed. A known display device can be used as the display unit 15. Moreover, in this embodiment, it is not limited to the structure which displays a message on the display part 15 with a text, It replaces with or in addition to it, the time zone and exercise amount etc. which should be exercised to a user with an audio | voice or light. You can also be notified.

  Such a body state information estimation apparatus 10 of this embodiment may be configured as a smartphone having a pedometer function, for example. When the body state information estimation device 10 is configured as a smartphone, a known configuration included in the smartphone can be used for the acceleration sensor 11, the timer 17, the related information storage memory 19, the input unit 21, and the display unit 15.

(Physical condition information estimation system)
In addition, the embodiment of the present invention is not limited to the configuration of the body state information estimation device 10 described above, and the exercise information acquisition device that acquires exercise information, and the acquired exercise information is processed to obtain the body state The body state information estimation device that estimates information may be a separate body.
FIG. 2A and FIG. 2B are diagrams illustrating a configuration in which the exercise information acquisition device and the body state information estimation device are separated. In the present embodiment, a configuration in which the exercise information acquisition device and the body state information estimation device are separately provided is also referred to as a “body state information estimation system”. The configuration shown in FIG. 2A shows an example in which a body state information estimation system is constructed by an exercise information acquisition device 30 and a body state information estimation device 50 that estimates body state information using body state information. ing. The exercise information acquisition device 30 includes an output interface (I / F) 31 in addition to the acceleration sensor 11, the exercise information creation unit 131 and the timer 17. The body state information estimation device 50 includes an input interface (I / F) 51 in addition to the body state information estimation unit 132, the message creation unit 133, the related information storage memory 19, the input unit 21, and the display unit 15.

The output I / F 31 and the input I / F 51 may input exercise information from the exercise information acquisition device 30 to the body state information estimation device 50 using a data recording medium. Further, the exercise information may be exchanged by wire or wireless, and the exercise information may be transmitted / received by infrared communication.
In addition, as shown in FIG. 2B, the present embodiment includes an exercise information acquisition device 20 including an acceleration sensor 11, an exercise information creation unit 131 and a timer 17, a body state information estimation unit 132, and a message creation unit. 133, the related information storage memory 19, the input unit 21, and the body state information estimation device 40 including the display unit 15 may be connected to the network N to construct a computer system.

When this embodiment is divided into the exercise information acquisition device 30 and the body state information estimation device 50 as shown in FIG. 2 (a), the exercise information acquisition device worn by the user on the body is downsized, and the user's It is possible to reduce the load applied to the exercise information acquisition device. Moreover, since the body state information estimation part 132 and the message preparation part 133 can be made into a large sized apparatus, body state information can be estimated with high precision. In addition, the types of body state information that can be estimated or displayed and the contents of messages can be diversified or enhanced.
Further, as shown in FIG. 2B, when the present embodiment is divided into the exercise information acquisition device 20 and the body state information estimation device 40 and connected to the network N, the acquired exercise information is sequentially transmitted to the body state information estimation device. You can send and measure the number of steps and exercise intensity in real time. And a message can be transmitted to a user in real time.

[Physical condition information estimation method]
Next, the body state information estimation method of this embodiment will be described.
In the body state information estimation method of the present embodiment, at least the exercise performed by the user and this exercise were performed on the body state related information representing the relationship between the exercise information of the subject and the body state information of the subject. It includes the step of estimating the user's physical condition information by applying the user's exercise information regarding the time zone. In the present embodiment, prior to the description of such a body state information estimation method, first, body state related information will be described.

(Physical condition related information)
The present inventors acquired exercise information of each person using 500 men as subjects. The exercise information was obtained by using the walking of the subject as an index of exercise, the number of steps taken as “momentum”, and the walking intensity as “exercise intensity”. Further, the exercise information was acquired by putting the exercise information acquisition device 30 shown in FIG. 2A on the waist while the subject was awake for 28 days. Furthermore, the exercise information was acquired by taking a walk performed within a time range of 3 hours as one unit. For this reason, in this embodiment, the number of steps of the subject's 28-day walk and the walking intensity are recorded in association with the time zone every 3 hours.

  The present inventors have found that there is a correlation between the number of steps taken by the subject, the walking intensity, and the time zone during which the walking was performed, and the physical condition information of the subject. For example, during the period from noon to afternoon, energy metabolism is higher than other times, and hormone secretion is also active. According to the investigation by the present inventors, when exercise is performed in such a time zone, fat can be burned efficiently. Also, during the evening and evening hours, speed and endurance are higher than in other hours, making it easier to exercise. Furthermore, nighttime exercise is effective in enhancing muscle strength such as weight lifting because cells produce more protein than other time zones. The results of such surveys are considered valid from the viewpoints of kinematics and nutrition. In addition to such kinematics, the present inventors came up with the idea of advising training according to the user's request using the correspondence between the actual physical condition information of the subject and the exercise information, and the present invention Completed.

  In the case where the exercise is walking (including running), the present embodiment defines 44 types of parameters shown in the following (1) to (10). Then, using this parameter, body state related information for estimating the body state information of the subject is created.

(1) 1-8: Average value of the number of steps in each time zone The number of steps (Ns _3-6 ) for each set time zone of 3 hours (for example, 3-6 o'clock) is measured. Then, an average value (Ns _3-6ave ) of 28 days of the number of steps in each time zone is calculated and set as the average value of the number of steps in each time zone.
Ns _3-6ave , Ns _6-9ave , Ns _9-12ave , Ns _12-15ave , Ns _15-18ave , Ns _18-21ave , Ns _21-24ave , Ns _24-3ave

(2) 9 to 16: Average walking intensity in each time zone Measure the walking strength (Np _3-6 ) every 3 hours set time (for example, 3-6 o'clock) for 1 second as described above The walking intensity is determined at a determination interval of 10 seconds or less, for example, 4 seconds or 6 seconds. Since the walking intensity changes during 3 hours, the walking intensity within the time determined by the exercise information creation unit 131 that the user is walking is calculated for each intensity determination interval, and the time-averaged values are calculated as follows: Let it be the average walking strength during that time period. Then, an average value (Np _3-6ave ) for 28 days is calculated with respect to the average walking strength in each time zone, and the average walking strength in each time zone is calculated.
Np _3-6ave , Np _6-9ave , Np _9-12ave , Np _12-15ave , Np _15-18ave , Np _18-21ave , Np _21-24ave , Np _24-3ave

(3) 17-27; average value of appearance frequency of intensity at each stage (0-9 and 0.5) Intensity appearing at every determination interval in one day is shown for each intensity (Nf0, Nf0.5, Nf1, Nf2) Nf3, Nf4, Nf5, Nf6, Nf7, Nf8, Nf9). Then, an average value (Nf0ave) for 28 days is calculated with respect to the appearance frequency of each intensity, and is set as the average value of the intensity frequency at each stage.
Nf0ave, Nf0.5ave, Nf1ave, Nf2ave, Nf3ave, Nf4ave, Nf5ave, Nf6ave, Nf7ave, Nf8ave, Nf9ave

(4) 28: Variation coefficient of the number of steps The standard deviation Ns _sd of the number of steps for 28 days is calculated. Further, an average value (Ns _ave ) obtained by averaging the measured number of steps over 28 days is calculated. Then, the following value obtained by dividing the standard deviation Ns _sd by the average value (Ns _ave ) is set as the variation coefficient of the number of steps.
Ns _sd / Ns _ave

(5) 29: Coefficient of wearing time variation The standard deviation Ni _sd of the wearing time for 28 days is calculated. In addition, an average value (Ni _ave ) obtained by averaging the measured wearing time over 28 days is calculated. Then, the following value obtained by dividing the standard deviation Ni _sd by the average value Ni _ave is taken as the wearing time variation coefficient.
Ni _sd / Ni _ave

(6) 30: Coefficient of variation in walking strength The standard deviation Np _sd of walking strength for 28 days is calculated. In addition, an average value (Np _ave ) obtained by averaging the measured walking intensity over 28 days is calculated. Then, the following value obtained by dividing the standard deviation Np _sd by the average value Np _ave is defined as a walking strength variation coefficient.
Np _sd / Np _ave

(7) 31-41; coefficient of variation of the frequency of walking intensity at each stage (0-9 and 0.5) The frequency of walking at the intensity of each stage (0-9 and 0.5) (Nf ₀ , Nf _0.5 , Nf ₁ , Nf ₂ , Nf ₃ , Nf ₄ , Nf ₅ , Nf ₆ , Nf ₇ , Nf ₈ , Nf ₉ ) are counted daily. The standard deviation of the counted frequency is calculated for each intensity (Nsd ₀ , Nsd _0.5 , Nsd ₁ , Nsd ₂ , Nsd ₃ , Nsd ₄ , Nsd ₅ , Nsd ₆ , Nsd ₇ , Nsd ₈ , Nsd ₉ ). Each intensity shown in (3) with the above standard deviation (Nsd ₀ , Nsd _0.5 , Nsd ₁ , Nsd ₂ , Nsd ₃ , Nsd ₄ , Nsd ₅ , Nsd ₆ , Nsd ₇ , Nsd ₈ , Nsd ₉ ) Average of 28 days (Nf 0 _ave , Nf _{0.5 ave} , Nf 1 _ave , Nf 2 _ave , Nf 3 _ave , Nf 4 _ave , Nf 5 _ave , Nf _{6 ave} , Nf _{7 ave} , Nf _{8 ave} , Nf _{8 ave} The coefficient of variation in the frequency of walking intensity.
_{Nsd 0 / Nf 0ave, Nsd 0.5} / Nf 0.5ave, Nsd 1 / Nf 1ave, Nsd 2 / Nf 2ave, Nsd 3 / Nf 3ave, Nsd 4 / Nf 4ave, Nsd 5 / Nf 5ave, Nsd 6 / Nf _{6 ave} , Nsd ₇ / Nf _{7 ave} , Nsd ₈ / Nf _{8 ave} , Nsd ₉ / Nf _{9 ave}
However, both Nsd ₀ and Nf _0ave exclude information on a time zone when the subject is not wearing the exercise information acquisition device 30.
(8) 42; Age (9) 43; Height (10) 44; Weight

Table 1, Table 2, and Table 3 exemplify the parameters used for estimating the physical condition information of the subject and the physical condition information among the parameters. Tables 1 to 3 show the correlation between the actually measured value and the estimated value of the body condition information of the subject. In the parameter column, the number in parentheses following “;” corresponds to the number in parentheses of each parameter described above.
In Table 1, visceral fat, abdominal circumference, skeletal muscle index, and body fat percentage are listed as body condition information. Table 2 is a table following Table 1. In Table 2, the ratio between the abdominal circumference and the waist circumference (abdominal circumference / waist circumference, hereinafter referred to as “waist / hip ratio”) as body condition information. And grip strength. In particular, grip strength is a parameter highly correlated with whole-body muscle strength. Furthermore, in Table 3, as the body state information, intracellular water content, extracellular water content, protein content, mineral content, body water content, and ECW / TBC are listed. As shown in Tables 1 to 3, in the estimation of the body condition information excluding the grip strength and ECW / TBC using the parameters of the present embodiment, the correlation function R with the actually measured value is 0.709 to 0.94, the coefficient of determination R ² has a high value of 0.502 to 0.883.

Among the above parameters, the average value of the walking intensity (1) can be used for estimating the walking speed of the user. The walking strength is estimated by applying an average value of walking strength to the multiple regression equation. The multiple regression equation for estimating the walking speed is as follows.
(male)
Estimated walking speed (Km / h) = 0.862 (average walking intensity) +0.035 (height (cm))-4.705
(Woman)
Estimated walking speed (Km / h) = 0.684 (average walking intensity) +1.851

The numerical values such as walking intensity “5” in the present embodiment are, for example, the maximum walking intensity that the user is supposed to ingest oxygen with the maximum oxygen intake determined by METs, and the minimum oxygen intake at rest. And can be determined by dividing the interval. In METs, for example, 3METs walks on flat ground at 67 m / min, 3.3 METs walks on flat ground at 81 m / min, 3.8 METs walks on flat ground at 94 m / min, 4 METs ranges from 95 m to 100 m / min It is determined that walking on the flat ground in minutes and 5METs are walking fast on the flat ground at 107 m / min.
The regression analysis of this embodiment was performed using commercially available statistical calculation software. For regression analysis, multivariate regression analysis or logistic regression analysis is used. In the regression analysis, a parameter that increases the correct answer rate is selected while changing the combination by performing the variable increasing method, the variable decreasing method, or both for the parameters used for the explanatory variables. Furthermore, the coefficient attached to the parameter is appropriately selected.

In addition, in the body state information estimation method of the present embodiment, as shown in Tables 1 to 3, the body state information is estimated using at least one of height, weight, and age in addition to the body state information. Estimating body condition information. In the present embodiment, body state related information is determined using at least one of the subject's height, weight, and age together with the subject's exercise information, and the height and weight together with the user's exercise information for the determined body state related information. And the user's physical condition information is estimated by applying at least one of age.
Furthermore, in the body state information estimation method of the present embodiment, as shown in Tables 1 to 3, information on the amount of exercise or exercise intensity of the exercise performed by the subject during a specific time period of the day is obtained. It is used as
The (+) added to the end of the parameters such as body condition information and height shown in Tables 1 to 3 indicates that the estimated value of the body condition information increases as the parameter increases. Moreover, (-) has shown that the estimated value of body state information becomes small, if the parameter becomes large.

In addition, the present embodiment uses not only the measured exercise information itself but also the degree of movement of exercise performed by the subject or the degree of dispersion of exercise intensity as parameters used for estimation of body state information. The degree of dispersion of the exercise amount or the exercise intensity is a parameter indicating “variation” within the measurement period of the exercise amount or the exercise intensity, for example, and is represented by the variation coefficient in the present embodiment.
Further, in the present embodiment, information relating to the distribution of the amount of exercise during one day of exercise can also be used for estimation as exercise information. The distribution of the amount of exercise is represented by, for example, “morning exercise time ratio”, “daytime exercise time ratio”, “night exercise time ratio”, and the like. The morning exercise time ratio indicates the ratio of the number of steps taken from 3:00 to 9:00 to the number of steps per day. The daytime exercise time ratio indicates the ratio of the number of steps taken from 9:00 to 18:00 to the number of steps per day. The night exercise time ratio indicates the ratio of the number of steps taken from 18:00 to 3 o'clock to the number of steps per day.

However, the parameter including the exercise information of the present embodiment is not limited to the example described above. For example, the exercise information is not limited to information measured as one unit every three hours, and may be information measured in arbitrary time. The average value of the parameters is not limited to the average during the measurement time, and may be an average value per arbitrary unit time or an average value per day.
Moreover, this embodiment is not limited to what records a test subject's step count and walking intensity over 28 days. The number of steps may be recorded for 7 days or more.

The correlation coefficient R and the coefficient of determination R ² shown in Table 3 Table 1 shows the measured values of the physical condition information of the subject, the correlation between the estimated value estimated using parameters. The actual measurement values of each body state information are values measured from impedance measured by passing a weak current through the subject's body. The visceral fat, the correlation coefficient R is 0.805, the coefficient of determination ^{R 2} to obtain a high correlation of 0.649. Further, in the abdominal circumference, the correlation coefficient R is 0.911, the coefficient of determination ^{R 2} is 0.830, the correlation coefficient R is in skeletal muscle index 0.846, the coefficient of determination ^{R 2} is 0.715, the phases in the body fat percentage The correlation number R was 0.781, the determination coefficient R ² was 0.610, and the waist-hip ratio was such that the correlation coefficient R was 0.709 and the determination coefficient R ² was 0.502.
As described above, the present embodiment can estimate the body condition information of the subject with high reliability.

Next, a specific example of the relationship between the actual measurement value and the estimated value of the body condition information of the subject described above will be shown.
FIG. 3 is a diagram showing the relationship between the measured value and estimated value of the visceral fat area (VFA) in the body condition information. The vertical axis in FIG. 3 indicates actual measurement values, and the horizontal axis indicates estimated values. In this example, the estimated value shown on the horizontal axis is calculated by the following equation (1). Equation (1) is a function obtained as a result of statistical logistic regression analysis of the relationship between exercise information and an estimated value.

(Equation 1)
−4 × 10 ⁻³ (average number of steps from 6 o'clock to 9 o'clock) −7 × 10 ⁻³ (average value of steps from 12 o'clock to 15 o'clock) +3.479 (weight) −1.587 (height) +0. 706 (age)
... Formula (1)
Found an estimated value shown in FIG. 3, the correlation coefficient R is 0.805, the coefficient of determination ^{R 2} has a high correlation with 0.649. Expression (1) is an example of body state related information indicating the relationship between the exercise information of the subject and the body state information (visceral fat area). This embodiment applies a user's thing to the parameter shown in the parenthesis in Formula (1), and estimates a user's physical condition information.

  FIG. 4 is a diagram showing the relationship between the measured value of the skeletal muscle index (SMI) and the estimated value of the skeletal muscle index in the body state information. The vertical axis in FIG. 4 indicates actual measurement values, and the horizontal axis indicates estimated values. In this example, the estimated value shown on the horizontal axis is calculated by the following equation (2). Equation (2) is a function obtained as a result of statistical logistic regression analysis of the relationship between exercise information and an estimated value.

(Equation 2)
1.38 × 10 ⁻⁴ (average number of steps from 9 o'clock to 12 o'clock) + 8 × 10 ⁻⁵ (average number of steps from 15 o'clock to 18 o'clock) +0.206 (average value of walking intensity between 18 o'clock and 21 o'clock) +0.062 (weight) -0.11 (height) ... Formula (2)
Found an estimated value shown in FIG. 4, the correlation coefficient R is 0.846, the coefficient of determination ^{R 2} has a high correlation with 0.715. Expression (2) is an example of body state related information indicating the relationship between the exercise information of the subject and the body state information (skeletal muscle index). This embodiment applies a user's thing to the parameter shown in the parenthesis in Formula (2), and estimates a user's physical condition information.

  Furthermore, the present inventor has found that the grip strength shown in Table 2 can be estimated by the body state related information represented by the following formulas (3) and (4). Equation (3) is body state related information for estimating grip strength from parameters for men, and Equation (4) is body state related information for estimating grip strength from parameters for women.

(Equation 3)
7 × 10 ⁻⁴ (average number of steps during 12-15 o'clock) + 5 × 10 ⁻⁴ (average number of steps during 18-21 o'clock) −0.328 (age) +0.232 (height) +0.126 (weight) +10.599 Formula (3)
(Equation 4)
0.385 (average walking intensity at 3-6 o'clock) +0.754 (average walking intensity at 15-18 o'clock) -0.163 (age) +0.204 (height) +0.108 (weight) ) -4.86 Formula (4)
In addition, as a matter of course, the body condition related information of the present embodiment is not limited to the form of the primary expression such as Expression (1) to Expression (4). The physical state related information may be any information as long as it obtains the physical state information by inputting the user's exercise information, height, etc., for example, may be an arithmetic expression other than the primary expression. Alternatively, it may be a correspondence table such as a table.

(message)
Next, an example of a message including advice information created based on a result obtained by applying exercise information to the above-described body state related information will be described.
The message creation unit 133 creates a message including advice regarding exercise to be performed by the user based on the body state information targeted by the user and the body state related information corresponding to the body state information.
In the above description, the advice is information that suggests the amount of exercise, intensity, time zone for exercise, etc. to the user, and a message is created by appropriately adding necessary information to the advice information. The information added to the advice information includes, for example, the diagram shown in FIG.

FIG. 5 is a diagram illustrating a message added to the advice. FIG. 5 shows “muscle strength” indicating what percentage the user's grip strength is compared with the average value of the same-sex, same-sex grip strength. Since “muscle strength” has an average value of 50%, a numerical value of 50% or less is displayed in the message when the grip strength of the user is less than the average value. When the user's grip strength is greater than or equal to the average value, a numerical value of 50% or more is displayed in the message.
Further, the message illustrated in FIG. 5 includes a “muscle strength level” in which the muscle strength level is indicated by a pentagonal graph, and “muscle strength age” that indicates an average value of the same age as that of the user. ,It is included. In the “muscle strength level”, the region indicated by “2” indicates an average value, the region indicated by “1” indicates the average value or less, and the region indicated by “3” indicates the average value or more. In the message, for example, an area corresponding to the grip strength of the user may be colored in a predetermined color and displayed to the user.
Furthermore, the message shown in FIG. 5 includes “muscle age” indicating which age of the same sex the user's grip strength falls into. Since the grip strength has a high correlation with the muscle strength of the whole body, it is suitable as an index for estimating the user's muscle strength.

  The above-described message may be further printed on a paper medium and output, or may be transmitted as e-mail or the like to the user's smartphone or the like. Such an email may be transmitted to a third party (a family member, etc.) registered in advance in addition to the person himself / herself. Furthermore, in the present embodiment, a display unit (not shown) may be provided in the exercise information acquisition device 30 and a message may be presented to both through the display unit of the exercise information acquisition device 30. Furthermore, in the present embodiment, when the exercise information acquisition device 30 is connected to the body state information estimation device 50, a message can be displayed on the display unit 15 of the body state information estimation device 50.

In the present embodiment, the input unit 21 shown in FIG. 1 and FIG. 2 uses the body state information such as the visceral fat area targeted by the user (hereinafter referred to as “target value”), the exercise amount set by the user, An upper limit value of exercise intensity can be input in advance. The message creation unit 133 inputs the height, weight, and age of the user in the body state related information shown in the formula (1), and the user should walk from 6 o'clock to 9 o'clock according to the target value, and 12 The number of steps from 15:00 to 15:00 is calculated.
Next, the message creation unit 133 calculates a difference between the calculated number of steps and the acquired number of steps of the user, for example, “Let's increase the number of steps at 6 o'clock” Send a message with information.
In such processing, the user's weight, height, and age are registered in advance in the body state information estimation device 50 using the input unit 21 when the user starts using the body state information estimation method of the present embodiment. Alternatively, it may be input from the input unit 21 at an arbitrary timing.

In the present embodiment, when the amount of exercise or exercise intensity to be increased exceeds the upper limit set by the user in the above processing, the message creation unit 133 walks with the number of steps or intensity set to the upper limit. Create a message to advise users. According to such processing, even if the difference between the user's actual body condition information and the target value is relatively large, the body state information is brought closer to the target value by suppressing the user's pain by taking time. Can do.
Further, when the user's body condition information reaches the target value, the message creating unit 133 may create a message such as “The visceral fat area has been reduced to xxx, the goal has been achieved”.

(Estimation of user physical condition information)
FIG. 6 is a flowchart for explaining the body state information estimation method of the present embodiment. Moreover, the flowchart of FIG. 6 has shown the example performed by the computer comprised as the body state information estimation apparatus 50 shown to Fig.2 (a). This flowchart exemplifies a process of measuring exercise intensity as user exercise information for 3 hours and calculating an average value of the measured values. Further, in the flowchart of FIG. 6, an example in which one piece of exercise information is acquired once is shown for the sake of simplicity. However, as shown in Tables 1 to 3, this embodiment often acquires a plurality of types of exercise information a plurality of times.
In the body state information estimation method of the present embodiment, when the process is started, the acceleration sensor 11 of the exercise information acquisition device 30 starts acquisition of the user's exercise information (step S501). Note that such processing may be started automatically at a time corresponding to the estimated content of the body state information desired by the user, or may be started at the same time as getting up. Good.
The “time according to the estimated content of the body condition information desired by the user” refers to, for example, 6 o'clock or 12 o'clock when the user desires the reduction of the internal fat shown in Table 1.

  When acquisition of user exercise information is started, the timer 17 continues to measure time until three hours elapse (step S502). While the timer 17 is measuring time, the acceleration sensor 11 detects the acceleration applied to the user and continues to output it as exercise intensity to the exercise information creation unit 131. When the time measurement for 3 hours is completed (step S502: Yes), the exercise information creation unit 131 calculates an average value of the exercise intensity measured by the acceleration sensor 11 for 3 hours (step S503). In addition, the exercise information creation unit 131 creates exercise information by associating the calculated average value with the time zone during which the measurement is performed. The created exercise information is sent to the body state information estimation unit 132 via the output I / F 31 and the input I / F 51. The body state information estimation unit 132 reads the body state related information from the related information storage memory 19 and applies the exercise information of the user to estimate the body state information (step S504).

For example, the message creation unit 133 creates advice information that advises the user on the number of steps and exercise intensity based on the difference between the estimated physical condition information of the user and the actual physical condition information. Then, a message is created by adding body condition information or the like to the advice information (step S505). The message is output to the display unit 15 (step S506).
The message output is not limited to that described in the flowchart shown in FIG. For example, as in the case of the skeletal muscle index shown in Table 1, when acquiring exercise information from three exercises from 9 o'clock to 12 o'clock, 15 o'clock to 18 o'clock, and 18 o'clock to 21 o'clock, The body state information is estimated from the motion information of the motions performed so far. Then, a message created based on the estimated body condition information may be provided to the user at the start of exercise the next day, for example.

  At least steps S504 to S506 in the flowchart described above are processed by a program realized by a computer (not shown) in the body state information estimation apparatus 50, for example.

In the present embodiment described above, the user's physical state information is estimated based on the exercise performed by the user. For this reason, the user can estimate the body state information without using a special device. Moreover, since this embodiment can automatically acquire exercise information from a user, it is possible to make body condition information estimation habitual without placing a burden on the user.
Further, in the present embodiment, the body state information is estimated by applying the exercise information to the body state related information considering the actual measurement value of the subject based on the principle of temporal behavior. For this reason, an estimated value having high correlation with the actually measured value can be obtained.

[Modification]
Further, as described above, the present embodiment is not limited to estimating body state information from exercise information. For example, the method further includes a disease prediction step of comparing a user's exercise information with a subject's exercise information to predict a disorder or disease that may occur in the future (hereinafter referred to as “disease etc.”). You can also.
When predicting a disease or the like, disease related information is stored in the related information storage memory 19 shown in FIG. 2 instead of the physical state related information. The disease-related information is information indicating a relationship between an activity expressed using information related to the activity of the subject as a parameter and a predicted value (INDEX) of the disease. For example, disease-related information for obtaining an INDEX related to dementia (disease) is expressed as follows.
-1.629 (average value of the intensity of walking performed at 3 to 6 o'clock) -0.02 (average value of the number of steps of walking performed at 21 to 24 o'clock) +0.192 (age) -17.139 Equation (5)

In the present modification, in the flowchart shown in FIG. 6, the body state information estimation unit 132 shown in FIG. 2 reads out disease-related information of Formula (5), for example, from the related information storage memory 19, and Formula (5) By applying parameters related to user activity (walking) and parameters such as age within parentheses () shown in (), it is possible to predict whether or not the user may develop dementia and its degree .
In this modification, the disease-related information is not limited to the form of a formula, as in the case of the body condition-related information, and any information can be used as long as it can provide activity information such as a table and obtain a predicted value of the disease. It may be of a form.

The above embodiments and examples include the following technical ideas.
<1>
At least body motion related information representing a relationship between exercise performed by a plurality of subjects acquired in advance and subject motion information related to a time zone during which the motion was performed, and subject physical status information regarding the subject's body, Body state information comprising a body state information estimating step of estimating the user's body state information by applying the user's motion information relating to the exercise performed by the user and the time zone during which the exercise was performed Estimation method.
<2>
The physical condition information according to <1>, wherein in the physical condition information estimation step, the physical condition information of the user is further estimated based on information on at least one of the height, weight, and age of the user. Estimation method.
<3>
The body condition information estimation method according to <1> or <2>, wherein the subject exercise information is information relating to an exercise amount or an exercise intensity of an exercise performed by the subject during a specific time of the day.
<4>
The body condition information estimation method according to <1> or <2>, wherein the subject exercise information is information related to a degree of movement or exercise intensity dispersion of exercise performed by the subject.
<5>
The body condition information estimation method according to <1> or <2>, wherein the subject exercise information is information related to a degree of exercise amount or intensity distribution of exercise performed by the subject.
<6>
<1> to <5, further comprising a message creation step of creating a message including advice on exercises to be performed by the user based on the body condition related information corresponding to the body condition information targeted by the user. > The body state information estimation method according to any one of the above.
<7>
Disease prediction that predicts a disease or disorder that the user develops by applying the user movement information to disease-related information that represents a relationship between the subject movement information and subject disease information related to the subject's disease or disorder The body state information estimation method according to any one of <1> to <6>, further including a step.
<8>
The body state related information representing the relationship between at least the subject exercise information acquired in advance and the subject exercise information related to the time zone in which the exercise was performed and the subject's body state information, A body state information estimation program comprising a body state information estimation method step of estimating body state information of a user by applying user motion information relating to a performed exercise and a time zone in which the exercise was performed.
<9>
At least body motion related information representing a relationship between exercise performed by a plurality of subjects acquired in advance and subject motion information related to a time zone during which the motion was performed, and subject physical status information regarding the subject's body, Body state information including a body state information estimation unit that estimates user's body state information by applying user motion information related to the exercise performed by the user and the time zone during which the exercise was performed Estimating device.
<10>
An exercise information acquisition device for acquiring user exercise information related to the exercise performed by the user and the time zone during which the exercise was performed;
The body state information estimation device according to <9>, wherein the user motion information is input from the motion information acquisition device, and body state information related to the user's body is estimated based on the user motion information;
The body state information estimation system characterized by including.

10, 40, 50 Physical state information estimation device 11 Acceleration sensor 13 Control unit 15 Display unit 17 Timer 19 Related information storage memory 20, 30 Exercise information acquisition device 21 Input unit 31 Output I / F
51 Input I / F
131 exercise information creation unit 132 body condition information estimation unit 133 message creation unit N network

Claims (9)

  At least body motion related information representing a relationship between exercise performed by a plurality of subjects acquired in advance and subject motion information related to a time zone during which the motion was performed, and subject physical status information regarding the subject's body, Body state information comprising a body state information estimating step of estimating the user's body state information by applying the user's motion information relating to the exercise performed by the user and the time zone during which the exercise was performed Estimation method.   The physical condition information according to claim 1, wherein in the physical condition information estimation step, the physical condition information of the user is further estimated based on information on at least one of the height, weight, and age of the user. Estimation method.   The body condition information estimation method according to claim 1, wherein the subject exercise information is information relating to an exercise amount or an exercise intensity of an exercise performed by the subject during a specific time of the day.   The body condition information estimation method according to claim 1, wherein the subject exercise information is information related to a degree of movement or exercise intensity dispersion of exercise performed by the subject.   5. A message creating step of creating a message including advice relating to exercise to be performed by the user based on the physical condition related information corresponding to the physical condition information targeted by the user. The body state information estimation method according to any one of the above.   Disease prediction that predicts a disease or disorder that the user develops by applying the user movement information to disease-related information that represents a relationship between the subject movement information and subject disease information related to the subject's disease or disorder The body condition information estimation method according to claim 1, further comprising a step.   The body state related information representing the relationship between at least the subject exercise information acquired in advance and the subject exercise information related to the time zone in which the exercise was performed and the subject's body state information, A body state information estimation program comprising a body state information estimation method step of estimating body state information of a user by applying user motion information relating to a performed exercise and a time zone in which the exercise was performed.   At least body motion related information representing a relationship between exercise performed by a plurality of subjects acquired in advance and subject motion information related to a time zone during which the motion was performed, and subject physical status information regarding the subject's body, Body state information including a body state information estimation unit that estimates user's body state information by applying user motion information related to the exercise performed by the user and the time zone during which the exercise was performed Estimating device. An exercise information acquisition device for acquiring user exercise information related to the exercise performed by the user and the time zone during which the exercise was performed;
The body state information estimation device according to claim 8, wherein the user motion information is input from the motion information acquisition device, and body state information related to the user's body is estimated based on the user motion information;
The body state information estimation system characterized by including.

Images