Equipment control parameter optimization method and device based on physical ability monitoring device

Abstract

The invention provides an equipment control parameter optimization method and device based on a physical ability monitoring device, relates to the technical field of data processing, and obtains a real-time physical ability data set and operates fitness equipment in real time through an interaction physical ability monitoring device. And synchronizing the real-time physical fitness data set and the real-time running fitness equipment to an adaptive decision support network to carry out equipment control parameter adjustment analysis, and obtaining real-time equipment control parameters to execute control parameter adjustment optimization of the optimized equipment. The technical problems that in the prior art, setting of control parameters of fitness equipment depends on subjective physiological function feelings of fitness users, so that setting of the control parameters of the fitness equipment is not scientific enough, the exercise effect is affected, and even the sport injury risk is increased are solved. The technical effects that fitness equipment control parameter self-adaption adjustment is carried out based on the actually measured user physiological function data, the fitness equipment control parameter setting, the user fitness requirement and the physiological function adaptation degree are improved, and the sport injury risk is avoided are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and a device for optimizing equipment control parameters based on a physical fitness monitoring device. Background Art

[0002] In the existing fitness environment, users often adjust the parameters of fitness equipment according to their own feelings, such as the speed and slope of a treadmill, the weight selection of a strength trainer, etc.

[0003] For example, a running enthusiast may set the treadmill speed too fast based on his or her feeling alone, exceeding his or her current heart rate safety threshold, causing the heart rate to rise rapidly. Not only does this fail to achieve the purpose of effective exercise, but it also increases the burden on the heart and the risk of sports injuries. This situation shows that there are obvious flaws in the control parameter settings of fitness equipment that rely on the user's subjective feelings.

[0004] In summary, there is a technical problem in the prior art that the control parameter setting of fitness equipment depends on the subjective physiological function feeling of the fitness user, which leads to unscientific setting of the control parameter of the fitness equipment, affects the exercise effect, and even increases the risk of sports injuries. Summary of the invention

[0005] The present application provides a method and device for optimizing equipment control parameters based on a physical fitness monitoring device, which is used to solve the technical problem in the prior art that the control parameter setting of fitness equipment depends on the subjective physiological function feeling of the fitness user, resulting in unscientific setting of the control parameter of the fitness equipment, affecting the exercise effect, and even increasing the risk of sports injuries.

[0006] In view of the above problems, the present application provides a method and device for optimizing equipment control parameters based on a physical fitness monitoring device.

[0007] The first aspect of the present application provides an equipment control parameter optimization method based on a physical fitness monitoring device, the method comprising: interactively obtaining target basic information of a target monitoring user, locally quantifying the target basic information, and obtaining quantitative basic information, wherein the quantitative basic information includes age information, BIM value, physical fitness level coefficient, and health status coefficient; performing data mining and expansion with the quantitative basic information as a constraint to obtain multiple sample data sets of multiple sample monitoring users, wherein each sample data set includes multiple sample physical fitness data and multiple sample equipment parameter settings; calling an adaptive decision support network, wherein the adaptive decision support network includes M adaptive decision support networks in parallel. Support channel, the adaptive decision support network adopts the multiple sample data sets as construction data to be constructed; the interactive physical fitness monitoring device obtains the real-time physical fitness data set and the real-time running fitness equipment, wherein the physical fitness monitoring device is integrated with the fitness equipment communication interface, and the target monitoring user wears the physical fitness monitoring device at a specific position during exercise; the real-time physical fitness data set and the real-time running fitness equipment are synchronized to the adaptive decision support network to perform equipment control parameter adjustment analysis to obtain real-time equipment control parameters; the target optimization equipment is located according to the real-time running fitness equipment, and the control parameter adjustment optimization of the target optimization equipment is performed using the real-time equipment control parameters.

[0008] The second aspect of the present application provides an equipment control parameter optimization device based on a physical fitness monitoring device, the device comprising: a basic information quantization unit, used to interactively obtain the target basic information of the target monitoring user, locally quantize the target basic information, and obtain quantitative basic information, wherein the quantitative basic information includes age information, BIM value, physical fitness level coefficient and health status coefficient; a data mining execution unit, used to perform data mining expansion with the quantitative basic information as a constraint, and obtain multiple sample data sets of multiple sample monitoring users, wherein each sample data set includes multiple sample physical fitness data and multiple sample equipment parameter settings; a decision network construction unit, used to call an adaptive decision support network, wherein the adaptive decision support network includes M adaptive decision support networks in parallel. Support channel, the adaptive decision support network adopts the multiple sample data sets as construction data to be constructed; a real-time information acquisition unit is used to interact with the physical fitness monitoring device to obtain the real-time physical fitness data set and the real-time running fitness equipment, wherein the physical fitness monitoring device is integrated with a fitness equipment communication interface, and the target monitoring user wears the physical fitness monitoring device at a specific position during exercise; a control adjustment analysis unit is used to synchronize the real-time physical fitness data set and the real-time running fitness equipment to the adaptive decision support network to perform equipment control parameter adjustment analysis to obtain real-time equipment control parameters; an equipment control adjustment unit is used to locate the target optimization equipment according to the real-time running fitness equipment, and use the real-time equipment control parameters to perform the control parameter adjustment optimization of the target optimization equipment.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages: The method provided by the embodiment of the present application obtains the target basic information of the target monitoring user through interaction, locally quantifies the target basic information, and obtains the quantitative basic information, wherein the quantitative basic information includes age information, BIM value, physical fitness level coefficient and health status coefficient; performs data mining expansion with the quantitative basic information as a constraint to obtain multiple sample data sets of multiple sample monitoring users, wherein each sample data set includes multiple sample physical fitness data and multiple sample equipment parameter settings; calls an adaptive decision support network, wherein the adaptive decision support network includes M adaptive decision support channels in parallel, and the adaptive decision support network is constructed using the multiple sample data sets as construction data; the interactive physical fitness monitoring device obtains a real-time physical fitness data set and a real-time running fitness equipment, wherein the physical fitness monitoring device is integrated with a fitness equipment communication interface, and the target monitoring user wears the physical fitness monitoring device at a specific position during exercise; synchronizes the real-time physical fitness data set and the real-time running fitness equipment to the adaptive decision support network for equipment control parameter adjustment analysis to obtain real-time equipment control parameters; locates the target optimization equipment according to the real-time running fitness equipment, and uses the real-time equipment control parameters to perform control parameter adjustment optimization of the target optimization equipment. The technical effect of adaptively adjusting the control parameters of fitness equipment based on the measured physiological function data of users, improving the adaptability of the control parameter settings of fitness equipment to the fitness needs and physiological functions of users, and avoiding the risk of sports injuries is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic diagram of the flow chart of the equipment control parameter optimization method based on the physical fitness monitoring device provided in this application; Figure 2 A schematic diagram of a process for constructing an adaptive decision support network in the equipment control parameter optimization method based on a physical fitness monitoring device provided in the present application; Figure 3 This is a schematic diagram of the structure of the equipment control parameter optimization device based on the physical fitness monitoring device provided in this application.

[0011] Explanation of the accompanying drawings: basic information quantification unit 11, data mining execution unit 12, decision network construction unit 13, real-time information collection unit 14, control and regulation analysis unit 15, equipment control and regulation unit 16. DETAILED DESCRIPTION

[0012] This application provides a method and device for optimizing equipment control parameters based on a physical fitness monitoring device, which is used to solve the technical problem in the prior art that the setting of fitness equipment control parameters depends on the subjective physiological function of fitness users, resulting in unscientific setting of fitness equipment control parameters, affecting exercise effects, and even increasing the risk of sports injuries. The method achieves the technical effect of adaptively adjusting fitness equipment control parameters based on measured user physiological function data, improving the adaptability of fitness equipment control parameter settings to user fitness needs and physiological functions, and avoiding the risk of sports injuries.

[0013] Below, the technical solutions in the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments described herein. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. It should also be noted that, for the convenience of description, only the parts related to the present invention are shown in the accompanying drawings, rather than all of them.

[0014] Embodiment 1, as Figure 1 As shown, the present application provides a method for optimizing equipment control parameters based on a physical fitness monitoring device, the method comprising: A100: Interactively obtain target basic information of the target monitoring user, locally quantify the target basic information, and obtain quantitative basic information, wherein the quantitative basic information includes age information, BIM value, physical fitness level coefficient and health status coefficient.

[0015] In one embodiment, the target basic information of the target monitoring user is interactively obtained, and the target basic information is locally quantified to obtain the quantified basic information, wherein the quantified basic information includes age information, BIM value, physical fitness level coefficient and health status coefficient. Before, the method step A100 provided by the present invention also includes: A110: Pre-construct a basic information quantification model, wherein the basic information quantification model includes a BIM value quantification branch, a physical fitness level quantification branch, and a health status quantification branch connected in parallel.

[0016] A120: Call the BMI weight index calculation formula, and introduce the BMI weight index calculation formula into the BIM value quantification branch to complete the construction of the BIM value quantification branch.

[0017] A130: Interactively obtain multiple sample fitness level arrays and multiple sample fitness level coefficients, and perform multiple regression analysis based on the multiple sample fitness level arrays and multiple sample fitness level coefficients to obtain a fitness level quantification formula, wherein each sample fitness level array includes a sample maximum oxygen uptake, a sample heart rate recovery, a sample muscle strength, a sample muscle endurance, and a sample metabolic equivalent.

[0018] A140: Introduce the physical fitness level quantification formula into the physical fitness level quantification branch to complete the construction of the physical fitness level quantification branch.

[0019] A150: Interactively obtain multiple sample health status arrays and multiple sample health status coefficients, and perform multivariate regression analysis based on the multiple sample health status arrays and multiple sample health status coefficients to obtain a health status quantification formula, wherein each sample health status array includes a sample heart rate, a sample blood pressure, a sample respiratory rate, and a sample body fat percentage.

[0020] A160: Quantify the health status formula and introduce the health status quantification formula into the health status quantification branch to complete the construction of the health status quantification branch.

[0021] Specifically, in this embodiment, a basic information quantization model is pre-constructed, and the basic information quantization model is used to reduce the parameter composition of the basic information, thereby improving the efficiency of obtaining sample monitoring users with similar basic information composition based on the target basic information comparison of the target monitoring user.

[0022] The basic information quantification model includes a BIM value quantification branch, a physical fitness level quantification branch and a health status quantification branch connected in parallel.

[0023] Call the BMI body mass index calculation formula: , and introduce the BMI weight index calculation formula into the BIM value quantification branch to complete the construction of the BIM value quantification branch. The BIM quantification branch calls the height and weight of the target monitored user from the target basic information and inputs them into the BIM value quantification branch to calculate the BIM value in the quantitative basic information.

[0024] Multiple sample fitness level arrays and multiple sample fitness level coefficients are interactively obtained, each sample fitness level array includes sample maximum oxygen uptake, sample heart rate recovery, sample muscle strength, sample muscle endurance and sample metabolic equivalent, and each sample fitness level coefficient is the average of multiple comprehensive fitness level scores obtained by evaluating the corresponding sample fitness level arrays based on historical experience by multiple experts in the field of sports health.

[0025] The plurality of sample fitness level arrays are used as independent variables, and the plurality of sample fitness level coefficients are used as dependent variables. A conventional multiple regression analysis method is used to organize the mapping relationship between the plurality of sample fitness level arrays and the plurality of sample fitness level coefficients into a matrix form, and then a multiple regression model is established to predict the fitness level coefficient. The form of the regression model is y=Xβ+ε, where y is the fitness level coefficient, X is the fitness level data matrix, β is the regression coefficient, and ε is the error term. The regression coefficient β is estimated using the ordinary least squares method (OLS), that is, the best fitting coefficient is found by minimizing the difference between the actual fitness level coefficient y and the regression prediction value Xβ, and the multiple regression analysis is completed to obtain the fitness level quantitative formula.

[0026] The physical fitness level quantification formula is introduced into the physical fitness level quantification branch to complete the construction of the physical fitness level quantification branch. The physical fitness level quantification branch calls the maximum oxygen uptake, heart rate recovery, muscle strength, muscle endurance and metabolic equivalent measured under the historical health status of the target monitoring user from the target basic information and inputs them into the physical fitness level quantification branch to calculate the physical fitness level coefficient in the quantified basic information.

[0027] By analogy, the same method of constructing the physical fitness level quantification branch is adopted to interactively obtain multiple sample health status arrays and multiple sample health status coefficients, and a multivariate regression analysis is performed based on the multiple sample health status arrays and multiple sample health status coefficients to obtain a health status quantification formula, each sample health status array includes a sample heart rate, a sample blood pressure, a sample respiratory rate and a sample body fat percentage.

[0028] The health status quantification formula is introduced into the health status quantification branch to complete the construction of the health status quantification branch. The heart rate, blood pressure, respiratory rate and body fat percentage measured in the recent historical health and non-exercise state of the target monitoring user are called from the target basic information and input into the physical fitness level quantification branch to calculate the health status coefficient in the quantitative basic information.

[0029] This embodiment constructs a basic information quantification model to achieve the technical effect of reducing the parameter composition of the target basic information, thereby improving the efficiency of obtaining sample monitoring users with similar basic information composition based on target basic information comparison of target monitoring users.

[0030] After interactively obtaining the target basic information generated by various body function data of the target monitoring user in a non-exercise health state, the target basic information is input into the basic information quantification model for local quantification to obtain the BIM value, physical fitness level coefficient and health status coefficient.

[0031] Furthermore, age information is extracted from the target basic information, and the age information, BIM value, physical fitness level coefficient and health status coefficient are stored jointly to obtain the quantitative basic information.

[0032] A200: Perform data mining and expansion with the quantitative basic information as a constraint to obtain multiple sample data sets of multiple sample monitored users, wherein each sample data set includes multiple sample physical fitness data and multiple sample equipment parameter settings.

[0033] In one embodiment, data mining and expansion are performed with the quantified basic information as a constraint to obtain multiple sample data sets of multiple sample monitoring users. Step A200 of the method provided by the present invention further includes: A210: Preset data mining constraints, wherein the data mining constraints include age deviation threshold, BIM value deviation threshold, physical fitness level deviation threshold and health status deviation threshold.

[0034] A220: Perform data mining expansion according to the data mining constraints and the quantitative basic information to obtain multiple original data sets of multiple sample monitoring users.

[0035] A230: Pre-built abnormal data removal model.

[0036] A240: The abnormal data elimination model is used to traverse the multiple original data sets of the multiple sample monitoring users to identify and eliminate abnormal data, and multiple sample data sets of the multiple sample monitoring users are obtained, wherein each sample data set includes multiple sample physical fitness data and multiple sample equipment parameter settings.

[0037] In one embodiment, a model for eliminating abnormal data is pre-built, and step A230 of the method provided by the present invention further includes: A231: Interactively obtain the safe change threshold of heart rate, blood pressure, respiratory rate, body temperature and blood oxygen.

[0038] A232: Based on the heart rate safety change threshold, blood pressure safety change threshold, respiratory rate safety change threshold, body temperature safety change threshold and blood oxygen safety change threshold mapping, construct a heart rate abnormality judgment branch, a blood pressure abnormality judgment branch, a respiratory abnormality judgment branch, a body temperature abnormality judgment branch and a blood oxygen abnormality judgment branch.

[0039] A233: The abnormal heart rate judgment branch, the abnormal blood pressure judgment branch, the abnormal breathing judgment branch, the abnormal body temperature judgment branch and the abnormal blood oxygen judgment branch are connected in parallel to obtain a single-dimensional abnormal judgment layer.

[0040] A234: Introduce a comprehensive anomaly calculation function and a comprehensive anomaly judgment threshold, and construct a comprehensive anomaly judgment layer based on the comprehensive anomaly calculation function and the comprehensive anomaly judgment threshold, wherein the comprehensive anomaly calculation function is as follows: ; in, is the comprehensive anomaly coefficient is the heart rate variation, is the blood pressure change, is the change in respiratory rate, is the body temperature change, is the change in blood oxygen, is the heart rate safety change threshold, is the safe change threshold of blood pressure, is the safe change threshold of respiratory rate, is the safe change threshold of body temperature, is the safe change threshold of blood oxygen, is the heart rate weight, is the blood pressure weight, is the breathing weight, is the body temperature weight, is the blood oxygen weight.

[0041] A235: Cascade the single-dimensional anomaly judgment layer and the comprehensive anomaly judgment layer to generate the abnormal data elimination model.

[0042] In one embodiment, the abnormal data elimination model is used to traverse multiple original data sets of the multiple sample monitoring users to identify and eliminate abnormal data, so as to obtain multiple sample data sets of the multiple sample monitoring users. Step A240 of the method provided by the present invention further includes: A241: Each of the multiple original data sets includes multiple original physical fitness data and multiple original equipment parameter settings, wherein each original physical fitness data includes a pre-exercise physical fitness monitoring array and a post-exercise physical fitness monitoring array.

[0043] A242: Extract and obtain first original physical fitness data and first original equipment parameter settings based on the multiple original data sets.

[0044] A243: Input the first original physical fitness data into the one-dimensional abnormality judgment layer of the abnormal data elimination model.

[0045] A244: If the output result of any abnormal judgment branch of the single-dimensional abnormal judgment layer is abnormal, the first original physical fitness data and the first original equipment parameter setting are marked as abnormal data.

[0046] A245: If the output results of all the abnormality judgment branches of the one-dimensional abnormality judgment layer are normal, the comprehensive abnormality judgment layer is activated and the first original physical fitness data is substituted into the comprehensive abnormality calculation function to obtain the first original comprehensive abnormality coefficient. If the first original comprehensive abnormality coefficient does not meet the comprehensive abnormality judgment threshold, the first original physical fitness data and the first original equipment parameter setting are marked as abnormal data.

[0047] A246: Similarly, the abnormal data elimination model is used to traverse the multiple original data sets of the multiple sample monitoring users to identify and eliminate abnormal data, thereby obtaining multiple sample data sets of the multiple sample monitoring users.

[0048] Specifically, in this embodiment, data mining constraints are preset, and the data mining constraints include age deviation thresholds, BIM value deviation thresholds, physical fitness level deviation thresholds, and health status deviation thresholds. Age deviation boundaries, BIM value deviation boundaries, physical fitness level deviation boundaries, and health status deviation boundaries are generated according to the data mining constraints and the quantitative basic information.

[0049] Exemplarily, the BIM value deviation threshold is ±0.5, the BIM value in the quantitative basic information is 19.7, and the BIM value deviation boundary is [19.2, 20.3].

[0050] If and only if all the sample quantified basic information of the sample monitoring user falls within the age deviation boundary, BIM value deviation boundary, physical fitness level deviation boundary and health status deviation boundary, it is considered that the historical physical fitness monitoring data and historical fitness equipment control parameters of the sample monitoring user can be used as a reference for the current target monitoring user to adjust the fitness equipment control parameters.

[0051] Interactively obtain basic information of several samples of several sample monitoring users, and then adopt the same method as step A100 to obtain quantitative basic information, quantify the basic information of several samples in the above text, and obtain quantitative basic information of several samples.

[0052] The age deviation boundary, BIM value deviation boundary, physical fitness level deviation boundary and health status deviation boundary are used to traverse the plurality of sample quantified basic information to obtain the plurality of sample monitoring users whose all indicators fall within the plurality of sample quantified basic information.

[0053] Then, the historical data of the plurality of sample monitoring users exercising with unspecified fitness equipment are dispatched to obtain the plurality of original data sets. Each of the plurality of original data sets corresponds to a sample monitoring user, and each original data set includes a plurality of original physical fitness data and a plurality of original equipment parameter settings, and each original equipment parameter setting has a fitness equipment type identifier.

[0054] Each original physical fitness data includes a pre-exercise physical fitness monitoring array and a post-exercise physical fitness monitoring array. The pre-exercise physical fitness monitoring array is a set of data including heart rate, blood pressure, respiratory rate, body temperature, and blood oxygen saturation obtained based on the measurement of the physical fitness monitoring device at the beginning of the use of the fitness equipment. The post-exercise physical fitness monitoring array is a set of data including heart rate, blood pressure, respiratory rate, body temperature, and blood oxygen saturation obtained based on the measurement of the physical fitness monitoring device after the sample monitoring user has used the fitness equipment for a certain period of time, for example, 30 minutes. The original physical fitness data reflects the changes in physiological parameters of the sample monitoring user before and after exercising with the fitness equipment.

[0055] It should be understood that exercise will cause certain changes in a person's physiological parameters (such as heart rate, blood pressure, respiratory rate, body temperature, and blood oxygen saturation). If the physiological functions change too much, it may lead to problems such as overtraining and long-term fatigue, affecting the body's recovery and health.

[0056] Based on this, an abnormal data elimination model is pre-constructed, and the abnormal data elimination model is used to eliminate the original physical fitness data with abnormal physiological function changes and its corresponding original equipment parameter settings, and obtain the equipment parameter settings that conform to the normal physiological function changes of the user, so as to serve as training data for constructing an adaptive decision support network. This embodiment elaborates on the construction method and usage function of the adaptive decision support network in the subsequent description.

[0057] The safe change thresholds of heart rate, blood pressure, respiratory rate, body temperature and blood oxygen are obtained interactively, and the safe change thresholds of heart rate, blood pressure, respiratory rate, body temperature and blood oxygen are respectively the safe change thresholds of heart rate after exercise and heart rate before exercise, the safe change thresholds of blood pressure after exercise and blood pressure before exercise, the safe change thresholds of respiratory rate after exercise and respiratory rate before and after exercise, the safe change thresholds of body temperature after exercise and body temperature before exercise, and the safe change thresholds of blood oxygen saturation after exercise and blood oxygen saturation before exercise.

[0058] Based on the heart rate safety change threshold, blood pressure safety change threshold, respiratory rate safety change threshold, body temperature safety change threshold and blood oxygen safety change threshold mapping, a heart rate abnormality judgment branch, a blood pressure abnormality judgment branch, a respiratory abnormality judgment branch, a body temperature abnormality judgment branch and a blood oxygen abnormality judgment branch are constructed. It should be understood that each abnormality judgment branch has a calculation engine that calculates the absolute value (change amount) of the data difference before and after the change.

[0059] The abnormal heart rate judgment branch, the abnormal blood pressure judgment branch, the abnormal breathing judgment branch, the abnormal body temperature judgment branch and the abnormal blood oxygen judgment branch are connected in parallel to obtain a single-dimensional abnormal judgment layer.

[0060] A comprehensive anomaly calculation function and a comprehensive anomaly judgment threshold are introduced, and a comprehensive anomaly judgment layer is constructed based on the comprehensive anomaly calculation function and the comprehensive anomaly judgment threshold, wherein the comprehensive anomaly calculation function is as follows: ; in, is the comprehensive anomaly coefficient, is the heart rate variation, is the blood pressure change, is the change in respiratory rate, is the body temperature change, is the change in blood oxygen, is the heart rate safety change threshold, is the safe change threshold of blood pressure, is the safe change threshold of respiratory rate, is the safe change threshold of body temperature, is the safe change threshold of blood oxygen, is the heart rate weight, is the blood pressure weight, is the breathing weight, is the body temperature weight, It is the blood oxygen weight. It should be understood that the weight assignments here are not limited to the comprehensive abnormal judgment threshold in this embodiment and can be manually set according to the actual target of monitoring the user's physical condition and training tasks.

[0061] The single-dimensional anomaly judgment layer and the comprehensive anomaly judgment layer are cascaded to generate the abnormal data elimination model.

[0062] The specific process of traversing multiple original data sets of multiple sample monitoring users by the abnormal data elimination model to identify and eliminate abnormal data is as follows: Each of the plurality of original data sets includes a plurality of original physical fitness data and a plurality of original equipment parameter settings, wherein each of the original physical fitness data includes a pre-exercise physical fitness monitoring array and a post-exercise physical fitness monitoring array.

[0063] The first original physical fitness data and the first original equipment parameter setting are extracted based on the multiple original data sets. It should be understood that based on the data composition characteristics that each original physical fitness data includes a pre-exercise physical fitness monitoring array and a post-exercise physical fitness monitoring array, the first original physical fitness data includes a first pre-exercise physical fitness monitoring array and a first post-exercise physical fitness monitoring array.

[0064] The first pre-exercise physical fitness monitoring array and the first post-exercise physical fitness monitoring array in the first original physical fitness data are input into the one-dimensional abnormal judgment layer of the abnormal data elimination model, and the first heart rate change, the first blood pressure change, the first respiratory rate change, the first body temperature change and the first blood oxygen saturation change are respectively calculated based on the calculation engine in the heart rate abnormal judgment branch, the blood pressure abnormal judgment branch, the respiratory abnormal judgment branch, the body temperature abnormal judgment branch and the blood oxygen abnormal judgment branch of the one-dimensional abnormal judgment layer. Then, in each abnormal judgment branch, the first heart rate change, the first blood pressure change, the first respiratory rate change, the first body temperature change and the first blood oxygen saturation change are mapped and compared to see whether they fall into the heart rate safety change threshold, the blood pressure safety change threshold, the respiratory rate safety change threshold, the body temperature safety change threshold and the blood oxygen safety change threshold. If they fall into, it is normal, and if they do not fall into, it is abnormal.

[0065] If the output result of any abnormality judgment branch of the one-dimensional abnormality judgment layer is abnormal, the first original physical fitness data and the first original equipment parameter setting are marked as abnormal data.

[0066] On the contrary, if the output results of all the abnormal judgment branches of the one-dimensional abnormal judgment layer are normal, the comprehensive abnormal judgment layer is activated and the first heart rate change, the first blood pressure change, the first respiratory rate change, the first body temperature change and the first blood oxygen saturation change obtained by calculating at the unit abnormal judgment layer based on the first original physical fitness data are substituted into the comprehensive abnormality calculation function to obtain the first original comprehensive abnormality coefficient. If the first original comprehensive abnormality coefficient does not meet (fall into) the comprehensive abnormality judgment threshold, the first original physical fitness data and the first original equipment parameter setting are marked as abnormal data.

[0067] By analogy, the abnormal data elimination model traverses multiple original data sets of the multiple sample monitoring users to identify and eliminate abnormal data, thereby obtaining multiple sample data sets of the multiple sample monitoring users.

[0068] This embodiment achieves the technical effect of eliminating abnormal data in sample data, providing reliable training data for subsequent model building based on sample data, and improving the credibility of the subsequent fitness equipment control parameter analysis decision output of the adaptive decision support network.

[0069] A300: Calling an adaptive decision support network, wherein the adaptive decision support network includes M adaptive decision support channels connected in parallel, and the adaptive decision support network is constructed using the multiple sample data sets as construction data.

[0070] In one embodiment, Figure 2 As shown, the method step A300 provided by the present invention also includes: A310: Perform fitness equipment type aggregation on the multiple sample data sets to obtain M types of sample fitness equipment.

[0071] A320: Perform data reclustering on the multiple sample data sets of the multiple sample monitoring users according to the M types of sample fitness equipment to obtain M sample physical fitness data sets and M sample equipment parameter setting sets of the M types of sample fitness equipment.

[0072] A330: Construct the M adaptive decision support channels based on the M sample physical fitness data sets and the M sample equipment parameter setting sets.

[0073] A340: Connect the M adaptive decision support channels in parallel to obtain the adaptive decision support network.

[0074] In one embodiment, the M adaptive decision support channels are constructed based on the M sample fitness data sets and the M sample equipment parameter setting sets. Step A330 of the method provided by the present invention further includes: A331: Randomly call M random operators from the operator library to construct the M adaptive decision support channels.

[0075] A332: Extract M pre-sample monitoring data sets from the M sample physical fitness data sets.

[0076] A333: Use the M pre-sample monitoring data sets and the M sample equipment parameter setting sets as training data to train the M adaptive decision support channels, and complete decision optimization of the M adaptive decision support channels.

[0077] Specifically, in this embodiment, the adaptive decision support network is used to generate fitness equipment control parameters that are adapted to the current user's physical fitness and can enable the user to exercise effectively based on the user's physical fitness data collected in real time and the fitness equipment used by the user.

[0078] The construction process of the adaptive decision support network is as follows: Based on the foregoing, it can be known that each original data set includes multiple original physical fitness data and multiple original equipment parameter settings, and each original equipment parameter setting has a fitness equipment type identification. Therefore, in the multiple sample data sets obtained by screening multiple original data sets in this embodiment, each sample data set includes multiple sample physical fitness data and multiple sample equipment parameter settings, and each sample equipment parameter setting has a fitness equipment type identification.

[0079] Based on this, this embodiment performs fitness equipment type identification extraction and aggregation on the multiple sample data sets to obtain M types of sample fitness equipment.

[0080] Then, data reclustering is performed on multiple sample data sets of the multiple sample monitoring users according to the M types of sample fitness equipment, and the division restrictions of the sample monitoring users are removed to obtain M sample physical fitness data sets and M sample equipment parameter setting sets based on the M types of sample fitness equipment for division judgment. It should be understood that the sample physical fitness data sets and sample equipment parameter setting sets with a mapping relationship are multiple equipment control parameter settings for achieving multiple physical fitness states under effective fitness conditions when using one sample fitness equipment.

[0081] A pre-built operator library is a collection or database that contains a variety of available operators. These operators can be mathematical operators, logical operators, functions, or algorithms, etc.

[0082] An operator is randomly selected from the operator library. Each selection may be different and uncertain. A total of M random operators are randomly called from the operator library to construct the M adaptive decision support channels.

[0083] Since the training methods of each adaptive decision support channel are similar, this embodiment takes the training of the first adaptive decision support channel as an example to elaborate on the technical solution in detail.

[0084] According to the first adaptive decision support channel, the first sample physical fitness data set is called among the M sample physical fitness data sets. It should be understood that the first sample physical fitness data set includes multiple sample physical fitness data, and based on the foregoing, each sample physical fitness data includes a pre-exercise physical fitness monitoring array and a post-exercise physical fitness monitoring array.

[0085] The pre-exercise physical fitness monitoring array of each sample physical fitness data in the plurality of sample physical fitness data of the first sample physical fitness data set is extracted to obtain a first pre-sample monitoring data set.

[0086] The first sample equipment parameter setting set is called in the M sample equipment parameter setting sets according to the first adaptive decision support channel. It should be understood that the first sample equipment parameter setting set includes multiple sample equipment parameter settings mapped to multiple sample physical fitness data in the first sample physical fitness data set.

[0087] The first pre-sample monitoring data set and the first sample equipment parameter setting set are used as training data, and the conventional training method of the random operator used to construct the first adaptive decision support channel is adopted to perform training of the first adaptive decision support channel until the accuracy of the fitness equipment control parameter setting output of the first adaptive decision support channel is stably higher than the preset accuracy.

[0088] Exemplarily, if the random operator of the first adaptive decision support channel is a back propagation network, the first sample pre-monitoring data set and multiple groups of sample physical fitness data-sample equipment parameter settings of the first sample equipment parameters are divided into a training set, a test set and a verification set according to a data volume identifier of, for example, 17:2:1, and a conventional training method of the back propagation network is adopted. The first adaptive decision support channel is trained and tested based on the training set and the test set, and the accuracy of the fitness equipment control parameters output by the first adaptive decision support channel is verified based on the verification set, thereby completing the construction training of the first adaptive decision support channel.

[0089] By analogy, the M pre-sample monitoring data sets and the M sample equipment parameter setting sets are used as training data to train the M adaptive decision support channels, and the decision optimization of the M adaptive decision support channels is completed. The M adaptive decision support channels are connected in parallel to obtain the adaptive decision support network.

[0090] This embodiment achieves the technical effect of replacing the user's subjective experience and subjective training sensation by constructing an adaptive decision support network, realizing adaptive adjustment of fitness equipment control parameters based on measured user physiological function data, and improving the adaptability of fitness equipment control parameter settings to user fitness needs and physiological functions.

[0091] A400: The interactive physical fitness monitoring device obtains a real-time physical fitness data set and real-time running fitness equipment, wherein the physical fitness monitoring device is integrated with a fitness equipment communication interface, and the target monitoring user wears the physical fitness monitoring device at a specific position during exercise.

[0092] A500: Synchronize the real-time physical fitness data set and the real-time running fitness equipment to the adaptive decision support network to perform equipment control parameter adjustment analysis to obtain real-time equipment control parameters.

[0093] Specifically, in this embodiment, the target monitored user wears the physical fitness monitoring device at a specific position during exercise, and the physical fitness monitoring device can collect the real-time heart rate, blood pressure, respiratory rate, body temperature, and blood oxygen saturation of the target monitored user.

[0094] At the same time, the physical fitness monitoring device is integrated with a fitness equipment communication interface and can directly obtain the type of fitness equipment currently used by the target monitoring user.

[0095] Therefore, this embodiment directly interacts with the physical fitness monitoring device to obtain real-time physical fitness data sets (real-time heart rate, blood pressure, respiratory rate, body temperature, blood oxygen saturation) and real-time operation of fitness equipment.

[0096] According to the mapping of the real-time running fitness equipment to the M adaptive decision support channels of the adaptive decision support network, corresponding types of channels are activated to obtain real-time adaptive decision support channels.

[0097] The real-time physical fitness data set is synchronized to the real-time adaptive decision support channel to perform equipment control parameter adjustment analysis to obtain real-time equipment control parameters.

[0098] A600: Locate target optimization equipment according to the real-time running fitness equipment, and use the real-time equipment control parameters to perform control parameter adjustment optimization of the target optimization equipment.

[0099] Specifically, in this embodiment, the target optimization equipment is located according to the real-time running fitness equipment, and the real-time equipment control parameters are communicated and transmitted to the target optimization equipment to perform control parameter adjustment optimization.

[0100] This embodiment achieves the technical effect of adaptively adjusting the control parameters of the fitness equipment based on the measured physiological function data of the user, thereby improving the adaptability of the control parameter settings of the fitness equipment to the user's fitness needs and physiological functions.

[0101] Embodiment 2 is based on the same inventive concept as the method for optimizing equipment control parameters based on a physical fitness monitoring device in the aforementioned embodiment. Figure 3 As shown, the present application provides an equipment control parameter optimization device based on a physical fitness monitoring device, wherein the device includes: The basic information quantification unit 11 is used to interactively obtain the target basic information of the target monitoring user, locally quantify the target basic information, and obtain quantitative basic information, wherein the quantitative basic information includes age information, BIM value, physical fitness level coefficient and health status coefficient.

[0102] The data mining execution unit 12 is used to perform data mining expansion with the quantitative basic information as a constraint to obtain multiple sample data sets of multiple sample monitored users, wherein each sample data set includes multiple sample physical fitness data and multiple sample equipment parameter settings.

[0103] The decision network construction unit 13 is used to call an adaptive decision support network, wherein the adaptive decision support network includes M adaptive decision support channels connected in parallel, and the adaptive decision support network is constructed using the multiple sample data sets as construction data.

[0104] The real-time information collection unit 14 is used to interact with the physical fitness monitoring device to obtain a real-time physical fitness data set and to operate the fitness equipment in real time, wherein the physical fitness monitoring device is integrated with a fitness equipment communication interface, and the target monitoring user wears the physical fitness monitoring device at a specific position during exercise.

[0105] The control adjustment analysis unit 15 is used to synchronize the real-time physical fitness data set and the real-time running fitness equipment to the adaptive decision support network to perform equipment control parameter adjustment analysis to obtain real-time equipment control parameters.

[0106] The equipment control and adjustment unit 16 is used to locate the target optimization equipment according to the real-time running fitness equipment, and use the real-time equipment control parameters to perform control parameter adjustment and optimization of the target optimization equipment.

[0107] In one embodiment, the basic information quantization unit 11 further includes: A basic information quantification model is pre-constructed, wherein the basic information quantification model includes a parallel BIM value quantification branch, a physical fitness level quantification branch, and a health status quantification branch; a BMI weight index calculation formula is called, and the BMI weight index calculation formula is introduced into the BIM value quantification branch to complete the construction of the BIM value quantification branch; multiple sample physical fitness level arrays and multiple sample physical fitness level coefficients are interactively obtained, and multiple regression analysis is performed based on the multiple sample physical fitness level arrays and the multiple sample physical fitness level coefficients to obtain a physical fitness level quantification formula, wherein each sample physical fitness level array includes a sample maximum oxygen uptake, a sample heart rate recovery, a sample muscle strength quantity, sample muscle endurance and sample metabolic equivalent; introduce the physical fitness level quantification formula into the physical fitness level quantification branch to complete the construction of the physical fitness level quantification branch; interactively obtain multiple sample health status arrays and multiple sample health status coefficients, and perform multivariate regression analysis based on the multiple sample health status arrays and multiple sample health status coefficients to obtain a health status quantification formula, wherein each sample health status array includes a sample heart rate, a sample blood pressure, a sample respiratory rate and a sample body fat percentage; quantify the health status formula, and introduce the health status quantification formula into the health status quantification branch to complete the construction of the health status quantification branch.

[0108] In one embodiment, the data mining execution unit 12 further includes: Preset data mining constraints, wherein the data mining constraints include age deviation thresholds, BIM value deviation thresholds, physical fitness level deviation thresholds, and health status deviation thresholds; perform data mining expansion according to the data mining constraints and the quantitative basic information to obtain multiple original data sets of multiple sample monitoring users; pre-build an abnormal data elimination model; traverse the multiple original data sets of the multiple sample monitoring users through the abnormal data elimination model to identify and eliminate abnormal data, and obtain multiple sample data sets of the multiple sample monitoring users, wherein each sample data set includes multiple sample physical fitness data and multiple sample equipment parameter settings.

[0109] In one embodiment, the data mining execution unit 12 further includes: Interactively obtain a heart rate safety change threshold, a blood pressure safety change threshold, a respiratory rate safety change threshold, a body temperature safety change threshold, and a blood oxygen safety change threshold; construct a heart rate abnormality judgment branch, a blood pressure abnormality judgment branch, a respiratory abnormality judgment branch, a body temperature abnormality judgment branch, and a blood oxygen abnormality judgment branch based on the heart rate safety change threshold, the blood pressure safety change threshold, the respiratory rate safety change threshold, the body temperature safety change threshold, and the blood oxygen safety change threshold mapping; connect the heart rate abnormality judgment branch, the blood pressure abnormality judgment branch, the respiratory abnormality judgment branch, the body temperature abnormality judgment branch, and the blood oxygen abnormality judgment branch in parallel to obtain a single-dimensional abnormality judgment layer; introduce a comprehensive abnormality calculation function and a comprehensive abnormality judgment threshold, and construct and generate a comprehensive abnormality judgment layer based on the comprehensive abnormality calculation function and the comprehensive abnormality judgment threshold, wherein the comprehensive abnormality calculation function is as follows: ; in, is the comprehensive anomaly coefficient, is the heart rate variation, is the blood pressure change, is the change in respiratory rate, is the body temperature change, is the change in blood oxygen, is the heart rate safety change threshold, is the safe change threshold of blood pressure, is the safe change threshold of respiratory rate, is the safe temperature change threshold, is the safe change threshold of blood oxygen, is the heart rate weight, is the blood pressure weight, is the breathing weight, is the body temperature weight, is the blood oxygen weight; the single-dimensional abnormality judgment layer and the comprehensive abnormality judgment layer are cascaded to generate the abnormal data elimination model.

[0110] In one embodiment, the data mining execution unit 12 further includes: Each of the multiple original data sets includes multiple original physical fitness data and multiple original equipment parameter settings, wherein each original physical fitness data includes a pre-exercise physical fitness monitoring array and a post-exercise physical fitness monitoring array; first original physical fitness data and first original equipment parameter settings are extracted based on the multiple original data sets; the first original physical fitness data is input into the one-dimensional abnormal judgment layer of the abnormal data elimination model; if the output result of any abnormal judgment branch of the one-dimensional abnormal judgment layer is abnormal, the first original physical fitness data and the first original equipment parameter settings are marked as abnormal data; if the output results of all abnormal judgment branches of the one-dimensional abnormal judgment layer are normal, the comprehensive abnormal judgment layer is activated and the first original physical fitness data is substituted into the comprehensive abnormality calculation function to obtain a first original comprehensive abnormality coefficient, if the first original comprehensive abnormality coefficient does not meet the comprehensive abnormality judgment threshold, the first original physical fitness data and the first original equipment parameter settings are marked as abnormal data; and so on, the multiple original data sets of the multiple sample monitoring users are traversed by the abnormal data elimination model to identify and eliminate abnormal data, and multiple sample data sets of the multiple sample monitoring users are obtained.

[0111] In one embodiment, the decision network construction unit 13 further includes: Perform fitness equipment type aggregation on the multiple sample data sets to obtain M types of sample fitness equipment; perform data reclustering on the multiple sample data sets of the multiple sample monitoring users according to the M types of sample fitness equipment to obtain M sample physical fitness data sets and M sample equipment parameter setting sets of the M types of sample fitness equipment; construct the M adaptive decision support channels based on the M sample physical fitness data sets and the M sample equipment parameter setting sets; and connect the M adaptive decision support channels in parallel to obtain the adaptive decision support network.

[0112] In one embodiment, the decision network construction unit 13 further includes: Randomly call M random operators from an operator library to construct the M adaptive decision support channels; extract M pre-sample monitoring data sets from the M sample physical fitness data sets; use the M pre-sample monitoring data sets and the M sample equipment parameter setting sets as training data to train the M adaptive decision support channels, and complete the decision optimization of the M adaptive decision support channels.

[0113] Any of the methods or steps described above may be stored as computer instructions or programs in various types of computer memories, and the computer instructions or programs may be recognized by various types of computer processors to implement any of the methods or steps described above.

[0114] Based on the above specific embodiments of the present invention, any improvements and modifications made to the present invention by those skilled in the art without departing from the principles of the present invention shall fall within the patent protection scope of the present invention.

Claims

1. A method for optimizing equipment control parameters based on a physical fitness monitoring device, characterized in that: The method comprises: Interactively obtain target basic information of the target monitoring user, locally quantify the target basic information, and obtain quantitative basic information, wherein the quantitative basic information includes age information, BIM value, physical fitness level coefficient and health status coefficient; Performing data mining and expansion with the quantitative basic information as a constraint to obtain multiple sample data sets of multiple sample monitoring users, wherein each sample data set includes multiple sample physical fitness data and multiple sample equipment parameter settings; Calling an adaptive decision support network, wherein the adaptive decision support network includes M adaptive decision support channels connected in parallel, and the adaptive decision support network is constructed using the multiple sample data sets as construction data; The interactive physical fitness monitoring device obtains a real-time physical fitness data set and operates the fitness equipment in real time, wherein the physical fitness monitoring device is integrated with a fitness equipment communication interface, and the target monitoring user wears the physical fitness monitoring device at a specific position during exercise; Synchronizing the real-time physical fitness data set and the real-time running fitness equipment to the adaptive decision support network to perform equipment control parameter adjustment analysis to obtain real-time equipment control parameters; The target optimization equipment is located according to the real-time running fitness equipment, and the control parameter adjustment optimization of the target optimization equipment is performed using the real-time equipment control parameters.

2. The equipment control parameter optimization method based on the physical fitness monitoring device according to claim 1, characterized in that: Interactively obtain target basic information of the target monitoring user, locally quantify the target basic information, and obtain quantitative basic information, wherein the quantitative basic information includes age information, BIM value, physical fitness level coefficient and health status coefficient. Before that, the method also includes: Pre-constructing a basic information quantification model, wherein the basic information quantification model includes a BIM value quantification branch, a physical fitness level quantification branch, and a health status quantification branch connected in parallel; Calling the BMI weight index calculation formula, and introducing the BMI weight index calculation formula into the BIM value quantification branch, completing the construction of the BIM value quantification branch; Interactively obtain multiple sample fitness level arrays and multiple sample fitness level coefficients, and perform multiple regression analysis based on the multiple sample fitness level arrays and multiple sample fitness level coefficients to obtain a fitness level quantification formula, wherein each sample fitness level array includes a sample maximum oxygen uptake, a sample heart rate recovery, a sample muscle strength, a sample muscle endurance, and a sample metabolic equivalent; Introducing the physical fitness level quantification formula into the physical fitness level quantification branch to complete the construction of the physical fitness level quantification branch; Interactively obtain multiple sample health status arrays and multiple sample health status coefficients, and perform multiple regression analysis based on the multiple sample health status arrays and multiple sample health status coefficients to obtain a health status quantification formula, wherein each sample health status array includes a sample heart rate, a sample blood pressure, a sample respiratory rate, and a sample body fat percentage; The health status quantification formula is introduced into the health status quantification branch to complete the construction of the health status quantification branch.

3. The equipment control parameter optimization method based on the physical fitness monitoring device according to claim 1, characterized in that: Data mining and expansion are performed with the quantified basic information as a constraint to obtain multiple sample data sets of multiple sample monitoring users. The method further includes: Preset data mining constraints, wherein the data mining constraints include age deviation threshold, BIM value deviation threshold, physical fitness level deviation threshold and health status deviation threshold; Perform data mining expansion according to the data mining constraints and the quantitative basic information to obtain multiple original data sets of multiple sample monitoring users; Pre-build abnormal data elimination model; The abnormal data elimination model is used to traverse multiple original data sets of the multiple sample monitoring users to identify and eliminate abnormal data, so as to obtain multiple sample data sets of the multiple sample monitoring users, wherein each sample data set includes multiple sample physical fitness data and multiple sample equipment parameter settings.

4. The equipment control parameter optimization method based on the physical fitness monitoring device according to claim 3, characterized in that: Pre-building an abnormal data elimination model, the method further includes: Interactively obtain the safe change threshold of heart rate, blood pressure, respiratory rate, body temperature and blood oxygen; Based on the heart rate safety change threshold, blood pressure safety change threshold, respiratory rate safety change threshold, body temperature safety change threshold and blood oxygen safety change threshold mapping, a heart rate abnormality judgment branch, a blood pressure abnormality judgment branch, a respiratory abnormality judgment branch, a body temperature abnormality judgment branch and a blood oxygen abnormality judgment branch are constructed; The abnormal heart rate judgment branch, the abnormal blood pressure judgment branch, the abnormal breathing judgment branch, the abnormal body temperature judgment branch and the abnormal blood oxygen judgment branch are connected in parallel to obtain a single-dimensional abnormal judgment layer; A comprehensive anomaly calculation function and a comprehensive anomaly judgment threshold are introduced, and a comprehensive anomaly judgment layer is constructed based on the comprehensive anomaly calculation function and the comprehensive anomaly judgment threshold, wherein the comprehensive anomaly calculation function is as follows: ； in, is the comprehensive anomaly coefficient, is the heart rate variation, is the blood pressure change, is the change in respiratory rate, is the body temperature change, is the change in blood oxygen, is the heart rate safety change threshold, is the safe change threshold of blood pressure, is the safe change threshold of respiratory rate, is the safe temperature change threshold, is the safe change threshold of blood oxygen, is the heart rate weight, is the blood pressure weight, is the breathing weight, is the body temperature weight, is the blood oxygen weight; The single-dimensional anomaly judgment layer and the comprehensive anomaly judgment layer are cascaded to generate the abnormal data elimination model.

5. The equipment control parameter optimization method based on the physical fitness monitoring device according to claim 4, characterized in that: The abnormal data elimination model is used to traverse multiple original data sets of the multiple sample monitoring users to identify and eliminate abnormal data, so as to obtain multiple sample data sets of the multiple sample monitoring users. The method further includes: Each of the plurality of original data sets includes a plurality of original physical fitness data and a plurality of original equipment parameter settings, wherein each of the original physical fitness data includes a pre-exercise physical fitness monitoring array and a post-exercise physical fitness monitoring array; Extracting and obtaining first original physical fitness data and first original equipment parameter settings based on the multiple original data sets; Inputting the first original physical fitness data into the single-dimensional abnormality judgment layer of the abnormal data elimination model; If the output result of any abnormality judgment branch of the one-dimensional abnormality judgment layer is abnormal, marking the first original physical fitness data and the first original equipment parameter setting as abnormal data; If the output results of all abnormality judgment branches of the single-dimensional abnormality judgment layer are normal, the comprehensive abnormality judgment layer is activated and the first original physical fitness data is substituted into the comprehensive abnormality calculation function to obtain a first original comprehensive abnormality coefficient; if the first original comprehensive abnormality coefficient does not meet the comprehensive abnormality judgment threshold, the first original physical fitness data and the first original equipment parameter setting mark are set as abnormal data; By analogy, the abnormal data elimination model traverses multiple original data sets of the multiple sample monitoring users to identify and eliminate abnormal data, thereby obtaining multiple sample data sets of the multiple sample monitoring users.

6. The equipment control parameter optimization method based on the physical fitness monitoring device according to claim 1, characterized in that: The method further comprises: Perform fitness equipment type aggregation on the multiple sample data sets to obtain M types of sample fitness equipment; Re-clustering the multiple sample data sets of the multiple sample monitoring users according to the M types of sample fitness equipment to obtain M sample physical fitness data sets and M sample equipment parameter setting sets of the M types of sample fitness equipment; constructing the M adaptive decision support channels based on the M sample physical fitness data sets and the M sample equipment parameter setting sets; The M adaptive decision support channels are connected in parallel to obtain the adaptive decision support network.

7. The equipment control parameter optimization method based on the physical fitness monitoring device according to claim 6, characterized in that: Constructing the M adaptive decision support channels based on the M sample fitness data sets and the M sample equipment parameter setting sets, the method further comprising: Randomly calling M random operators from an operator library to construct the M adaptive decision support channels; Extracting M pre-sample monitoring data sets from the M sample physical fitness data sets to obtain; The M pre-sample monitoring data sets and the M sample equipment parameter setting sets are used as training data to train the M adaptive decision support channels, thereby completing decision optimization of the M adaptive decision support channels.

8. An equipment control parameter optimization device based on a physical fitness monitoring device, characterized in that: The device is used to implement the equipment control parameter optimization method based on the physical fitness monitoring device according to any one of claims 1 to 7, the device comprising: A basic information quantification unit, used for interactively obtaining target basic information of a target monitoring user, locally quantifying the target basic information, and obtaining quantified basic information, wherein the quantified basic information includes age information, BIM value, physical fitness level coefficient, and health status coefficient; A data mining execution unit, configured to perform data mining expansion based on the quantified basic information as a constraint, to obtain a plurality of sample data sets of a plurality of sample monitored users, wherein each sample data set includes a plurality of sample physical fitness data and a plurality of sample equipment parameter settings; A decision network construction unit, used for calling an adaptive decision support network, wherein the adaptive decision support network comprises M adaptive decision support channels connected in parallel, and the adaptive decision support network is constructed by using the multiple sample data sets as construction data; A real-time information collection unit, used to interact with a physical fitness monitoring device to obtain a real-time physical fitness data set and to operate fitness equipment in real time, wherein the physical fitness monitoring device is integrated with a fitness equipment communication interface, and the target monitoring user wears the physical fitness monitoring device at a specific position during exercise; A control adjustment analysis unit, used for synchronizing the real-time physical fitness data set and the real-time running fitness equipment to the adaptive decision support network to perform equipment control parameter adjustment analysis to obtain real-time equipment control parameters; The equipment control and adjustment unit is used to locate the target optimization equipment according to the real-time running fitness equipment, and use the real-time equipment control parameters to perform control parameter adjustment and optimization of the target optimization equipment.

Images