TWI804358B - The method of real-time adjustment of gait training parameters - Google Patents

Abstract

A method for adjusting gait training parameters in real time, comprising the steps of: (a) collecting the muscle-relaxed gait data of the first user in the muscle-relaxed state, and the active-effort gait data of the first user in the active-effort state, by Based on the ratio of the first user's active effort gait data to the first user's muscle relaxation gait data, a standard motion model is established; (b) obtain the second user's motion model, including the muscle relaxation state of the second user The muscle relaxation gait data of the second user, by combining the muscle relaxation gait data of the second user with the standard motion model, estimates the personalized training model; (c) judging whether the actual training of the second user conforms to the personalized training model Standards, and then adjust the personalized training model, and provide auxiliary training models.

Description

The method of real-time adjustment of gait training parameters

The present invention relates to gait training technology, in particular to a method for real-time adjustment of gait training parameters.

Generally, in the process of gait training, a gait training device is usually used to assist the user in gait training.

Please refer to a kind of dynamic orthosis provided by U.S. Patent No. US 8147436, as shown in Figure 7 of the said patent, which mainly collects the walking data of 6 normal people who actively exert force, as an ideal model of gait trajectory, And the allowable error space of the tunnel type is planned on the periphery of the gait trajectory, so as to provide the user with a training effect close to the ideal model in the gait training.

However, as in the above-mentioned U.S. Patent No. US 8147436, the technology of applying the ideal model to all users for training does not take into account the individual differences of users to plan the exercise model. Therefore, the ideal model planned in this patent is relatively Difficult to adapt to different users.

In addition, please refer to the adaptive active training system provided by the Chinese patent No. CN 113244084A, as shown in Figure 6 of the said patent, which mainly includes a sensing module, a control module and a motion module, by recording the user's muscle strength Relax the physiological signals of each section when being driven by the exoskeleton, calculate the physiological signal threshold of each section, and adjust the training difficulty in real time according to the user's physiological state signal during training.

However, as in the above-mentioned Chinese Patent No. CN 113244084A, only the gait data of the user itself is used as a reference, and no reference is made to the gait data of normal people or other users. Therefore, the training model planned in this patent cannot Achieve optimal gait training effect.

The main purpose of the present invention is to provide a method for real-time adjustment of gait training parameters, which can plan a personalized exercise model according to the state of different users, and can recommend suitable ones according to the data of the user's cooperation and output during training. Training difficulty, to achieve the effect of real-time adjustment of training difficulty according to the actual performance during training.

In order to achieve the above-mentioned purpose, the present invention provides a method for adjusting gait training parameters in real time, which is suitable for one-step training equipment. The gait training equipment includes a sensing unit, a training unit and a control unit. The control unit and The sensing unit is electrically connected to the training unit, and controls the training unit to act. The method for adjusting gait training parameters in real time includes steps:

Step (a) The sensing unit collects muscle relaxation gait data of at least one first user measured during gait training in a muscle relaxation state, and the at least one first user actively exerts force The control unit uses the ratio of the first user’s active effort gait data to the muscle relaxation gait data of the first user measured during the gait training , to establish a standard motion model.

Step (b) The control unit obtains a motion model of a second user, including muscle relaxation gait data of the second user measured during the gait training in a muscle relaxation state, by The muscle relaxation gait data of the second user is combined with the standard movement model to estimate at least one personalized training model.

Step (c) The control unit judges whether the actual training state of the second user meets the standard of the at least one personal training model, and then adjusts the at least one personal training model, and provides an auxiliary training model.

In this way, the present invention provides a method for real-time adjustment of gait training parameters, which can plan a personalized exercise model belonging to the second user according to the state of the second user, and can be trained according to the second user's According to the output data, a suitable auxiliary training model is recommended to achieve the effect of adjusting the difficulty of training in real time according to the actual performance during training.

10: The method of real-time adjustment of gait training parameters

100: Gait training equipment

101:Left foot force sensor

102: Right foot power sensor

103:Left knee pressure sensor

104: Right knee pressure sensor

105: upper sensing element

106: Lower sensing element

11: Pedal

F1: center of gravity transfer interval

F2: Hip flexion zone

F3: Knee extension zone

L1: 100% difficulty curve

L12: 10% difficulty curve

Fig. 1 is a flow chart of a preferred embodiment of the present invention.

Fig. 2 is a schematic diagram of the use state of a preferred embodiment of the present invention used in conjunction with gait training equipment.

Figure 2a is a schematic diagram of a preferred embodiment of the present invention showing the gait cycle.

Fig. 2b is a graph of a preferred embodiment of the present invention, showing the muscle-relaxed gait data of the first user measured during gait training in the muscle-relaxed state.

Fig. 2c is a graph of a preferred embodiment of the present invention, showing the first user's active exertion gait data measured during gait training in the active exertion state of the first user.

Fig. 2d is a graph of a preferred embodiment of the present invention, showing the ratio of the first user's active effort gait data to the first user's muscle relaxation gait data.

Fig. 2e is a graph of a preferred embodiment of the present invention, showing the ratio and average value of data measured by a plurality of first users in active effort and muscle relaxation states.

Fig. 2f is a graph of a preferred embodiment of the present invention, showing the center of gravity transfer interval and the hip flexion interval.

Fig. 2g is a graph of a preferred embodiment of the present invention, showing the shifting interval of the center of gravity and the extension interval of the knee.

Fig. 2h is a schematic diagram of a preferred embodiment of the present invention, showing the implementation state of the upper sensing element and the lower sensing element of the knee pressure sensor.

Fig. 3 is a graph of a preferred embodiment of the present invention, showing a personalized training model.

Fig. 3a is a graph of a preferred embodiment of the present invention, showing a plurality of personalized training models.

Fig. 3b is a graph of a preferred embodiment of the present invention, showing the muscle relaxation state data of the second user.

Fig. 3c is a graph of a preferred embodiment of the present invention, showing the predicted maximum active effort and the predicted minimum active effort in the personalized training model for the second user.

Fig. 3d is a graph of a preferred embodiment of the present invention, showing the maximum value of the actual active effort and the minimum value of the actual active effort of the second user in the actual training state.

Fig. 3e is a graph of a preferred embodiment of the present invention, showing the auxiliary training model obtained after adjusting the personalized training model.

In order to describe the technical characteristics of the present invention in detail, hereby aim at the following preferred embodiment, and describe it as follows in conjunction with the drawings, wherein, as shown in Figure 1-2, the method 10 of the present invention for adjusting gait training parameters in real time, It is mainly used with a gait training device 100, and the gait training device 100 mainly includes a sensing unit, a training unit and a control unit. The sensing unit includes two plantar force sensors and two knee pressure sensors, wherein the plantar force sensors are respectively a left foot force sensor 101 and a right foot force sensor 102. The knee pressure sensors are respectively a left knee pressure sensor 103 and a right knee pressure sensor 104 . The training unit includes two pedals 11 and other components for driving the user's lower limbs for training. The left foot force sensor 101 is arranged on one of the pedals 11, and the right foot force sensor 102 is arranged on the other. Pedal 11. The control unit and the sensing unit and the training sheet The unit is electrically connected and controls the operation of the training unit. The control unit has analysis and calculation capabilities, which can be, but not limited to, a central processing unit (Central Processing Unit, CPU) or other information processing components with analysis and calculation capabilities. When a first user or a second user uses the gait training device 100, the gait training device 100 provides the control, calculation and action required by the method 10 for real-time adjustment of gait training parameters, the real-time adjustment step The method 10 for dynamically training parameters mainly includes steps (a), (b) and (c). In this preferred embodiment, the left foot force sensor 101 and the right foot force sensor 102 are Load Cells, the left knee pressure sensor 103 and the right knee pressure sensor 104 As a thin-film pressure sensor, it is worth mentioning that users can choose a suitable sensor according to actual needs, and it is not limited to this.

In this preferred embodiment, as shown in Figure 2a, the gait training includes at least one gait cycle, which corresponds to the gait trajectory of one of the feet, which is simulated by a human when walking on the right The process from heel strike to left toe off the ground, left heel to right toe off the ground and finally back to right heel strike, Figure 2b, 2c, 2d, 2e, 2f, 2g, 3, 3a, 3b, 3c , 3d, and 3e correspond to the gait cycle in Figure 2a, divide the data on the graph into 100 equal parts, and use the position where the heel of the user's single foot touches the ground corresponds to the starting point of the gait cycle (that is, the data point marked 0 on the horizontal axis), and the position before the heel of the same foot touches the ground again corresponds to the 99th data point on the horizontal axis.

As shown in Figures 1, 2b, 2c, 2d and 2e, in this step (a), the sensing unit collects a first user's muscle relaxation measured in the gait training in the muscle relaxation state of the first user Gait data (as shown in Figure 2b), and the first user's active effort gait data (as shown in Figure 2c) measured in the gait training under the active exertion state of the first user, the control unit uses the The ratio of the first user's active exertion gait data to the first user's muscle relaxation gait data is used to establish a standard motion model (as shown in FIG. 2d ). The "muscle relaxation state" here means that the user does not need to make any effort during the gait training, and only the control unit of the gait training device 100 drives the training unit, thereby driving the user's feet to swing. "Active effort state" refers to the fact that the user's feet must actively exert force during the operation of the training unit.

In this preferred embodiment, in order to improve the stability of various data, the number of samples of the first user is taken as an example, and the average value of the first user's active effort gait data and The ratio of the average value of the plurality of muscle relaxation gait data of the first user is used to establish the standard motion model (as shown in FIG. 2e ). In other preferred embodiments, if the first user's active effort gait data and the first user's muscle relaxation gait data of the first user are representative enough, the first user The number of users can also be taken as one, so the number of the first user is not limited to this preferred embodiment.

In this preferred embodiment, as shown in Figures 2a, 2f and 2g, the gait cycle is mainly divided into a center of gravity transfer interval F1, a hip flexion interval F2 and a knee extension interval F3, and the center of gravity transfer interval F1 is Located in the 0-40 equal division of the gait cycle, the hip flexion interval F2 is located in the 45-70 equal division of the gait cycle, and the knee extension interval F3 is located in the 80-99 equal division of the gait cycle.

Wherein, taking the right foot of the first user as an example (the judging method of the left foot is also the same and will not be repeated here), as shown in Figure 2f, when the center of gravity transfer interval F1 is located, the first user The value sensed by the right foot stepping on the right foot force sensor 102 is greater than a model threshold (the first user's 100% active effort prediction value), when the right foot is in the hip flexion zone F2, the right foot stepping on the right foot force The value sensed by the sensor 102 is less than the model threshold. As shown in FIG. 2g, when the knee is in the straightening zone F3, the right knee pressure sensor 104 is less than the model threshold.

In this preferred embodiment, as shown in FIG. 2h, the left knee pressure sensor 103 and the right knee pressure sensor 104 respectively have an upper sensing element 105 and a lower sensing element 106 (due to the left, The upper and lower sensing elements 105, 106 of the right knee pressure sensors 103, 104 are the same elements and have the same configuration relationship, so only one diagram is used as the left knee pressure sensor 103 and the right knee Schematic of the pressure sensor 104), wherein, assuming that the pressure value measured by the upper sensing element 105 is P _{K 1} , the pressure value measured by the lower sensing element 106 is P _{K 2} , the upper sensing element 105 The shortest distance between the central point of the lower sensing element 106 and the lower end surface of the lower sensing element 106 is X ₁ (100 mm in this embodiment), and the shortest distance between the central point of the lower sensing element 106 and the lower end surface of the lower sensing element 106 The distance is X ₂ (10mm in this embodiment), then the pressure center position of the left knee pressure sensor 103 (or the right knee pressure sensor 104) =

As shown in Figures 1 and 3, in step (b), the control unit acquires a second user's motion model, which includes the second user's movement in the gait training center in a state of muscle relaxation. The measured muscle relaxation gait data of a second user is combined with the standard motion model to estimate a personalized training model (as shown in FIG. 3 ). In this preferred embodiment, as shown in Figure 3a, the personal training model is used to estimate 10%, 15%, 20%, 25%, 30%, 40%, 50%, 60%, 70% , 80%, 90% and 100% difficulty curves (only the 100% difficulty curve L1 and the 10% difficulty curve L12 are marked in FIG. It can be adjusted according to requirements, so these difficulty curves are not limited to this preferred embodiment.

Wherein, taking the right foot as an example, since the center of gravity transfer interval F1 is the stepping down stage of the right foot, the higher the value measured by the right foot force sensor 102, the more difficult the personalized training model is. The higher the value, the lower the value measured by the right foot strength sensor 102, the lower the difficulty of the personalized training model. Therefore, between about the gait cycle 0-40, the uppermost curve It is the 100% difficulty curve L1, the lowermost curve is the 10% difficulty curve L12, and the knee flexion interval F2 and the knee extension interval F3 are the stages of raising the right foot. Therefore, when the right foot strength sensor 102 The lower the measured value, the higher the difficulty of the personalized training model, and the higher the value measured by the right foot force sensor 102, the lower the difficulty of the personalized training model. The gait cycle is approximately between 45-100, the lowermost curve is the 100% difficulty curve L1, and the uppermost curve is the 10% difficulty curve L12.

該重心轉移區間F1的出力程度。 In this preferred embodiment, as shown in Figures 3b, 3c, 3d, and 3e, the method of estimating the most suitable personalized training model for the second user from the personalized training models of different difficulties, first, The second user is in a state of muscle relaxation. Taking the right foot as an example, the value obtained by the right foot force sensor 102 can be obtained when the second user is in a state of muscle relaxation. The maximum value of the muscle relaxation state and the minimum value of a muscle relaxation state (as shown in Figure 3b) are then estimated by the standard motion model when the second user is actively exerting force, a predicted active effort in the gait cycle The maximum value and a predicted minimum value of active effort (as shown in Figure 3c), and then use the value obtained by the right foot force sensor 102 in the state of the second user's active effort to obtain the second user's active effort , in the gait cycle, an actual maximum active force and an actual minimum active force (as shown in Figure 3d), and respectively the actual maximum active force, the predicted maximum active force and the muscle relaxation The maximum value of the state is brought into a calculation formula of the center of gravity transfer interval, and the minimum value of the actual active output force, the minimum value of the predicted active output force and the minimum value of the muscle relaxation state are respectively brought into the calculation formula of a hip flexion interval to obtain the center of gravity transfer interval and The output degree of the hip flexion range, and then the lower output degree recommends the suitable personalized training model (as shown in Figure 3e). The specific calculation method is as follows: the calculation formula of the center of gravity transfer interval:

The output level of the center of gravity shift section F1.

。 In this preferred embodiment, as shown in Figures 3c and 3d, the degree of effort of the second user in the center of gravity transfer interval F1 =

.

該髖屈曲區間F2的出力程度。 Calculation formula for hip flexion range:

The degree of effort in the hip flexion zone F2.

。 In this preferred embodiment, as shown in Figures 3c and 3d, the degree of effort of the second user in the hip flexion zone F2 =

.

Since the output of the hip flexion zone F2 is smaller than the output of the center of gravity transfer zone F1, the individualized training model is recommended based on the output of the hip flexion zone F2, for example, the 80% difficulty curve in Figure 3a The represented model serves as the personalized training model.

As shown in Figures 1, 3c, 3d, 3e, and 4, in step (c), the control unit judges whether the user's actual training state meets the standard of the personalized training model, and then adjusts the personalized training model, and provides a Auxiliary training model.

In this preferred embodiment, the method for the control unit to judge whether the actual training state of the second user meets the standard of the personalized training model includes a continuous judgment method in an interval and a single-point trigger judgment method. The continuous judgment method is in one of the intervals of the gait cycle (for example: the center of gravity transfer interval F1, the hip flexion interval F2, and the knee extension interval F3), and continuously judges whether the actual training state of the second user conforms to the The standard of the personalized training model, when the second user meets the standard at the beginning of the training, the training unit of the gait training device 100 maintains the original set speed, when the standard is not met, the control unit controls the training unit to reduce the running speed (In this preferred embodiment, the running speed is set to be reduced by 12% each time, and the minimum is reduced to 25% of the original set speed, but not limited to this), when the second user slows down after the training unit When meeting the standard again, the control unit controls the operating speed of the training unit to increase by 38% each time, and the maximum reaches 100% of the original set speed; Any data in the center of gravity transfer interval F1, the hip flexion interval F2, and the knee extension interval F3) reaches the personalized training The standard of the model is deemed to have reached the standard of the personalized training model, so as to avoid the need for the second user to continuously exert effort to adjust the personalized training model.

、該右腳力量感測器102感測該第二使用者於主動出力狀態下之力量P _F 、該右腳力量感測器102感測該第二使用者於放鬆狀態下的力量U _FR 、該個人化訓練模型U _FP 及設定難度R%等參數進行判斷；當判斷該第二使用者在該髖屈曲區間F2達到髖關節屈曲時，須符合以下條件：(X _K >

+R%×U _RKX )∩(P _F <(U _FP -U _FR )×R%+U _FP )，其中，該第二使用者於放鬆狀態下的壓力中心變動範圍U _RKX 的算法為，該第二使用者於放鬆狀態下的該髖屈曲區間F2所記錄到的壓力中心位置之最大值與最小值差值的一半，平均壓力中心位置

則是該髖屈曲區間F2紀錄到的壓力中心位置平均值。 In this preferred embodiment, one of the methods for the control unit to determine whether the second user has reached hip flexion in the hip flexion interval F2 is, taking the right foot as an example, combining the second user in the active exertion state The pressure center position X _K measured by the right knee pressure sensor 104, the average pressure center position measured by the second user in a relaxed state

, the right foot force sensor 102 senses the second user's force P _F in the active exertion state, the right foot force sensor 102 senses the second user's force U _FR in the relaxed state, The personalized training model U _FP and the setting difficulty R % are used for judgment; when it is judged that the second user reaches hip flexion in the hip flexion interval F2, the following conditions must be met: ( X _K >

+ R %× U _RKX )∩( P _F <( U _FP -U _FR )× R %+ U _FP ), wherein, the algorithm of the variation range U _RKX of the pressure center of the second user in the relaxed state is, the Half of the difference between the maximum value and the minimum value of the pressure center position recorded by the second user in the hip flexion zone F2 in the relaxed state, the average pressure center position

is the average value of the pressure center position recorded in the hip flexion interval F2.

In this preferred embodiment, one of the methods for the control unit to judge whether the second user has reached knee straightening in the knee straightening section F3 is, taking the right foot as an example, it is necessary to combine the second user with the active The pressure value P _K measured by the right knee pressure sensor 104 in the exertion state, the pressure value U _RKP measured by the right knee pressure sensor 104 when the second user relaxes the muscles, and the setting Difficulty R % and other parameters are used for judgment; when it is judged that the second user has reached the knee straightening action in the knee straightening interval F3, the following conditions must be met: P _K <0.9-0.4× R %× U _RKP .

In this preferred embodiment, it is judged whether the actual training state of the second user meets the standard of the personalized training model by means of continuous judgment in the interval. Whether the measurement data in the hip flexion interval F2 reaches 80% of the predicted value of the personalized training model, if it does not reach 80% of the predicted value of the personalized training model, it is considered not to meet the standard, if it only reaches the personalized training model 50% of the predicted value of the training model is only considered to have participated in the gait training. In addition, in the personalized training model, after the second user undergoes the gait training of the gait cycle for five times, if four of them meet the standard of the personalized training model, the control unit will The auxiliary training model is provided by increasing the difficulty of the personalized training model. After the second user has undergone five gait trainings of the gait cycle, if four of them do not meet the requirements of the personalized training model standard, the control unit will provide the auxiliary training model by reducing the difficulty of the personalized training model.

In this preferred embodiment, as shown in FIG. 3e, the 70% difficulty of the personalized training model is used as the auxiliary training model as an example. In other preferred embodiments, the personalized training model is judged and adjusted in the manner of continuous judgment in the interval, and 10%, 15%, 20%, 25%, 30%, 40% can be defined according to the personalized training model. %, 50%, 60%, 80%, 90%, and 100% of difficulty as the auxiliary training model; judging and adjusting the personalized training model by means of the single-point trigger judgment can be defined according to the personalized training model Difficulties of 20%, 40%, 60%, 80%, and 100% are used as the auxiliary training model.

Thus, the present invention provides a method 10 for real-time adjustment of gait training parameters, which can plan a personalized exercise model belonging to the second user according to the state of the second user, and can be used in training according to the second user. Based on the output data, the operator recommends a suitable auxiliary training model to achieve the effect of adjusting the difficulty of training in real time according to the actual performance during training.

The above-mentioned preferred embodiments are to help understand the principle and method of the present invention, and the present invention is not limited to the above-mentioned preferred embodiments. Any combination and modification within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

10: The method of real-time adjustment of gait training parameters

Claims (7)

A method for real-time adjustment of gait training parameters, suitable for one-step training equipment, the gait training equipment includes a sensing unit, a training unit and a control unit, the control unit is electrically connected to the sensing unit and the training unit Connecting and controlling the training unit to act, the method for adjusting the gait training parameters in real time includes the steps: (a) the sensing unit collects at least one first user’s first measured gait training in the muscle relaxation state; A user's muscle relaxation gait data, and the first user's active effort gait data measured by the at least one first user in the active effort state during the gait training, the control unit uses the first The ratio of the user's active effort gait data to the first user's muscle relaxation gait data is used to establish a standard motion model, wherein the gait training includes at least one step cycle, and the gait cycle is mainly divided into a center of gravity transfer interval , a hip flexion interval and a knee extension interval; (b) the control unit obtains a motion model of a second user, including a first motion measured by the second user during the gait training in a state of muscle relaxation Two user's muscle relaxation gait data, by combining the second user's muscle relaxation gait data with the standard motion model, at least one personalized training model is estimated; wherein the control unit estimates that the calculation method of the personalized training model is: , from the muscle relaxation gait data of the second user, when the second user is in the muscle relaxation state, a maximum value of the muscle relaxation state and a minimum value of the muscle relaxation state in the gait cycle are obtained, and then by the standard The motion model estimates a predicted maximum value of active force and a predicted minimum value of active force in the gait cycle when the second user is actively exerting force, and then uses the sense When the second user actively exerts force, an actual maximum active effort and a minimum actual active effort in the gait cycle can be obtained value, and respectively bring the actual maximum value of active output, the predicted maximum value of active output and the maximum value of the muscle relaxation state into a center of gravity transfer interval calculation formula, and the actual minimum value of active output, the predicted minimum value of active output and the minimum value of the muscle relaxation state into a hip flexion interval calculation formula to obtain the center of gravity transfer interval and the output level of the hip flexion interval, and then use the lower output level as the personalized training model for the second user; And (c) the control unit judges whether the actual training state of the second user meets the standard of the at least one personalized training model, and then adjusts the at least one personalized training model and provides an auxiliary training model. The method for adjusting gait training parameters in real time according to Claim 1, wherein: in the step (b), the at least one humanized training model is plural. The method for adjusting gait training parameters in real time as described in Claim 1, wherein: the sensing unit includes two knee pressure sensors and two plantar force sensors, in the step of the method for real-time adjusting gait training parameters In (c), when the control unit judges whether the second user has reached hip flexion in the hip flexion interval, the following conditions must be met: ( X _K >

+ R %× U _RKX )∩( P _F <( U _FP - U _FR )× R %+ U _FP ), wherein, X _K is one of the knee pressure sensors when the second user is in the active exertion state The pressure center position measured by the instrument,

is the average pressure center position measured by the knee pressure sensor when the second user is in a relaxed state, and U _FR is measured by one of the plantar force sensors when the second user is in a relaxed state The strength value of , U _FP is the personalized training model, and R % is the setting difficulty. The method for adjusting gait training parameters in real time as described in Claim 1, wherein: the sensing unit includes two knee pressure sensors and two plantar force sensors, in the step of the method for real-time adjusting gait training parameters In (c), when the control unit judges whether the second user reaches knee extension in the knee extension interval, the following conditions must be met: P _K <0.9-0.4× R %× U _RKP , where P _K is The pressure value measured by one of the knee pressure sensors when the second user is in the active exertion state, U _RKP is the pressure measured by the knee pressure sensor when the second user is in muscle relaxation Value, R % is the set difficulty. The method for adjusting gait training parameters in real time as described in Claim 1, wherein: in the step (c), the method of judging whether the actual training state of the second user meets the standard of the personalized training model includes an interval Internal continuous judgment mode and single-point trigger judgment mode. The method for adjusting gait training parameters in real time as described in claim 1, wherein: in the step (c), when the actual training state of the second user does not meet the standard of the personalized training model, the control unit lowers the The means of personalizing the difficulty of the training model provides the auxiliary training model. The method for adjusting gait training parameters in real time as described in claim 1, wherein: in the step (c), when the actual training state of the second user has met the standard of the personalized training model, the control unit will increase the The means of personalizing the difficulty of the training model provides the auxiliary training model.

Images