CN116030937B - Method for generating running exercise prescription - Google Patents
Method for generating running exercise prescription Download PDFInfo
- Publication number
- CN116030937B CN116030937B CN202310048692.6A CN202310048692A CN116030937B CN 116030937 B CN116030937 B CN 116030937B CN 202310048692 A CN202310048692 A CN 202310048692A CN 116030937 B CN116030937 B CN 116030937B
- Authority
- CN
- China
- Prior art keywords
- exercise
- prescription
- load
- current
- exercise prescription
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention relates to the technical field of sports health management, and discloses a method for generating a running exercise prescription, which is based on real-time body function parameters reflected by a tester in the running process, quantifies the real-time body exercise state of the tester by establishing a body load quantification model, adjusts the testing environment parameters and exercise indexes step by step according to the relation between quantification data and a preset load threshold value, and can dynamically generate the personalized exercise prescription which is suitable for different running environments and accords with different individual body change states.
Description
Technical Field
The invention relates to the technical field of sports health management, in particular to a method for generating a running sports prescription.
Background
With the enhancement of national physical health consciousness, sports and body building become important components in people's life. Among them, running exercise is an aerobic exercise with low requirements on technology, places and equipment conditions, and has very important effects in improving human cardiopulmonary function and aerobic endurance. Proper running exercise is beneficial to promoting physical and mental health of people, but because of the general lack of scientific running knowledge, insufficient exercise amount cannot achieve the expected exercise effect, and excessive exercise causes unnecessary physical burden. Proper exercise refers to exercise according to the health condition, physical quality and exercise capacity of different individuals, and the aim of exercise is achieved on the premise of ensuring safety. An effective exercise regimen, i.e., exercise prescription, is formulated based on the health of the different individuals and the current exercise capabilities.
At present, in the running exercise, a method for making an exercise prescription for different individuals mainly takes heart and lung endurance as an important index of human health level, analyzes heart and lung endurance level of a runner according to body measurement data (heart rate and maximum oxygen uptake) by acquiring the body measurement data of the runner, performs user portrait on the runner, recommends a proper exercise scheme for the runner by combining the user portrait and the making rule of the exercise prescription, and finally adjusts the exercise prescription through subjective feeling (exercise comfort, body ache degree and the like) of the runner. The method can help runners to quickly make personalized exercise schemes, so that exercise capacity is improved more efficiently. However, the physical functions of the same individual in different exercise environments are different, and adjusting an exercise prescription based on the subjective feelings of runners lacks objectivity.
In view of this, the present application is specifically proposed.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: the existing method for generating the exercise prescription can only generate the exercise prescription in the current exercise environment, and the generated exercise prescription is influenced by subjective feelings of runners and is not matched with the actual heart-lung endurance condition of the runners. The method for generating the running exercise prescription comprehensively considers the influence of environmental factors on the physical function of a tester, quantifies the physical load of the tester in the running process in a modeling mode, and objectively reflects the real-time exercise state of the tester; and the environment parameters and the motion indexes are dynamically adjusted according to the real-time motion state, so that the personalized motion prescription is generated according to different environments and different individuals.
The invention is realized by the following technical scheme:
a method of generating a running exercise prescription, comprising the steps of: s1: establishing a body load quantification model and setting a load threshold; s2: generating a recommended prescription, and taking the recommended prescription as a current exercise prescription; the current exercise prescription comprises a plurality of environmental parameters and a plurality of exercise indexes; s3: adjusting a current test environment according to a plurality of environment parameters of the current exercise prescription; s4: allowing the tester to run according to the current exercise prescription; after the time period T, acquiring physical function parameters of a tester in the running process in real time, and acquiring real-time physical load indexes according to the physical function parameters and the physical load quantification model; s5: comparing the real-time body load index with the load threshold; if the real-time body load index is greater than the load threshold, executing S6; otherwise, executing S7; s6: stopping running, and checking whether the current test environment is the same as the current atmospheric environment; if the current exercise prescriptions are different, the exercise load is reduced by adjusting one environmental parameter of the current exercise prescriptions, the current exercise prescriptions are updated, and the test person returns to S3 after body recovery; otherwise, reducing exercise load by adjusting one exercise index of the current exercise prescription, updating the current exercise prescription, and returning to the step S4 after waiting for the body recovery of the tester; s7: judging whether the current exercise prescription is a recommended prescription or not; if the prescription is recommended, executing S8; otherwise, executing S9; s8: increasing exercise load by adjusting one exercise parameter of the current exercise prescription, updating the current exercise prescription, and returning to the step S4; s9: allowing a tester to run continuously according to the current exercise prescription, collecting body function parameters of the tester in real time in the running process, acquiring real-time body load indexes according to the body function parameters and the body load quantification model, and comparing the real-time body load indexes with the load threshold; if the real-time body load index is more than the load threshold before the test is finished, returning to S6; if the real-time body load index is kept to be smaller than or equal to the load threshold value before the test is finished, outputting the current exercise prescription as the final running exercise prescription after the test is finished.
Wherein the plurality of environmental parameters of the current athletic prescription include temperature, humidity, and air pressure; the plurality of athletic metrics of the current athletic prescription include duration, speed, distance, stride frequency, stride length, and grade. The body function parameters include respiratory rate minimum, upper quartile of heart rate, electrocardiographic signal margin factor, heart rate mean, respiratory rate mean, number of R-R interval zero crossings, and lower quartile of heart rate.
In the above method, in S6, reducing the exercise load by adjusting an environmental parameter of the current exercise prescription includes: heating, cooling, humidifying, dehumidifying, pressurizing and depressurizing. In S6, adjusting an athletic index of the current athletic prescription includes one of increasing a duration, slowing down, shortening a distance, decreasing a stride frequency, decreasing a stride length, and decreasing a slope. In S8, adjusting an athletic index of the current athletic prescription includes one of shortening a duration, increasing a speed, extending a distance, increasing a stride frequency, expanding a stride, and increasing a slope.
Further, the method for adjusting an environmental parameter of the current exercise prescription is to arrange the temperature, humidity and air pressure in a queue according to any sequence; when each time of adjustment is carried out, the environmental parameter at the head of the team is selected as an adjustment object to be adjusted; after the adjustment is completed, setting the environment parameters corresponding to the adjustment objects at the tail of the team; the method for adjusting one exercise index of the current exercise prescription is to arrange the duration, the speed, the distance, the step frequency, the stride and the gradient into a queue according to any sequence; when each time of adjustment is carried out, a motion index at the head of a team is selected as an adjustment object to be adjusted; and after the adjustment is finished, the motion index corresponding to the adjustment object is placed at the tail of the team.
Further, the establishment of the body load quantification model comprises the following steps: summoning a plurality of volunteers for running test; in the test, collecting a plurality of physical function parameters of each volunteer in real time to obtain a parameter sample; carrying out feature extraction on the parameter samples by using time domain feature calculation, fourier transformation, heart rate variability analysis, empirical mode decomposition, hilbert analysis, complex network conversion and dynamic time warping method to obtain feature samples; performing feature screening on the feature samples to obtain significant feature samples; according to the significant feature samples, a first body load detection model based on logistic regression and a second body load detection model based on a support vector machine are respectively established; and establishing a body load quantification model according to the first body load detection model and the second body load detection model.
Further, before the feature extraction of the sample data, the method comprises the following steps: dividing the parameter sample into a plurality of first-stage samples according to the age of a tester; dividing each primary sample into a plurality of secondary samples according to the body shape of a tester; and carrying out noise reduction treatment and zero drift removal on each secondary sample.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. the method comprehensively considers the influence of environmental factors on the physical function of a tester in the running process, and the defect that the exercise prescription is not matched with the actual heart-lung endurance condition of the runner easily caused by the mode of adjusting the exercise prescription according to the subjective feeling of the runner.
2. In the adjustment of environmental parameters or motion indexes, a mode of adjusting only one parameter or index at a time is adopted, so that the situation that the reason affecting the physical condition of a tester is difficult to accurately find due to the fact that a plurality of influencing factors are considered at the same time can be avoided; and the objects adjusted each time are different through the form of the queue, so that the continuous adjustment of a single influencing factor is avoided, and the exercise prescription conforming to the physical characteristics of an individual can be quickly matched from different latitudes.
3. In the process of establishing the body load quantification model, parameter samples are divided according to ages and statures, so that the load quantification model which accords with physiological characteristics of testers in different age ranges and different statures in the same age range can be established.
Drawings
In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the drawings that are needed in the examples will be briefly described below, it being understood that the following drawings only illustrate some examples of the present invention and therefore should not be considered as limiting the scope, and that other related drawings may be obtained from these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a running exercise prescription generating method according to embodiment 1 of the present invention.
Detailed Description
For the purpose of making apparent the objects, technical solutions and advantages of the present invention, the present invention will be further described in detail with reference to the following examples and the accompanying drawings, wherein the exemplary embodiments of the present invention and the descriptions thereof are for illustrating the present invention only and are not to be construed as limiting the present invention.
Example 1
Aiming at the problems that the existing method for generating the exercise prescription can only generate the exercise prescription under the current exercise environment and the generated exercise prescription is influenced by subjective feeling of a runner and is not matched with the actual heart-lung endurance condition of the runner, the embodiment provides the method for generating the exercise prescription shown in fig. 1, which is based on real-time physical function parameters reflected by a tester in the running process, quantifies the real-time physical movement state of the tester by establishing a physical load quantification model, and adjusts the test environment parameters and the exercise indexes successively according to the relation between quantification data and a preset load threshold value, so as to dynamically generate the personalized exercise prescription which is suitable for different running environments and accords with different individual physical change states.
Specifically, the method comprises the following steps:
s1: and (5) establishing a body load quantification model and setting a load threshold.
It should be noted that, the body load quantization model is used to calculate and obtain the body load index of the tester, and the body load index is used in this embodiment to quantify the load of the tester during running.
The body load index is a value ranging from 0 to 100. The load threshold is the maximum load that the body of the tester can bear (provided that the tester is ensured to run safely). When the body load index is greater than the load threshold, the current exercise load exceeds the range that the tester body can bear.
The present embodiment uses 50 as the load threshold. Of course, the load threshold may be dependent on the physical quality of the tester and other needs.
S2: generating a recommended prescription, and taking the recommended prescription as a current exercise prescription. The current sports prescription includes environmental parameters and a plurality of sports indexes.
It should be noted that, the recommended prescription is a reference exercise prescription provided for the tester according to the basic information of the age, stature, physical quality, and the like of the tester when the first running test is performed.
The reference exercise recipe may be derived from a previously stored exercise recipe of the tester that matches the basic information of the current tester; if no sports prescriptions are stored previously, the recommended prescriptions can also be sports prescriptions searched from the network according to the basic information of the current testers; the method can also refer to the existing exercise prescription generation method and combine the basic information of the testers to preliminarily make an exercise prescription.
In this embodiment, the recommended prescriptions are obtained by acquiring basic information (such as age, height, weight, etc.) of the testers, and searching the matched exercise prescriptions from the exercise prescription recommendation library according to the basic information of the testers. Of course, in the case that the sports prescription recommendation library is not established, the above manner may be selected according to the actual situation to generate an appropriate recommended prescription for the tester.
In addition, in the present embodiment, the current exercise prescription includes 3 environmental parameters of temperature, humidity and air pressure, and 6 exercise indexes of duration, speed, distance, stride frequency, stride length and gradient. To facilitate the explanation of the following implementation steps, the present embodiment sets the current exercise recipe to 28 ℃, the humidity to 70%, the air pressure to 100kpa, the duration to 10min, the distance to 800m, the stride frequency to 100 times/minute, the stride to 1m, and the treadmill grade to 5 °.
S3: and adjusting the current testing environment according to the temperature, humidity and air pressure of the current exercise prescription.
Specifically, the temperature in the test chamber was set to 28 ℃, the humidity was set to 70%, and the air pressure was set to 100kpa. Meanwhile, parameters of the running machine are set according to the exercise index of the current exercise prescription, namely running duration is set to be 10min, running distance is set to be 800m, and gradient of the running machine is set to be 5 degrees.
S4: allowing the tester to run according to the current exercise prescription; and after the time period T, acquiring physical function parameters of the tester in the running process in real time, and acquiring real-time physical load indexes according to the physical function parameters and the physical load quantification model.
Specifically, the tester is guided to stand on the running machine, and the running machine is started to run to a stable state according to preset parameters. The tester then starts running on the treadmill for a period of T minutes in advance (the duration may be as the case may be). Real-time physical function data of a tester during running was collected using a Bioharness device, including an electrocardiographic signal (sampling frequency of 250 hz), a respiratory signal (sampling frequency of 18 hz), an R-R interval (sampling frequency of 1 hz), a heart rate (sampling frequency of 1 hz), a respiratory frequency (sampling frequency of 1 hz), and a respiratory amplitude (sampling frequency of 1 hz). And inputting the acquired real-time body function parameters into an established body load quantification model, and calculating to obtain real-time body load indexes.
S5: comparing the real-time body load index with the load threshold; if the real-time body load index is greater than the load threshold, executing S6; otherwise, S7 is performed.
Specifically, the real-time body load index calculated in S4 (for example, the calculated real-time load index is 55) is compared in size with the load threshold 50. Since the real-time body load index 55 > the load threshold 50 at this time indicates that the body of the tester cannot bear the burden of the current exercise prescription, the current exercise prescription needs to be adjusted, i.e., S6 is performed. If the real-time body load index calculated at S4 is less than or equal to the load threshold (e.g., real-time body load index 45 < load threshold 50), indicating that the tester' S body is capable of withstanding the load imposed by the current exercise prescription, then S7 is performed.
S6: stopping running, and checking whether the current test environment is the same as the current atmospheric environment; if the current exercise prescriptions are different, the exercise load is reduced by adjusting one environmental parameter of the current exercise prescriptions, the current exercise prescriptions are updated, and the test person returns to S3 after body recovery; otherwise, the exercise load is reduced by adjusting one exercise index of the current exercise prescription, the current exercise prescription is updated, and the test person returns to S4 after body recovery.
When the real-time body load index is larger than the load threshold, the body of the tester cannot bear the load brought by the current exercise prescription, and then the current exercise prescription needs to be adjusted so as to reduce the exercise load. The adjustment mode adopted by S6 is that there are two kinds: one is to reduce the exercise load by adjusting an environmental parameter of the current exercise prescription, and the other is to reduce the exercise load by adjusting an exercise index of the current exercise prescription.
The method S6 is a method of first adjusting the environmental parameter and then adjusting the sports index. Since it is considered that the physical function of the tester in running is easily affected by external factors of the environment to be lowered (for example, the temperature of the tester is raised to cause discomfort, or the air pressure is too low to cause the tester to breathe smoothly, etc.), it is necessary to eliminate the influence of the external factors first; under the condition that the influence of environmental factors is eliminated, whether the current exercise prescription is suitable for the physical condition of a tester is considered.
It should be further noted that in S6, it is necessary to check whether the current test environment is the same as the current atmospheric environment. Since the role of the sports prescription is to provide a reference for the tester to run in an environment other than the current test environment (atmospheric environment), when the environmental parameters of the current sports prescription are adjusted, the corresponding parameters of the current atmospheric environment should be taken as thresholds. If the real-time physical load index is greater than the load threshold, the current test environment is checked to be different from the current atmospheric environment, which means that the current test environment affects the physical function of the tester, the current test environment needs to be adjusted to eliminate the influence of environmental factors, the current exercise prescription is updated, the step S3 is returned, and the step S4 is executed to enable the tester to continue running test again according to the adjusted current exercise prescription. If the real-time physical load index is greater than the load threshold, the current test environment is the same as the current atmospheric environment, which means that the exercise index has a larger influence on the physical function of the tester, the exercise index should be adjusted to adapt the exercise prescription to the tester, the current exercise prescription is updated, and the running test is performed by the tester continuously in the current atmospheric environment with the adjusted current exercise prescription ring.
S7: judging whether the current exercise prescription is a recommended prescription or not; if the prescription is recommended, executing S8; otherwise, S9 is performed.
S8: and (4) increasing exercise load by adjusting one exercise parameter of the current exercise prescription, updating the current exercise prescription, and returning to the step (S4).
S9: allowing a tester to run continuously according to the current exercise prescription, collecting body function parameters of the tester in real time in the running process, acquiring real-time body load indexes according to the body function parameters and the body load quantification model, and comparing the real-time body load indexes with the load threshold; if the real-time body load index is more than the load threshold before the test is finished, returning to S6; if the real-time body load index is kept to be smaller than or equal to the load threshold value before the test is finished, outputting the current exercise prescription as the final running exercise prescription after the test is finished.
When the real-time body load index is less than or equal to the load threshold value, the body of the tester can bear the load brought by the current exercise prescription, namely the body limit of the tester is not reached. For the purpose of exercise, it is also necessary to adjust the current exercise prescription to increase the load it places on the tester. The adjustment principle is as follows:
When the real-time body load index is less than or equal to the load threshold value, firstly, judging whether the current exercise prescription is a recommended prescription or not. The reasons include the following two aspects:
on the one hand, if the current exercise prescription is a recommended prescription, it is explained that the test of the present round is the first test, and the tester can adapt to the load brought by the recommended prescription, and it is further explained that the tester can adapt to the current exercise load in the current environment. In order to achieve the purpose of running and body building, the exercise load is increased by executing S8 to adjust the exercise index of the current exercise prescription, the current exercise prescription is updated, S4 is returned, and the tester continues to test according to the adjusted current exercise prescription.
On the other hand, if the current exercise prescription is not already a recommended prescription, indicating that the current test run is ≡2 and the recommended prescription has been adjusted, further indicating that the tester is not able to accommodate the load imposed by the recommended prescription (i.e., the real-time body load index > load threshold during the first test run). At this time, the real-time body load index is less than or equal to the load threshold, and the detection result is obtained after the exercise prescription of the previous round of test is adjusted through S6 and the exercise load is increased under the condition that the real-time body load index is greater than the load threshold. It should be noted that, at this time, the real-time body load index is less than or equal to the load threshold, and the detection result is the first appearance in the initial stage of the present round of test, which only indicates that the tester can adapt to the load brought by the current exercise prescription in the initial stage of the present round of test, and the body function of the tester is reduced along with the continuous running of the exercise, and in the subsequent running process, the real-time body load index > the load threshold may also appear for the tester. Thus, the tester should be allowed to complete the running test of the present round with the adjusted current exercise prescription, thereby verifying the validity of the adjusted current exercise prescription. When the real-time body load index is less than or equal to the load threshold and the current exercise prescription is not the recommended prescription, the tester runs continuously according to the current exercise prescription and monitors the physical function change condition of the tester in real time by executing S9. If during subsequent runs, the real-time physical load index > the load threshold occurs due to reduced physical function of the tester, indicating that the tester is not able to adapt to the adjusted current exercise prescription, the test also requires adjustment of the current exercise prescription, i.e., reducing the load of the current exercise prescription by returning to execution S6, and checking the adjusted current prescription. If the real-time body load index of the tester is not more than the load threshold value all the time in the subsequent running process until the test is finished, the tester is indicated to be capable of adapting to the adjusted current exercise prescription and smoothly completing the test, namely, the current exercise prescription can be used as the final running exercise prescription.
In addition, it should be noted that: in S6, reducing the exercise load by adjusting an environmental parameter of the current exercise recipe includes: one of heating, cooling, humidifying, dehumidifying, pressurizing and depressurizing; one athletic indicator by adjusting the current athletic prescription includes one of increasing duration, slowing down, shortening distance, decreasing stride frequency, decreasing stride length, and decreasing grade. In S8, adjusting an athletic index of the current athletic prescription includes one of shortening a duration, increasing a speed, extending a distance, increasing a stride frequency, expanding a stride, and increasing a slope.
And, the method for adjusting one environmental parameter of the current sports prescription is as follows: arranging the temperature, the humidity and the air pressure into a queue according to any sequence; when each time of adjustment is carried out, the environmental parameter at the head of the team is selected as an adjustment object to be adjusted; and after the adjustment is finished, setting the environment parameters corresponding to the adjustment object at the tail of the team. The method for adjusting one sports index of the current sports prescription comprises the following steps: the duration, the speed, the distance, the step frequency, the stride and the gradient are arranged into a queue according to any sequence; when each time of adjustment is carried out, a motion index at the head of a team is selected as an adjustment object to be adjusted; and after the adjustment is finished, the motion index corresponding to the adjustment object is placed at the tail of the team.
By adopting the method for adjusting the environmental parameters or the motion indexes, the mode of adjusting only one parameter or index at a time can be avoided, and the situation that the reasons affecting the physical condition of a tester are difficult to accurately find out due to the fact that a plurality of influencing factors are considered at the same time; and the objects adjusted each time are different through the form of the queue, so that the continuous adjustment of a single influencing factor is avoided, and the exercise prescription conforming to the physical characteristics of an individual can be quickly matched from different latitudes.
Next, a specific method for building the body load quantification model in S1 is described in addition, including the following real-time steps:
step 1.1: multiple volunteers were summoned for running tests. This example sumps 25 volunteers of 22-27 years of age, each of which was tested for running, of different heights and weights. Each volunteer was required to have a healthy physical condition and each tester was required to ensure good sleep prior to testing.
Step 1.2: in the test, a plurality of physical function parameters of each volunteer are collected in real time to obtain a parameter sample. Specifically, each tester was allowed to run an energy test of 800 meters in 10 minutes on a treadmill with a treadmill slope set at 5 °. Real-time physical function data of each tester during running was collected using a Bioharness device, including an electrocardiographic signal (sampling frequency of 250 hz), a respiratory signal (sampling frequency of 18 hz), an R-R interval (sampling frequency of 1 hz), a heart rate (sampling frequency of 1 hz), a respiratory frequency (sampling frequency of 1 hz), and a respiratory amplitude (sampling frequency of 1 hz). All body function data of the 25 volunteers measured were combined into a reference sample.
Step 1.3: will beThe parameter samples are divided into a plurality of first-stage samples according to the age of a tester; dividing each primary sample into a plurality of secondary samples according to the body shape of a tester; and carrying out noise reduction treatment and zero drift removal on each secondary sample. In this embodiment, the reference samples are divided into 6 samples and 6 samples at an age of 1 year old, and then each first-level sample is divided into 2 second-level samples according to height and weight, respectively, and 12 second-level samples are all used. Then, the electrocardiosignal is firstly subjected to 5-order sliding filtering, and then is selectedcoif3Performing 8-layer discrete wavelet decomposition to remove baseline drift, and finally removing signal noise by applying a Biossp algorithm; for respiratory signals, thendmeyThe wavelet is a wavelet base for 3 layers of wavelet packet decomposition to realize denoising.
It should be noted that, in this embodiment, the parameter samples are divided according to ages and statures, so that a load quantization model conforming to physiological characteristics of testers in different age ranges and different statures in the same age range can be established.
Step 1.4: and carrying out feature extraction on the parameter samples by using time domain feature calculation, fourier transformation, heart rate variability analysis, empirical mode decomposition, hilbert analysis, complex network conversion and dynamic time warping method to obtain feature samples.
Step 1.5: and carrying out feature extraction on the parameter samples by using time domain feature calculation, fourier transformation, heart rate variability analysis, empirical mode decomposition, hilbert analysis, complex network conversion and dynamic time warping method to obtain feature samples.
The description is as follows: 1. since the electrocardiosignals in the physical function parameters are essentially time series data in the running process, the time domain feature calculation is carried out on the electrocardiosignals, and the heart rate variability feature of the electrocardiosignals in the time domain is extracted. 2. Since the respiration signal in the body function signal is characterized by the respiration rate in nature during running, the respiration signal is fourier transformed to obtain the frequency variation characteristic in the frequency domain. 3. The heart rate variability analysis mainly refers to linear analysis, and because of complex change of the central electric signal of the body function parameter, the PQRST wave group needs to be positioned on the electrocardiosignal; the present embodiment combines the modified WFDB algorithm and the neuroslit algorithm to achieve PQRST wave group localization. 4. Extracting deeper characteristic information of each parameter in the body function parameters by using empirical mode decomposition and Hilbert analysis; 5. because the signal-to-noise ratio of the electrocardiosignal is low, the conventional time sequence feature processing method is difficult to effectively extract features, and therefore the feature extraction efficiency of the electrocardiosignal is improved by converting the electrocardiosignal into a complex network.
Step 1.6: and carrying out feature screening on the feature samples to obtain remarkable feature samples. As a result of step 1.5, a large number of features with different latitudes are extracted from the body function parameters by using the feature extraction method in step 6, and in order to reduce the complexity of the algorithm and improve the recognition accuracy, the embodiment performs feature screening on the generated feature samples. The screening process mainly adopts 1, deletion value and abnormal value investigation, and deletes the characteristic that the ratio of the deletion value or the abnormal value (the value is infinite or obviously unreasonable) is more than 20 percent; 2. variance filtering and mutual information checking, namely deleting the characteristic that the variance is 0 or the mutual information is 0; 3. and 9 simple time-frequency signal characteristics are screened from the characteristic samples processed in the steps 1 and 2 according to physiological evaluation indexes commonly used in the field, namely, the body function parameters comprise a respiratory frequency minimum value, a heart rate upper quartile value, a respiratory frequency upper quartile value, an electrocardiosignal margin factor, a heart rate average value, a respiratory frequency average value, the number of R-R interval zero crossing points and a heart rate lower quartile value.
Step 1.7: and respectively establishing a first body load detection model based on logistic regression and a second body load detection model based on a support vector machine according to the salient feature samples. Wherein the expression of the first body load detection model based on logistic regression can be expressed as
It should be noted that, the expression of the first body load detection model and the expression of the second body load detection model are both one of the expressions obtained by calculation according to the values of the features selected by the extraction in this embodiment, and do not represent all of the first body load detection model and the second body load detection model. And the coefficients of the finally obtained model expression are changed according to the actually obtained body function parameters and the values of the screened characteristics.
Step 1.8: and establishing a body load quantification model according to the first body load detection model and the second body load detection model. According to the above model expressions (1) (2), the expression of the constructed body load quantization model is as follows:
According to the body load quantification model provided in the embodiment, the calculated value range of the body load index is 0-100, and the larger the value is, the larger the body load is. The present embodiment takes 50 as the load threshold, which may, of course, be determined according to the physical quality of the tester and other requirements.
In summary, the method for generating a running exercise prescription provided in this embodiment comprehensively considers the influence of environmental factors on the physical function of a tester in the running process, and the defect that the exercise prescription is not matched with the actual heart-lung endurance condition of the runner in a manner of adjusting the exercise prescription according to the subjective feeling of the runner.
Example 2
This embodiment describes a specific process of generating a running exercise prescription according to the method of generating a running exercise prescription provided in embodiment 1 as follows.
First, a body load quantification model is established, and a load threshold is set.
Then, generating a recommended prescription, and taking the recommended prescription as a current exercise prescription; the current athletic prescription includes a plurality of environmental parameters and a plurality of athletic metrics.
Next, a first round of testing was performed:
step 1: the current test environment is adjusted according to a plurality of environmental parameters of the current exercise prescription.
Step 2: allowing the tester to run according to the current exercise prescription; and after the time period T, acquiring physical function parameters of the tester in the running process in real time, and acquiring real-time physical load indexes according to the physical function parameters and the physical load quantification model.
Step 3: comparing the real-time body load index with the load threshold. The comparison result includes the following two cases:
in the first case, the real-time body load index > load threshold, which means that the current exercise prescription (recommended prescription) is overloaded, so that the tester cannot adapt to the current exercise prescription, and the current exercise prescription needs to be adjusted. In the second case, the real-time body load index is less than or equal to the load threshold, which indicates that the current exercise prescription (recommended prescription) is insufficiently loaded, and the current exercise prescription needs to be adjusted for the purpose of body building.
This round of testing is described for the first case.
In the first case, when the load of the current exercise prescription (recommended prescription) is excessive, it is necessary to appropriately reduce the load of the current exercise prescription by performing step 4.
Step 4: running is stopped. First, it is checked whether the current test environment is the same as the current atmospheric environment (this round of test is described by taking the case that the current test environment is different from the current atmospheric environment). If the current test environment is different from the current atmosphere environment, the current test environment is adjustable, the exercise load is reduced by adjusting one environment parameter of the current exercise prescription, the current exercise prescription is updated at the same time, and the test returns to the step 1 to enter a second round of test after waiting for the body recovery of the tester.
Second theory test:
step 1: the current test environment is adjusted according to a plurality of environmental parameters of the current exercise prescription.
Step 2: allowing the tester to run according to the current exercise prescription; and after the time period T, acquiring physical function parameters of the tester in the running process in real time, and acquiring real-time physical load indexes according to the physical function parameters and the physical load quantification model.
Step 3: comparing the real-time body load index with the load threshold. Both of the above cases are also included. The present test is still described for the first case described above.
In the second test, if the real-time body load index > load threshold still appears, which indicates that the current exercise prescription after the first adjustment is not suitable for the testers, the current exercise prescription of the second test needs to be adjusted in the manner of the step 4.
The present test is described taking the example that the current test environment is the same as the current atmospheric environment after the first round of adjustment.
Step 4: stopping running, and checking whether the current test environment is the same as the current atmospheric environment. If the current test environment is the same as the current atmospheric environment, reducing the exercise load by adjusting one exercise index of the current exercise prescription, updating the current exercise prescription, waiting for the body recovery of the tester, returning to the step 2, and entering a third-round test.
Third round of test:
step 2: allowing the tester to run according to the current exercise prescription; and after the time period T, acquiring physical function parameters of the tester in the running process in real time, and acquiring real-time physical load indexes according to the physical function parameters and the physical load quantification model. (since the current test environment is the same as the current atmospheric environment, no adjustment is required to the current test environment.)
Step 3: comparing the real-time body load index with the load threshold. Both of the above cases are also included. The test is illustrated by taking the example that the real-time body load index is less than or equal to the load threshold value after the adjustment of the previous two tests.
In the third test, if the real-time body load index is less than or equal to the load threshold value, the current exercise prescription adjusted by the second test is indicated to be applicable to the testers, and the step 5 is executed.
Step 5: it is determined whether the current sports prescription is a recommended prescription. The current sports prescription is not already the recommended prescription due to the adjustment of the two rounds of testing, in which case step 7 is performed instead.
It should be noted that, after the determination in step 5, if the situation that the current exercise prescription is the recommended prescription belongs to the second situation mentioned in the first round of test, that is, during the first round of test, the real-time body load index is compared with the load threshold value in step 3, when the real-time body load index is less than or equal to the load threshold value, it is indicated that the load of the current exercise prescription (recommended prescription) is insufficient, and in order to achieve the purpose of body building, the current exercise prescription needs to be adjusted, so as to increase the exercise load, then step 6 is executed instead.
Step 7: allowing the tester to run according to the current exercise prescription, collecting physical function parameters of the tester in real time in the running process, and obtaining real-time physical load indexes according to the physical function parameters and the physical load quantification model. Comparing the real-time body load index with the load threshold; if the real-time body load index is larger than the load threshold before the test is finished, the current exercise prescription is still not suitable for the testers after the previous two rounds of test, namely, larger exercise load is still generated for the testers, and the exercise load of the current exercise prescription needs to be reduced. Thus, returning to S6 (explanation of specific principles with reference to example 1); if the real-time body load index is maintained at or below the load threshold until the end of the test, the current exercise prescription is output as the final running exercise prescription after the end of the test (for a specific principle, refer to the explanation of example 1).
Next, a second case of the first round of testing will be described.
In the second case, when the current exercise prescription (recommended prescription) is insufficiently loaded, it is necessary to increase the load of the current prescription, and first, step 5 is performed instead.
Step 5: it is determined whether the current sports prescription is a recommended prescription. Since the current test is the first round of test, the current prescription is the recommended prescription, in this case, the step 6 is executed instead, and the load of the current prescription is increased by executing the step 6.
Step 6: and (3) increasing exercise load by adjusting one exercise parameter of the current exercise prescription, updating the current exercise prescription, returning to the step (2), and entering a second round of test.
It should be noted that, by increasing the exercise load in step 6, the following two cases may occur:
first case: in the first round of test, after the exercise load is increased in the step 6, the real-time body load index > the load threshold value appears due to the excessive increased load; in the second case, in the first round of testing, after the exercise load is increased in the step 6, the real-time body load index is still less than or equal to the load threshold.
A second test (this test is described by taking the example that the real-time body load index > load threshold value after the exercise load is increased in the step 6):
Step 2: allowing the tester to run according to the current exercise prescription; and after the time period T, acquiring physical function parameters of the tester in the running process in real time, and acquiring real-time physical load indexes according to the physical function parameters and the physical load quantification model.
Step 3: comparing the real-time body load index with the load threshold. If the real-time body load index > the load threshold still appears, the added load is overlarge after the first round of adjustment, so that the current exercise prescription is not suitable for a tester. For this case, the current exercise recipe for the second round of testing needs to be adjusted in the manner of step 4 above.
Step 4: stopping running, adjusting the current exercise prescription, and entering a third round of test. The specific adjustment manner in step 4 refers to the first case, and is not described herein.
Third round of test (described by taking the example that the real-time body load index is less than or equal to the load threshold value after the adjustment of the second round of test):
step 2: allowing the tester to run according to the current exercise prescription; and after the time period T, acquiring physical function parameters of the tester in the running process in real time, and acquiring real-time physical load indexes according to the physical function parameters and the physical load quantification model. Since the current test environment is the same as the current atmospheric environment, no adjustment is required to the current test environment.
Step 3: comparing the real-time body load index with the load threshold. In the third test, if the real-time body load index is less than or equal to the load threshold value, the current exercise prescription adjusted by the second test is indicated to be applicable to the testers, and the step 5 is executed.
Step 5: it is determined whether the current sports prescription is a recommended prescription. The current sports prescription is not already the recommended prescription due to the adjustment of the two rounds of testing, in which case step 7 is performed instead.
Step 7: allowing a tester to run continuously according to the current exercise prescription, collecting body function parameters of the tester in real time in the running process, acquiring real-time body load indexes according to the body function parameters and the body load quantification model, and comparing the real-time body load indexes with the load threshold; if the real-time body load index is more than the load threshold before the test is finished, returning to S6; if the real-time body load index is kept to be smaller than or equal to the load threshold value before the test is finished, outputting the current exercise prescription as the final running exercise prescription after the test is finished.
It should be noted that, after the exercise load is increased in step 6, if the real-time body load index is still less than or equal to the load threshold, in the second round of testing, after step 2 and step 3 are performed, step 5 is performed instead. Since the current sports prescription is no longer a recommended prescription, step 7 is performed instead.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (7)
1. A method of generating a running exercise prescription, comprising the steps of:
s1: establishing a body load quantification model and setting a load threshold;
s2: generating a recommended prescription, and taking the recommended prescription as a current exercise prescription; the current exercise prescription comprises a plurality of environmental parameters and a plurality of exercise indexes;
s3: adjusting a current test environment according to a plurality of environment parameters of the current exercise prescription;
s4: allowing the tester to run according to the current exercise prescription; after the time period T, acquiring physical function parameters of a tester in the running process in real time, and acquiring real-time physical load indexes according to the physical function parameters and the physical load quantification model;
s5: comparing the real-time body load index with the load threshold; if the real-time body load index is greater than the load threshold, executing S6; otherwise, executing S7;
S6: stopping running, and checking whether the current test environment is the same as the current atmospheric environment; if the current exercise prescriptions are different, the exercise load is reduced by adjusting one environmental parameter of the current exercise prescriptions, the current exercise prescriptions are updated, and the test person returns to S3 after body recovery; otherwise, reducing exercise load by adjusting one exercise index of the current exercise prescription, updating the current exercise prescription, and returning to the step S4 after waiting for the body recovery of the tester;
s7: judging whether the current exercise prescription is a recommended prescription or not; if the prescription is recommended, executing S8; otherwise, executing S9;
s8: increasing exercise load by adjusting one exercise parameter of the current exercise prescription, updating the current exercise prescription, and returning to the step S4;
s9: allowing a tester to run continuously according to the current exercise prescription, collecting body function parameters of the tester in real time in the running process, acquiring real-time body load indexes according to the body function parameters and the body load quantification model, and comparing the real-time body load indexes with the load threshold; if the real-time body load index is more than the load threshold before the test is finished, returning to S6; if the real-time body load index is kept to be smaller than or equal to the load threshold value before the test is finished, outputting the current exercise prescription as the final running exercise prescription after the test is finished.
2. A method of generating a running exercise prescription as defined in claim 1,
the plurality of environmental parameters of the current athletic prescription include temperature, humidity, and air pressure;
the plurality of exercise indexes of the current exercise prescription comprise duration, speed, distance, step frequency, stride and gradient;
in S6, reducing the exercise load by adjusting an environmental parameter of the current exercise prescription includes: one of heating, cooling, humidifying, dehumidifying, pressurizing and depressurizing;
in the step S6, reducing the exercise load by adjusting an exercise index of the current exercise prescription includes: increasing one of duration, slowing down, shortening distance, decreasing step frequency, decreasing stride, and decreasing grade;
in S8, increasing the exercise load by adjusting an exercise parameter of the current exercise prescription includes: shortening the duration, increasing the speed, extending the distance, increasing the step frequency, expanding the stride, and increasing the grade.
3. A method of generating a running exercise prescription as defined in claim 2,
said adjusting an environmental parameter of the current athletic prescription includes the steps of: arranging the temperature, the humidity and the air pressure into a queue according to any sequence; when each time of adjustment is carried out, the environmental parameter at the head of the team is selected as an adjustment object to be adjusted; after the adjustment is completed, setting the environment parameters corresponding to the adjustment objects at the tail of the team;
The step of adjusting an exercise index of the current exercise prescription comprises the following steps: the duration, the speed, the distance, the step frequency, the stride and the gradient are arranged into a queue according to any sequence; when each time of adjustment is carried out, a motion index at the head of a team is selected as an adjustment object to be adjusted; and after the adjustment is finished, the motion index corresponding to the adjustment object is placed at the tail of the team.
4. A method of generating a running exercise prescription according to any one of claims 1-3, wherein said building a body load quantification model comprises the steps of:
summoning a plurality of volunteers for running test;
in the test, collecting a plurality of physical function parameters of each volunteer in real time to obtain a parameter sample;
carrying out feature extraction on the parameter samples by using time domain feature calculation, fourier transformation, heart rate variability analysis, empirical mode decomposition, hilbert analysis, complex network conversion and dynamic time warping method to obtain feature samples;
performing feature screening on the feature samples to obtain significant feature samples;
according to the significant feature samples, a first body load detection model based on logistic regression and a second body load detection model based on a support vector machine are respectively established;
And establishing a body load quantification model according to the first body load detection model and the second body load detection model.
5. A method of generating a running exercise prescription as defined in claim 4,
before the feature extraction of the sample data, the method comprises the following steps: dividing the parameter samples into a plurality of first-stage samples according to the ages of testers; dividing each primary sample into a plurality of secondary samples according to the body shape of a tester;
and carrying out noise reduction treatment and zero drift removal on each secondary sample.
6. A method of generating a running exercise prescription according to claim 1 or 5, wherein said generating a recommended prescription comprises the steps of:
obtaining basic information of a tester, wherein the basic information comprises age, height and weight;
searching the sports prescriptions matched with the basic information from a sports prescription recommendation library according to the basic information, and taking the searched sports prescriptions as recommendation prescriptions.
7. A method of generating a running exercise prescription as claimed in claim 4 wherein said body function parameters include respiratory rate minimum, cardiac rate upper quartile value, respiratory rate upper quartile value, electrocardiographic signal margin factor, cardiac rate average, respiratory rate average, R-R interval zero crossing number and cardiac rate lower quartile value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310048692.6A CN116030937B (en) | 2023-02-01 | 2023-02-01 | Method for generating running exercise prescription |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310048692.6A CN116030937B (en) | 2023-02-01 | 2023-02-01 | Method for generating running exercise prescription |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116030937A CN116030937A (en) | 2023-04-28 |
| CN116030937B true CN116030937B (en) | 2023-06-02 |
Family
ID=86073749
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310048692.6A Active CN116030937B (en) | 2023-02-01 | 2023-02-01 | Method for generating running exercise prescription |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116030937B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103400332A (en) * | 2013-08-14 | 2013-11-20 | 宁波天瑞医疗器械有限公司 | Health service platform system based on real-time monitoring |
| CN108364674A (en) * | 2018-02-22 | 2018-08-03 | 国家体育总局体育科学研究所 | A kind of intelligent body-building guidance method and system using exercise prescription |
| CN110010223A (en) * | 2019-01-23 | 2019-07-12 | 深圳市中银科技有限公司 | A kind of sport health data capture management prescription, based terminal system based on artificial intelligence |
| CN110322947A (en) * | 2019-06-14 | 2019-10-11 | 电子科技大学 | A kind of hypertension the elderly's exercise prescription recommended method based on deep learning |
| CN111883227A (en) * | 2020-04-24 | 2020-11-03 | 深圳市时代智汇科技有限公司 | Management method and system for executing exercise prescription |
| CN114822763A (en) * | 2022-04-29 | 2022-07-29 | 浙江工业大学 | Personalized exercise prescription recommendation method driven by exercise data |
-
2023
- 2023-02-01 CN CN202310048692.6A patent/CN116030937B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103400332A (en) * | 2013-08-14 | 2013-11-20 | 宁波天瑞医疗器械有限公司 | Health service platform system based on real-time monitoring |
| CN108364674A (en) * | 2018-02-22 | 2018-08-03 | 国家体育总局体育科学研究所 | A kind of intelligent body-building guidance method and system using exercise prescription |
| CN110010223A (en) * | 2019-01-23 | 2019-07-12 | 深圳市中银科技有限公司 | A kind of sport health data capture management prescription, based terminal system based on artificial intelligence |
| CN110322947A (en) * | 2019-06-14 | 2019-10-11 | 电子科技大学 | A kind of hypertension the elderly's exercise prescription recommended method based on deep learning |
| CN111883227A (en) * | 2020-04-24 | 2020-11-03 | 深圳市时代智汇科技有限公司 | Management method and system for executing exercise prescription |
| CN114822763A (en) * | 2022-04-29 | 2022-07-29 | 浙江工业大学 | Personalized exercise prescription recommendation method driven by exercise data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116030937A (en) | 2023-04-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wierzgała et al. | Most popular signal processing methods in motor-imagery BCI: a review and meta-analysis | |
| CN113080986B (en) | Method and system for detecting exercise fatigue based on wearable equipment | |
| CN109864714A (en) | A kind of ECG Signal Analysis method based on deep learning | |
| CN111248928A (en) | Pressure identification method and device | |
| CN110623678A (en) | Blood glucose measuring device, data processing method thereof and storage medium | |
| Hayet et al. | Sleep-wake stages classification based on heart rate variability | |
| CN113261981A (en) | Quantitative assessment method and system for upper limb spasm based on surface myoelectric signal | |
| CN107918487A (en) | A kind of method that Chinese emotion word is identified based on skin electrical signal | |
| Zhang et al. | A hybrid model for blood pressure prediction from a PPG signal based on MIV and GA-BP neural network | |
| CN115363586A (en) | Psychological stress grade assessment system and method based on pulse wave signals | |
| CN109934179B (en) | Human body action recognition method based on automatic feature selection and integrated learning algorithm | |
| CN116030937B (en) | Method for generating running exercise prescription | |
| CN113509183A (en) | Method for analyzing emotional anxiety, depression and tension based on AR artificial intelligence | |
| She et al. | Study on chaotic characteristics of heart sound based on correlation dimension and K entropy | |
| CN116211308A (en) | Method for evaluating body fatigue under high-strength exercise | |
| Yu | Research on athlete skipping surface electromyography and energy consumption based on principal component analysis of wavelet packet | |
| CN115399735A (en) | Multi-head attention mechanism sleep staging method based on time-frequency double-current enhancement | |
| CN111466877B (en) | LSTM network-based oxygen reduction state prediction method | |
| CN107767934A (en) | A kind of HRV characteristic range methods of estimation for being used to describe pressure | |
| CN109192315B (en) | Comprehensive age detection system based on weighted kernel regression and packaged deviation search | |
| Ide et al. | Workplace stress estimation method based on multivariate analysis of physiological indices | |
| Zhao et al. | Identification of psychological stress states based on joint analysis of multidomain features of skin conductance | |
| CN117257303B (en) | Anxiety detection method and device, electronic equipment and storage medium | |
| CN116189899B (en) | Emergency critical illness auxiliary evaluation system based on machine learning | |
| CN111150411B (en) | Psychological stress evaluation grading method based on improved genetic algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |