Health state estimation device, health state estimation system, and health state estimation method

Abstract

A health state estimation system (1) comprises: a storage unit (310) that stores a trained model (312) trained in advance so as to estimate a health state of a user of chopsticks (100) or cutlery when a movement amount (AUC) relating to eating behavior is input; a measurement unit (101) that measures movement of the chopsticks (100) or cutlery; a calculation unit (322) that calculates the movement amount (AUC) on the basis of measurement data of the movement measured by the measurement unit (101); an estimation unit (323) that estimates the health state by inputting the movement amount (AUC) to the trained model (312); and an output unit (324) that outputs the health state.

Description

Health state estimation device, health state estimation system, and health state estimation method

[0001] The present disclosure relates to a health state estimation device, a health state estimation system, and a health state estimation method.

[0002] The determination results of so-called eating behaviors, such as what the user eats during a meal in what order and how the user holds and operates chopsticks, are utilized for estimating the health state in the fields of rehabilitation and healthcare. Conventionally, for example, the operation of chopsticks has been determined based on the data of an acceleration sensor attached to the chopsticks (see, for example, Patent Document 1).

[0003] Japanese Patent Application Laid-Open No. 2015-225277

[0004] However, although information regarding the operation of chopsticks can be obtained based on the data of an acceleration sensor attached to the chopsticks, it has been difficult to estimate the health state of the user.

[0005] In consideration of the above points, an object of the present disclosure is to propose a health state estimation device, a health state estimation system, and a health state estimation method that can easily estimate the health state of a user.

[0006] To solve such problems, the health state estimation device of the present disclosure includes a storage unit that stores a learned model pre-learned to estimate the health state of a user of chopsticks or cutlery when an amount of exercise related to eating behavior is input, a measurement unit that measures the operation of chopsticks or cutlery, a calculation unit that calculates the amount of exercise based on the measurement data of the operation measured by the measurement unit, an estimation unit that estimates the health state by inputting the amount of exercise into the learned model, and an output unit that outputs the health state.

[0007] In the present disclosure, the eating behavior preferably includes all operations related to eating via chopsticks or cutlery, such as the type of operation of chopsticks or cutlery, the amount of movement of chopsticks or cutlery, the moving speed of chopsticks or cutlery, the chewing time of the user, and the posture of the user.

[0008] In this disclosure, it is preferable that the measuring unit includes an motion detection sensor for detecting the movement of chopsticks or cutlery, or a pressure sensor for detecting the pressure applied by the user when holding the chopsticks or cutlery with their fingers.

[0009] In this disclosure, it is preferable that the calculation unit calculates the amount of motion based on the user's chewing time, which corresponds to the measurement time of the angular velocity of the chopsticks or cutlery by the motion detection sensor.

[0010] In this disclosure, health status preferably includes one of the following: blood glucose level, body fat percentage, body composition including skeletal muscle mass, BMI (Body Mass Index), or degree of obesity.

[0011] To solve the aforementioned problems, this disclosure provides a health status estimation system including a measuring device and an estimation device, wherein the measuring device includes a measuring unit for measuring the movement of chopsticks or cutlery, and a transmitting unit for transmitting measurement data of the movement measured by the measuring unit, and the estimation device includes a storage unit that stores a pre-trained model that is learned to estimate the health status of a user of chopsticks or cutlery when the amount of movement related to the user's eating behavior with chopsticks or cutlery is input, a receiving unit for receiving measurement data, a calculation unit for calculating the amount of movement based on the measurement data, an estimation unit for estimating the health status by inputting the amount of movement into the pre-trained model, and an output unit for outputting the health status.

[0012] To solve the aforementioned problems, this disclosure provides a health status estimation system including a measuring device, a terminal device, and a server device, wherein the measuring device includes a measuring unit for measuring the movement of chopsticks or cutlery, and a transmitting unit for transmitting measurement data of the movement measured by the measuring unit; the terminal device includes a first transmitting / receiving unit for receiving measurement data from the measuring device, transmitting measurement data to the server device, and receiving the user's health status from the server device, and a display unit for displaying the health status; the server device includes a second transmitting / receiving unit for receiving measurement data from the terminal device and transmitting the health status to the terminal device, a storage unit for storing a pre-trained model that is learned in advance to estimate the user's health status with respect to chopsticks or cutlery when the amount of movement related to the user's eating behavior with chopsticks or cutlery is input, a calculation unit for calculating the amount of movement based on the measurement data, and an estimation unit for estimating the health status by inputting the amount of movement into the pre-trained model.

[0013] To solve the aforementioned problems, the health status estimation method of the present disclosure is characterized by having the following steps: inputting the amount of movement related to eating behavior, storing a pre-trained model in a memory unit that has been learned in advance to estimate the health status of the user of chopsticks or cutlery, measuring the movement of chopsticks or cutlery with a measurement unit, calculating the amount of movement with a calculation unit based on the measurement data of the movement measured by the measurement unit, estimating the health status by inputting the amount of movement into the pre-trained model, and outputting the health status with an output unit.

[0014] The health status estimation device, health status estimation system, and health status estimation method relating to this disclosure can easily estimate the user's health status in accordance with their eating habits.

[0015] This figure shows the schematic configuration of the health status estimation system according to the first embodiment of this disclosure. This figure shows the schematic configuration of the chopstick-shaped device. This figure shows the circuit configuration of the chopstick-shaped device. This figure shows the circuit configuration of the terminal device. This figure shows the circuit configuration of the server device. These are graphs (A) and (B) showing the relationship between the user's grip strength and the pressure when holding the chopsticks 100a and 100b of the chopstick-shaped device. This is a graph showing the relationship between the number of food items and the amount of exercise consumed (AUC). These are graphs (A) to (D) showing the relationship between the type of food and the amount of exercise consumed (AUC). These are graphs showing the relationship between chewing time and the amount of exercise consumed (AUC) (A) and the relationship between chewing time and body fat percentage (B). This is a graph showing the relationship between the amount of exercise consumed (AUC) and body fat percentage. This is a graph showing the relationship between the amount of exercise consumed (AUC) and body fat percentage when the same food is consumed. This is a sequence chart showing the procedure for estimating body fat percentage according to the amount of exercise consumed (AUC). This is a flowchart showing the body fat percentage estimation process. This figure shows the schematic configuration of the health status estimation system according to the second embodiment of this disclosure. This figure shows the circuit configuration of the terminal device according to the second embodiment of this disclosure. This is a sequence chart showing the procedure for estimating body fat percentage in the second embodiment.

[0016] <First Embodiment> A health status estimation system relating to one aspect of the first embodiment will be described below with reference to the figures. However, it should be noted that the technical scope of this disclosure is not limited to these embodiments, but extends to the disclosures described in the claims and their equivalents.

[0017] <Overall Configuration of Health Status Estimation System> Figure 1 is a diagram showing the schematic configuration of the health status estimation system 1 according to the first embodiment of this disclosure.

[0018] As shown in Figure 1, the health status estimation system 1 is a system that estimates and outputs an indicator of health status, such as body fat percentage, based on the amount of physical activity related to the user's eating behavior. Here, eating behavior includes various choices in eating (when to eat, what to eat, how much to eat, etc.). Eating behavior also includes all actions related to the user's eating with chopsticks, such as the types of chopstick movements the user makes when eating (loosening food with chopsticks, cutting food with chopsticks, picking up food with chopsticks, bringing food to the mouth with chopsticks, stirring food with chopsticks, the number of times to chew and chewing time, the time until swallowing food, etc.), the amount of chopstick movement, the speed of chopstick movement, the chewing time of the user using chopsticks, and the user's posture.

[0019] The health status estimation system 1 comprises a chopstick-shaped device 100, a terminal device 200, and a server device 300. The chopstick-shaped device 100, the terminal device 200, and the server device 300 are connected to each other via a network N so as to be able to communicate with each other. The network N is a wired network such as the Internet or an intranet. The network N may also be a wireless network such as a wireless LAN (Local Area Network).

[0020] <External structure of the chopstick-shaped device> Figure 2 shows the schematic structure of the chopstick-shaped device.

[0021] The chopstick-shaped device 100 has chopstick sticks 100a and 100b, and a measuring section 101. In this case, chopstick stick 100a is the working chopstick, and chopstick stick 100b is the fixed chopstick. The working chopstick is the chopstick that moves more when using chopsticks. The fixed chopstick is the chopstick that moves less when using chopsticks. The measuring section 101 is provided on chopstick stick 100a. The measuring section 101 may also be provided on chopstick stick 100b. The chopstick-shaped device 100 is an example of chopsticks.

[0022] The measuring unit 101 measures the operation of the chopstick-shaped device 100. The measuring unit 101 has an operation detection sensor 102 and a pressure sensor 103. The operation detection sensor 102 is included in a processing unit 110 which consists of an IC chip capable of measuring the operation (acceleration and angular velocity) of the chopstick stick 100a, and the processing unit 110 is attached to the chopstick head portion of the chopstick stick 100a with the processing unit 110 embedded in it. Alternatively, the processing unit 110 may be attached to the chopstick tip portion of the chopstick stick 100a with the processing unit 110 embedded in it.

[0023] The pressure sensor 103 is fixed to the central part of the chopstick handle 100a in the longitudinal direction, where the index finger makes contact, with its surface slightly protruding. In other words, the pressure sensor 103 is provided so that it can be contacted by the user's index finger when holding the chopstick handle 100a.

[0024] The pressure sensor 103 is a capacitive or piezoelectric sensor that detects the pressure applied when a user holds the central portion of the chopstick stick 100a of the chopstick-shaped device 100 with their fingers. However, the pressure sensor 103 may also be a tactile sensor that detects the contact pressure of the fingers.

[0025] <Circuit configuration of the chopstick-shaped device> Figure 3 shows the circuit configuration of the chopstick-shaped device 100.

[0026] The chopstick-shaped device 100 includes a measuring unit 101, a processing unit 110, and a battery for supplying power. The measuring unit 101 includes a motion detection sensor 102 and a pressure sensor 103, as described above. The processing unit 110 includes the motion detection sensor 102, a storage unit 111, a transmitting / receiving unit 112, a control unit 113 such as a CPU (Central Processing Unit), and a communication interface 114, which are interconnected via a CPU bus or the like. The processing unit 110 is realized by the hardware resources constituting the chopstick-shaped device 100 cooperating with a program pre-installed on the chopstick-shaped device 100.

[0027] The motion detection sensor 102 detects measurement data, including acceleration data and angular velocity data related to the movement of the chopsticks 100a, for example, every second, and outputs it to the storage unit 111. The pressure sensor 103 is connected to the processing unit 110 via the communication interface 114. The pressure sensor 103 detects measurement data, including the pressing force (pressure value) applied by the user's index finger holding the chopsticks 100a, for example, every second, and outputs it to the storage unit 111. The pressure sensor 103 may also detect the average pressure value per minute as measurement data.

[0028] The control unit 113 of the processing unit 110 operates based on a program previously stored in the storage unit 111. A DSP (digital signal processor), LSI (large scale integration), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), etc., may be used as the control unit 113.

[0029] The storage unit 111 is a memory device such as RAM (Random Access Memory), ROM (Read Only Memory), or USB memory. The storage unit 111 stores measurement data related to the movement of the chopsticks stick 100a detected by the motion detection sensor 102 and the pressure sensor 103.

[0030] The transmitting / receiving unit 112 has an antenna for transmitting and receiving wireless signals and a wireless communication interface circuit that conforms to a communication protocol such as a wireless LAN (Local Area Network), and connects wirelessly to the network N in accordance with a communication standard such as a wireless LAN.

[0031] The transmitting / receiving unit 112 can wirelessly transmit measurement data received from the storage unit 111 to terminal devices 200 and server devices 300, etc., via the network N. The transmitting / receiving unit 112 can also wirelessly receive data from terminal devices 200 and server devices 300 via the network N. Specifically, the transmitting / receiving unit 112 has a wireless communication interface circuit conforming to communication standards such as LTE (Long Term Evolution) and 5G, and wirelessly connects to the network N via a base station. Alternatively, the transmitting / receiving unit 112 may have a wired communication interface circuit conforming to communication protocols such as TCP / IP (Transmission Control Protocol / Internet Protocol) and Bluetooth (registered trademark), and may connect to the network N via a wired connection according to a predetermined communication standard.

[0032] <Circuit Configuration of Terminal Device> Figure 4 shows the circuit configuration of terminal device 200.

[0033] The terminal device 200 is, for example, a smartphone. However, the terminal device 200 may also be a personal computer, a notebook PC or tablet PC, a game console, etc.

[0034] The terminal device 200 includes a first transmitting / receiving unit 201, a storage unit 210, a processing unit 220, a display unit 230, and an input unit 250, etc. The first transmitting / receiving unit 201, the storage unit 210, the processing unit 220, the display unit 230, and the input unit 250 are interconnected via a CPU bus or the like.

[0035] The first transceiver unit 201 has an antenna for transmitting and receiving wireless signals and a wireless communication interface circuit that conforms to a communication protocol such as wireless LAN, and connects wirelessly to the network N in accordance with a communication standard such as wireless LAN. The first transceiver unit 201 may also have a wireless communication interface circuit that conforms to a communication standard such as LTE or 5G, and connect to the network N via a base station. Alternatively, the first transceiver unit 201 may also have a wired communication interface circuit that conforms to a communication protocol such as TCP / IP or Bluetooth (registered trademark), and connect to the network N via a wired connection in accordance with a predetermined communication standard. The first transceiver unit 201 receives measurement data from the motion detection sensor 102 and pressure sensor 103 of the chopstick-shaped device 100, transmits this measurement data to the server device 300, and receives the estimated result of the user's body fat percentage from the server device 300.

[0036] The storage unit 210 includes memory devices such as RAM and ROM, fixed disk devices such as hard disks, and portable storage devices such as USB memory. The storage unit 210 stores measurement data received by the first transmitting / receiving unit 201 from the motion detection sensor 102 and pressure sensor 103 of the chopstick-shaped device 100, and stores the estimated result of the user's body fat percentage received from the server device 300.

[0037] The processing unit 220 operates based on a program pre-stored in the storage unit 210 and provides overall control. The processing unit 220 is, for example, a CPU, but a DSP, LSI, ASIC, FPGA, etc. may also be used. The processing unit 220 transmits the measurement data stored in the storage unit 210 to the server device 300 via the first transmission / reception unit 201. The processing unit 220 also displays the estimated result of the user's body fat percentage, which is stored in the storage unit 210, on the display unit 230.

[0038] The display unit 230 has a display including an organic EL (Electro Luminescence) or liquid crystal display and an interface circuit that outputs image data to the display, and displays an image on the display based on the image data. The display unit 230 displays the estimated result of the user's body fat percentage (BFP) received from the server device 300 via the first transceiver unit 201. Body fat percentage (BFP) is one example of an indicator of the user's health status.

[0039] The input unit 250 includes a touch panel keyboard for inputting information to the terminal device 200, physical buttons such as a power button, and accepts user input.

[0040] <Server Device Circuit Configuration> Figure 5 shows the circuit configuration of the server device 300. The server device 300 is a computer device, and may be a personal computer, notebook PC, tablet PC, etc. The server device 300 has a second transceiver unit 301, a storage unit 310, and a processing unit 320, etc. The second transceiver unit 301, the storage unit 310, and the processing unit 320 are interconnected via a CPU bus or the like. The server device 300 is an example of an estimation device.

[0041] The second transceiver unit 301 has an antenna for transmitting and receiving wireless signals and a wireless communication interface circuit that conforms to a communication protocol such as wireless LAN, and connects wirelessly to the network N according to a communication standard such as wireless LAN or Bluetooth. The second transceiver unit 301 may also have a wireless communication interface circuit that conforms to a communication standard such as LTE or 5G, similar to the first transceiver unit 201, and connect to the network N via a base station. Alternatively, the second transceiver unit 301 may have a wired communication interface circuit that conforms to a communication protocol such as TCP / IP or Bluetooth, and connect to the network N via a wired connection according to a predetermined communication standard. The second transceiver unit 301 receives measurement data from the chopstick-shaped device 100 from the terminal device 200 and transmits the estimated result of the user's body fat percentage (BFP) to the terminal device 200.

[0042] The storage unit 310 stores programs 311 used for various processes of the server device 300, and various data such as databases, tables, etc. The program 311 may be installed in the storage unit 310 using a known setup program or the like from a computer-readable portable recording medium. The portable recording medium is, for example, a CD-ROM, a DVD-ROM, etc. The program 311 may be stored in a recording medium possessed by a predetermined server and installed via the network N.

[0043] In addition to the above, a learned model 312 is stored in the storage unit 310. The learned model 312 is a combination of a plurality of data sets of the amount of movement related to eating behavior (hereinafter referred to as "meal movement amount (AUC (Area under the curve))") calculated based on measurement data from the chopstick-type device 100 in the processing unit 320 described later, and the body fat percentage (BFP) corresponding to the meal movement amount (AUC). Using this as teacher data, it is pre-learned in advance by a neural network, a support vector machine, or the like. When the meal movement amount (AUC) corresponding to the operation of the chopstick-type device 100 is input, the learned model 312 is pre-learned to output the body fat percentage (BFP) corresponding to the meal movement amount (AUC) as an estimation result.

[0044] The meal movement amount (AUC) is a series of activity amounts (movement amounts) generated along with eating behavior corresponding to measurement data corresponding to the operation of the chopstick bar 100a detected by the motion detection sensor 102 and the pressure sensor 103 in the chopstick-type device 100, respectively. The measurement data is, for example, the movement amount of the chopstick bar 100a, the movement speed of the chopstick bar 100a, the angular velocity of the chopstick bar 100a, the measurement time when these are detected (the usage time of the chopstick bar 100a), the pressure value for grasping the chopstick bar 100a, etc. The meal movement amount (AUC) is an example of the movement amount.

[0045] The processing unit 320 includes an acquisition unit 321, a calculation unit 322, an estimation unit 323, an output unit 324, etc. The processing unit 320 functions as the acquisition unit 321, the calculation unit 322, the estimation unit 323, and the output unit 324 by the cooperation of the program 311 stored in the storage unit 310 and the hardware resources constituting the server device 300.

[0046] <Relationship between the user's grip strength and the pressure for holding the chopstick-type device> Figure 6 is a graph showing the relationships (A) and (B) between the user's grip strength and the pressure for holding the chopstick rods 100a and 100b of the chopstick-type device 100.

[0047] In FIG. 6(A), between the user's grip strength value (Hand grip) and the pressure value (grip) when holding the chopstick rods 100a and 100b of the chopstick-type device 用手指で食事をするときの圧力値(grip)とは、握力値(Hand grip)が大きくなるほど圧力値(grip)が大きくなる傾向が示されている。ここで、箸型デバイス100の箸棒100a、100bを指で保持する圧力値(grip)は、箸型デバイス100の圧力センサ103によって検出される測定データである。

[0048] Also, in FIG. (B), between the user's grip strength value (Hand grip) and the pressure value (grip) for holding the chopstick-type device 100 with the fingers, regardless of the type of meal (noodles such as soba, donburi rice, simple meals that are single items such as curry rice, and balanced meals with a large number of items served in 4 or 5 dishes like ichiju sansai), the higher the user's grip strength value (Hand grip), the greater the pressure value (grip) tends to be. That is, the grip strength value (Hand grip) and the pressure value (grip) are in a proportional relationship, and it is assumed that as the pressure value (grip) increases, the meal exercise amount (AUC) will naturally increase.

[0049] <Relationship between the number of food items in a meal and the meal exercise amount (AUC)> Figure 7 is a graph showing the relationship between the number of food items in a meal and the meal exercise amount (AUC).

[0050] Figure 7 shows a tendency for the amount of eating activity (AUC) to increase as the number of food items (types) increases, as shown in A (7 types) to D (1 type). This is because the more food items (types) there are, the more times the user moves the chopstick-shaped device 100, and the greater the amount of movement of the chopstick-shaped device 100, as well as the greater the pressure value (grip) when holding the chopstick-shaped device 100 with the fingers. In other words, a correlation can be observed where the amount of eating activity (AUC) increases as the number of food items (types) increases. The number of times the chopstick stick 100a moves when the chopstick-shaped device 100 is moved, the amount of movement of the chopstick stick 100a, the speed of movement of the chopstick stick 100a, and the angular velocity while holding the chopstick stick 100a, as well as the measurement time (usage time) when these are detected, are measurement data detected by the motion detection sensor 102 of the chopstick-shaped device 100.

[0051] <Relationship between food type and dietary exercise (AUC)> Figure 8 is a graph showing the relationship between food type and dietary exercise (AUC) (A) to (D).

[0052] Figures 8(A) to 8(D) show the waveforms of the amount of eating exercise (AUC) over time when a user eats "rice," "fish," "kimpira / roots," and "noodles" using the chopstick-shaped device 100. In other words, the calculation unit 322 of the server device 300 can calculate the amount of eating exercise (AUC) according to the measurement time of the chopstick-shaped device 100, which differs depending on the type of food.

[0053] Furthermore, as shown in Figures 8(A) to 8(D), there are waveform patterns for dietary exercise volume (AUC) corresponding to different types of food. Therefore, the estimation unit 323 of the server device 300 compares the waveform of dietary exercise volume (AUC) calculated by the calculation unit 322 with the waveform patterns of dietary exercise volume (AUC) previously stored in the storage unit 310 using known techniques such as pattern matching. This allows the estimation unit 323 to estimate the types of food consumed by the user, as well as the number of different types of food consumed. It is expected that the dietary exercise volume (AUC) will increase as the variety of foods consumed increases. Therefore, in addition to estimating the body fat percentage according to the dietary exercise volume (AUC), the estimation unit 323 can also estimate the contents of the food consumed by the user based on the estimated food types, making it possible to suggest types of food that are helpful in reducing body fat percentage.

[0054] <Relationship between chewing time and dietary exercise (AUC) and relationship between chewing time and body fat percentage> Figure 9 is a graph showing the relationship between chewing time and dietary exercise (AUC) (A) and the relationship between chewing time and body fat percentage (BFP) (B).

[0055] Figure 9(A) shows a correlation (shown by a dashed line) indicating that the longer the chewing time, the greater the amount of exercise during meals (AUC). In other words, longer chewing time means greater exercise during meals (AUC). Figure 9(B) also shows a correlation (shown by a dashed line) indicating that the longer the chewing time, the smaller the body fat percentage (BFP). In other words, longer chewing time means that you are exercising for a longer period of time, which means that your body fat will decrease.

[0056] While the user is chewing, the chopsticks 100a are not moved significantly, so the motion detection sensor 102 hardly measures any acceleration. However, because the angle of the chopsticks 100a changes, angular velocity data is measured. In other words, the measurement time during which the motion detection sensor 102 detects measurement data including angular velocity data (the usage time of the chopsticks 100a) can be considered to be the user's chewing time. Therefore, it is possible to calculate the amount of exercise during meals (AUC) based on the measurement time during which measurement data including the angular velocity of the chopsticks 100a is detected (the usage time of the chopsticks 100a), i.e., the user's chewing time.

[0057] Furthermore, when the user's posture changes, the angle of the chopsticks 100a changes, and angular velocity data is measured. In other words, the measurement time (the usage time of the chopsticks 100a) during which measurement data including angular velocity data is detected by the motion detection sensor 102 can be considered to be the time during which the user's posture during eating changed. Therefore, it is possible to calculate the amount of eating exercise (AUC) based on the measurement time during which the angular velocity of the chopsticks 100a is detected, that is, the posture change time during which the user's posture during eating changes.

[0058] <Relationship between AUC (Amount of Dietary and Physical Activity) and Body Fat Percentage> Figure 10 is a graph showing the relationship between AUC (Amount of Dietary and Physical Activity) and body fat percentage (BFP). Figure 10 shows a tendency (correlation) where the larger the AUC, the smaller the body fat percentage (BFP) (shown by the dashed line). Body fat percentage (BFP) is the percentage of body fat relative to body weight.

[0059] Figure 11 is a graph showing the relationship between dietary exercise (AUC) and body fat percentage (BFP) when consuming the same foods. Figure 11 shows a correlation (shown by the dashed line) that, even when consuming the same foods, the greater the dietary exercise (AUC), the lower the body fat percentage (BFP).

[0060] From the above, it can be concluded that when a balanced meal with many different items, where the pressure value when holding the chopsticks 100a is large, and the amount and speed of movement of the chopsticks 100a are large, is eaten over a period of time corresponding to the chewing time and posture change time corresponding to the measurement time for detecting the angular velocity of the chopsticks 100a, the amount of eating exercise (AUC) will be large. A correlation has been observed between the amount of eating exercise (AUC) and body fat percentage (BFP), where as the amount of eating exercise (AUC) increases, the body fat percentage (BFP) decreases. Therefore, it is possible to estimate the body fat percentage (BFP) according to the user's amount of eating exercise (AUC).

[0061] <Procedure for estimating body fat percentage based on diet and exercise (AUC)> Figure 12 is a sequence chart showing the procedure for estimating body fat percentage (BFP) based on diet and exercise (AUC).

[0062] The motion detection sensor 102 and pressure sensor 103 in the chopstick-shaped device 100 measure the movement of the chopstick-shaped device 100 by the user eating (step S101). The motion detection sensor 102 and pressure sensor 103 each acquire measurement data corresponding to the movement of the chopstick stick 100a, which is the working chopstick.

[0063] The control unit 113 of the chopstick-shaped device 100 stores the measurement data measured by the motion detection sensor 102 and the pressure sensor 103, respectively, in the storage unit 111 and transmits it to the terminal device 200 via the transmitting / receiving unit 112 (step S102). In this case, the control unit 113 transmits the measurement data to the terminal device 200 sequentially each time it is measured during the user's meal. However, the control unit 113 is not limited to this, and may transmit all the measurement data stored in the storage unit 111 during the meal to the terminal device 200 all at once after the user has finished eating.

[0064] The first transmitting / receiving unit 201 of the terminal device 200 receives measurement data from the transmitting / receiving unit 112 of the chopstick-shaped device 100 via the network N (step S201). The processing unit 220 of the terminal device 200 stores the measurement data received via the first transmitting / receiving unit 201 in the storage unit 210.

[0065] The processing unit 220 of the terminal device 200 transmits the measurement data to the server device 300 via the first transmitting / receiving unit 201 (step S202). The processing unit 220 transmits the measurement data to the server device 300 each time it receives measurement data from the chopstick-shaped device 100. However, the processing unit 220 may also transmit all of the measurement data to the server device 300 together if it receives all the measurement data from the chopstick-shaped device 100 at once after the user has finished eating.

[0066] The second transmitting / receiving unit 301 of the server device 300 receives measurement data from the terminal device 200 and stores it in the storage unit 310, while the acquisition unit 321 of the processing unit 320 acquires the measurement data (step S301). The acquisition unit 321 outputs the measurement data to the calculation unit 322.

[0067] The calculation unit 322 of the server device 300 calculates the amount of eating exercise (AUC) related to the user's eating behavior via the chopsticks 100a, based on the measurement time of the motion detection sensor 102 (usage time of the chopsticks 100a) and the pressure value of the pressure sensor 103, from the measurement data corresponding to the operation of the chopsticks stick 100a of the chopstick-shaped device 100 (step S302). The calculation unit 322 outputs the calculated amount of eating exercise (AUC) to the estimation unit 323.

[0068] The amount of exercise during a meal (AUC) is the value obtained from the moment the motion detection sensor 102 and pressure sensor 103 detect measurement data when the user starts eating until the end of the meal, and is calculated by the following equation (1).

[0069] AUC = Σ(T) Ｕ ×P ｈ )×1 / 2……………………………………………………(1) T Ｕ : Usage time of chopsticks stick 100a (time when measurement data from motion detection sensor 102 was detected) P ｈ : Maximum value of pressure sensor 103

[0070] The estimation unit 323 of the server device 300 estimates the user's body fat percentage (BFP) based on the amount of dietary exercise (AUC) obtained by equation (1) (step S303). Specifically, the estimation unit 323 inputs the amount of dietary exercise (AUC) into the trained model 312 of the storage unit 310 to estimate the body fat percentage (BFP) corresponding to the amount of dietary exercise (AUC), and outputs the estimation result to the output unit 324. Details of this estimation process will be described later.

[0071] The output unit 324 of the server device 300 transmits the estimated body fat percentage (BFP) result to the terminal device 200 via the network N using the second transmission / reception unit 301 (step S304). At this time, the output unit 324 stores the estimated result in the storage unit 310.

[0072] The first transmitting / receiving unit 201 of the terminal device 200 receives an estimated result regarding the user's body fat percentage (BFP) from the server device 300 (step S203). The processing unit 220 of the terminal device 200 stores the estimated result received via the first transmitting / receiving unit 201 in the storage unit 210 and outputs it to the display unit 230.

[0073] The display unit 230 of the terminal device 200 displays the estimation result (step S204). By displaying the estimated result of body fat percentage (BFP), the display unit 230 can notify the user of their body fat percentage (BFP) according to their eating habits.

[0074] <Body Fat Percentage Estimation Process> Figure 13 is a flowchart showing the body fat percentage (BFP) estimation process.

[0075] The estimation unit 323 of the server device 300 inputs the amount of diet and exercise (AUC) calculated by the calculation unit 322 to the trained model 312 (step S3011). As a result of inputting the amount of diet and exercise (AUC) to the trained model 312, the estimation unit 323 obtains the body fat percentage (BFP) output from the trained model 312.

[0076] The estimation unit 323 of the server device 300 determines whether the body fat percentage (BFP) output from the trained model 312 is 14.9% or less (step S3012). If the body fat percentage (BFP) is 14.9% or less (step S3012: YES), the estimation unit 323 estimates the user's body fat percentage corresponding to the amount of diet and exercise (AUC) as "low" (step S3013).

[0077] If the body fat percentage (BFP) is greater than 14.9% (step S3012: NO), the estimation unit 323 of the server device 300 determines whether the body fat percentage (BFP) is greater than 14.9% but 24.9% or less (step S3014). If the body fat percentage (BFP) is greater than 14.9% but 24.9% or less (step S3014: YES), the estimation unit 323 estimates the user's body fat percentage corresponding to the amount of diet and exercise (AUC) as "standard" (step S3015).

[0078] The estimation unit 323 of the server device 300 estimates the user's body fat percentage, corresponding to their diet and exercise volume (AUC), as "high" if the body fat percentage (BFP) is greater than 24.9% (step S3014: NO) (step S3016).

[0079] The estimation unit 323 of the server device 300 determines the estimation result regarding the user's body fat percentage (BFP) estimated in step S3013, step S3014, or step S3015 (step S3017), and terminates the series of estimation processes. Note that any numerical value may be used as the criterion percentage when estimating "low," "standard," or "high" body fat percentage.

[0080] In this way, while the user is eating using the chopstick-shaped device 100, measurement data corresponding to eating behavior is transmitted from the chopstick-shaped device 100 to the server device 300 via the terminal device 200. When measurement data is obtained from the motion detection sensor 102 and pressure sensor 103 of the chopstick-shaped device 100, it means that the user is performing various eating actions.

[0081] Therefore, the server device 300 calculates the amount of exercise consumed during a meal (AUC) based on the measurement data from the chopstick-shaped device 100 using the calculation unit 322, estimates the body fat percentage (BFP) corresponding to the amount of exercise consumed during a meal (AUC) using the estimation unit 323, and transmits the estimation result to the terminal device 200. The terminal device 200 displays the estimated result of the body fat percentage (BFP) received from the server device 300 on the display unit 230, so that the user can quickly recognize the estimated result of the body fat percentage (BFP) after a meal.

[0082] As detailed above, the health status estimation system 1 measures the movement of the chopsticks 100a of the chopstick-shaped device 100 using the measurement unit 101, and calculates the amount of exercise during meals (AUC) based on the measurement data regarding the movement of the chopsticks 100a using the server device 300. The health status estimation system 1 can estimate and output the body fat percentage (BFP) by inputting the calculated amount of exercise during meals (AUC) into the trained model 312. Thus, a health status estimation system 1 can be realized that can easily estimate the body fat percentage (BFP) in response to all of the user's eating actions via the chopstick-shaped device 100.

[0083] <Second Embodiment> The health status estimation system relating to one aspect of the second embodiment will be described below with reference to the figures.

[0084] Figure 14 is a diagram showing the schematic configuration of the health status estimation system 1A according to the second embodiment of this disclosure.

[0085] As shown in Figure 14, where the corresponding parts are denoted with the same reference numerals as in Figure 1, the health status estimation system 1A is a system that estimates and outputs body fat percentage (BFP), which is an indicator of health status, based on the amount of dietary exercise (AUC) related to the user's eating behavior.

[0086] The health status estimation system 1A has a chopstick-shaped device 100 and a terminal device 200a, but does not have a server device 300. The chopstick-shaped device 100 and the terminal device 200a are connected to each other so as to be able to communicate with each other via a network N. The chopstick-shaped device 100 has the same configuration as in the first embodiment.

[0087] Figure 15 is a diagram showing the circuit configuration of a terminal device according to the second embodiment of this disclosure.

[0088] The terminal device 200a has a processing unit 240 that has the same functions as the processing unit 320 of the server device 300 compared to the terminal device 200 in the first embodiment, a storage unit 210 that stores the program 311 and the learned model 312 stored in the storage unit 310 of the server device 300, and an input unit 250. The first transmitting / receiving unit 201 and the display unit 230 of the terminal device 200a are the same as those of the terminal device 200 in the first embodiment.

[0089] Figure 16 is a sequence chart showing the procedure for estimating body fat percentage in the second embodiment.

[0090] The motion detection sensor 102 and pressure sensor 103 of the chopstick-shaped device 100 measure the movement of the chopstick stick 100a of the chopstick-shaped device 100 when a user is eating, and acquire measurement data corresponding to the movement of the chopstick stick 100a (step S101).

[0091] The control unit 113 of the chopstick-shaped device 100 stores the measurement data measured by the motion detection sensor 102 and the pressure sensor 103, respectively, in the storage unit 111, and transmits it to the terminal device 200 via the transmitting / receiving unit 112 (step S102).

[0092] The first transmitting / receiving unit 201 of the terminal device 200 receives measurement data from the transmitting / receiving unit 112 of the chopstick-shaped device 100 via the network N, stores the measurement data in the storage unit 210, and the acquisition unit 241 acquires the measurement data (step S211).

[0093] The calculation unit 242 of the terminal device 200 calculates the amount of exercise related to eating behavior (AUC) using the above-mentioned equation (1) based on the acquired measurement data, and outputs the calculated amount of exercise related to eating behavior (AUC) to the estimation unit 243 (step S212).

[0094] The estimation unit 243 of the terminal device 200 inputs the amount of dietary exercise (AUC) into the trained model 312 in the storage unit 210 and obtains the body fat percentage (BFP) output from the trained model 312 as the estimation result (step S213). The processing unit 240 of the terminal device 200 stores the estimation result from the estimation unit 243 in the storage unit 210 and outputs it to the display unit 230.

[0095] The display unit 230 of the terminal device 200 displays one of the estimated body fat percentages as "low," "standard," or "high" (step S214).

[0096] In this way, when a user eats using the chopstick-shaped device 100, the measurement data from the measurement unit 101 is automatically transmitted from the chopstick-shaped device 100 to the terminal device 200. The terminal device 200 then calculates the amount of exercise during meals (AUC) from the measurement data, estimates the body fat percentage (BFP) based on the amount of exercise during meals (AUC), and displays the estimated result on the display unit 230. This allows the user to quickly recognize the estimated result of their post-meal body fat percentage.

[0097] As detailed above, the health status estimation system 1A measures the movement of the chopsticks 100a of the chopstick-shaped device 100 using the motion detection sensor 102 and the pressure sensor 103, and calculates the amount of exercise during meals (AUC) based on the measurement data of the movement of the chopsticks 100a using the terminal device 200. The health status estimation system 1A then estimates the body fat percentage (BFP) by inputting the amount of exercise during meals (AUC) into the trained model 312, and the estimation result can be displayed on the display unit 230. Thus, with a simple configuration consisting only of the chopstick-shaped device 100 and the terminal device 200, a health status estimation system 1A that can easily estimate the body fat percentage (BFP) according to the user's eating behavior can be realized.

[0098] <Other Embodiments> In the first and second embodiments, the case in which a chopstick-shaped device 100 is used as the object for calculating the amount of eating exercise (AUC) was described, but the invention is not limited to this, and cutlery such as spoons, forks, and knives equipped with motion detection sensors 102 and pressure sensors 103 may also be used.

[0099] In the estimation unit 323 of the first embodiment and the estimation unit 243 of the second embodiment, the user's body fat percentage (BFP) is estimated as an indicator of health status. However, the system is not limited to this, and the user's blood glucose level, body composition including skeletal muscle mass, BMI (Body Mass Index), degree of obesity, nutritional status, etc., may also be estimated as indicators of health status.

[0100] Furthermore, in the estimation unit 323 of the first embodiment and the estimation unit 243 of the second embodiment, the user's body fat percentage (BFP) is estimated as an indicator of their health status. However, the estimation units 323 and 243 are not limited to this, and may also determine the type of food according to the amount of exercise consumed (AUC) as shown in Figure 8, or the type of meal the user eats according to the measurement time of the measurement data (for example, eating simple meals quickly, or eating balanced meals without chewing properly). As a result, the server device 300 may be equipped with a recommendation unit (not shown) and, based on the determination results by the estimation units 323 and 243, provide dietary guidance or nutritional guidance to the user by recommending appropriate foods and nutrients through the recommendation unit.

[0101] The estimation unit 323 of the first embodiment and the estimation unit 243 of the second embodiment estimate body fat percentage (BFP) using a trained model 312. However, the system is not limited to this, and tables relating dietary exercise (AUC) values ​​to body fat percentages of "low," "standard," or "high" may be stored in the storage units 310 and 210 in advance, and the body fat percentage of "low," "standard," or "high" corresponding to the dietary exercise (AUC) values ​​may be output as the estimation result.

[0102] In the first embodiment, the estimation unit 323, and in the second embodiment, the estimation unit 243, output the body fat percentage as a category of "low," "standard," or "high" as the estimation result. However, they may also output the body fat percentage (BFP) value corresponding to the amount of dietary exercise (AUC) in percentage form.

[0103] In the first embodiment of the health status estimation system 1, the server device 300 outputs the estimated body fat percentage (BFP) result, and in the second embodiment of the health status estimation system 1A, the terminal device 200 outputs the estimated body fat percentage (BFP) result. However, the system is not limited to this, and the chopstick-shaped device 100 may also be provided with a storage unit 111 that stores a trained model 312, a processing unit 110 having a calculation unit 322 and an estimation unit 323, and a display unit 230. In this case, the chopstick-shaped device 100 alone can display the estimated body fat percentage (BFP) result.

[0104] In the first and second embodiments, the calculation unit 322 of the server device 300 or the calculation unit 242 of the terminal device 200 calculates the amount of exercise consumed (AUC) using measurement data measured by the motion detection sensor 102 and the pressure sensor 103, respectively. However, the calculation is not limited to this, and the amount of exercise consumed (AUC) may be calculated using only the measurement data of either the motion detection sensor 102 or the pressure sensor 103.

[0105] In the first and second embodiments, measurement data measured by the motion detection sensor 102 and the pressure sensor 103, respectively, were used. However, the invention is not limited to this, and measurement data may also be calculated based on images (including still images and videos) of the movement of the chopsticks 100a captured by an external imaging device. Alternatively, the amount of exercise during meals (AUC) may be calculated using measurement data corresponding to the movement of the arm measured by a device including the motion detection sensor 102 attached to the arm.

[0106] The motion detection sensor 102 is configured to be included in an IC chip capable of measuring the motion (acceleration and angular velocity) of the chopstick stick 100a, but it is not limited to this configuration. It may also be configured by combining a piezoelectric accelerometer or servo accelerometer, a three-axis accelerometer such as a strain gauge type accelerometer or semiconductor type accelerometer, or a three-axis angular velocity sensor such as a gyroscope.

[0107] 1, 1A... Health status estimation system, 100... Chopstick-shaped device, 100a, 100b... Chopstick stick, 101... Measurement unit, 102... Motion detection sensor, 103... Pressure sensor, 110... Processing unit, 111... Storage unit, 112... Transmit / receive unit, 113... Control unit, 114... Communication interface, 200, 200a... Terminal device, 201... First transmit / receive unit, 210... Storage unit, 220... Processing unit, 230... Display unit, 240... Processing unit, 241... Acquisition unit, 242... Calculation unit, 243... Estimation unit, 244... Output unit, 300... Server device, 301... Second transmit / receive unit, 310... Storage unit, 311... Program, 312... Trained model, 320... Processing unit, 321... Acquisition unit, 322... Calculation unit, 323... Estimation unit, 324... Output unit, N... Network.

Claims

1. A health status estimation device comprising: a storage unit that stores a pre-trained model that is learned in advance to estimate the health status of a chopstick or cutlery user when the amount of movement related to eating behavior is input; a measurement unit that measures the movement of the chopsticks or cutlery; a calculation unit that calculates the amount of movement based on the measurement data of the movement measured by the measurement unit; an estimation unit that estimates the health status by inputting the amount of movement into the pre-trained model; and an output unit that outputs the health status.

2. The health state estimation device according to claim 1, wherein the eating behavior includes all actions related to eating with chopsticks or cutlery, such as the type of movement of the chopsticks or cutlery, the amount of movement of the chopsticks or cutlery, the speed of movement of the chopsticks or cutlery, the angular velocity of the chopsticks or cutlery, the chewing time of the user, and the posture of the user.

3. The health state estimation device according to claim 1 or 2, wherein the measuring unit includes an motion detection sensor for detecting the movement of the chopsticks or cutlery, or a pressure sensor for detecting the pressure applied by the user when holding the chopsticks or cutlery with their fingers.

4. The health status estimation device according to claim 3, wherein the calculation unit calculates the amount of exercise based on the user's chewing time, which corresponds to the measurement time of the angular velocity of the chopsticks or cutlery by the motion detection sensor.

5. The health status estimation device according to claim 1, wherein the health status includes one of the following: blood glucose level, body fat percentage, body composition including skeletal muscle mass, BMI (Body Mass Index), or degree of obesity.

6. A health status estimation system including a measuring device and an estimation device, wherein the measuring device comprises a measuring unit for measuring the movement of chopsticks or cutlery, and a transmitting unit for transmitting measurement data of the movement measured by the measuring unit, and the estimation device comprises a storage unit for storing a pre-trained model that is trained to estimate the health status of a user when the amount of movement related to the user's eating behavior with chopsticks or cutlery is input, a receiving unit for receiving the measurement data, a calculation unit for calculating the amount of movement based on the measurement data, an estimation unit for estimating the health status by inputting the amount of movement into the pre-trained model, and an output unit for outputting the health status.

7. A health status estimation system comprising a measuring device, a terminal device, and a server device, wherein the measuring device comprises: a measuring unit for measuring the movement of chopsticks or cutlery; and a transmitting unit for transmitting measurement data of the movement measured by the measuring unit; the terminal device comprises: a first transmitting / receiving unit for receiving the measurement data from the measuring device, transmitting the measurement data to the server device, and receiving the user's health status from the server device; and a display unit for displaying the health status; the server device comprises: a second transmitting / receiving unit for receiving the measurement data from the terminal device and transmitting the health status to the terminal device; a storage unit for storing a pre-trained model that is learned in advance to estimate the user's health status when the amount of movement related to the user's eating behavior with chopsticks or cutlery is input; a calculation unit for calculating the amount of movement based on the measurement data; and an estimation unit for estimating the health status by inputting the amount of movement into the pre-trained model.

8. A method for estimating a health state, comprising the steps of: inputting the amount of movement related to eating behavior, storing a pre-trained model in a memory unit that is trained to estimate the health state of the user of chopsticks or cutlery; measuring the movement of the chopsticks or cutlery with a measurement unit; calculating the amount of movement with a calculation unit based on the measurement data of the movement measured by the measurement unit; estimating the health state with an estimation unit by inputting the amount of movement into the pre-trained model; and outputting the health state with an output unit.

Images