Motion frequency guiding method and device

Abstract

The invention relates to a motion frequency guiding method and device, and relates to the field of motion intelligent assistance, and the method comprises the steps: monitoring the motion progress, motion amplitude and environment parameters of a user, carrying out the physical ability increase and decline sample analysis in combination with the basic information of the user, and obtaining a corresponding influence coefficient; meanwhile, analyzing the motion amplitude data to obtain a motion amplitude influence growth rate, and processing environmental parameters by using an environmental influence evaluation model; and comprehensively processing the basic recommendation frequency and various influence factors through a motion frequency guide function, and dynamically generating and updating a motion frequency recommendation value displayed by a user side. The technical problem that in the prior art, individuation, real-time dynamic adjustment and environmental adaptability are lacked in the aspect of exercise frequency guidance is solved, the exercise frequency is dynamically adjusted and recommended according to the personal physical characteristics of the user, the real-time exercise data and the environmental factors, intelligent and individualized exercise frequency guidance is provided, and the user experience is improved. And the technical effect of sports experience is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of sports intelligence assistance, and in particular to a sports frequency guiding method and device. BACKGROUND

[0002] With the improvement of health awareness, more and more people begin to pay attention to physical exercise. In order to help users exercise more scientifically and effectively, various sports assistance devices and fitness equipment have appeared, such as smart bands, sports watches, treadmills, etc. However, the existing sports assistance devices and fitness equipment still have some deficiencies in sports frequency guidance. First, the sports frequency guidance provided by most devices is relatively single, and cannot be adjusted according to the personal physical characteristics of the user, lacking personalized guidance. Second, the existing devices can usually only set the sports frequency, such as the step frequency in running, and cannot dynamically adjust in real time according to the changes in the user's state during the movement. In addition, these sports assistance devices and fitness equipment also do not fully consider the influence of environmental factors during the movement, lacking environmental adaptability. The above problems lead to poor sports frequency guidance effect of the existing sports assistance devices and fitness equipment, which cannot provide the best sports experience and assistance effect for the user, affecting the sports effect. SUMMARY

[0003] The present application provides a sports frequency guiding method and device to solve the technical problems of lack of personalization, real-time dynamic adjustment and environmental adaptability in the prior art in sports frequency guidance.

[0004] The technical solution of the present application to solve the above technical problems is as follows:

[0005] In a first aspect, the present application provides a sports frequency guiding method, comprising: in response to a selected sports type of a user terminal, matching a basic recommended frequency and returning to a user terminal display interface for display, while monitoring a first movement progress, a first movement amplitude and a first environmental parameter; obtaining basic information of a logged user; performing physical ability increase sample analysis according to the basic information of the logged user to obtain a physical ability increase influence rate coefficient; performing physical ability decline sample analysis according to the basic information of the logged user to obtain a physical ability decline influence rate coefficient; performing movement amplitude sample analysis according to the basic information of the logged user and the first movement amplitude to obtain a movement amplitude influence growth rate; inputting the first environmental parameter into an environmental influence evaluation model for processing to obtain an environmental factor influence coefficient; processing the basic recommended frequency, the first movement progress, the first movement amplitude, the physical ability increase influence rate coefficient, the physical ability decline influence rate coefficient, the movement amplitude influence growth rate and the environmental factor influence coefficient through a sports frequency guiding function to obtain a first movement progress recommended frequency; and returning the first movement progress recommended frequency to the user terminal display interface to replace and display the basic recommended frequency.

[0006] In a second aspect, the application provides a motion frequency guiding device, comprising: a motion type matching module, configured to match a basic recommended frequency to a user terminal display interface for display in response to a motion type selected by the user terminal, while monitoring a first motion progress, a first motion amplitude and a first environment parameter; a user basic information module, configured to obtain login user basic information; a physical fitness increase analysis module, configured to perform physical fitness increase sample analysis according to the login user basic information to obtain a physical fitness increase influence rate coefficient; a physical fitness decline analysis module, configured to perform physical fitness decline sample analysis according to the login user basic information to obtain a physical fitness decline influence rate coefficient; a motion amplitude analysis module, configured to perform motion amplitude sample analysis according to the login user basic information and the first motion amplitude to obtain a motion amplitude influence growth rate; an environment assessment module, configured to input the first environment parameter into an environment influence assessment model for processing to obtain an environment factor influence coefficient; a frequency guiding module, configured to process the basic recommended frequency, the first motion progress, the first motion amplitude, the physical fitness increase influence rate coefficient, the physical fitness decline influence rate coefficient, the motion amplitude influence growth rate and the environment factor influence coefficient through a motion frequency guiding function to obtain a first motion progress recommended frequency; and a motion frequency display module, configured to return the first motion progress recommended frequency to the user terminal display interface to replace the basic recommended frequency for display.

[0007] In a third aspect, the application provides an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute a motion frequency guiding method provided by the application.

[0008] In a fourth aspect, the application provides a computer readable storage medium, storing a computer program, the computer program being configured to execute a motion frequency guiding method provided by the application.

[0009] The application has the following beneficial effects:

[0010] In response to the user-end selected exercise type, such as running, skipping, cycling or jumping, etc., the matched basic recommended frequency is returned to the user-end display interface for display, while monitoring the first exercise progress, the first exercise amplitude and the first environmental parameter, providing the initial recommended exercise frequency according to the user-selected exercise type, and obtaining the user's exercise data and environmental parameters in real time to provide a basis for subsequent personalized exercise frequency adjustment; obtaining the login user basic information to provide a basis for subsequent physical ability analysis; performing physical ability increase sample analysis according to the login user basic information to obtain the physical ability increase influence rate coefficient, estimating the user's physical ability improvement rate by analyzing the user's basic information and exercise data, so as to consider the influence of physical ability growth when adjusting the exercise frequency; performing physical ability decline sample analysis according to the login user basic information to obtain the physical ability decline influence rate coefficient, estimating the user's physical ability decline rate by analyzing the user data, so as to consider the influence of physical ability decline when adjusting the exercise frequency; performing exercise amplitude sample analysis according to the login user basic information and the first exercise amplitude to obtain the exercise amplitude influence growth rate, predicting the influence of exercise amplitude on the recommended exercise frequency by analyzing the user's exercise amplitude change, so that the exercise frequency adjustment is more accurate; inputting the first environmental parameter into the environmental influence evaluation model for processing to obtain the environmental factor influence coefficient, calculating the influence coefficient of the environment on the recommended exercise frequency by considering the influence of environmental factors in the exercise process, and improving the adaptability of the exercise frequency guidance; processing the basic recommended frequency, the first exercise progress, the first exercise amplitude, the physical ability increase influence rate coefficient, the physical ability decline influence rate coefficient, the exercise amplitude influence growth rate and the environmental factor influence coefficient through the exercise frequency guidance function to obtain the first exercise progress recommended frequency, dynamically calculating the optimal recommended exercise frequency through the exercise frequency guidance function by comprehensively considering various influencing factors, and realizing personalized and intelligent exercise frequency guidance; replacing the basic recommended frequency with the first exercise progress recommended frequency on the user-end display interface, and feeding back the calculated recommended exercise frequency to the user in real time to guide the user to adjust the exercise rhythm, realize intelligent and personalized exercise frequency guidance, and improve the exercise experience and effect. BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1 A flowchart of a motion frequency guidance method provided by the present application;

[0012] Figure 2 A structure diagram of a motion frequency guidance device provided by the present application;

[0013] Figure 3 A structure diagram of an electronic device provided by the present application;

[0014] Figure 4 A structure diagram of a computer readable storage medium provided by the present application;

[0015] Figure 5 A step frequency recommendation result data line chart for example 1.

[0016] Figure 6 A step frequency recommendation result data line chart for example 2.

[0017] In the drawings, components represented by various reference numerals are as follows:

[0018] The motion type matching module 11, the user basic information module 12, the physical ability increase analysis module 13, the physical ability decline analysis module 14, the motion amplitude analysis module 15, the environment evaluation module 16, the frequency guiding module 17, the motion frequency display module 18, the electronic device 200, the memory 210, the processor 220, the first computer program 211, the computer readable storage medium 300, and the second computer program 311. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0020] In the description of the present application, the terms "first", "second" are used only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "multiple" is two or more, unless otherwise specifically limited.

[0021] In the description of the present application, the term "for example" is used to indicate "as an example, illustration or explanation". Any embodiment described as "for example" in the present application is not necessarily interpreted as more preferred or more advantageous than other embodiments. The following description is given in order to enable any person skilled in the art to implement and use the present application. In the following description, details are listed for the purpose of explanation. It should be understood that those skilled in the art can realize the present application without using these specific details. In other examples, well-known structures and processes will not be described in detail to avoid unnecessary details making the description of the present application obscure. Therefore, the present application is not intended to be limited to the shown embodiments, but is consistent with the broadest scope of principles and features disclosed.

[0022] Embodiment one:

[0023] AsFigure 1 As shown, the embodiment of the present application provides a motion frequency guiding method, comprising:

[0024] S100: In response to the motion type selected by the user terminal, the matched basic recommended frequency is returned to the display interface of the user terminal for display, while monitoring the first motion progress, the first motion amplitude and the first environmental parameter.

[0025] Specifically, first, an interactive interface is provided on the user terminal for the user to select the motion type. The user selects a specific motion type, such as running, skipping, cycling or jumping, through the interface, and sends the selection result to the server. After the server receives the motion type selection information, it matches the corresponding basic recommended frequency from the pre-set motion type corresponding motion frequency database, and returns the basic recommended frequency to the display interface of the user terminal for real-time display. The basic recommended frequency is an initial motion frequency value set according to the motion type, which provides a benchmark for subsequent personalized adjustment.

[0026] At the same time, the first motion progress, the first motion amplitude and the first environmental parameter of the user during the motion are monitored in real time. Among them, in the motion type of running, the first motion progress can be the time progress, i.e. the proportion of the current motion time length to the total time length, or the distance progress, i.e. the proportion of the current motion distance to the total distance. Similarly, in other motion types, there are similar concepts. For example, in the motion type of skipping, the first motion progress can be the time progress, i.e. the proportion of the current motion time length to the total time length, or the skipping number progress, i.e. the proportion of the current skipping number to the planned skipping number. For example, in the motion type of cycling, the first motion progress can be the time progress, i.e. the proportion of the current motion time length to the total time length, or the cycling mileage progress, i.e. the proportion of the current cycling mileage to the total planned cycling mileage. For example, in the motion type of jumping, the first motion progress can be the time progress, i.e. the proportion of the current motion time length to the total time length, or the action completion progress, i.e. the proportion of the current completed action group number or times to the total planned action group number or times. More specifically, assuming that a set of exercises has 10 action groups, each action group is repeated 8 times, and 5 groups have been completed, then the action completion progress is 50%. Through this concept, the completion progress of the whole set of exercises in the jumping process can be determined. The first motion amplitude refers to the current motion amplitude of the user. The first motion progress and the first motion amplitude are collected and calculated through the built-in step counting module, counting module, GPS module or camera of the user terminal. The first environmental parameter is a series of environmental factor data including the current temperature, humidity, road type, etc., which is collected by the built-in environmental sensor of the user terminal or manually selected and input by the user.

[0027] Through the selection of the type of exercise and the initial display of the recommended frequency, and real-time acquisition of parameters such as exercise progress, exercise amplitude and environment affecting the subsequent dynamic adjustment of exercise frequency, basic data support is provided for intelligent and personalized exercise frequency guidance. On this basis, the recommended exercise frequency will be further optimized in combination with the personal physical characteristics of the user.

[0028] S200: Obtain the basic information of the logged-in user.

[0029] Specifically, the basic information of the currently logged-in user is obtained so as to subsequently make personalized adjustment of the exercise frequency recommendation according to the personal characteristics of the user.

[0030] The server is connected with the user management database, and when the user logs in the account at the user end, the server can call the basic information of the user from the user management database according to the user account. The basic information of the logged-in user is input when the user first registers the account and is stored in the user management database. If the user needs to update the basic information subsequently, the user can also update the basic information by modifying the personal account information.

[0031] After obtaining the basic information of the logged-in user, the basic information of the logged-in user is used as the personal characteristics data of the user in the subsequent link to analyze and calculate various coefficients affecting the exercise frequency recommendation result, so that the exercise frequency recommendation is more suitable for the physical condition of the current user and has good personalized exercise effect.

[0032] Through the acquisition of the basic information of the logged-in user, the data basis for realizing personalized exercise frequency recommendation is obtained, and necessary user attribute parameters are provided for subsequent physical ability analysis, exercise amplitude analysis and the like, which helps to improve the pertinence and practicality of the whole exercise frequency guidance.

[0033] S300: Perform physical ability increase sample analysis according to the basic information of the logged-in user to obtain a physical ability increase influence rate coefficient.

[0034] Specifically, after obtaining the basic information of the logged-in user, the server analyzes historical sample data according to the basic information of the logged-in user to obtain a physical ability increase influence rate coefficient matched with the physical characteristics of the current user. The physical ability increase influence rate coefficient reflects the physical ability improvement rate of the user and has a direct influence on the recommended exercise frequency value.

[0035] Firstly, the server takes the login user basic information as the search constraint condition, takes the body energy increase influence rate coefficient as the search target, and searches the sample data similar to the current user characteristics in the historical exercise database. The historical exercise database stores a large amount of exercise record data of different users, including user basic information, exercise parameters (such as running step length, rope length, cycling crank length or jumping action amplitude, etc.) and corresponding body energy increase influence rate coefficient, body energy decline influence rate coefficient and exercise amplitude influence growth rate. Through the search, a set of historical calibration values of the body energy increase influence rate coefficient similar to the current user condition is obtained. Next, the set of historical calibration values of the body energy increase influence rate coefficient obtained by the search is subjected to centralized trend analysis, and a fitting value of the body energy increase influence rate coefficient is obtained. For example, clustering analysis is performed through K-means, DBSCAN and other clustering analysis algorithms, the central value of the set of historical calibration values of the body energy increase influence rate coefficient is obtained by calculating the distance between different samples, and the central value is taken as the centralized trend value of the body energy increase influence rate coefficient of the category to which the current user belongs, so as to obtain the body energy increase influence rate coefficient.

[0036] Through sample search and centralized trend analysis, the body energy increase influence rate coefficient is dynamically adjusted according to the personal characteristics of the user, thereby providing a basis for realizing personalized exercise frequency recommendation.

[0037] S400: According to the login user basic information, the body energy decline sample analysis is performed to obtain the body energy decline influence rate coefficient.

[0038] Specifically, after obtaining the login user basic information, the server obtains the body energy decline influence rate coefficient matched with the body energy characteristics of the current user by analyzing the historical sample data according to the login user basic information. The body energy decline influence rate coefficient reflects the rate of body energy decline of the user in the exercise process, and has a direct influence on the recommended exercise frequency value.

[0039] Firstly, the server takes the login user basic information as the search constraint condition, takes the body energy decline influence rate coefficient as the search target, and searches the sample data similar to the current user characteristics in the historical exercise database. Through the search, a set of historical calibration values of the body energy decline influence rate coefficient similar to the current user condition is obtained. Next, the set of historical calibration values of the body energy decline influence rate coefficient obtained by the search is subjected to centralized trend analysis, and a fitting value of the body energy decline influence rate coefficient is obtained. For example, the mode of all body energy decline influence rate coefficients in the set of historical calibration values of the body energy decline influence rate coefficient is calculated to obtain the body energy decline influence rate coefficient fitting value, which is taken as the body energy decline influence rate coefficient of the current user.

[0040] Through sample retrieval and central tendency analysis, the influence rate coefficient of physical decline is dynamically adjusted according to the personal characteristics of the user, and combined with the influence rate coefficient of physical increase, the physical characteristics of the user can be more comprehensively and dynamically reflected, so that the exercise frequency recommendation is more scientific and accurate.

[0041] S500: Perform exercise amplitude sample analysis according to the login user basic information and the first exercise amplitude, and obtain an exercise amplitude influence growth rate.

[0042] Specifically, after obtaining the login user basic information, the server obtains the exercise amplitude influence growth rate matched with the exercise amplitude characteristics of the current user by analyzing historical sample data according to the login user basic information and the first exercise amplitude. The exercise amplitude influence growth rate reflects the influence degree of the exercise amplitude on the exercise frequency in the exercise process of the user, and has a direct influence on the recommended exercise frequency value.

[0043] Firstly, the server obtains two types of data, namely the obtained login user basic information and the first exercise amplitude of the user monitored in real time. Then, taking the two types of data as the retrieval constraint conditions and taking the exercise amplitude influence growth rate as the retrieval target, the sample data similar to the current user characteristics is retrieved in the historical exercise database. Through the retrieval, the exercise amplitude influence growth rate historical calibration value set highly matched with the exercise amplitude characteristics of the current user is obtained. After obtaining the exercise amplitude influence growth rate historical calibration value set, the trend value representing the exercise amplitude influence growth rate of the current user is further fitted. For example, the mean value of all exercise amplitude influence growth rates in the exercise amplitude influence growth rate historical calibration value set is obtained, and the fitted value of the exercise amplitude influence growth rate is obtained as the exercise amplitude influence growth rate of the current user.

[0044] Through sample retrieval and central tendency analysis, the influence rate coefficient of physical decline is dynamically adjusted according to the personal characteristics of the user, and combined with the influence rate coefficient of physical increase, the physical characteristics of the user can be more comprehensively and dynamically reflected, so that the exercise frequency recommendation is more scientific and accurate.

[0045] S600: Input the first environment parameter into an environment influence evaluation model for processing, and obtain an environment factor influence coefficient.

[0046] Specifically, first, the server obtains a large amount of environmental parameter record data and corresponding environmental impact coefficient calibration data from the environmental parameter database and the environmental impact coefficient database, and constructs a training data set of the environmental impact evaluation model. Among them, the environmental parameters include temperature, humidity, altitude and other dimensions, and the environmental impact coefficient is obtained by professional personnel according to the influence law of various environmental conditions on the movement frequency. Corresponding to each other, the input features and target outputs required for model training are formed. After obtaining the training data set, a support vector regression algorithm is used to construct the environmental impact evaluation model. The support vector regression algorithm is an application form of the support vector machine in regression problems, and the goal is to find an optimal hyperplane that minimizes the sum of distances from all sample points to the hyperplane. In training the environmental impact evaluation model, first, the environmental parameter data is normalized to map it to the [0, 1] interval to eliminate the influence of different parameter dimensions; then, a Gaussian kernel function is selected as the kernel function of the support vector regression, and the parameters of the kernel function, the kernel width and the penalty coefficient, are optimized by grid search and cross-validation. Among them, the kernel width controls the width of the Gaussian kernel function, and the penalty coefficient controls the penalty degree of the error term. By continuously adjusting the values of the kernel width and the penalty coefficient, the parameter combination that minimizes the validation set error is found, and the trained environmental impact evaluation model is obtained. When the first environmental parameter is input into the trained environmental impact evaluation model, the first environmental parameter is first subjected to the same normalization processing as in the training stage, and then substituted into the model for prediction. The environmental impact evaluation model outputs the corresponding environmental impact coefficient according to the input first environmental parameter.

[0047] By introducing the environmental impact evaluation model, the internal relationship between environmental factors and user movement frequency adjustment is fully tapped, and real-time and accurate impact evaluation is given for new input environmental parameters to obtain environmental factor impact coefficients, so that subsequent movement frequency recommendations are more comprehensive and objective, and also provide targeted guidance and prompts for user movement in complex environments.

[0048] S700: processing the base recommended frequency, the first movement progress, the first movement amplitude, the physical ability increase influence rate coefficient, the physical ability decline influence rate coefficient, the movement amplitude influence growth rate and the environmental factor influence coefficient through the movement frequency guide function to obtain a first movement progress recommended frequency.

[0049] Specifically, the server substitutes the obtained first movement progress, first movement amplitude, physical ability increase influence rate coefficient, physical ability decline influence rate coefficient, movement amplitude influence growth rate and environmental factor influence coefficient into the movement frequency guide function to correct the base recommended frequency, calculate the recommended movement frequency value under the current movement progress, realize comprehensive consideration of various factors affecting the movement frequency, and obtain a personalized recommended movement frequency.

[0050] Firstly, by collecting a large amount of historical data of users during exercise, including exercise duration, exercise intensity, physical condition change, environmental conditions and other multi-dimensional information, the data is cleaned and preprocessed. Then the machine learning algorithm is used to analyze the correlation between the data, extract the exercise frequency influencing factors including exercise progress, exercise amplitude, physical fitness increase influence rate coefficient, physical fitness decline influence rate coefficient, exercise amplitude influence growth rate and environmental factor influence coefficient, and establish a feature vector. Next, a regression analysis method is used to construct the mapping relationship between each exercise frequency influencing factor and exercise frequency adjustment amount based on the basic recommended frequency, and through repeated training and optimization, an exercise frequency guide function is obtained which can accurately describe the influence of multiple variables on exercise frequency. After obtaining the basic recommended frequency, the first exercise progress, the first exercise amplitude, the physical fitness increase influence rate coefficient, the physical fitness decline influence rate coefficient, the exercise amplitude influence growth rate and the environmental factor influence coefficient of the current user, the corresponding exercise frequency adjustment amount is obtained by using the exercise frequency guide function, and the first exercise progress recommended frequency is obtained by combining the basic recommended frequency.

[0051] By combining the aforementioned basic recommended frequency, first exercise progress, first exercise amplitude, physical fitness increase influence rate coefficient, physical fitness decline influence rate coefficient, exercise amplitude influence growth rate and environmental factor influence coefficient with the preset exercise frequency guide function, the calculation and generation of personalized exercise frequency recommendation value are realized, and the physiological characteristics, exercise ability and environmental factors of the user are comprehensively considered, which improves the exercise efficiency and quality while maximizing the exercise safety and comfort.

[0052] S800: Return the first exercise progress recommended frequency to the user end display interface to replace and display the basic recommended frequency.

[0053] Specifically, after obtaining the first exercise progress recommended frequency, the first exercise progress recommended frequency is sent to the user end. After receiving the first exercise progress recommended frequency, the user end replaces the basic recommended frequency value on the current user end interface with the newly received first exercise progress recommended frequency, ensuring that the user can see the latest and most appropriate exercise frequency recommendation value in time and adjust their exercise frequency according to the value. Among them, the first exercise progress recommended frequency can be presented in the form of numbers, charts, voices and other forms to meet the usage habits of different users. For example, the recommended step frequency value is dynamically updated on the user end interface, and a column chart or curve chart is used to show the trend of step frequency change; a voice broadcast function can also be set to read out the current recommended step frequency and remind the user to adjust in time. No matter what display method is used, the recommended result must be clear, intuitive and updated in real time to realize the guidance of exercise frequency for the user.

[0054] By transmitting and displaying the personalized recommended exercise frequency to the user interface in real time, the exercise frequency recommendation is completed, the precise and intelligent exercise guidance is realized, and the exercise experience and exercise effect of the user are improved.

[0055] Further, the login user basic information includes user weight information, user height information, user body fat rate information and user age information.

[0056] In a preferred embodiment, the obtained login user basic information includes user weight information, user height information, user body fat rate information and user age information, which comprehensively reflects the basic physical condition and physiological characteristics of the user and is an important factor affecting the exercise ability and exercise frequency of the user.

[0057] Among them, the user weight information reflects the overall physique and strength level of the user, the greater the weight, the greater the resistance to be overcome in exercise, so the recommended exercise frequency needs to be appropriately reduced; the user height information affects the exercise amplitude and limb coordination, the user with higher height usually has larger exercise amplitude; the user body fat rate information reflects the body composition and metabolic level of the user, and high body fat rate often means decreased exercise ability; the user age information affects physiological indicators such as heart and lung function and skeletal muscle, and the greater the age, the lower the overall exercise ability and recovery ability of the body.

[0058] By obtaining the user weight information, user height information, user body fat rate information and user age information, the physical condition and exercise potential of the user can be comprehensively evaluated, the individual differences of the user are fully considered in the subsequent exercise frequency recommendation, and more accurate and personalized exercise frequency guidance is provided.

[0059] Further, the embodiments of the present application also include:

[0060] S310: taking the login user basic information as a search constraint and taking the body ability increase influence rate coefficient as a search target, searching for a neighboring sample in a historical exercise database to obtain a set of historical calibration values of the body ability increase influence rate coefficient;

[0061] S320: performing centralized trend analysis on the set of historical calibration values of the body ability increase influence rate coefficient to obtain a fitted value of the body ability increase influence rate coefficient.

[0062] In a feasible implementation manner, after obtaining the basic information of the login user, the body ability increase influence rate coefficient of the current user is obtained through body ability increase sample analysis.

[0063] First, the login user basic information is taken as the retrieval constraint, and the physical fitness increase influence rate coefficient is taken as the retrieval target to search the sample data similar to the current user characteristics in the historical exercise database. By setting the retrieval constraint, the sample similar to the current user condition is quickly and accurately found, thereby providing a reference for subsequent analysis. The retrieval result is a set of historical calibration values of the physical fitness increase influence rate coefficient, which reflects the physical fitness increase rate characteristics of a group of users similar to the current user characteristics. Then, trend analysis is performed on the obtained set of historical calibration values of the physical fitness increase influence rate coefficient to extract an index representing the overall trend, i.e., the physical fitness increase influence rate coefficient fitting value, from the set of historical calibration values of the physical fitness increase influence rate coefficient. The centralized trend analysis can adopt statistical indexes such as the mean value method, the median value method, and the mode method, or can adopt time series analysis methods such as the moving average method and the exponential smoothing method. Through the trend analysis, the influence of individual differences and random fluctuations is removed, and the stable and reliable physical fitness increase influence rate coefficient is obtained.

[0064] By intelligently extracting the physical fitness increase influence rate coefficient from the historical data according to the personal characteristics of the user, the subjectivity and limitations of simple estimation or manual setting are overcome, the value of the historical data is fully utilized, and the coefficient estimation is more objective and accurate. At the same time, due to the retrieval of similar characteristic samples and the centralized trend analysis, the system has good individualized adaptability, and can give the physical fitness increase influence rate coefficient conforming to the characteristics of the user according to the actual situation of the user.

[0065] Further, the embodiments of the application further include:

[0066] S330: When the login user is registered, the login user basic information is obtained;

[0067] S340: The login user basic information is sent to the management end for setting the physical fitness increase influence rate coefficient, and a physical fitness increase influence rate coefficient setting value is obtained;

[0068] S350: The physical fitness increase influence rate coefficient setting value is associated with the login user basic information and stored.

[0069] In a preferred embodiment, when a new user registers an account, the user is required to fill in basic physiological characteristic information such as weight, height, body fat rate and age, etc., to obtain the basic information of the logged-in user, and the subsequent personalized exercise frequency recommendation provides the necessary data basis. Subsequently, the basic information of the logged-in user submitted by the logged-in user during registration is sent to the management end, and the professional personnel at the management end preliminarily sets the physical fitness increase influence rate coefficient of the user according to these information, referring to medical knowledge, exercise physiology principles and a large number of historical data of users, comprehensively considering the influence of different physiological characteristics on the physical fitness growth rate, to obtain the set value of the physical fitness increase influence rate coefficient. Subsequently, the set value of the physical fitness increase influence rate coefficient obtained by the management end is associated and stored with the basic information of the new user. Through the associated storage mode, the static physiological characteristics of the user can be organically combined with the dynamic physical fitness growth characteristics, and complete data support is provided for the subsequent personalized exercise frequency recommendation. At the same time, these associated data can also be used as samples to supplement the historical exercise database, providing a reference for the analysis of the physical fitness growth characteristics of other users, and producing an amplification effect of data value.

[0070] Through the initialization setting and storage of the physical fitness increase influence rate coefficient of the new user, an initial parameter basis is laid for the subsequent personalized exercise frequency recommendation. This new user coefficient acquisition method makes full use of expert knowledge and prior experience, makes up for the problem of insufficient sample data in the early stage, and improves the practicability and robustness.

[0071] Further, the embodiments of the application also include:

[0072] S610: Based on the historical exercise database, obtain environment parameter record data and environment factor influence coefficient record data, and construct environment influence evaluation model training data set;

[0073] S620: Divide the environment influence evaluation model training data set into K parts to obtain K groups of environment influence evaluation model training data;

[0074] S630: K times of sampling with replacement are performed on the K groups of environment influence evaluation model training data to obtain a first environment influence evaluation model training data set, a first environment influence evaluation model is trained by taking the environment factor influence coefficient record data as supervision and the environment parameter record data as input variable;

[0075] S640: Until Q times of sampling with replacement are performed on the K groups of environment influence evaluation model training data to obtain a Qth environment influence evaluation model training data set, a Qth environment influence evaluation model is trained by taking the environment factor influence coefficient record data as supervision and the environment parameter record data as input variable, Q≥5;

[0076] S650: Mean full connection is performed on the first environmental impact evaluation model to the Qth environmental impact evaluation model to obtain the environmental impact evaluation model.

[0077] In a preferred embodiment, the data set required for model training is obtained through the historical motion database, and then a model aggregation strategy is adopted to construct multiple independent environmental impact evaluation models through multiple rounds of random sampling and regression decision tree training, and then these models are combined to obtain the final environmental impact evaluation model.

[0078] Firstly, two types of data are extracted from the historical motion database, which are environmental parameter record data and environmental factor influence coefficient record data. Among them, the environmental parameter record data includes temperature, humidity, altitude, wind force and other multi-dimensional environmental measurement values, reflecting the objective environmental conditions when the user exercises; the environmental factor influence coefficient record data is a quantitative index of the influence degree of these environmental conditions on exercise step frequency, which is obtained through expert experience estimation or user feedback. Matching and combining these two types of data can obtain the complete environmental impact evaluation model training data set. Then, the obtained environmental impact evaluation model training data set is divided into K parts to obtain K sets of environmental impact evaluation model training data, each set of environmental impact evaluation model training data contains complete input features and target output, and the time span and data volume of each part of data are basically equivalent. This data grouping method can not only ensure the representativeness and diversity of each part of data, but also provide convenience for subsequent random sampling and sub-model training.

[0079] Subsequently, K times of random sampling with replacement is performed on the divided K sets of environmental impact assessment model training data to obtain a first environmental impact assessment model training dataset. The term "with replacement" means that after each set of environmental impact assessment model training data is extracted, it is returned to the K sets of environmental impact assessment model training data, so that the set of environmental impact assessment model training data has a chance of being selected in the next extraction. This sampling method allows the first environmental impact assessment model training dataset to potentially contain duplicate samples, thereby introducing data perturbations and increasing the diversity of the models. Then, a regression decision tree sub-model is trained using the first environmental impact assessment model training dataset as the training data, the environmental factor influence coefficient record data as the supervision signal, and the environmental parameter record data as the input feature variable. Regression decision tree is a machine learning algorithm based on recursive partitioning of feature space. By minimizing loss functions such as mean square error, it divides complex feature-target relationships into a series of simple regional judgments and local linear regressions to achieve nonlinear modeling and prediction. After training, a regression decision tree that can better fit the first environmental impact assessment model training dataset is obtained, which describes the nonlinear mapping relationship between the environmental parameters and the environmental factor influence coefficients in the dataset, i.e., the first environmental impact assessment model. Repeat the process until K sets of environmental impact assessment model training data are sampled K times with replacement for Q times. Each time, a new environmental impact assessment model training dataset is obtained by sampling K times with replacement from the original K sets of environmental impact assessment model training data, and a new regression decision tree sub-model is trained based on the training dataset until the Qth environmental impact assessment model is obtained. The number of repeated training Q is not less than 5 to ensure the stability and robustness of the ensemble model. The larger the value of Q, the more sub-models there are, and the better the ensemble effect may be, but the computational overhead will also increase. Therefore, the selection of Q value needs to balance performance and efficiency, and is generally determined based on the complexity of the actual problem and available computing resources.

[0080] Subsequently, a mean connection layer is constructed using a combination strategy of mean full connection, and the outputs of the first environmental impact assessment model to the Qth environmental impact assessment model are connected to the inputs of the mean connection layer to obtain the environmental impact assessment model. Since the first environmental impact assessment model to the Qth environmental impact assessment model are all approximate estimates of the environmental factor influence coefficients, the estimation errors are independent of each other, so that the random errors of each sub-model can be eliminated by averaging to obtain a more accurate and stable estimation result as the environmental factor influence coefficient.

[0081] By integrating the first environmental impact assessment model to the Qth environmental impact assessment model, the final environmental impact assessment model is obtained, which can provide a more robust and reliable environmental factor influence coefficient for new environmental parameters, providing key environmental adaptability support for subsequent motion frequency recommendation.

[0082] Further, the movement frequency guiding function is:

[0083] When the preset movement type belongs to at least one of endurance running, training running and long-time running, the movement frequency guiding function is:

[0084]

[0085] wherein D represents the first movement progress, BPM (0) represents the basic recommended frequency, ΔB represents the preset interval difference of step frequency, e represents the natural constant, k1 represents the physical fitness increase influence rate coefficient, a represents the amplification factor of the physical fitness increase influence rate coefficient, ∫ max represents the preset upper limit of the increased step frequency, ∫ min represents the preset lower limit of the increased step frequency, k2 represents the physical fitness decline influence rate coefficient, x0 represents the first movement amplitude, K3 represents the step amplitude influence weight on the step frequency, β represents the movement amplitude influence growth rate, K4 represents the environmental factor preset weight, and γ represents the environmental factor influence coefficient.

[0086] When the preset movement type belongs to at least one of speed running, competitive running and short-time running, the movement frequency guiding function is, and the input data is the first movement progress:

[0087]

[0088] wherein x1 represents the preset offset of the movement frequency influence from acceleration to deceleration, x2 represents the preset offset of the movement frequency influence from deceleration to acceleration, ΔB1 represents the first preset interval difference of step frequency, ΔB2 represents the second preset interval difference of step frequency, BPM (0) represents the basic recommended frequency, and e represents the natural constant.

[0089] In a preferred embodiment, when the preset movement type belongs to at least one of endurance running, training running and long-time running, the specific form of the movement frequency guiding function is as follows:

[0090]

[0091] BPM (D) represents the recommended step frequency value under the movement progress D, and the unit is steps / minute. BPM (0) represents the basic recommended frequency, that is, the initial step frequency value at the beginning of the movement, which is related to the movement type, personal habits and other factors, and is set through statistical analysis or expert experience. represents the step frequency increment caused by the gradual increase of physical fitness during the movement. Wherein, ΔB is the preset interval difference of step frequency increase, k1 is the physical fitness increase influence rate coefficient, a is the amplification factor of the coefficient, e is the natural constant. This term describes the nonlinear growth trend of step frequency with the progress of movement, and reflects the promoting effect of physical fitness improvement on step frequency. represents the step frequency attenuation caused by movement fatigue. Wherein, max and min are the preset upper and lower limits of step frequency attenuation respectively, k2 is the physical fitness decline influence rate coefficient, x0 is the progress offset of fatigue adjustment. This term describes the downward trend of step frequency in the later stage of movement due to fatigue accumulation, and reflects the negative effect of physical fitness decline on step frequency. K3·D β represents the step frequency adjustment caused by stride length change. Wherein, K3 is the influence weight of stride length on step frequency, β is the growth rate of stride length influence. This term considers the influence of dynamic change of stride length on step frequency during movement, when the stride length increases, the step frequency needs to be appropriately reduced to ensure the speed. K4·γ represents the step frequency adjustment caused by environmental factors. Wherein, K4 is the preset weight of environmental factors, γ is the environmental factor influence coefficient. This term considers the influence of temperature, humidity, terrain and other environmental conditions on step frequency, so that the movement frequency recommendation can adapt to different movement environments.

[0092] Through the movement frequency guidance function, scientific and reasonable movement frequency guidance can be continuously given throughout the movement process, guiding users to take the optimal movement frequency at different stages, so as to achieve the purpose of improving movement effect and reducing movement risk.

[0093] Further, the embodiments of the present application also include:

[0094] In the running type of movement, when the first movement progress is time progress, D=t / T, wherein t is the current time, T is the total time; when the first movement progress is distance progress, D=s / S, wherein s is the current distance, S is the total distance.

[0095] In a preferred embodiment, in the given movement frequency guidance function, D represents the movement progress, which is a normalized dimensionless parameter, and the value range is [0, 1]. Considering two kinds of movement progress representation methods: time progress and distance progress, the specific calculation formula of D value is given.

[0096] When using time progress representation, the formula for calculating D is: D = t / T. Where t represents the duration of the current exercise, and T represents the preset total exercise time. For example, if the total time of an exercise is set to 60 minutes, when the user has exercised for 30 minutes, the exercise progress D at this time is equal to 30 / 60 = 0.5, which means that the user has completed half of the total exercise time.

[0097] When using distance progress representation, the formula for calculating D is: D = s / S. Where s represents the current distance exercised, and S represents the preset total exercise distance. For example, if the total distance of an exercise is set to 10 kilometers, when the user has exercised 4 kilometers, the exercise progress D at this time is equal to 4 / 10 = 0.4, which means that the user has completed 40% of the total exercise distance.

[0098] Whether using time progress or distance progress, the D value is a continuous parameter from 0 to 1, representing the degree of completion of the exercise task. In the exercise frequency guide function, according to the different D values, the exercise frequency recommendation value can be dynamically adjusted to synchronize with the exercise progress, thereby realizing real-time and dynamic step frequency guidance.

[0099] Wherein, time progress and distance progress are exercise progress representation methods, but not the only choice. In actual application, other appropriate progress measurement indicators can also be used according to specific needs, such as heart rate change progress, energy consumption progress, etc. As long as it can quantitatively reflect the completion of the exercise task and match the step frequency adjustment strategy, it can be used as the basis for calculating the D value.

[0100] By introducing the normalized exercise progress D and giving the D value calculation formula based on time and distance progress representation, the exercise frequency guide function provides a time-varying input parameter, so that the exercise frequency recommendation can dynamically adapt to different stages of the exercise process and provide more accurate and real-time guidance.

[0101] Further, when the preset exercise type belongs to at least one of speed running, competitive running, and short-time running, the exercise frequency guide function is:

[0102]

[0103] Example 1, as shown in Figure 5 For a male 1000-meter running training plan for the physical examination of the middle school entrance examination, the full score is 3 minutes and 40 seconds to run 1000 meters, according to the physical distribution principle and the time distribution rhythm of the exercise extreme point, the rhythm is guided in the rhythm of accelerating running-slowing down energy storage-full sprint, parameters: BPM (0)= 180 BPM; ΔB1 = 42 BPM; ΔB2 = 40 BPM; k1 = 18; x1 = 0.5; k2 = 14; x2 = 0.6, formula calculation: The motion distance is 1000 meters, and each 100 meters is a point. The formula is calculated to obtain the result.

[0104] S BPM 0 222 10 222 100 222 200 222 300 221.5 400 218.3 500 209 600 206 700 213.2 800 217.9 900 219.4 1000 219.9

[0105] S BPM 0 200.02 8 200.02 80 200.03 160 200 240 199.5 320 196.61 400 189.26 480 186.72 560 192.31 640 196.99 720 199 800 200 .

[0106] The motion frequency guiding method provided by the embodiment of the application has at least the following technical effects:

[0107] In response to the user-end selected exercise type, the matched basic recommended frequency is returned to the user-end display interface for display, while the first exercise progress, the first exercise amplitude and the first environmental parameter are monitored to provide initial values and data basis for subsequent personalized exercise frequency adjustment, so that the exercise frequency guidance can be dynamically adjusted according to the actual situation of the user. The login user basic information is obtained to provide necessary user personal data for subsequent physical ability analysis, so that the exercise frequency guidance can be personalized adjusted according to the physical characteristics of different users. The physical ability increase sample analysis is performed according to the login user basic information to obtain a physical ability increase influence rate coefficient, which considers the influence of user physical ability improvement in the exercise frequency adjustment process, so that the recommended exercise frequency can be dynamically increased with the improvement of user physical ability, and more reasonable guidance is provided. The physical ability decline sample analysis is performed according to the login user basic information to obtain a physical ability decline influence rate coefficient, which considers the influence of user physical ability decline in the exercise frequency adjustment process, so that the recommended exercise frequency can be dynamically reduced with the decline of user physical ability, avoiding fatigue and damage caused by excessive exercise. The exercise amplitude sample analysis is performed according to the login user basic information and the first exercise amplitude to obtain an exercise amplitude influence growth rate, which considers the influence of user exercise amplitude change in the exercise frequency adjustment process, so that the recommended exercise frequency can be fine-tuned according to the actual exercise amplitude of the user, improving the accuracy of the exercise frequency guidance. The first environmental parameter is input into the environmental influence evaluation model for processing to obtain an environmental factor influence coefficient, which considers the influence of the exercise environment in the exercise frequency adjustment process, so that the recommended exercise frequency can be dynamically adjusted according to different environmental conditions (such as terrain, weather, etc.), improving the adaptability of the exercise frequency guidance. Through the exercise frequency guidance function, the basic recommended frequency, the first exercise progress, the first exercise amplitude, the physical ability increase influence rate coefficient, the physical ability decline influence rate coefficient, the exercise amplitude influence growth rate and the environmental factor influence coefficient are processed to obtain the first exercise progress recommended frequency, which comprehensively considers the user's personal physical ability characteristics, exercise data, environmental factors and other influencing factors to calculate the optimal recommended exercise frequency, realizing personalized and intelligent dynamic exercise frequency guidance. The first exercise progress recommended frequency is returned to the user-end display interface to replace the basic recommended frequency for display, and the optimal exercise frequency obtained is fed back to the user in real time to guide the user to adjust the exercise rhythm in time, so that the user can always maintain the most suitable exercise frequency, achieving the purpose of improving the exercise experience and effect.

[0108] Embodiment two:

[0109] As shown in Figure 2 based on the same inventive concept as the exercise frequency guidance method provided in embodiment one, the present embodiment also provides an exercise frequency guidance device, which comprises a server end, comprising:

[0110] The motion type matching module 11 is configured to match the basic recommended frequency to the user terminal display interface for display in response to the motion type selected by the user terminal, while monitoring the first motion progress, the first motion amplitude and the first environmental parameter;

[0111] The user basic information module 12 is configured to obtain the login user basic information;

[0112] The physical fitness increase analysis module 13 is configured to perform physical fitness increase sample analysis according to the login user basic information to obtain a physical fitness increase influence rate coefficient;

[0113] The physical fitness decline analysis module 14 is configured to perform physical fitness decline sample analysis according to the login user basic information to obtain a physical fitness decline influence rate coefficient;

[0114] The motion amplitude analysis module 15 is configured to perform motion amplitude sample analysis according to the login user basic information and the first motion amplitude to obtain a motion amplitude influence growth rate;

[0115] The environmental assessment module 16 is configured to input the first environmental parameter into an environmental influence assessment model for processing to obtain an environmental factor influence coefficient;

[0116] The frequency guidance module 17 is configured to process the basic recommended frequency, the first motion progress, the first motion amplitude, the physical fitness increase influence rate coefficient, the physical fitness decline influence rate coefficient, the motion amplitude influence growth rate and the environmental factor influence coefficient through a motion frequency guidance function to obtain a first motion progress recommended frequency.

[0117] The motion frequency display module 18 is configured to return the first motion progress recommended frequency to the user terminal display interface to replace the basic recommended frequency for display.

[0118] Further, the login user basic information includes user weight information, user height information, user body fat rate information and user age information.

[0119] Further, the physical fitness increase analysis module 13 includes the following execution steps:

[0120] The login user basic information is used as a search constraint, and the physical fitness increase influence rate coefficient is used as a search target to search for a proximal sample in a historical motion database to obtain a set of historical calibration values of the physical fitness increase influence rate coefficient;

[0121] The set of historical calibration values of the physical fitness increase influence rate coefficient is subjected to centralized trend analysis to obtain a fitted value of the physical fitness increase influence rate coefficient.

[0122] Further, the physical fitness increase analysis module 13 further includes the following execution steps:

[0123] obtaining the login user basic information when the login user registers;

[0124] sending the login user basic information to the management end to set the physical ability increase influence rate coefficient, and obtaining a physical ability increase influence rate coefficient setting value;

[0125] storing the physical ability increase influence rate coefficient setting value and the login user basic information in one-to-one association.

[0126] Further, the environment evaluation module 16 includes the following execution steps:

[0127] Based on the historical exercise database, obtain the environment parameter record data and the environment factor influence coefficient record data, and construct an environment influence evaluation model training data set;

[0128] Divide the environment influence evaluation model training data set into K parts to obtain K groups of environment influence evaluation model training data;

[0129] K times with replacement sampling is performed on the K groups of environment influence evaluation model training data to obtain a first environment influence evaluation model training data set. The environment factor influence coefficient record data is used as supervision, and the environment parameter record data is used as an input variable to train a regression decision tree to obtain a first environment influence evaluation model;

[0130] Until Q times with replacement sampling is performed on the K groups of environment influence evaluation model training data to obtain a Qth environment influence evaluation model training data set. The environment factor influence coefficient record data is used as supervision, and the environment parameter record data is used as an input variable to train a regression decision tree to obtain a Qth environment influence evaluation model, Q≥5;

[0131] Mean full connection is performed on the first environment influence evaluation model to the Qth environment influence evaluation model to obtain the environment influence evaluation model.

[0132] Further, the exercise frequency guidance function is:

[0133]

[0134] wherein D represents the first exercise progress, BPM (0) represents the basic recommended frequency, ΔB represents the step frequency preset interval difference value, e represents the natural constant, k1 represents the physical ability increase influence rate coefficient, α represents the magnification factor of the physical ability increase influence rate coefficient, and ∫ max represents the preset increase step frequency upper limit, and ∫ minThe preset increase in step frequency is represented by k2, which represents the rate coefficient of physical decline, x0 represents the first movement amplitude, K3 represents the weight of the influence of stride length on step frequency, β represents the growth rate of the influence of movement amplitude, K4 represents the preset weight of environmental factors, and γ represents the influence coefficient of environmental factors.

[0135] Furthermore, the motion frequency guiding function also includes:

[0136] When the first movement progress is a time progress, D = t / T, where t is the current time and T is the total time;

[0137] When the first movement progress is the distance progress, D = s / S, where s is the current distance and S is the total distance.

[0138] Example 3:

[0139] Please see Figure 3 , Figure 3 This is a schematic diagram illustrating an embodiment of the electronic device provided in this invention. For example... Figure 3 As shown, an electronic device 200 provided in this embodiment of the invention includes a memory 210, a processor 220, and a first computer program 211 stored in the memory 210 and executable on the processor 220. When the processor 220 executes the first computer program 211, it implements a motion frequency guidance method.

[0140] Example 4:

[0141] Please see Figure 4 , Figure 4 This is a schematic diagram illustrating an embodiment of a computer-readable storage medium provided by an embodiment of the present invention. For example... Figure 4 As shown, this embodiment provides a computer-readable storage medium 300 on which a second computer program 311 is stored. When the second computer program 311 is executed by a processor, it implements a motion frequency guidance method.

[0142] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0143] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0144] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or blocks of the flowcharts. Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or blocks of the flowcharts.

[0145] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or blocks of the flowcharts. Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or blocks of the flowcharts.

[0146] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or blocks of the flowcharts. Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or blocks of the flowcharts.

[0147] Although preferred embodiments of the application have been described, those skilled in the art will recognize that additional modifications and variations are possible without departing from the spirit and scope of the application.

[0148] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the application, modifications and variations of this application can be made by those skilled in the art upon the reading and understanding of the detailed description of the application.

Claims

1. A method for guiding motion frequency, characterized in that, An application to a motion frequency guidance device, the device including a server, comprising: In response to the type of exercise selected by the user, the system returns the basic recommended frequency to the user's display interface for display, while simultaneously monitoring the first exercise progress, the first exercise amplitude, and the first environmental parameters. Obtain basic information about the logged-in user; Based on the basic information of the logged-in users, a sample analysis of physical fitness increase was conducted to obtain the rate coefficient of physical fitness increase. Based on the basic information of the logged-in users, a sample analysis of physical fitness decline was conducted to obtain the rate coefficient of physical fitness decline impact. Based on the basic information of the logged-in user and the first motion amplitude, a motion amplitude sample analysis is performed to obtain the growth rate of the influence of motion amplitude. The first environmental parameter is input into the environmental impact assessment model for processing to obtain the environmental factor impact coefficient. By using the exercise frequency guidance function, the basic recommended frequency, the first exercise progress, the first exercise amplitude, the coefficient of the rate of increase in physical fitness, the coefficient of the rate of decrease in physical fitness, the growth rate of the exercise amplitude, and the coefficient of the environmental factors are processed to obtain the first recommended frequency of exercise progress. The first recommended exercise progress frequency is returned to the user's display interface to replace the basic recommended frequency.

2. The method as described in claim 1, characterized in that, Obtain basic information of the logged-in user, including: user weight information, user height information, user body fat percentage information, and user age information.

3. The method as described in claim 1, characterized in that, Based on the basic information of the logged-in users, a sample analysis of physical fitness increase was conducted to obtain the rate coefficient of physical fitness increase, including: Using the basic information of the logged-in user as the retrieval constraint and the coefficient of the rate of increase in physical fitness as the retrieval target, the system retrieves neighboring samples in the historical exercise database to obtain a set of historical calibration values ​​for the coefficient of the rate of increase in physical fitness. A central tendency analysis was performed on the set of historical calibration values ​​of the rate coefficient of physical fitness increase to obtain the fitted value of the rate coefficient of physical fitness increase.

4. The method as described in claim 3, characterized in that, Based on the basic information of the logged-in users, a sample analysis of physical fitness increase is performed to obtain the rate coefficient of physical fitness increase. This also includes: When a logged-in user registers, the basic information of the logged-in user is obtained; The basic information of the logged-in user is sent to the management terminal to set the coefficient of the rate of physical fitness increase, and the set value of the coefficient of the rate of physical fitness increase is obtained. The set value of the rate of increase in physical fitness is associated with and stored one by one with the basic information of the logged-in user.

5. The method as described in claim 1, characterized in that, The first environmental parameter is input into the environmental impact assessment model for processing to obtain the environmental factor impact coefficients, including: Based on historical motion databases, environmental parameter records and environmental factor influence coefficient records are obtained to construct an environmental impact assessment model training dataset. The training dataset of the environmental impact assessment model is divided into K parts to obtain K sets of environmental impact assessment model training data. K sets of environmental impact assessment model training data are sampled with replacement to obtain the first environmental impact assessment model training dataset. The environmental factor impact coefficient record data is used as supervision, and the environmental parameter record data is used as input variables to train a regression decision tree to obtain the first environmental impact assessment model. The training dataset for the Qth environmental impact assessment model is obtained by sampling with replacement K times on the K sets of environmental impact assessment model training data. The environmental factor impact coefficient record data is used as supervision, and the environmental parameter record data is used as input variables to train a regression decision tree to obtain the Qth environmental impact assessment model, where Q≥5. The environmental impact assessment model is obtained by performing a mean-full connection on the first environmental impact assessment model up to the Qth environmental impact assessment model.

6. The method as described in claim 1, characterized in that, The motion frequency guiding function is: When the preset exercise type belongs to at least one of endurance running, training running, and long-duration running, the exercise frequency guiding function is: Where D represents the progress of the first motion, BPM (0) The base recommended frequency is represented by ΔB, the step frequency preset interval difference is represented by e, the natural constant is represented by k1, the rate coefficient of physical fitness increase is represented by α, and the amplification factor of the rate coefficient of physical fitness increase is represented by ∫ max The characterization pre-sets an increase in the step frequency upper limit, ∫ min The preset increase in step frequency is represented by k2, which represents the rate coefficient of physical fitness decline, x0 represents the first movement amplitude, K3 represents the weight of the influence of step length on step frequency, β represents the growth rate of the influence of movement amplitude, K4 represents the preset weight of environmental factors, and γ represents the influence coefficient of environmental factors. When the preset exercise type belongs to at least one of speed running, competitive running, and short-duration running, the exercise frequency guidance function is, and the input data is the first exercise progress: Where x1 represents the influence of the motion frequency from acceleration to deceleration on the preset offset, x2 represents the influence of the motion frequency from deceleration to acceleration on the preset offset, ΔB1 ​​represents the difference in the preset interval of the first step frequency, and ΔB2 represents the difference in the preset interval of the second step frequency. BPM (0) The frequency of the basic recommendation is represented by e, and the natural constant is represented by e.

7. The method as described in claim 6, characterized in that, include: When the first movement progress is a time progress, D = t / T, where t is the current time and T is the total time; When the first movement progress is the distance progress, D = s / S, where s is the current distance and S is the total distance.

8. A motion frequency guiding device, characterized in that, For implementing a motion frequency guidance method according to any one of claims 1-7, the apparatus includes a server, comprising: The exercise type matching module is used to respond to the exercise type selected by the user terminal, match the basic recommendation frequency and return it to the user terminal display interface for display, and at the same time monitor the first exercise progress, the first exercise amplitude and the first environmental parameters. User basic information module, which is used to obtain the basic information of logged-in users; The physical fitness increase analysis module is used to perform physical fitness increase sample analysis based on the basic information of the logged-in user to obtain the physical fitness increase rate coefficient. The physical fitness decline analysis module is used to perform physical fitness decline sample analysis based on the basic information of the logged-in user to obtain the physical fitness decline impact rate coefficient. The motion amplitude analysis module is used to perform motion amplitude sample analysis based on the login user's basic information and the first motion amplitude to obtain the growth rate of the influence of motion amplitude. An environmental assessment module is used to input the first environmental parameter into an environmental impact assessment model for processing to obtain the environmental factor impact coefficient. The frequency guidance module is used to process the basic recommended frequency, the first exercise progress, the first exercise amplitude, the rate coefficient of the increase in physical fitness, the rate coefficient of the decline in physical fitness, the growth rate of the exercise amplitude, and the environmental factor influence coefficient through the exercise frequency guidance function to obtain the first recommended frequency for exercise progress. The exercise frequency display module is used to return the first recommended exercise frequency to the user terminal display interface to replace the basic recommended frequency.

9. An electronic device, characterized in that, include: Memory, used to store computer software programs; A processor is configured to read and execute the computer software program, thereby implementing the motion frequency guidance method according to any one of claims 1-7.

10. A non-transitory computer-readable storage medium, characterized in that, The storage medium stores a computer software program, which, when executed by a processor, implements a motion frequency guidance method as described in any one of claims 1-7.

Images