Training support device, method and program

Abstract

To provide a training menu using an appropriate training machine to a user doing training.SOLUTION: A training support device 100 includes: an acceleration data acquisition part 110; a joint angle data calculation part 120 calculating joint angle data in one walking period on the basis of acceleration data; a muscle evaluation score calculation part 130 calculating muscle evaluation scores about a plurality of muscles related to walking respectively on the basis of reference data of the joint angle data and the joint angle data; a muscle to train determination part 140 for determining the muscle to train on the basis of the muscle evaluation scores; a training menu generation part 150 selecting a training machine to use for training of the determined muscle and generating a training menu including a training using the selected training machine; and a training menu output part 160 outputting the training menu.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a technique for providing training information to a user who is performing training. [Background technology]

[0002] In recent years, training to improve human athletic performance, such as muscle strength and cardiopulmonary capacity, and to promote health has become widespread, regardless of age, gender, or occupation. In particular, in recent years, many training facilities equipped with various training equipment have been opened and used. When training, trainers often have a clear goal in mind, such as "I want to improve my endurance running time" or "I want to strengthen my leg muscles." However, determining the type of training to achieve such a goal requires specialized knowledge, making it difficult for the general public to train efficiently. In particular, the general public is unfamiliar with the various training equipment installed in training facilities, making it difficult to recognize which training equipment will produce what effects.

[0003] One way to solve this problem is to get advice from trainers, who are professionals affiliated with training facilities. However, there are limits to the number of trainers available, and getting the best advice for each individual requires a reasonable fee, so it has not been easy to get advice from a trainer casually.

[0004] In recent years, there are many training facilities that do not have trainers on-site. In such training facilities, it is sometimes possible to receive advice from a trainer using remote communication means such as telephone. However, it is difficult to provide appropriate advice remotely.

[0005] In light of the above, there has been a demand for users who wish to train to easily obtain training information, such as what training equipment to use and what type of training they should do, without receiving advice from a trainer or other expert. One possible method for obtaining such training information is to first grasp the current state of the user's body as an objective evaluation value, and then generate training information using this evaluation value using a computer. In the system described in Patent Document 1, an accelerometer is attached to a walker, and walking speed, stride length, knee extension force, and dorsiflexion force are estimated as objective evaluation values ​​related to walking based on the detected acceleration, and an exercise menu is displayed based on each estimated evaluation value. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Patent No. 4915263 Summary of the Invention [Problem to be solved by the invention]

[0007] However, the exercise menu presented in the method described in Patent Document 1 does not involve the use of training equipment, and therefore cannot accommodate training using any type of training equipment. One of the reasons for this is thought to be that, while training using training equipment clearly identifies the target muscles, the method described in Patent Document 1 does not identify the muscles to be trained, and therefore does not allow the selection of corresponding training equipment.

[0008] The present invention has been made in consideration of the above circumstances, and its purpose is to provide a training support device, method, and program that can provide a training menu using appropriate training equipment to a user performing training. [Means for solving the problem]

[0009] In order to achieve the above object, the training support device of the present invention is characterized by comprising an acceleration data acquisition unit that acquires acceleration data of a user while walking, measured by an acceleration sensor fixed to the user performing training; a joint angle data calculation unit that calculates joint angle data for one walking cycle based on the acquired acceleration data; a muscle evaluation score calculation unit that calculates muscle evaluation scores, which are muscle-related evaluation scores, for multiple muscles involved in walking based on the calculated joint angle data and reference data for the joint angle data; a training target muscle determination unit that determines muscles to be trained based on the calculated muscle evaluation scores; a training menu generation unit that selects training equipment to be used in training the muscles based on the determined muscles and generates a training menu that includes training using the selected training equipment; and a training menu output unit that outputs the generated training menu. [Effects of the Invention]

[0010] According to the present invention, a muscle evaluation score is calculated from acceleration data of a user while walking, and target muscles for training are determined based on the muscle evaluation score. Then, training equipment to be used for training the target muscles is selected, and a training menu including training using the selected training equipment is generated. This makes it possible to provide a training menu using appropriate training equipment to the user who is undergoing training. [Brief explanation of the drawings]

[0011] [Figure 1] Functional block diagram of the training support device [Figure 2] Flowchart for explaining the operation of the training support device [Figure 3] An example of measured acceleration data [Figure 4] FIG. 1 is a diagram illustrating standardization and averaging of acceleration data. [Figure 5] An example of averaged joint angle data [Figure 6] FIG. 10 is a diagram illustrating the calculation process of joint angle data. [Figure 7] A diagram explaining the calculation process of joint scores [Figure 8] A diagram explaining the relationship between the sagittal plane angle of the hip joint and muscle movement during one gait cycle [Figure 9] A diagram explaining the relationship between the sagittal plane angle of the knee joint and muscle movement during one gait cycle [Figure 10] A diagram explaining the relationship between the sagittal plane angle of the ankle joint and muscle movement during one gait cycle [Figure 11] Diagram explaining the period of exertion of muscle force in one direction cycle [Figure 12] An example of a training menu [Figure 13] FIG. 10 is a diagram illustrating exercise using a training support device according to a second embodiment. [Figure 14] Functional block diagram of a training support device according to a third embodiment. [Figure 15] Functional block diagram of a training support device according to a fourth embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] (First embodiment) A training support device according to a first embodiment of the present invention will be described with reference to the drawings, in which Fig. 1 is a functional block diagram of the training support device, and Fig. 2 is a flowchart illustrating the operation of the training support device.

[0013] The training support device 100 according to this embodiment is carried by the user and acquires acceleration data of the user while walking. The training support device 100 then calculates right and left joint angle data for one walking cycle of the user based on the acquired acceleration data, and further calculates a muscle evaluation score based on the calculated right and left joint angle data. The training support device 100 then determines the muscle to be trained based on the calculated muscle evaluation score, selects training equipment to be used in training the muscle based on the determined muscle, and generates a training menu that includes training using the selected training equipment. The training support device 100 presents the generated training menu to the user.

[0014] 1, training support device 100 includes acceleration data acquisition unit 110, joint angle data calculation unit 120, muscle evaluation score calculation unit 130, training target muscle determination unit 140, training menu generation unit 150, training menu output unit 160, and storage unit 170. An acceleration sensor 200 and a display device 300 are connected to training support device 100.

[0015] Each unit of the training support device 100 can be configured by a conventionally known computer equipped with a main processing unit, a main memory unit, an auxiliary memory unit, an input device, etc. The training support device 100 can be implemented by installing a program that causes each unit to function as the above-mentioned units into a computer. The training support device 100 can be implemented as dedicated hardware. The training support device 100 can also be implemented in a distributed manner across multiple devices. In this embodiment, the training support device 100 is implemented by installing a program into a highly functional mobile communication terminal known as a "smartphone," which has a built-in acceleration sensor 200 and display device 300.

[0016] The acceleration sensor 200 is a well-known three-axis inertial sensor that detects the acceleration of the user while walking. The accelerations detected here are the acceleration in the vertical direction (Z-axis direction), the acceleration in the walking direction (Y-axis direction), and the acceleration in the horizontal directions (X-axis direction) to the left and right of the walking direction. In this embodiment, the right direction of the X-axis with respect to the walking direction is positive and the left direction is negative.

[0017] The acceleration data acquiring unit 110 acquires acceleration data of the walking user measured by the acceleration sensor 200 at a predetermined measurement rate (e.g., 100 Hz) (step S1 in FIG. 2 ). During acceleration measurement, the relative position of the acceleration sensor 200 with respect to the user, i.e., the relative position of the training support device 100, is fixed so that each axial direction of the acceleration sensor 200 remains constant. The training support device 100 is preferably fixed as close to the user's midline as possible in the left-right direction. Furthermore, the training support device 100 is preferably fixed above the crotch and below the neck in the vertical direction. Therefore, during acceleration measurement, the training support device 100 is preferably fixed around the navel in the center of the user's abdomen or around the center of the waist on the back side in the left-right direction. The acceleration data acquiring unit 110 stores the acquired acceleration data 171 in the storage unit 170. An example of the acquired acceleration data 171 is shown in FIG. 3 .

[0018] The joint angle data calculation unit 120 calculates joint angle data 172 for one walking cycle based on the acquired acceleration data 171 (step S2 in FIG. 2). First, the joint angle data calculation unit 120 sets a time range to be analyzed from the acceleration data 171. This is because the acceleration data 171 acquired by the acceleration data acquisition unit 110 includes a period from the start to the end of measurement during which the person is not walking, and because walking is not stable immediately after starting walking or immediately before ending walking. Therefore, the time range is set so that only acceleration data related to stable walking is analyzed.

[0019] The joint angle data calculation unit 120 adds the accelerations of the X-axis, Y-axis, and Z-axis of the acceleration data 171 and applies a low-pass filter to the added acceleration data to remove noise (sine wave processing) to generate combined acceleration data. The joint angle data calculation unit 120 sets a time range to be analyzed based on this combined acceleration data. The time when this combined acceleration reaches a peak value (maximum value) equal to or greater than a predetermined value is the time of heel contact, and the period from when the first peak value is detected to when the last peak value is detected is considered to be the walking time range.

[0020] The process of setting the time range by the joint angle data calculation unit 120 may be performed automatically using a predetermined algorithm, or may be performed based on input instructions from the user. In the former case, for example, the joint angle data calculation unit 120 detects the time when the resultant acceleration reaches a peak value (maximum value) equal to or greater than a predetermined value as the time of heel strike, and sets the time range to be analyzed from the second heel strike to the second-to-last heel strike. In the latter case, the joint angle data calculation unit 120 displays the resultant acceleration data on the display device 300, receives input from the user as the time range to be analyzed, and sets this as the time range to be analyzed.

[0021] Next, the joint angle data calculation unit 120 divides the acceleration data 171 into a first walking cycle, which is a walking cycle from when one of the user's feet touches the ground to when that foot touches the ground again, and a second walking cycle, which is a walking cycle from when the user's other foot touches the ground to when that other foot touches the ground again. Furthermore, the joint angle data calculation unit 120 determines whether the first walking cycle and the second walking cycle are walking cycles related to the right foot or the left foot, respectively. The walking cycle determination process in the joint angle data calculation unit 120 will be described in detail below.

[0022] The joint angle data calculation unit 120 refers to the total acceleration data described above within the set time range, detects and counts the time when the resultant acceleration reaches a peak value (maximum value) as the time of heel strike, and stores this as heel strike timing information.

[0023] Next, the joint angle data calculation unit 120 refers to the heel strike timing information and divides the acceleration data 171 into a plurality of sections between adjacent odd count values ​​(referred to as "odd phases") and a plurality of sections between adjacent even count values ​​(referred to as "even phases"). Each odd phase is a first walking cycle, which is a walking cycle from when one of the user's heels touches the ground to when that heel touches the ground again. Specifically, the odd phases are from the first heel strike to the third heel strike, from the third heel strike to the fifth heel strike, ..., and from the (2n+1)th heel strike to the (2n+3)th heel strike. Similarly, each even phase is a second walking cycle, which is a walking cycle from when the user's other heel touches the ground to when that other heel touches the ground again. Specifically, the even phases are from the second heel strike to the fourth heel strike, from the fourth heel strike to the sixth heel strike, ... and from the 2nth heel strike to the 2n+2nd heel strike.

[0024] Next, the joint angle data calculation unit 120 normalizes the time axis unit from real time to 0 to 1 (0 to 100%) for each walking cycle of the divided odd and even phases. In the present invention, joint angles are analyzed based on the waveform characteristics of acceleration in each walking cycle, but because the user's walking is unstable, there is variation in the periodic time of each walking cycle. For this reason, the present invention performs the time axis normalization process described above.

[0025] Next, as shown in Fig. 4, the joint angle data calculation unit 120 refers to the acceleration data 171 and calculates the arithmetic average of the accelerations on the X-axis, Y-axis, and Z-axis within each first walking cycle for the odd-numbered phases to calculate averaged acceleration data for each of the X-axis, Y-axis, and Z-axis within one walking cycle. The joint angle data calculation unit 120 similarly calculates averaged acceleration data for the even-numbered phases. Note that as a result of left / right determination for each phase by the process described below, the averaged acceleration data for each phase is treated as averaged acceleration data for the right foot (right averaged acceleration data) and averaged acceleration data for the left foot (left averaged acceleration data).

[0026] Next, the joint angle data calculation unit 120 determines whether each odd phase or even phase corresponds to a walking cycle of the right leg or the left leg. In this embodiment, the joint angle data calculation unit 120 determines whether the first walking cycle of the odd phase corresponds to the right leg or the left leg based on the waveform characteristics of the averaged X-axis acceleration of either the odd phase or the even phase (here, the odd phase).

[0027] Specifically, the joint angle data calculation unit 120 performs left-right determination based on the value of the averaged X-axis acceleration in the first half of the time axis direction of the walking cycle, preferably in a time range of 20 to 50%. More specifically, the number of positive averaged X-axis accelerations and the number of negative averaged X-axis accelerations are counted within the time range and compared. If the number of positive averaged X-axis accelerations is greater, the first walking cycle in the odd-numbered phase is determined to be a walking cycle associated with the left foot. On the other hand, if the number of negative averaged X-axis accelerations is greater, the first walking cycle in the odd-numbered phase is determined to be a walking cycle associated with the right foot. Hereinafter, a walking cycle determined to be a walking cycle associated with the right foot will be referred to as a right walking cycle. Similarly, a walking cycle determined to be a walking cycle associated with the left foot will be referred to as a left walking cycle.

[0028] In other embodiments, instead of the positive or negative value of the averaged acceleration on the X-axis, other statistical values, such as the integrated value of the averaged acceleration on the X-axis, can be used as the criterion for left-right determination. In other embodiments, the range of the time axis direction to be determined can be changed from the first half of the time axis direction to the second half of the time axis direction. In this case, the positive and negative values ​​of the averaged acceleration on the X-axis are determined to be reversed at the time of determination. In other embodiments, the left-right determination can be performed based on a plurality of second walking cycles in the even phases. In this case, the positive and negative values ​​of the averaged acceleration on the X-axis are determined to be reversed at the time of determination.

[0029] Next, the joint angle data calculation unit 120 calculates right-side joint angle data, which is angle data of the joints of the right half of the body in a right walking cycle, from the right averaged acceleration data in that walking cycle, using a multiple regression model calculated in advance, and calculates left-side joint angle data, which is angle data of the joints of the left half of the body in that walking cycle, from the left averaged acceleration data in that walking cycle. First, the multiple regression model used in this calculation process will be described in detail.

[0030] This multiple regression model is calculated in advance using another computer prior to the calculation process by the training support device 100. The parameters of the calculated multiple regression model are stored in advance in the storage unit 170 as analysis parameters 177.

[0031] This multiple regression model was calculated by performing principal component analysis and multiple regression analysis using samples of acceleration data (acceleration data for model generation) measured in advance for multiple subjects while they were walking, and joint angle data obtained by capturing and analyzing images during the measurement that correspond to the acceleration data for model generation. Here, the acceleration data for model generation and joint angle data used to calculate the multiple regression model include data related to both right and left walking cycles. In other words, the multiple regression model is not differentiated between right and left feet, but is a single model common to both right and left feet.

[0032] The joint angle data represents the angles between bones that make up the joints of the human body. The joint angle data also includes joint angle data relating to the right half of the body (right joint angle data) and joint angle data relating to the left half of the body (left joint angle data). The right joint angle data corresponds to acceleration data during a right walking cycle. The left joint angle data corresponds to acceleration data during a left walking cycle. In this embodiment, the subject's lower body, i.e., the joints below the waist, are the subject's target. Specifically, the subject's left and right pelvises, hip joints, knee joints, and ankle joints are the subject's target. Each joint angle data also includes an angle in the sagittal plane (angle viewed from the side), an angle in the frontal plane (angle viewed from the front), and an angle in the horizontal plane (angle viewed from above). Therefore, the left and right joint angle data each include 4 locations x 3 directions = 12 measurement values ​​per measurement timing.

[0033] The time range to be analyzed for the model generation acceleration data and the corresponding joint angle data used to create the multiple regression model is set in advance by processing similar to the time range setting processing described above.

[0034] Furthermore, by a process similar to the walking cycle determination process described above, the acceleration data for generating the model and the corresponding joint angle data are divided into a plurality of right walking cycles and left walking cycles, and normalized in the time axis direction.

[0035] Furthermore, the acceleration data for model generation and the corresponding joint angle data are averaged using a process similar to the gait cycle determination process described above. Specifically, the average of the accelerations on the X-axis, Y-axis, and Z-axis in each of a plurality of right walking cycles is calculated to calculate averaged acceleration data for each of the X-axis, Y-axis, and Z-axis in one right walking cycle. The same process is performed for the left walking cycle. The average of the right joint angle data in each direction of the pelvis (sagittal plane, frontal plane, horizontal plane) in each of a plurality of right walking cycles is also calculated to calculate averaged acceleration data for each direction in one right walking cycle. The same process is performed for the right joint angle data at the hip joint, knee joint, and ankle joint. Furthermore, the same process is performed for the left joint angle data.

[0036] The explanatory variable (independent variable) A of the multiple regression model is the principal component [A1, A2, ..., A N ] T Here, the number of samples of the observation variables to be subjected to the principal component analysis is two per one walk (a series of movements from the start to the end of walking): averaged acceleration data relating to the right walking cycle and averaged acceleration data relating to the left walking cycle. Therefore, the number of samples of the observation variables to be subjected to the principal component analysis is twice the number of walks related to the measurements for generating the model.

[0037] The observation variable that is the subject of principal component analysis is a data group consisting of averaged acceleration data for multiple axes at each measurement time within one walking cycle. As shown in the lower part of Figure 4, one piece of averaged acceleration data consists of averaged acceleration data for three axes (X-axis, Y-axis, and Z-axis). In other words, the entire graph in the lower part of Figure 4 is one observation variable. For example, if the measured values ​​of averaged acceleration data at 1% increments along the time axis within a walking cycle are used, the number of components of the observation variable will be 101 (0% to 100%) x 3 (X-axis, Y-axis, and Z-axis). In the present invention, this large number of components is converted into N principal components using a principal component analysis technique.

[0038] Specifically, first, (1) calculate the unstandardized principal component scores of the averaged acceleration data and the eigenvectors of each principal component axis (hereinafter referred to as "acceleration eigenvectors"). Here, N unstandardized principal component scores are selected from those with eigenvalues ​​of 1 or more for each principal component axis obtained by principal component analysis. (2) Next, standardization processing (average 0, variance 1) is performed on the unstandardized principal component scores of the averaged acceleration data calculated in (1) above to obtain standardized principal component scores A1, A2, ..., A N The acceleration eigenvectors of the principal component axes calculated in (1) above are stored in the storage unit 170 as one of the analysis parameters 177.

[0039] The dependent variable B of the multiple regression model is the M-dimensional (M: natural number) principal components [B1, B2, ..., B M ]T Here, since the averaged joint angle data corresponds to the averaged acceleration data, the number of samples of the observation variables to be subjected to the principal component analysis is the same as the number of samples in the principal component analysis of the averaged acceleration data.

[0040] The observation variables to be subjected to principal component analysis are a data group consisting of averaged joint angle data for multiple joints viewed from multiple directions at each measurement time within one gait cycle. FIG. 5 shows an example of averaged joint angle data. As shown in FIG. 5, one piece of averaged joint angle data consists of averaged joint angle data for multiple joints. Each averaged joint angle data for each joint consists of averaged joint angle data for multiple directions. In other words, the entirety of the multiple graphs in FIG. 5 constitutes one observation variable. For example, if measurements of averaged joint angle data are used in 1% increments along the time axis within a gait cycle, the number of components for each observation variable is 101 (0% to 100%) × 3 (sagittal plane, frontal plane, horizontal plane) × 4 (pelvis, hip joint, knee joint, ankle joint). In the present invention, this large number of components is converted into M principal components using a principal component analysis technique.

[0041] Specifically, first, (1) the unstandardized principal component scores of the averaged joint angle data and the eigenvectors of each principal component axis (hereinafter referred to as "joint angle eigenvectors") are calculated. Here, M unstandardized principal component scores are selected from those with eigenvalues ​​of 1 or more for each principal component axis obtained by principal component analysis. (2) Next, standardization processing (average 0, variance 1) is performed on the unstandardized principal component scores of the averaged joint angle data calculated in (1) above to obtain standardized principal component scores B1, B2, ..., B M The joint angle eigenvector of each principal component axis calculated in (1) above is stored in the storage unit 170 as one of the analysis parameters 177.

[0042] A multiple regression model is created by performing multiple regression analysis using the explanatory variable (independent variable) A and the response variable (dependent variable) obtained by the above process. The multiple regression model can be expressed by the following formula.

[0043] B1=α 11 A1+α 21 A2+α 31 A3+... +α N1 A N +β1 B2=α 12 A1+α 22 A2+α 32 A3+... +α N2 A N +β2 B3=α 13 A1+α 23 A2+α 33 A3+... +α N3 A N +β3 … B M =α 1M A1+α 2M A2+α 3M A3+... +α NM A N +β M

[0044] The above equation can be expressed as a vector as follows: B=αA+β

[0045] Here, α is an N×M-dimensional coefficient parameter, and β is an M-dimensional coefficient parameter. α and β are stored in the storage unit 170 as one of the analysis parameters 177.

[0046] 6, the joint angle data calculation unit 120 calculates right joint angle data from the right average acceleration speed data, and calculates left joint angle data from the left average acceleration speed data. Below, the details of the calculation process of joint angle data in the joint angle data calculation unit 120 will be explained. This process is the same for both the left and right, so here, the calculation process for the right side will be explained as an example.

[0047] First, the joint angle data calculation unit 120 converts the right foot averaged acceleration data into N principal components using a principal component analysis technique. Specifically, the right averaged acceleration data for each axis is multiplied by the acceleration eigenvector included in the analysis parameters 177 to calculate non-standardized principal component scores for the right averaged acceleration data, and then standardized (mean 0, variance 1) to calculate standardized principal component scores for the right averaged acceleration data. These standardized principal component scores for the right averaged acceleration data are explanatory variables (independent variables) A ​​of a multiple regression model consisting of N-dimensional principal components.

[0048] Next, the joint angle data calculation unit 120 uses the coefficient parameters of the multiple regression model included in the analysis parameters 177, i.e., the above-mentioned multiple regression model, to calculate the standardized principal component scores of the joint angle data, which are the objective variable (dependent variable) B, from the explanatory variable (independent variable) A. Here, the objective variable (dependent variable) B is M-dimensional data.

[0049] Next, the joint angle data calculation unit 120 uses the standardized principal component scores of the calculated M pieces of joint angle data as principal components and inversely transforms the principal components into joint angle data using a principal component analysis technique. Specifically, the joint angle data calculation unit 120 calculates joint angle data in each direction (sagittal plane, frontal plane, horizontal plane) of each joint (pelvis, hip joint, knee joint, ankle joint) of the right half of the body during one right walking cycle using the standardized principal component scores of the calculated joint angle data and the joint angle eigenvectors included in the analysis parameters 177. That is, right-side joint angle data is calculated for each combination of (joint, direction). In this embodiment, the right-side joint angle data consists of 4 joints × 3 directions = 12 joint angle data groups. Each joint angle data has 101 values ​​at 1% increments along the time axis during one walking cycle. The joint angle data calculation unit 120 stores the calculated joint angle data of each joint of the right half of the body in the storage unit 170 as right-side joint angle data.

[0050] The joint angle data calculation unit 120 performs a similar analysis process to calculate left-side joint angle data based on the averaged acceleration data related to the left foot, and stores the data in the storage unit 170. Note that the analysis parameters 177 used in this analysis process are common to both the left and right feet.

[0051] Through the above processing, the joint angle data calculation unit 120 calculates left and right (2) x 4 joints x 3 directions = 24 pieces of joint angle data 172.

[0052] The muscle evaluation score calculation unit 130 calculates muscle evaluation scores, which are evaluation scores related to the muscles, for each of the multiple muscles involved in walking, based on the calculated joint angle data and the reference data for the joint angle data.

[0053] The muscle evaluation score calculation unit 130 first calculates a joint score 173, which is an evaluation score of the movement of the joints in one walking cycle, from the joint angle data 172 in one walking cycle (step S3 in FIG. 2). More specifically, the muscle evaluation score calculation unit 130 calculates a right joint score in one walking cycle based on the right joint angle data in one walking cycle and its reference data 178, and calculates a left joint score in one walking cycle based on the left joint angle data and its reference data 178, and stores these in the storage unit 170.

[0054] As described above, each of the right and left joint angle data 172 consists of 12 pieces of joint angle data corresponding to each joint and each direction, so the muscle evaluation score calculation unit 130 calculates 12 joint scores 173 corresponding to each of the right and left joint angle data 172. In this embodiment, each joint score 173 has 101 values ​​in 1% increments along the time axis within one walking cycle.

[0055] The reference data 178 is calculated using right and left joint angle data 172 measured in advance for a plurality of subjects as samples. The reference data 178 is data that defines the probability distribution of the joint angles at each time within one gait cycle of the sample. In this embodiment, it is assumed that the probability distribution of each joint angle data 172 at each time t is a normal distribution, and the mean value μ(t) and standard deviation σ(t) at each time t are used as the reference data 178. This reference data 178 is stored in advance in the storage unit 170 for each joint and each direction. In this embodiment, 12 pieces of reference data 178 corresponding to each joint and each direction are stored. This reference data 178 is used as a standard for good walking style.

[0056] The joint score calculation process in the muscle evaluation score calculation unit 130 will be described below. Since this process is the same for both the left and right sides, the process for the right side will be described as an example with reference to Figure 7. Figure 7 is a diagram for explaining the calculation of the joint score for the right hip joint sagittal plane. In Figure 7, the reference data shows the average value μ.

[0057] At each time t within one walking cycle, the muscle evaluation score calculation unit 130 calculates a joint score (t) based on the difference (t) between the angle data (t) in the right joint angle data 172 and the average value μ(t) included in the reference data 178, and the difference d(t) and the standard deviation σ(t) included in the reference data 178. Here, the muscle evaluation score calculation unit 130 calculates the score so that the closer the angle data (t) is to the average value μ(t), the higher the score; that is, the closer the difference d(t) is to zero, the higher the score. More specifically, the muscle evaluation score calculation unit 130 calculates the score so that the smaller |difference d(t) / standard deviation σ(t)| is, the higher the score, and the larger |difference d(t) / standard deviation σ(t)| is, the lower the score.

[0058] For example, if the joint score is out of 100, then if angle data (t) = mean value μ(t), then score (t) = 100; if angle data (t) = mean value μ(t) ± standard deviation σ(t), then score (t) = 32; and if angle data (t) = mean value μ(t) ± 2 × standard deviation σ(t), then score (t) = 5 points.

[0059] The muscle evaluation score calculation unit 130 performs a similar calculation process to calculate a left joint score 173 based on the left joint angle data 172 and the reference data 178, and stores the calculated score in the storage unit 170. Note that the reference data 178 used in this calculation process is common to both the left and right sides.

[0060] Through the above processing, the muscle evaluation score calculation unit 130 calculates left and right (2) x 4 joints x 3 directions = 24 joint scores 173.

[0061] Next, the muscle evaluation score calculation unit 130 calculates muscle evaluation scores 174, which are evaluation scores for multiple muscles involved in walking, based on the right and left joint scores 173 (step S4 in FIG. 2). The muscle evaluation scores 174 are evaluation scores for muscle(s) associated with the movement of joints used in walking. In the present invention, when evaluating a muscle(s), the joint scores for the joints associated with the muscle(s) are used.

[0062] Figure 8 is a graph showing the sagittal plane joint angles of the hip, knee, and ankle joints, and the timing of muscle activity of the muscles associated with each joint. As shown in Figure 8, among the major muscles of the human body, the muscle activity in the sagittal plane of the gluteus maximus (lower part), adductor magnus, biceps femoris (long head), semimembranosus, and semitendinosus is active during sagittal plane extension of the hip joint. Here, these muscle groups are referred to as hip extensors. Furthermore, among the major muscles of the human body, the rectus femoris, iliacus, adductor longus, gracilis, and sartorius are active during sagittal plane flexion of the hip joint. Here, these muscle groups are referred to as hip flexors.

[0063] Similarly, as shown in Figure 9, among the major muscles of a human being, the muscle group that is active when the knee joint is extended in the sagittal plane is called the knee extensor muscles. Also, among the major muscles of a human being, the muscle group that is active when the knee joint is flexed in the sagittal plane is called the knee extensor muscles.

[0064] Similarly, as shown in Figure 10, among the major muscles of the human body, the muscle group that is active at the timing of dorsiflexion of the ankle joint in the sagittal plane is called the ankle dorsiflexors. Also, among the major muscles of the human body, the muscle group that is active at the timing of plantarflexion of the ankle joint in the sagittal plane is called the ankle plantarflexors.

[0065] Based on the above findings, the muscle evaluation score calculation unit 130 according to this embodiment calculates muscle evaluation scores 174 for six muscles, namely, hip extensors, hip flexors, knee extensors, knee flexors, ankle dorsiflexors, and ankle plantar flexors, for each of the right and left sides.

[0066] The muscle evaluation score calculation unit 130 sets muscle force exertion periods 179 in advance on the graphs shown in Figs. 8 to 10 and stores them in the storage unit 170. The muscle force exertion periods 179 are the periods during one walking cycle during which each muscle that affects walking exerts force for the corresponding joint and direction. The muscle force exertion periods 179 are common to both the left and right. An example of the muscle force exertion periods 179 is shown in Fig. 17.

[0067] The muscle evaluation score calculation unit 130 calculates the joint scores 173 for the joints associated with the right or left muscles, which are the average values ​​of the joint scores during the muscle strength exertion period 179, and sets this average value as the muscle evaluation score 174 for each muscle and left or right side. The muscle evaluation score is calculated using the following formula:

[0068]

number

[0069] Here, Tm is the number of samples within the muscle strength exertion period. The muscle evaluation score calculation unit 130 stores the calculated muscle evaluation score 174 in the storage unit 170.

[0070] The training target muscle determination unit 140 determines which muscles should be trained based on the muscle evaluation score 174 of each muscle calculated by the muscle evaluation score calculation unit 130 (step S5 in FIG. 2). In this embodiment, the training target muscle determination unit 140 determines that a muscle whose muscle evaluation score 174 is smaller than a predetermined threshold is a muscle that should be trained. Here, the threshold may be a different value for each muscle, or may be the same for all muscles. As another example, the training target muscle determination unit 140 determines that one or more muscles whose muscle evaluation score 174 is smaller than a predetermined threshold and that are arranged in ascending order of muscle evaluation score 174 are muscles that should be trained. The threshold may also be set according to the user's attributes, such as age, gender, and physique.

[0071] The training menu generation unit 150 generates a training menu 175 for improving the function of a muscle determined to be a training target, and stores the generated training menu 175 in the storage unit 170 (step S6 in FIG. 2). The generated training menu 175 includes information on at least one or more training devices. Specifically, the training menu generation unit 150 stores in advance in the storage unit 170 a correspondence table 176 between muscles to be trained (target muscles) and training devices used in training the muscles, and refers to the correspondence table 176 to select one or more training devices corresponding to the muscles to be trained. The training menu generation unit 150 then generates training using the selected training devices as the training menu 175. Note that there may be a one-to-one correspondence between training devices and training exercises, or there may be multiple training exercises corresponding to one training device. An example of the correspondence table 176 is shown in Table 1 below.

[0072] [Table 1]

[0073] The training menu generating section 150 can add training that does not use training equipment to the training menu 175. Furthermore, the training menu generating section 150 can add rest information, which includes at least the time or timing of rest during training, to the training menu 175.

[0074] Furthermore, when multiple training machines are selected, the training menu generation unit 150 can determine a priority order indicating which of the selected training machines should be used with higher priority, and add the determined priority order to the training menu 175. The priority order can be determined, for example, based on the muscle evaluation scores 174 of the muscles corresponding to the selected training machines, in ascending order of muscle evaluation scores 174.

[0075] Furthermore, when multiple training machines are selected, the training menu generation unit 150 can determine a use order indicating the order in which the selected multiple training machines should be used, and generate the training menu 175 so that the training using each training machine follows the use order.

[0076] In addition, the training menu generation unit 150 can select training equipment that should not be used in training the muscles that have been determined to be the training target, and add equipment information about the selected training equipment to the training menu 175.

[0077] An example of the generated training menu 175 is shown in Figure 12. In the example of Figure 12, training menu 175 includes multiple trainings with usage order information added, and further includes rest information and information on training equipment that should not be used as additional information.

[0078] The training menu output unit 160 outputs the training menu 175 generated by the training menu generation unit 150 (step S7 in FIG. 2). The output destination and output format are not important. In this embodiment, the training menu is notified to the user by displaying it on a display device 300 connected to the training support device 100. Note that instead of or in addition to notifying the user, notification may be given to others, such as a trainer or employees of a training facility. Various means for notifying others may be used, such as email or messaging tools.

[0079] According to the training support device 100 of this embodiment, a muscle evaluation score is calculated from acceleration data of the user while walking, and the muscles to be trained are determined based on this muscle evaluation score. Then, training equipment to be used in training the muscles to be trained is selected, and a training menu including training using this training equipment is generated. This makes it possible to provide a training menu using appropriate training equipment to the user who is undergoing training. In particular, since the training support device 100 of this embodiment uses a smartphone carried by the user, training support can be provided at low cost and is highly convenient for the user.

[0080] Furthermore, the training support device 100 according to this embodiment sets a muscle strength exertion period for each muscle in a stride cycle, and evaluates the muscle based on the joint score during this muscle strength exertion period, thereby enabling appropriate evaluation of each muscle.

[0081] Note that various data including the training menu 175 and muscle evaluation score 174 generated by the training support device 100 and stored in the storage unit 170 can be output to an external device at any timing. At this time, meta information such as identification information for identifying the user and the date and time of generation can be added to the output data.

[0082] (Second embodiment) A second embodiment of the present invention will be described with reference to the drawings. The training support device according to this embodiment differs from the first embodiment in the output destination and output format of the training menu. Other configurations, operations, etc. are the same as those of the first embodiment, so only the differences will be described here.

[0083] Similar to the first embodiment, the training support device 100a according to this embodiment is implemented in a highly functional mobile communication terminal called a smartphone that has an acceleration sensor 200 and a display device 300 built in.

[0084] As shown in FIG. 13, this training support device 100a is intended for use in a training facility used by users. A plurality of training machines 410 and 420 are installed in the training facility. Also installed in the training facility are display devices 411 and 421, such as lamps, that indicate the location of each training machine 410. In the example of FIG. 13, the display device 411 is attached to the training machine 410. Also in the example of FIG. 13, the display device 421 is placed near the training machine 420. Also installed in the training facility is a display device 430, such as an LCD display device or an LED panel, that can display various types of information. The training support device 100a is configured to be able to communicate data with each of the display devices 411, 421, and 430 via a predetermined communication path.

[0085] The training menu output unit 160 of the training assistance device 100a instructs the display devices 411, 421 corresponding to the training devices 410, 420 corresponding to the training included in the training menu 175 to notify the user of the location of the training device to be used by lighting up a lamp. In addition, the training menu output unit 160 of the training assistance device 100a instructs the display device 430 to display the training menu 175.

[0086] According to this training support device 100a, the lamps on the display devices 411, 412 attached to the training devices 410, 420 used in training light up, making it clear which training device to use for training. Also, the training menu is displayed on the display device 430, making it easy to check the training menu during training. This provides great convenience for the user. Other functions and effects are the same as those of the first embodiment.

[0087] (Third embodiment) A third embodiment of the present invention will be described with reference to the drawings. The training support device according to this embodiment differs from the first embodiment in that it is equipped with an analysis unit. The other configurations and operations are the same as those of the first embodiment, so only the differences will be described here.

[0088] As shown in FIG. 14, the training support device 100b according to this embodiment includes a first analysis unit 181 and a second analysis unit 182 in addition to the components of the training support device 100 according to the first embodiment.

[0089] The first analysis unit 181 has a function of displaying the history of the muscle evaluation score 174 of each muscle stored in the storage unit 170 on the display device 300. Here, the first analysis unit 181 controls the display of each data in a display mode that clearly shows the change over time in the muscle evaluation score 174 of each muscle. The first analysis unit 181 can further estimate the future muscle evaluation score 174 from the change over time in the muscle evaluation score 174 of each muscle and display this estimated value on the display device 300. Furthermore, the first analysis unit 181 can generate advice for the user based on the estimated value and display it on the display device 300. This advice may be, for example, a statement indicating the need for training, or may be, for example, a training menu generated from the estimated value.

[0090] The second analysis unit 182 has a function of displaying the muscle evaluation score 174 of each muscle stored in the storage unit 170 and the standard value of the muscle evaluation score on the display device 300. Here, the standard value of the muscle evaluation score is a statistical value such as the average or median of the muscle evaluation scores obtained in advance by measuring a large number of subjects. A plurality of standard values ​​of the muscle evaluation score may be prepared according to attributes such as the age and gender of the user. The second analysis unit 182 controls the display of both the user's muscle evaluation score 174 and the standard value in a display format that makes it easy to compare them.

[0091] The above-described first analysis unit 181 and second analysis unit 182 can improve the user's motivation to train. That is, if the user has not started training habitually, the motivation to start habitual training can be improved. Also, if the user is habitually training, the motivation to maintain such habit can be improved. This can encourage users to visit training facilities and maintain their use. Other actions and effects are the same as those of the first embodiment. It is not necessary to have both the first analysis unit 181 and the second analysis unit 182; it is sufficient to have only one of them.

[0092] (Fourth embodiment) A fourth embodiment of the present invention will be described with reference to the drawings. The training support device according to this embodiment differs from the first embodiment in that it searches for training facilities and links with systems operated by the training facilities. Other configurations and operations are the same as those of the first embodiment, so only the differences will be described here.

[0093] Similar to the first embodiment, the training support device 100c according to this embodiment is implemented in a highly functional mobile communication terminal called a smartphone that has an acceleration sensor 200 and a display device 300 built in.

[0094] This training support device 100c is intended to be used mainly outside a training facility. As shown in Fig. 15, the training support device 100c includes a search unit 191 and a linking unit 192 in addition to the components of the training support device 100 according to the first embodiment.

[0095] The search unit 191 searches for training facilities where the training equipment used in the training menu 175 generated by the training menu generation unit 150 is installed. That is, the search unit 191 searches for training facilities where the training menu 175 can be implemented. The search unit 191 stores in advance a database of correspondence between the training equipment and the training facilities where the training equipment is installed, and extracts training facilities where the training menu 175 can be implemented by referring to this database. Note that the above-mentioned database may be implemented, for example, on a server on the Internet, and the search unit 191 may search for training facilities by inquiring about the server. In this case, the server may be a system 500 operated by the training facility, which will be described later. The search unit 191 can display the extracted information about the training facilities on the display device 300.

[0096] The linking unit 192 connects to the system 500 operated by the training facility searched for by the search unit 191, or to the system 500 operated by a specified training facility, and performs linking processing for the system. Examples of linking processing include reservation processing for the training facility and inquiry processing for available time at the training facility. The training facility system 500 is deployed on the Internet, etc. In this embodiment, the system 500 is a client-server system, and the linking unit 192 operates as a client of the system.

[0097] Such a training support device 100b allows the user to identify training facilities where the generated training menu can be carried out and further allows the user to make reservations at the training facilities, which is highly convenient. Other functions and effects are the same as those of the first embodiment. It is not necessary to provide both the search unit 191 and the linking unit 192; it is sufficient to provide only one of them.

[0098] Although one embodiment of the present invention has been described in detail above, the present invention is not limited to the above embodiment, and various improvements and modifications may be made without departing from the spirit and scope of the present invention.

[0099] For example, in the above embodiment, the muscles of the user's lower body, that is, muscles below the waist, are evaluated and trained, but muscles of the upper body can also be evaluated and trained in the same way.

[0100] In the above embodiment, the muscle evaluation score 174 is calculated separately for each muscle on the right and left sides, and a training menu is generated based on these muscle evaluation scores 174. However, a muscle group consisting of multiple muscles may be set, and an evaluation score for the muscle group may be calculated from the muscle evaluation scores 174 for each muscle included in the muscle group, and a training menu may be generated based on the evaluation scores of the muscle group. An example of a muscle group is a muscle group consisting of a certain muscle on the right side and a corresponding muscle on the left side. Another example of a muscle group is a muscle group consisting of a certain muscle and a muscle that is closely related to the certain muscle in terms of human body structure.

[0101] Furthermore, in the above embodiment, one piece of reference data 178 is used, but multiple pieces of reference data may be prepared in advance according to gender and age group, and the reference data 178 to be used may be switched to the reference data corresponding to the user according to the user's gender and age group.

[0102] In the above embodiment, the correspondence table 176, the analysis parameters 177, the reference data 178, and the muscle strength exertion period 179 are stored in advance in the storage unit 170, but it is also possible to access a predetermined management server or storage via a network for each measurement process or periodically to obtain the latest data from the management server or the like.

[0103] In the above embodiment, the training support device 100 is implemented as a single device, including the acceleration sensor 200, acceleration data acquisition unit 110, joint angle data calculation unit 120, muscle evaluation score calculation unit 130, training target muscle determination unit 140, training menu generation unit 150, training menu output unit 160, storage unit 170, and display device 300. However, these components may be distributed and implemented in any combination across multiple devices. For example, the device for acquiring acceleration data, the device for calculating gait evaluation scores, and the device for selecting and presenting display menus may each be implemented as separate devices. [Explanation of symbols]

[0104] 100...Training support device 110...Acceleration data acquisition unit 120...Joint angle data calculation unit 130...Muscle evaluation score calculation section 140...Training target muscle determination section 150...Training menu generation section 160...Training menu output section 181...First analysis section 182...Second analysis section 191...Search section 192... Liaison Department 200...Acceleration sensor 300,411,421,430…display device 410,420...Training equipment 500...Training facility system

Claims

1. an acceleration data acquisition unit that acquires acceleration data of the user while walking, the acceleration data being measured by an acceleration sensor fixed to the user performing training; a joint angle data calculation unit that calculates joint angle data for one walking cycle based on the acquired acceleration data; a muscle evaluation score calculation unit that calculates muscle evaluation scores, which are evaluation scores related to muscles, for each of a plurality of muscles involved in walking based on the calculated joint angle data and reference data for the joint angle data; a training target muscle determination unit that determines muscles to be trained based on the calculated muscle evaluation score; a training menu generation unit that selects a training device to be used for training the muscle based on the determined muscle, and generates a training menu that includes training using the selected training device; a training menu output unit that outputs the generated training menu; A training support device characterized by:

2. The training menu generation unit selects a plurality of training machines, determines a priority order indicating which of the selected plurality of training machines should be used with higher priority, and adds the determined priority order to the training menu.

2. The training support device according to claim 1.

3. The training menu generation unit selects a plurality of training machines, determines a use order indicating an order in which the selected plurality of training machines should be used, and generates the training menu based on the determined use order.

2. The training support device according to claim 1.

4. The training menu generation unit selects training equipment that should not be used in training the muscle based on the determined muscle, and adds equipment information of the selected training equipment to the training menu.

2. The training support device according to claim 1.

5. The training menu generation unit adds rest information including at least the time or timing of rest during training to the training menu.

2. The training support device according to claim 1.

6. The training menu output unit notifies the user of a training menu on a terminal owned by the user.

2. The training support device according to claim 1.

7. a joint score calculation unit that calculates joint scores for one walking cycle based on the calculated joint angle data for one walking cycle and its reference data, The muscle evaluation score calculation unit includes a muscle force exertion period storage unit that stores a muscle force exertion period, which is a period during which a muscle that affects walking exerts force within one walking cycle, and calculates, as the muscle evaluation score, an average value of the joint scores for the joints associated with the muscle within the muscle force exertion period.

7. The training support device according to claim 1, wherein the training support device is a device for supporting a training exercise.

8. A training support method for providing a training menu to a user using a computer, comprising: acquiring acceleration data of the user while walking, the acceleration data being measured by an acceleration sensor fixed to the user performing training; calculating joint angle data for one walking cycle based on the acquired acceleration data; calculating muscle evaluation scores for each of a plurality of muscles involved in walking based on the calculated joint angle data and reference data for the joint angle data; A step of determining muscles to be trained based on the calculated muscle evaluation score; selecting a training device to be used for training the muscle based on the determined muscle, and generating a training menu including training using the selected training device; and outputting the generated training menu. A training support method comprising:

9. A computer is caused to function as the training support device according to claim 1. A training support program characterized by:

Images