A training method and system based on a horse riding trainer

Abstract

The present application relates to the technical field of horse riding training devices, and particularly relates to a training method and system based on a horse riding training device. The method comprises the following steps: obtaining evaluation data of a user, wherein the evaluation data comprises stress data, angle data and heart rate data; inputting the evaluation data into a trained ability evaluation model to obtain an evaluation result, wherein the evaluation result comprises a muscle strength score; the ability evaluation model is a machine learning model; determining training parameters of the user based on the evaluation result, wherein the training parameters comprise training resistance; and outputting the training parameters to enable the user to perform training based on the training parameters. The present application can improve the training effect of the user using the horse riding training device.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of horse riding training devices. More particularly, the present application relates to a training method and system based on a horse riding training device. BACKGROUND

[0002] A horse riding training device, also known as a horse riding machine, is a fitness device that simulates horse riding exercise, which can strengthen muscle strength, improve balance ability, and has a wide range of applications, not only meeting the training needs of professional equestrian athletes, but also meeting the training needs of amateur enthusiasts, rehabilitation patients, etc.

[0003] However, when performing horse riding training, the resistance and other training parameters are generally set directly according to experience. This training method is highly subjective and cannot match the actual situation and ability of the user. In particular, rehabilitation users and beginners are prone to overtraining or undertraining. Therefore, how to set the parameters of horse riding training according to the actual situation and ability of the user to perform effective training is a technical problem that needs to be solved at present. SUMMARY

[0004] To solve the above technical problem of being difficult to perform effective horse riding training by setting training parameters according to experience, the present application provides solutions in the following aspects.

[0005] In a first aspect, the present application provides a training method based on a horse riding training device, comprising: obtaining evaluation data of a user, the evaluation data comprising stress data, angle data and heart rate data; inputting the evaluation data into a trained ability evaluation model to obtain an evaluation result; the evaluation result comprising a muscle strength score; the ability evaluation model is a machine learning model; determining a training parameter of the user based on the evaluation result, the training parameter comprising a training resistance, the training resistance being positively correlated with the muscle strength score; outputting the training parameter to enable the user to perform training based on the training parameter.

[0006] Further, determining the training parameter of the user based on the evaluation result comprises: determining the training resistance according to the muscle strength score and a preset resistance interval, and the calculation expression of the training resistance is:

[0007]

[0008] wherein R represents the training resistance, R min represents the minimum value of the resistance interval, R max represents the maximum value of the resistance interval, and S represents the muscle strength score.

[0009] Further, the training plan further comprises a training speed, and the evaluation result further comprises the balance score.

[0010] The determining the training parameter of the user based on the evaluation result further comprises: determining the training speed according to the balance score and a preset speed interval, and a calculation expression of the training speed is:

[0011]

[0012] wherein, V represents the training speed, V min represents a minimum value of the speed interval, V max represents a maximum value of the speed interval, and B represents the balance score.

[0013] Further, the training plan further comprises a training speed, and the evaluation result further comprises the balance score; the determining the training parameter of the user based on the evaluation result further comprises: determining the training speed according to the balance score, the muscle strength score and a preset speed interval, and the training speed is positively correlated with the muscle strength score and the balance score.

[0014] Further, the method further comprises: collecting a heart rate of the user during the training; and in response to the heart rate being greater than a maximum value of a target heart rate interval and the heart rate lasting for a preset time, reducing the training resistance and / or the training speed.

[0015] Further, the method for obtaining the target heart rate interval comprises: obtaining a training target and an intensity coefficient of the user; matching a first percentage and a second percentage according to the training target; and determining a target heart rate, and a calculation expression of the target heart rate is:

[0016] HR target = HR rest + k(HR max - HR rest );

[0017] wherein, HR target represents the target heart rate, HR rest represents a resting heart rate of the user, HR max represents a maximum heart rate of the user, and k represents the intensity coefficient.

[0018] The method further comprises: determining the target heart rate interval based on the first percentage, the second percentage and the target heart rate.

[0019] Further, before inputting the evaluation data into the trained ability evaluation model, the method further comprises: pre-processing the evaluation data, and the pre-processing comprises denoising filtering, data alignment and feature extraction.

[0020] Further, the training parameter further comprises a training mode, and the evaluation result further comprises a coordination score; based on the evaluation result, determining the training parameter of the user further comprises: in response to the muscle strength score being less than a first threshold value and the coordination score being less than a second threshold value, determining the training mode as passive training.

[0021] Further, the method further comprises: in response to the training being ended, generating a training report, the training report comprising a training time, a training resistance, and a heart rate variation curve.

[0022] In a second aspect, the present application provides a horse riding trainer based training system comprising a processor and a memory, the memory storing computer program instructions which, when executed by the processor, implement a horse riding trainer based training method according to the first aspect.

[0023] The present application has the beneficial effects that: the present application can improve the accuracy of user ability evaluation by evaluating the ability according to the actual stress data, angle data and heart rate data of the user; the actual ability of the user can be ensured to match the training parameter by generating the training plan / training parameter of the user according to the evaluation result, thereby avoiding the situation of insufficient training or excessive training caused by setting the training parameter according to experience, and improving the training effect; the training safety can be ensured by reducing the training difficulty in time if the heart rate of the user exceeds the safety range during the training process, thereby improving the safety of the training. BRIEF DESCRIPTION OF DRAWINGS

[0024] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings in which a number of embodiments of the present application are illustrated by way of example and not limitation. Like or corresponding elements show in the figures are referred to by like reference numerals, in which:

[0025] Figure 1 is a flowchart schematically showing a horse riding trainer based training method according to one embodiment of the present application;

[0026] Figure 2 is a flowchart schematically showing a horse riding trainer based training method according to another embodiment of the present application;

[0027] Figure 3 is a structural diagram schematically showing a horse riding trainer according to an embodiment of the present application;

[0028] Figure 4 is a structural block diagram schematically showing a horse riding trainer based training system according to another embodiment of the present application. DETAILED DESCRIPTION

[0029] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the present application.

[0030] The specific embodiments of the present application will be described in detail below with reference to the drawings.

[0031] Figure 1 is a flowchart schematically showing a training method based on a horse riding trainer according to an embodiment of the present application.

[0032] In a first aspect, the present application provides a training method based on a horse riding trainer, as Figure 1 The method of the present application includes:

[0033] S101, acquiring evaluation data of a user.

[0034] The evaluation data refers to data collected by sensors when the user moves by himself / herself using the horse riding trainer within a specified time, for example, 3 minutes, before training. In the embodiment, the evaluation data includes pressure data, angle data and heart rate data, wherein the pressure data includes first pressure data, second pressure data and third pressure data.

[0035] Specifically, as Figure 3 shown, the first pressure data, the second pressure data and the third pressure data of the user can be collected by installing pressure sensors at the handrails, the seat and the pedals respectively; the heart rate data of the user can be collected by installing a heart rate sensor at the handrails or a wearable device; and the angle data when the user moves can be collected by installing an angle sensor on the moving part of the horse riding trainer. It should be noted that the horse riding trainer for implementing the method of the present application can adopt the mechanical structure of a conventional horse riding trainer, and in addition, a servo electric push rod should be provided, which is connected between the seat and the support of the trainer, for providing resistance and power during training.

[0036] By using the pressure data, the angle data and the heart rate data for evaluation, the movement ability and the physiological state of the user can be accurately evaluated.

[0037] S102, inputting the evaluation data into a trained ability evaluation model to obtain an evaluation result.

[0038] In one embodiment, before the evaluation data is input into the capability evaluation model, the evaluation data is further pre-processed, including denoising filtering, data alignment and feature extraction. Specifically, in the denoising filtering, the noise can be eliminated by Kalman filtering or low-pass filtering. In addition, the angle data can also be smoothed by the following method to reduce the interference of noise.

[0039]

[0040] In the formula, is the processed angle value at the t-th moment, and θ(t) is the angle value collected at the t-th moment, is the processed angle value at the t-1-th moment.

[0041] By denoising filtering the evaluation data, the interference of noise can be reduced, thereby improving the quality of the evaluation data and further improving the accuracy of the subsequent output evaluation results.

[0042] Data alignment can be synchronized by timestamp. By performing data alignment, the relationship between features is more clear, avoiding deviation and error caused by non-corresponding data, thereby ensuring the accuracy of evaluation. Further, feature extraction is performed on the evaluation data to obtain a feature vector. In the embodiment, the feature vector includes lower limb muscle strength features, upper limb muscle strength features, balance ability features, coordination features and heart rate features.

[0043] Specifically, the lower limb muscle strength features can be represented by the pressure data (third pressure data) and angle data at the pedal. In the embodiment, the power is taken as the lower limb muscle strength feature. Specifically, the calculation expression of the power is:

[0044]

[0045] In the formula, Power is the power, τ(t) is the torque at the t-th moment (estimated by the third pressure data), ω(t) is the angular velocity at the t-th moment (calculated by the collected angle), and T is the evaluation duration.

[0046] The upper limb muscle strength features can be represented by the pressure data at the handrail. In the embodiment, the standard deviation of the first pressure data is taken as the upper limb muscle strength feature. Specifically, the calculation expression of the upper limb muscle strength feature is:

[0047]

[0048] In the formula, Upper_Strength is the upper limb muscle strength feature, N is the total number of pressure sensors distributed at the handrail, is the average value of the first pressure data, P i is the pressure value collected by the i-th pressure sensor.

[0049] The balance ability feature can be characterized by the pressure distribution of the seat. In the embodiment, the root mean square error (RMSE) of the center of gravity trajectory is taken as the balance ability feature. The calculation expression of the center of gravity trajectory is:

[0050]

[0051] In the formula, GoG(t) is the center of gravity coordinate of the user at the t-th moment, P i is the pressure value collected by the i-th pressure sensor, x i is the horizontal coordinate of the i-th pressure sensor, y i is the vertical coordinate of the i-th pressure sensor, and N is the total number of pressure sensors distributed on the seat.

[0052] The coordination feature can be characterized by the difference in the upper and lower limb movement phases. In the embodiment, the calculation expression of the coordination feature is:

[0053]

[0054] In the formula, Sync is the coordination feature, is the upper limb movement phase at the t-th moment, is the lower limb movement phase at the t-th moment, and T is the evaluation duration. The upper limb movement phase can be calculated by the pressure change at the armrest, and the lower limb movement phase can be calculated by the angle at the pedal.

[0055] The heart rate feature can be characterized by the difference between the maximum heart rate and the resting heart rate. Specifically, the calculation expression of the heart rate feature is:

[0056] ΔHR = HR max -HR rest ;

[0057] In the formula, ΔHR is the heart rate interval of the user, HR max is the maximum heart rate of the user, and HR rest is the resting heart rate of the user. The maximum heart rate can be calculated according to the difference between 220 and the age of the user.

[0058] By selecting appropriate feature combinations as feature vectors, the accuracy and interpretability of the model can be improved, so that the evaluation results obtained can conform to the actual situation of the user.

[0059] Further, the feature vector [Power, Upper_Strength, RMSE, Sync, ΔHR] is input into the ability evaluation model to obtain an evaluation result. In this embodiment, the evaluation result includes muscle strength score, balance score and coordination score, and the values of the three scores are between 0 and 100.

[0060] Further, based on the evaluation result, an evaluation report is generated, which includes user personal information, muscle strength score, balance score, coordination score, maximum heart rate and resting heart rate. The personal information includes age, gender, weight, training target and the like.

[0061] In this embodiment, the ability evaluation model is a random forest model or a support vector machine model. In alternative embodiments, a person skilled in the art can select a suitable machine learning model according to actual needs.

[0062] S103, determining a training parameter of the user based on the evaluation result.

[0063] In one embodiment, the training parameter (training plan) includes training mode, training resistance, training speed, target heart rate interval and training duration, etc.

[0064] In one embodiment, the training mode can be determined according to the muscle strength score and the coordination score. Specifically, if the muscle strength score is less than a first threshold value and the coordination score is less than a second threshold value, the training mode is passive training (the power for training is provided by the horse riding trainer); if the muscle strength score is greater than or equal to the first threshold value and the coordination score is greater than or equal to the second threshold value, the training mode is active training (the power for training is provided by the user). In another embodiment, it can also be set that if the muscle strength score is less than the first threshold value, the training mode is passive training; if the muscle strength score is greater than or equal to the first threshold value, the training mode is active training. In this embodiment, the first threshold value is set to 50 and the second threshold value is set to 40, and in alternative embodiments, a person skilled in the art can set them according to actual needs.

[0065] In alternative embodiments, the training mode can also be determined according to the training target selected by the user. Specifically, if the user selects rehabilitation training or relaxation training, passive training is performed; if the user selects fitness enhancement or competitive training, active training is performed.

[0066] In one embodiment, the training resistance can be determined according to the muscle strength score and a preset resistance interval. Specifically, the calculation expression of the training resistance is:

[0067]

[0068] In the formula, R represents the training resistance of the user, Rmin R represents the minimum value of the resistance range. max This represents the maximum value of the resistance zone, and S represents the user's muscle strength score.

[0069] In this embodiment, the resistance range is from 10N to 100N. In optional embodiments, those skilled in the art can set this resistance range according to actual needs. It should be noted that this resistance range corresponds to ten resistance levels, with the first resistance level corresponding to 10N and the tenth resistance level corresponding to 100N.

[0070] In one embodiment, the training speed can be determined based on a balance score and a preset speed range. Specifically, the expression for calculating the training speed is:

[0071]

[0072] In the formula, V represents the user's training speed, V min V represents the minimum value in the speed range. max B represents the maximum value in the speed range, and B represents the user's balance rating.

[0073] In an optional embodiment, the training speed can also be determined by comprehensively considering balance score, muscle strength score, and speed range. Specifically, the calculation expression for training speed is:

[0074]

[0075] In the formula, V represents the user's training speed, V min V represents the minimum value in the speed range. max Let α represent the maximum value of the speed range, B represent the user's balance score, S represent the user's muscle strength score, and α represent the weight of the balance score.

[0076] In this embodiment, the speed range is 5 RPM to 30 RPM, and α is 0.6. In optional embodiments, those skilled in the art can set this speed range and the weight values ​​of the balance score according to actual needs.

[0077] In one embodiment, the target heart rate zone is determined by obtaining the user's training goal and intensity coefficient. Specifically, the user can input their training goal on the display screen of the horse riding trainer, and then the system displays the intensity coefficient that the user can select based on the training goal. The user selects the intensity coefficient according to their actual needs, thereby obtaining the user's training goal and intensity coefficient. Further, a first percentage and a second percentage are matched based on the training goal.

[0078] Specifically, a mapping relationship table of the training target and the intensity coefficient, the first percentage and the second percentage can be set, so that the corresponding intensity coefficient can be displayed according to the training target of the user, and the first percentage and the second percentage can be determined according to the training target. In one embodiment, the mapping relationship table is shown in Table 1:

[0079] Table 1

[0080] Training goals Intensity factor First percentage, second percentage Rehabilitation / relaxation 0.4-0.5 50％、60％ Endurance training 0.6-0.7 60％、70％ Strength enhancement 0.7-0.85 70％、85％

[0081] Further, the target heart rate is determined. In one embodiment, the calculation expression of the target heart rate is:

[0082] HR tarhet = HR rest + k(HR max - HR rest );

[0083] In the formula, HR target is the target heart rate, HR rest is the resting heart rate of the user, HR max is the maximum heart rate of the user, and k is the intensity coefficient selected by the user.

[0084] Further, based on the first percentage, the second percentage and the target heart rate, the target heart rate interval of the user is determined. Specifically, the first percentage is multiplied by the target heart rate to obtain the minimum value of the target heart rate interval, and the second percentage is multiplied by the target heart rate to obtain the maximum value of the target heart rate interval, so as to obtain the target heart rate interval.

[0085] In one embodiment, the training time can be determined according to the muscle strength score. Specifically, if the muscle strength score is less than 50, the training time is 10 minutes per set, and a total of three sets are trained; if the muscle strength score is greater than or equal to 50 and less than 70, the training time is 20 minutes per set, and a total of three sets are trained; if the muscle strength score is greater than or equal to 70, the training time is 30 minutes per set, and a total of three sets are trained.

[0086] In an optional embodiment, the training time can also be determined by comprehensively considering the muscle strength score, the balance score and the coordination score. Specifically, a weight is assigned to each score, and then the three scores are weighted and summed to obtain a comprehensive score; if the comprehensive score is less than 40, the training time is 10 minutes per set; if the comprehensive score is greater than or equal to 40 and less than 70, the training time is 20 minutes per set; if the comprehensive score is greater than or equal to 70, the training time is 30 minutes per set. These can be set according to actual conditions by those skilled in the art.

[0087] In an optional embodiment, if the user has historical data (training duration, training resistance, training speed, training completion, etc.), the training parameters can be determined based on the evaluation result and the historical data of the user.

[0088] The training parameters of the user are determined based on the evaluation result, which avoids the situation of insufficient training or overtraining caused by setting the training parameters based on experience, ensures that the actual ability of the user matches the training parameters, and thus improves the reliability and safety of the training.

[0089] S104, output the training parameters, so that the user trains based on the training parameters.

[0090] It should be noted that before the training parameters are output, the training parameters can also be displayed for the user to add, delete, and modify according to the actual situation.

[0091] In the process of training, the heart rate data of the user is collected in real time. If it is detected that the heart rate data of the user exceeds the maximum value of the target heart rate interval, and the heart rate lasts for a preset time, the training intensity is reduced or the training is stopped. In an embodiment, when it is detected that the heart rate of the user exceeds the maximum value of the target heart rate interval, a voice alarm is triggered, for example, "heart rate is too high, please reduce the intensity". In this embodiment, the preset time can be 5 seconds, the reduction of the training intensity can be setting the training resistance to 90% of the original, or setting the training speed to 90% of the original, and the stopping of the training can be stopping the training slowly by increasing the resistance. In an optional embodiment, the reduction ratio and the preset time can be set by the person skilled in the art according to the actual needs.

[0092] By monitoring the heart rate of the user in real time and processing in time, the harm caused by overtraining to the user can be avoided, and thus the safety of the training is improved.

[0093] Further, in the process of training, the user can also adjust the training resistance and the training speed of the user according to the actual situation or the training needs, which improves the flexibility of the training. In addition, the real-time resistance, speed, motion amplitude, and heart rate of the user and other training data can also be displayed.

[0094] Further, after the training is completed, a training report is generated, which includes the personal information of the user, the evaluation result, the training duration, the training resistance, the training speed, the heart rate change curve, and the like. In addition, corresponding charts are generated based on these data, and the training situation of the user is intuitively displayed through the charts.

[0095] Further, training suggestions can also be generated based on the training report, for example, "suggest increasing the training resistance", and the like, and voice broadcast is provided.

[0096] In another embodiment, the method of the present application can also be as followsFigure 2 as shown.

[0097] Figure 4 is a structural block diagram schematically showing a training system based on a horse riding trainer according to one of the embodiments.

[0098] In a second aspect, the present application also provides a training system based on a horse riding trainer. As shown, the system comprises a processor and a memory, the memory storing computer program instructions which, when executed by the processor, implement a training method based on a horse riding trainer according to the first aspect of the present application. Figure 4

[0099] The system further comprises other components such as communication interfaces and the like, which are well known to those skilled in the art, and thus will not be described in detail herein.

[0100] In the present application, the aforementioned memory can be any tangible medium that contains or stores a program, which can be used by or in connection with an instruction execution system, apparatus, or device. For example, the computer readable storage medium can be any suitable magnetic storage medium or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random-Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), and the like, or any other medium that can be used to store the desired information and that can be accessed by an application, module, or both. Any such computer storage media can be part of the device or accessible or connectable thereto. Any applications or modules described in the present application can be implemented using computer readable / executable instructions that can be stored or otherwise held by such computer readable media.

[0101] In the description of the present application, the meaning of "a plurality of" is at least two, such as two, three or more, and the like, unless otherwise explicitly specified. In addition, the division of steps of the above-mentioned method is only for the purpose of clear description, and in implementation, one step can be combined or some steps can be split and decomposed into multiple steps, as long as the same logical relationship is included.

[0102] ​While the specification has illustrated and described various embodiments of the application, it will be clear to those of ordinary skill in the art that various changes, modifications, and substitutions can be made thereto without departing from the spirit and scope of the application. It is understood that in the process of practicing the application, various alternatives, modifications, and equivalents can be employed.

Claims

1. A training method based on a horse riding trainer, characterized by, The method comprises: obtaining evaluation data of a user, the evaluation data comprising stress data, angle data and heart rate data; inputting the evaluation data into a trained ability evaluation model to obtain an evaluation result, the evaluation result comprising a muscle strength score and a balance score; the ability evaluation model is a machine learning model; inputting the evaluation data into the trained ability evaluation model comprises: performing feature extraction on the evaluation data to obtain a feature vector; and inputting the feature vector into the ability evaluation model; the feature vector comprises lower limb muscle strength features, upper limb muscle strength features and balance ability features, the lower limb muscle strength features being determined by the stress data and the angle data at the pedal, the upper limb muscle strength features being the standard deviation of the stress data at the handrail, and the balance ability features being the root mean square error of the center of gravity trajectory; based on the evaluation result, determining training parameters of the user, the training parameters comprising a training resistance and a training speed, the training resistance being positively correlated with the muscle strength score, and the training speed being positively correlated with the muscle strength score and the balance score; outputting the training parameters to enable the user to train based on the training parameters.

2. The horse riding training device-based training method according to claim 1, characterized by, Based on the evaluation result, determining the training parameters of the user comprises: determining the training resistance according to the muscle strength score and a preset resistance interval, the calculation expression of the training resistance being: ； wherein denotes the training resistance, denotes the minimum value of the resistance interval, denotes the maximum value of the resistance interval, denotes the muscle strength score.

3. The horse riding training device-based training method according to claim 2, characterized by, Based on the evaluation result, determining the training parameters of the user further comprises: determining the training speed according to the balance score and a preset speed interval, the calculation expression of the training speed being: ； wherein denotes the training speed, denotes the minimum value of the speed interval, denotes the maximum value of the speed interval, denotes the balance score.

4. The horse riding training device-based training method according to claim 1, characterized by, Further comprising: collecting the heart rate of the user during training; in response to the heart rate being greater than the maximum value of a target heart rate interval and the heart rate lasting for a preset time, reducing the training resistance and / or the training speed.

5. The horse riding training device-based training method according to claim 4, characterized by, The method for obtaining the target heart rate interval comprises: obtaining a training target and an intensity coefficient of the user; matching a first percentage and a second percentage according to the training target; determining a target heart rate, the calculation expression of the target heart rate being: ； wherein is the target heart rate, is the resting heart rate of the user, is the maximum heart rate of the user, k is the intensity coefficient; based on the first percentage, the second percentage and the target heart rate, determining the target heart rate interval.

6. The horse riding training device-based training method according to claim 1, characterized by, Before inputting the evaluation data into the trained ability evaluation model, further comprising: pre-processing the evaluation data, the pre-processing comprising denoising filtering, data alignment and feature extraction.

7. The horse riding training device-based training method according to claim 1, characterized by, The training parameters further comprise a training mode, and the evaluation result further comprises a coordination score; based on the evaluation result, determining the training parameters of the user further comprises: in response to the muscle strength score being less than a first threshold value and the coordination score being less than a second threshold value, determining the training mode as passive training.

8. The horse riding trainer based training method according to claim 1, characterized in that, Further comprising: in response to the end of training, generating a training report, the training report comprising training time, training resistance and heart rate change curve.

9. A horse riding trainer based training system characterized in that, The method comprises a processor and a memory, the memory storing computer program instructions which, when executed by the processor, implement a training method based on a horse riding trainer according to any one of claims 1-8.

Images