Teenager physical health intervention method and device and medium

Abstract

The invention discloses a teenager physical health intervention method and device and a medium, and belongs to the technical field of health management. A teenager physical health intervention model is constructed by adopting a machine learning algorithm, and the teenager physical health intervention model is trained by adopting historical data and physical type labels; according to the method, a trained teenager constitution classification model is obtained, then the trained teenager constitution classification model is adopted to identify the preprocessed basic body data and body measurement data to obtain a target constitution type label, and finally teenager constitution health intervention can be performed according to the target constitution type label. The requirement for professional knowledge can be effectively reduced, and the physique of teenagers is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of health management, and particularly relates to a method, device and medium for intervening in the physical health of teenagers. Background Art

[0002] With the development of society, the physical health problems of teenagers have become increasingly prominent. Health problems such as obesity, thinness, and poor physical fitness have seriously affected the healthy growth of teenagers. At present, the intervention methods for teenagers' physical health are relatively single, mainly relying on professional doctors to give advice for intervention, and precise advice requires extremely strong professional knowledge. However, generally high school students and college students stay inside the school for a long time, and it is difficult for teaching staff to give them precise advice, lacking systematicness and pertinence. Therefore, it is necessary to study a comprehensive and effective method for intervening in teenagers' physical health. Summary of the Invention

[0003] The present invention provides a method, device and medium for intervening in teenagers' physical health to solve the problems existing in the prior art.

[0004] In the first aspect, the present invention provides a method for intervening in teenagers' physical health, including: Obtaining the basic physical data and physical fitness test data corresponding to the teenagers to be intervened, and preprocessing the basic physical data and physical fitness test data to obtain the preprocessed basic physical data and physical fitness test data; Constructing a teenagers' physical fitness classification model by using a machine learning algorithm, and training the teenagers' physical fitness classification model by using historical data and physical fitness type labels to obtain the trained teenagers' physical fitness classification model; Identifying the preprocessed basic physical data and physical fitness test data by using the trained teenagers' physical fitness classification model to obtain the target physical fitness type label corresponding to the teenagers to be intervened; Based on the target physical fitness type label corresponding to the teenagers to be intervened, determining the physical health intervention plan corresponding to the target physical fitness type label in the physical health intervention plan library by using a look-up table method; Outputting the physical health intervention plan corresponding to the target physical fitness type label to the device designated by the staff to intervene in the physical health of teenagers according to the physical health intervention plan.

[0005] Further, obtaining the basic physical data and physical fitness test data corresponding to the teenagers to be intervened includes: Obtaining the age, gender, height, weight and three circumferences corresponding to the teenagers to be intervened to obtain the basic physical data corresponding to the teenagers to be intervened; Obtaining the long-distance running data, sprint data, vital capacity data, long jump data and pull-up data corresponding to the teenagers to be intervened to obtain the physical fitness test data corresponding to the teenagers to be intervened.

[0006] Further, preprocess the basic body data and physical fitness test data to obtain the preprocessed basic body data and physical fitness test data, including: normalizing the basic body data and physical fitness test data to obtain the preprocessed basic body data and physical fitness test data.

[0007] Further, train the adolescent physical fitness classification model using historical data and physical fitness type labels to obtain the trained adolescent physical fitness classification model, including: Obtain the pre-stored historical data and physical fitness type labels, and normalize the historical data to obtain the normalized historical data and the physical fitness type labels corresponding to the historical data; Initialize the hyperparameters of the adolescent physical fitness classification model to initialize the population to be trained; For each individual in the population to be trained, use the normalized historical data as the input and the physical fitness type labels corresponding to the historical data as the expected output to obtain the error function value corresponding to the individual; Determine the optimal individual in the population to be trained according to the error function values corresponding to all individuals; Adopt a random matching sine exploration strategy to perform diversity-preserving exploration on the individuals in the population to be trained to obtain the individuals after diversity-preserving exploration; Obtain the adaptive exploration parameter, according to the adaptive exploration parameter and the optimal individual, and adopt an optimal direction-guided exploration strategy to perform fast exploration on the individuals after diversity-preserving exploration to obtain the individuals after fast exploration; Obtain the adaptive inertia weight, according to the adaptive inertia weight, and adopt a spiral curve exploration strategy to perform high-precision exploration on the individuals after fast exploration to obtain the individuals after high-precision exploration; Obtain the local optimal detection factor. When the local optimal detection factor satisfies the training stagnation condition, then adopt a global random exploration strategy to perform global exploration on the individuals to obtain the individuals after global exploration; Judge whether the current training times meet the preset training end condition. If so, according to the individuals after high-precision exploration, output the optimal individual as the final hyperparameters of the adolescent physical fitness classification model to obtain the trained adolescent physical fitness classification model. Otherwise, based on the individuals after global exploration, return to the step of obtaining the error function value corresponding to the individual.

[0008] Further, adopt a random matching sine exploration strategy to perform diversity-preserving exploration on the individuals in the population to be trained to obtain the individuals after diversity-preserving exploration, including: For any individual in the population to be trained, randomly match an individual for the individual to obtain the random individual corresponding to the individual; Explore the diversity preservation of individuals in the population to be trained according to the corresponding random individuals of each individual, and obtain the individuals after the diversity preservation exploration; the individuals after the diversity preservation exploration are:

[0009] Among them, represents the t th individual in the m th training process, m = 1, 2, …, L, where L represents the total number of individuals in the population to be trained, represents the individual after the diversity preservation exploration, represents the corresponding random individual, represents the first random number between (0, 1), represents the second random number between (0, 1), and sin represents the sine function.

[0010] Furthermore, obtain the adaptive exploration parameter, and according to the adaptive exploration parameter and the optimal individual, adopt the optimal direction-guided exploration strategy to quickly explore the individuals after the diversity preservation exploration, and obtain the individuals after the quick exploration, including: Obtain the adaptive exploration parameter; the adaptive exploration parameter is:

[0011] Among them, C represents the adaptive exploration parameter, T represents the preset maximum number of training times, and t represents the current training times; According to the adaptive exploration parameter and the optimal individual, quickly explore the individuals after the diversity preservation exploration, and obtain the individuals after the quick exploration; the individuals after the quick exploration are:

[0012] Among them, represents the t th individual after the diversity preservation exploration in the n th training process, n = 1, 2, …, L, where L represents the total number of individuals in the population to be trained, represents the individual after the quick exploration, represents the third random number between (0, 1), represents the fourth random number between (0, 1), represents the pi, represents the optimal individual, and cos represents the cosine function.

[0013] Further, an adaptive inertia weight is obtained. According to the adaptive inertia weight, a spiral curve exploration strategy is adopted to perform high-precision exploration on the individuals after rapid exploration, and the individuals after high-precision exploration are obtained, including: Obtain the adaptive inertia weight; the adaptive inertia weight is:

[0014]

[0015] wherein, represents the adaptive inertia weight, represents the natural constant, U represents the spiral shape parameter, I represents a random parameter subject to a normal distribution, represents the fifth random number between (0, 1), T represents the preset maximum number of training times, represents the hyperbolic arctangent function; According to the adaptive inertia weight, high-precision exploration is performed on the individuals after rapid exploration, and the individuals after high-precision exploration are obtained; the individuals after high-precision exploration are:

[0016] wherein, represents the optimal individual, represents the t th individual after rapid exploration in the k rd training process, represents the individual after high-precision exploration, represents pi, represents the sixth random number between (0, 1), represents the seventh random number between (0, 1), and cos represents the cosine function.

[0017] Further, a local optimal detection factor is obtained. When the local optimal detection factor satisfies the training stagnation condition, a global random exploration strategy is adopted to perform global exploration on the individuals, and the individuals after global exploration are obtained, including: Obtain the local optimal detection factor; the local optimal detection factor is:

[0018] wherein, represents the local optimal detection factor, e represents the natural constant, and S represents the number of consecutive training times when the error function value corresponding to the optimal individual stagnates and decreases; Randomly generate a decision factor between (0, 1) and determine whether the decision factor is greater than the local optimal detection factor. If so, it is determined that the training stagnation condition is satisfied; otherwise, it is determined that the training stagnation condition is not satisfied; When the local optimal detection factor satisfies the training stagnation condition, global exploration is performed on the individual to obtain the individual after global exploration; the individual after global exploration is:

[0019]

[0020] Among them, represents the individual to be globally searched, represents the individual after global exploration, represents the eighth random number between (0, 1), represents a random individual different from the individual , represents the natural constant, t represents the current training times, T represents the maximum training times, cos represents the cosine function, represents the ninth random number between (0, 1), represents the tenth random number between (0, 1), represents the upper bound of the individual, represents the lower bound of the individual, B represents the boundary influence factor, represents the pi, represents the eleventh random number between (0, 1), sin represents the sine function.

[0021] In a second aspect, the present invention provides a device for intervening in the physical health of teenagers, including a processor and a memory; The memory stores computer execution instructions; The processor executes the computer execution instructions stored in the memory, so that the processor executes the method for intervening in the physical health of teenagers as described in the first aspect.

[0022] In a third aspect, the present invention provides a computer-readable storage medium, in which computer execution instructions are stored, and when the computer execution instructions are executed by a processor, they are used to implement the method for intervening in the physical health of teenagers as described in the first aspect.

[0023] A method, device and medium for intervening in the physical health of teenagers provided by the present invention, by using a machine learning algorithm to construct a physical fitness classification model for teenagers, and using historical data and physical fitness type labels to train the physical fitness classification model for teenagers to obtain the trained physical fitness classification model for teenagers, and then using the trained physical fitness classification model for teenagers to identify the preprocessed basic physical data and physical fitness test data to obtain the target physical fitness type label, and finally, physical health intervention for teenagers can be carried out according to the target physical fitness type label, which can effectively reduce the demand for professional knowledge and improve the physical fitness of teenagers. Description of the Drawings

[0024] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing embodiments in accordance with the present invention, and are used together with the specification to explain the principles of the present invention.

[0025] Figure 1 It is a flowchart of a method for intervening in the physical health of teenagers provided by an embodiment of the present invention.

[0026] Figure 2 It is a flowchart of training a physical fitness classification model for teenagers by using historical data and physical fitness type labels provided by an embodiment of the present invention.

[0027] Figure 3 It is a schematic structural diagram of a device for intervening in the physical health of teenagers provided by an embodiment of the present invention.

[0028] Among them, 31 - processor, 32 - memory, 33 - bus.

[0029] Through the above - mentioned accompanying drawings, specific embodiments of the present invention have been shown, and there will be more detailed descriptions hereinafter. These drawings and textual descriptions are not intended to limit the scope of the inventive concept in any way, but to illustrate the concept of the present invention to those skilled in the art by referring to specific embodiments. Detailed Description of Specific Embodiments

[0030] Here, exemplary embodiments will be described in detail, and the examples are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0031] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0032] As Figure 1 shown, an embodiment of the present invention provides a method for intervening in the physical health of teenagers, including: S11. Obtain the basic physical data and physical fitness test data corresponding to the teenagers to be intervened, and pre - process the basic physical data and physical fitness test data to obtain the pre - processed basic physical data and physical fitness test data; In an embodiment of the present invention, obtaining the basic physical data and physical fitness test data corresponding to the teenagers to be intervened includes: Obtain the age, gender, height, weight and three - dimensional measurements corresponding to the teenagers to be intervened to obtain the basic physical data corresponding to the teenagers to be intervened; Obtain the long-distance running data, sprint data, vital capacity data, long jump data, and chin-up data corresponding to the adolescents to be intervened, and obtain the physical fitness test data corresponding to the adolescents to be intervened.

[0033] In the embodiments of the present invention, preprocess the basic physical data and the physical fitness test data to obtain the preprocessed basic physical data and physical fitness test data, including: performing normalization processing on the basic physical data and the physical fitness test data to obtain the preprocessed basic physical data and physical fitness test data.

[0034] However, it is worth noting that in addition to the above basic physical data and physical fitness test data, other data can also be used as basic data to make the intervention of adolescents' physical health more accurate.

[0035] S12. Construct an adolescent physical fitness classification model using a machine learning algorithm, and train the adolescent physical fitness classification model using historical data and physical fitness type labels to obtain the trained adolescent physical fitness classification model; Constructing an adolescent physical fitness classification model using a machine learning algorithm may include: constructing an adolescent physical fitness classification model using a convolutional neural network or a BP neural network.

[0036] Optionally, an adolescent physical fitness classification model can be constructed for exercise, or an adolescent physical fitness classification model can be constructed for diet, or two adolescent physical fitness classification models can be constructed simultaneously to take both exercise and diet into account. For example, when it is necessary to intervene in the exercise of adolescents, the physical fitness type labels can be related to physical fitness or physique, and each physical fitness type label is associated with a personalized exercise plan; when it is necessary to intervene in the diet of adolescents, the physical fitness type labels can be related to body shape (such as overweight, obese, underweight, etc.), and each physical fitness type label is associated with a personalized privacy plan. However, it is worth noting that in addition to intervening in these two aspects, other aspects can also be intervened.

[0037] To help those skilled in the art better understand the technical solutions described in the embodiments of the present invention, some examples are given below: The personalized exercise plan may include: formulating a targeted exercise plan according to the physical characteristics of adolescents, including aerobic exercise, strength training, flexibility training, etc., to improve the cardiopulmonary function, muscle strength, and flexibility of adolescents.

[0038] Diet adjustment may include: formulating a reasonable dietary plan according to the eating habits of adolescents, ensuring a balanced diet, reducing the intake of high-calorie, high-fat, and high-sugar foods, and increasing the proportion of foods such as vegetables, fruits, and whole grains.

[0039] It should be noted that these adjustments are only for illustrative purposes, and other aspects such as psychology and daily routine can also be intervened to comprehensively improve the physical fitness of teenagers.

[0040] S13. Use the trained physical fitness classification model for teenagers to identify the basic physical data and physical fitness test data after preprocessing, and obtain the target physical fitness type label corresponding to the teenagers to be intervened; The basic physical data and physical fitness test data after preprocessing can be constructed as the input data of the physical fitness classification model for teenagers. After training, the physical fitness classification model for teenagers has the ability to identify the physical fitness type label. Therefore, the trained physical fitness classification model for teenagers can be used for identification, and finally a physical fitness health intervention plan is generated.

[0041] S14. Based on the target physical fitness type label corresponding to the teenagers to be intervened, use the look-up table method to determine the physical fitness health intervention plan corresponding to the target physical fitness type label in the physical fitness health intervention plan library; The physical fitness health intervention plan library is essentially a suggestion given by professional doctors, that is, professional doctors pre-set a variety of physical fitness health intervention plans in advance, and then each physical fitness health intervention plan corresponds to a physical fitness type label. When historical data is obtained, professional doctors perform manual labeling on these historical data to determine the physical fitness type label corresponding to each historical data, thereby reducing the requirements for professional knowledge and improving the management efficiency of teenagers' physical fitness health.

[0042] It should be noted that the data content of historical data should also include basic physical data and physical fitness test data to ensure that after training the physical fitness classification model for teenagers, the physical fitness classification model for teenagers can accurately identify the data.

[0043] S15. Output the physical fitness health intervention plan corresponding to the target physical fitness type label to the device designated by the staff to intervene in the physical fitness health of teenagers according to the physical fitness health intervention plan.

[0044] The device designated by the staff can be the device of the teaching staff, the device of the student's parents, or the device of the students themselves, so as to achieve physical fitness health intervention.

[0045] A method for intervening in the physical health of teenagers provided by the present invention constructs a physical fitness classification model for teenagers by using a machine learning algorithm, and trains the physical fitness classification model for teenagers by using historical data and physical fitness type labels to obtain the trained physical fitness classification model for teenagers. Then, the trained physical fitness classification model for teenagers is used to identify the basic physical data and physical fitness test data after preprocessing to obtain the target physical fitness type label. Finally, physical health intervention for teenagers can be carried out according to the target physical fitness type label, which can effectively reduce the demand for professional knowledge and improve the physical fitness of teenagers.

[0046] As Figure 2 shown, training the physical fitness classification model for teenagers by using historical data and physical fitness type labels to obtain the trained physical fitness classification model for teenagers includes: S21. Obtain the pre-stored historical data and physical fitness type labels, and perform normalization processing on the historical data to obtain the normalized historical data and the physical fitness type labels corresponding to the historical data; S22. Initialize the hyperparameters of the physical fitness classification model for teenagers to initialize the population to be trained; The hyperparameters of the physical fitness classification model for teenagers usually have an upper limit and a lower limit, and can be randomly initialized within this upper limit and lower limit, so as to obtain an individual. Multiple different individuals can be obtained to form the population to be trained.

[0047] Optionally, a chaos mapping strategy or a good point set strategy can also be used to initialize the population to be trained, so that the individuals at the initial moment are more evenly distributed in the solution space, thereby effectively improving the training speed of the algorithm.

[0048] S23. For each individual in the population to be trained, use the normalized historical data as the input and the physical fitness type labels corresponding to the historical data as the expected output to obtain the error function value corresponding to the individual; Optionally, the error function value corresponding to the individual can be obtained through error functions such as the cross-entropy loss function and the root mean square loss function.

[0049] S24. Determine the optimal individual in the population to be trained according to the error function values corresponding to all individuals; that is, determine the individual with the smallest error function value as the optimal individual.

[0050] S25. Use the random matching sine exploration strategy to perform diversity-preserving exploration on the individuals in the population to be trained to obtain the individuals after diversity-preserving exploration; S26. Obtain the adaptive exploration parameter, and according to the adaptive exploration parameter and the optimal individual, use the optimal direction-guided exploration strategy to perform rapid exploration on the individuals after diversity-preserving exploration to obtain the individuals after rapid exploration; S27. Obtain an adaptive inertia weight. According to the adaptive inertia weight, and adopt a spiral curve exploration strategy to perform high-precision exploration on the individuals after rapid exploration, so as to obtain the individuals after high-precision exploration; S28. Obtain a local optimal detection factor. When the local optimal detection factor satisfies the training stagnation condition, then adopt a global random exploration strategy to perform global exploration on the individuals, so as to obtain the individuals after global exploration; S29. Determine whether the current training times satisfy the preset training end condition. If so, then according to the individuals after high-precision exploration, output the optimal individuals as the final hyperparameters of the adolescent physical fitness classification model, so as to obtain the adolescent physical fitness classification model after training. Otherwise, based on the individuals after global exploration, return to the step of obtaining the error function value corresponding to the individuals.

[0051] In the embodiment of the present invention, a random matching sine exploration strategy is adopted to perform diversity maintenance exploration on the individuals in the population to be trained, so as to obtain the individuals after diversity maintenance exploration, including: For any individual in the population to be trained, randomly match an individual to the individual to obtain the random individual corresponding to the individual; According to the random individual corresponding to the individual, perform diversity maintenance exploration on the individuals in the population to be trained, so as to obtain the individuals after diversity maintenance exploration; the individuals after diversity maintenance exploration are:

[0052] Among them, represents the t th individual in the m th training process, m = 1, 2, …, L, where L represents the total number of individuals in the population to be trained, represents the individual after diversity maintenance exploration, represents the individual corresponding random individual, represents the first random number between (0, 1), represents the second random number between (0, 1), and sin represents the sine function.

[0053] The present invention enables the individual to randomly move towards another individual through the random matching sine exploration strategy, and move in a sine waveform during the moving process, which can not only realize the exploration of the unfamiliar area between two individuals, but also increase the possibility of exploring the global optimal solution.

[0054] In the embodiment of the present invention, obtain an adaptive exploration parameter. According to the adaptive exploration parameter and the optimal individual, and adopt an optimal direction guiding exploration strategy to perform rapid exploration on the individuals after diversity maintenance exploration, so as to obtain the individuals after rapid exploration, including: Obtain the adaptive exploration parameter; the adaptive exploration parameter is:

[0055] where C represents the adaptive exploration parameter, T represents the preset maximum number of training times, and t represents the current number of training times; According to the adaptive exploration parameter and the optimal individual, perform a fast exploration on the individuals after the diversity-maintaining exploration to obtain the individuals after the fast exploration; the individuals after the fast exploration are:

[0056] where represents the t th individual after the diversity-maintaining exploration in the n th training process, n i = 1, 2, …, L, where L represents the total number of individuals in the population to be trained, represents the individual after the fast exploration, represents the third random number between (0, 1), represents the fourth random number between (0, 1), represents pi, represents the optimal individual, and cos represents the cosine function.

[0057] The present invention enables the individual to move towards the position of the currently known optimal individual through the optimal direction-guided exploration strategy, and adaptively adjusts the moving distance during the moving process, can search in the waveform of the cosine function, can greatly improve the exploration speed of the algorithm, and at the same time can increase the possibility of exploring the global optimal solution. As the algorithm progresses, the moving distance gradually decreases, which can effectively improve the exploration accuracy of the algorithm.

[0058] In an embodiment of the present invention, obtain the adaptive inertia weight, and according to the adaptive inertia weight, adopt the spiral curve exploration strategy to perform high-precision exploration on the individuals after the fast exploration to obtain the individuals after the high-precision exploration, including: Obtain the adaptive inertia weight; the adaptive inertia weight is:

[0059]

[0060] where represents the adaptive inertia weight, represents the natural constant, U represents the spiral shape parameter, I represents a random parameter subject to a normal distribution, represents the fifth random number between (0, 1), T represents the preset maximum number of training times, represents the hyperbolic arctangent function; According to the adaptive inertia weight, high-precision exploration is performed on the individuals after rapid exploration to obtain individuals after high-precision exploration; the individuals after high-precision exploration are:

[0061] in, represents the optimal individual, Indicates t During the training process k After a quick exploration, represents the individual after high-precision exploration, represents pi, represents the sixth random number between (0,1), represents the seventh random number between (0,1), and cos represents the cosine function.

[0062] The present invention performs spiral search on individuals through a spiral curve exploration strategy, so that the search trajectories of all individuals in the solution space are spiral, and adaptively adjusts the inertia weight, which can increase the influence of the optimal position in the later stage of the algorithm, thereby realizing the exploration of the optimal position and improving the training accuracy of the algorithm.

[0063] In the embodiment of the present invention, a local optimal detection factor is obtained. When the local optimal detection factor satisfies the training stagnation condition, a global random exploration strategy is used to perform global exploration on the individual to obtain the individual after global exploration, including: Get the local optimal detection factor; the local optimal detection factor is:

[0064] in, represents the local optimal detection factor, e represents the natural constant, and S represents the number of training times during which the error function value corresponding to the optimal individual continuously stagnates and decreases; A decision factor between (0,1) is randomly generated, and it is determined whether the decision factor is greater than the local optimal detection factor. If so, it is determined that the training stagnation condition is met, otherwise it is determined that the training stagnation condition is not met; When the local optimal detection factor meets the training stagnation condition, the individual is globally explored to obtain the individual after global exploration; the individual after global exploration is:

[0065]

[0066] in, represents the individual to be searched globally, represents the individual after global exploration, represents the eighth random number between (0,1), Represents an individual Different random individuals, Represents the natural constant, t represents the current training times, T represents the maximum training times, cos represents the cosine function, Represents the ninth random number between (0, 1), Represents the tenth random number between (0, 1), Represents the upper bound of the individual, that is, the individual composed of the upper limits of the hyperparameters of each dimension; Represents the lower bound of the individual, that is, the individual composed of the lower limits of the hyperparameters of each dimension; B Represents the boundary influence factor, Represents pi, Represents the eleventh random number between (0, 1), sin represents the sine function.

[0067] The present invention provides a global random exploration strategy, which has strong randomness and takes into account the influence of the boundary, can effectively make the individual escape from the local optimum, and improve the global search ability of the algorithm.

[0068] The training algorithm provided by the embodiments of the present invention can effectively improve the exploration accuracy and exploration effect of the algorithm, assist the algorithm to achieve true global search, ultimately improve the data classification accuracy, and make the intervention of adolescent physical health more accurate.

[0069] Optionally, after each exploration, the individuals after exploration are processed for out-of-bounds, so that the hyperparameters are always valid. After training to a certain extent (such as when t is greater than 2 / 3), after global exploration, greedy processing can also be performed on the obtained results to ensure the search efficiency of the algorithm, and the simulated annealing algorithm can also be used to control the global exploration.

[0070] Such as Figure 3 As shown, the embodiments of the present invention provide a device for intervening in adolescent physical health, including a processor 31 and a memory 32, and the processor 31 and the memory 32 are connected through a bus 33; The memory 32 stores computer execution instructions; The processor 31 executes the computer execution instructions stored in the memory 32, so that the processor 31 executes the above-mentioned method for intervening in adolescent physical health.

[0071] The embodiments of the present invention provide a computer-readable storage medium, in which computer execution instructions are stored, and when the computer execution instructions are executed by a processor, they are used to implement the above-mentioned method for intervening in adolescent physical health.

[0072] All or part of the steps of the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a readable memory. When the program is executed, it executes the steps including the above method embodiments; and the foregoing memory (storage medium) includes: read-only memory (abbreviation: ROM), RAM, flash memory, hard disk, solid state drive, magnetic tape, floppy disk, optical disc, and any combination thereof.

[0073] Embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processing unit of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processing unit of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0074] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0075] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0076] Other embodiments of the present invention will be readily apparent to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the invention following the general principles of the invention and including known or customary techniques in the art not disclosed herein. The specification and examples are only to be considered as exemplary, and the true scope and spirit of the invention are pointed out by the claims.

[0077] It should be understood that the present invention is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

Claims

1. A method for intervening in the physical health of teenagers, characterized in that, Including: Obtain the basic physical data and physical fitness test data corresponding to the teenagers to be intervened, and preprocess the basic physical data and physical fitness test data to obtain the preprocessed basic physical data and physical fitness test data; Construct a teenagers' physical fitness classification model using machine learning algorithms, and train the teenagers' physical fitness classification model with historical data and physical fitness type labels to obtain the trained teenagers' physical fitness classification model; Use the trained teenagers' physical fitness classification model to identify the preprocessed basic physical data and physical fitness test data to obtain the target physical fitness type label corresponding to the teenagers to be intervened; Based on the target physical fitness type label corresponding to the teenagers to be intervened, use the look-up table method to determine the physical fitness health intervention plan corresponding to the target physical fitness type label in the physical fitness health intervention plan library; Output the physical fitness health intervention plan corresponding to the target physical fitness type label to the device designated by the staff to intervene in the physical fitness health of teenagers according to the physical fitness health intervention plan.

2. The adolescent physical health intervention method according to claim 1, wherein Obtain the basic physical data and physical fitness test data corresponding to the teenagers to be intervened, including: Obtain the age, gender, height, weight and three circumferences corresponding to the teenagers to be intervened to obtain the basic physical data corresponding to the teenagers to be intervened; Obtain the long-distance running data, sprint data, vital capacity data, long jump data and chin-up data corresponding to the teenagers to be intervened to obtain the physical fitness test data corresponding to the teenagers to be intervened.

3. The adolescent physical health intervention method according to claim 1, wherein Preprocess the basic physical data and physical fitness test data to obtain the preprocessed basic physical data and physical fitness test data, including: perform normalization processing on the basic physical data and physical fitness test data to obtain the preprocessed basic physical data and physical fitness test data.

4. The adolescent physical health intervention method according to claim 1, wherein Train the teenagers' physical fitness classification model with historical data and physical fitness type labels to obtain the trained teenagers' physical fitness classification model, including: Obtain the pre-stored historical data and physical fitness type labels, and perform normalization processing on the historical data to obtain the normalized historical data and the physical fitness type labels corresponding to the historical data; Initialize the hyperparameters of the teenagers' physical fitness classification model to initialize the population to be trained; For each individual in the population to be trained, use the normalized historical data as the input and the physical fitness type label corresponding to the historical data as the expected output to obtain the error function value corresponding to the individual; Determine the optimal individual in the population to be trained according to the error function values corresponding to all individuals; Use the random matching sine exploration strategy to perform diversity-preserving exploration on the individuals in the population to be trained to obtain the individuals after diversity-preserving exploration; Obtain the adaptive exploration parameter, according to the adaptive exploration parameter and the optimal individual, and use the optimal direction-guided exploration strategy to perform rapid exploration on the individuals after diversity-preserving exploration to obtain the individuals after rapid exploration; Obtain the adaptive inertia weight, according to the adaptive inertia weight, and use the spiral curve exploration strategy to perform high-precision exploration on the individuals after rapid exploration to obtain the individuals after high-precision exploration; Obtain the local optimal detection factor. When the local optimal detection factor meets the training stagnation condition, a global random exploration strategy is used to globally explore the individual to obtain the individual after global exploration. Judge whether the current number of training times meets the preset training end condition. If so, based on the individual after high-precision exploration, the optimal individual is output as the final hyperparameter of the adolescent physical fitness classification model, and the trained adolescent physical fitness classification model is obtained. Otherwise, based on the individual after global exploration, return to the step of obtaining the error function value corresponding to the individual.

5. The adolescent physical health intervention method according to claim 4, wherein Use the random matching sine exploration strategy to perform diversity-preserving exploration on the individuals in the population to be trained, and obtain the individuals after diversity-preserving exploration, including: For any individual in the population to be trained, randomly match an individual to obtain the corresponding random individual of the individual. According to the random individual corresponding to the individual, perform diversity-preserving exploration on the individuals in the population to be trained to obtain the individuals after diversity-preserving exploration. The individuals after diversity-preserving exploration are: Among them, denotes the t th individual in the m th training process, m = 1, 2, …, L, where L represents the total number of individuals in the population to be trained, denotes the individual after diversity-preserving exploration, denotes the corresponding random individual, denotes the first random number between (0, 1), denotes the second random number between (0, 1), and sin denotes the sine function.

6. The adolescent physical health intervention method according to claim 5, wherein Obtain the adaptive exploration parameter. According to the adaptive exploration parameter and the optimal individual, and use the optimal direction-guided exploration strategy to quickly explore the individuals after diversity-preserving exploration to obtain the individuals after quick exploration, including: Obtain the adaptive exploration parameter. The adaptive exploration parameter is: Where C represents the adaptive exploration parameter, T represents the preset maximum number of training times, and t represents the current number of training times. According to the adaptive exploration parameter and the optimal individual, quickly explore the individuals after diversity-preserving exploration to obtain the individuals after quick exploration. The individuals after quick exploration are: Among them, represents the individual after the t -th diversity-maintaining exploration in the n -th training process, n = 1, 2, …, L, where L represents the total number of individuals in the population to be trained, represents the individual after rapid exploration, represents the third random number between (0, 1), represents the fourth random number between (0, 1), represents pi, represents the optimal individual, and cos represents the cosine function.

7. The adolescent physical health intervention method according to claim 6, characterized in that, Obtain the adaptive inertia weight. According to the adaptive inertia weight, and use the spiral curve exploration strategy to perform high-precision exploration on the individuals after quick exploration to obtain the individuals after high-precision exploration, including: Obtain the adaptive inertia weight. The adaptive inertia weight is: Among them, represents the adaptive inertia weight, represents the natural constant, U represents the spiral shape parameter, I represents the random parameter subject to the normal distribution, represents the fifth random number between (0, 1), T represents the preset maximum number of training times, represents the hyperbolic arctangent function; According to the adaptive inertia weight, perform high-precision exploration on the individuals after quick exploration to obtain the individuals after high-precision exploration. The individuals after high-precision exploration are: Among them, represents the optimal individual, represents the t th individual after the k th rapid exploration during the th training process, represents the individual after high-precision exploration, represents the sixth random number between (0, 1), represents the seventh random number between (0, 1), and cos represents the cosine function.

8. The adolescent physical health intervention method according to claim 7, characterized in that, Obtain the local optimal detection factor. When the local optimal detection factor meets the training stagnation condition, a global random exploration strategy is used to globally explore the individual to obtain the individual after global exploration, including: Obtain the local optimal detection factor. The local optimal detection factor is: Among them, represents the local optimal detection factor, e represents the natural constant, and S represents the number of consecutive training times when the error function value corresponding to the optimal individual stagnates and decreases; Randomly generate a decision factor between (0, 1), and judge whether the decision factor is greater than the local optimal detection factor. If so, it is determined that the training stagnation condition is met; otherwise, it is determined that the training stagnation condition is not met. When the local optimal detection factor meets the training stagnation condition, globally explore the individual to obtain the individual after global exploration. The individuals after global exploration are: Among them, represents the individual to be globally searched, represents the individual after global exploration, represents the eighth random number between (0, 1), represents the individual a different random individual, represents the natural constant, t represents the current training times, T represents the maximum training times, cos represents the cosine function, represents the ninth random number between (0, 1), represents the tenth random number between (0, 1), represents the upper bound of the individual, represents the lower bound of the individual, B represents the boundary influence factor, represents the pi, represents the eleventh random number between (0, 1), sin represents the sine function.

9. An intervention device for the physical health of teenagers, characterized in that, Include a processor and a memory. The memory stores computer execution instructions. The processor executes the computer execution instructions stored in the memory, so that the processor executes the adolescent physical fitness health intervention method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which are used to implement the adolescent physical health intervention method according to any one of claims 1 to 8 when the computer-executable instructions are executed by a processor.

Images