Exercise heart rate monitoring and intensity linkage early warning system

Abstract

The invention relates to the technical field of exercise health monitoring, in particular to an exercise heart rate monitoring and intensity linkage early warning system which comprises a linkage early warning center, a multi-dimensional exercise module, a data processing module, a body state evaluation module, a linkage control module, a feedback evaluation unit and an early warning execution module. Core data related to user motion characteristics are collected in real time, analysis deviation caused by data missing is avoided, the heart rate-motion intensity correlation model is constructed based on data processing, the heart rate abnormal state is accurately recognized through real-time heart rate monitoring and motion intensity correlation analysis, and the user experience is improved. Closed-loop management of accurate judgment, graded early warning and effective response is achieved, the exercise safety is remarkably improved, meanwhile, early warning triggering better fits the actual state of the user through comprehensive evaluation, the heart rate threshold value is dynamically adjusted according to the real-time body state and the exercise duration of the user, and the user experience is improved. The problems that a traditional static threshold value is too strict in the initial stage of movement and lags behind in the later stage of movement are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sports health monitoring, in particular to a sports heart rate monitoring and intensity linkage early warning system. BACKGROUND

[0002] With the improvement of the national fitness consciousness, more and more users improve their health conditions through exercise, but the health risks caused by the lack of timely heart rate monitoring and the mismatch between exercise intensity and their own physical condition (such as dizziness and palpitations caused by high heart rate, or poor exercise effect caused by insufficient exercise intensity) gradually become prominent during exercise;

[0003] The existing sports heart rate monitoring devices mostly only have a single heart rate display function, and cannot comprehensively analyze the user's basic physiological data (such as age, resting heart rate, and previous exercise history) and real-time exercise intensity (such as speed, resistance, and frequency). Some devices with early warning function only issue prompts through simple threshold judgment, lack linkage control capability with exercise devices, cannot adjust exercise intensity in time, and traditional sports heart rate early warning is mostly based on fixed maximum heart rate threshold or target heart rate interval, without considering the dynamic body state changes and external environmental influences during user exercise, resulting in a large deviation between the early warning result and the actual physical tolerance, and the early warning result cannot truly reflect the exercise risk.

[0004] In view of the above technical defects, a solution is proposed. SUMMARY

[0005] The purpose of the present application is to provide a sports heart rate monitoring and intensity linkage early warning system to solve the above technical defects. The present application collects core data related to user exercise characteristics in real time, avoids analysis deviation caused by data loss, and constructs a heart rate-exercise intensity correlation model based on data processing. Through real-time heart rate monitoring and exercise intensity correlation analysis, the abnormal state of heart rate is accurately identified, the closed-loop management of accurate judgment, graded early warning, and effective response is realized, the exercise safety is significantly improved, and the early warning trigger is more suitable for the actual state of the user through comprehensive evaluation. The heart rate threshold can be dynamically adjusted according to the real-time physical state of the user and the exercise duration, solving the problem of too strict at the beginning of exercise and lag at the end of exercise of the traditional static threshold.

[0006] The purpose of the present application can be realized by the following technical scheme: a sports heart rate monitoring and intensity linkage early warning system, comprising a linkage early warning center, a multi-dimensional exercise module, a data processing module, a physical state evaluation module, a linkage control module, a feedback evaluation unit, and an early warning execution module;

[0007] The multi-dimensional exercise module is used for collecting heart rate data, basic physiological data, current exercise type information, and exercise intensity parameters under the corresponding exercise type during the user's exercise period in real time and sending them to the linkage early warning center for storage;

[0008] The data processing module is used for constructing a heart rate-movement intensity correlation model and accompanying a verification feedback analysis process;

[0009] The physical state evaluation module is used for continuously evaluating and analyzing the collected movement original data of the current user, and calculating a comprehensive state index by weighting a physiological state index, a fatigue index and an environmental influence factor;

[0010] The linkage control module is used for comparing and analyzing the matching degree between the current real-time heart rate and the theoretical heart rate range in real time, judging whether the current real-time heart rate exceeds the maximum heart rate threshold or deviates from the theoretical heart rate range, and outputting a first-level warning signal or a second-level warning signal;

[0011] The feedback evaluation unit is used for performing a warning evaluation feedback analysis on the collected historical feedback data of the user, and obtaining a feedback optimization signal, a mild influence signal or a severe influence signal.

[0012] Preferably, the analysis process of the data processing module is as follows:

[0013] S1: preprocessing the collected heart rate data, basic physiological data, current movement type information and movement intensity parameters under the corresponding movement type to obtain standardized multi-dimensional data;

[0014] S2: dividing the standardized multi-dimensional data into a training set and a test set according to a preset proportion, and constructing a heart rate-movement intensity correlation model based on the training set;

[0015] S3: obtaining a verification result by performing a targeted verification on the heart rate-movement intensity correlation model;

[0016] S4: performing a discrimination process on the verification result, if the verification is passed, obtaining a final heart rate-movement intensity correlation model, if the verification is not passed, re-executing steps S1-S4 until a final heart rate-movement intensity correlation model is obtained.

[0017] Preferably, the targeted verification analysis process is as follows:

[0018] The standardized multi-dimensional data is divided into subgroups according to age grouping, movement type grouping, movement ability grouping and health condition grouping;

[0019] According to a preset proportion, all sample data of each subgroup is extracted;

[0020] All sample data of each subgroup is input into the heart rate-movement intensity correlation model to obtain an output predicted heart rate value, and a heart rate mean absolute error M is calculated based on the predicted heart rate value YC and the actual heart rate value SJ;

[0021] Discrimination processing is performed on the mean absolute error M of the heart rate to obtain a discrimination result of unqualified and qualified.

[0022] Preferably, the analysis process of the physical state evaluation module is as follows:

[0023] The motion original data of the current user is obtained, and the motion original data includes a physiological state index, a fatigue index, and an environmental influence factor (a value obtained by weighted calculation of a difference between an environmental temperature value and a preset reference temperature and a difference between an environmental humidity value and a preset reference humidity);

[0024] The physiological state index, the preset physiological state index weight coefficient, the fatigue index, the preset fatigue index weight coefficient, the environmental influence factor, and the preset environmental influence factor weight coefficient are calculated to obtain a comprehensive state index.

[0025] Preferably, the real-time heart rate, the resting heart rate, the real-time body temperature, the normal body temperature, and the blood oxygen concentration of the current user are obtained, and a value calculated by real-time heart rate / resting heart rate x a1 + (1-blood oxygen concentration) x a2 + (real-time body temperature-normal body temperature) x a3 is set as the physiological state index, wherein a1, a2, and a3 are all preset weight coefficients, and a1, a2, and a3 are all greater than zero.

[0026] The real-time heart rate at time t in the motion period of the current user and the initial heart rate at the start motion time are obtained, t is a natural number greater than zero, the time cumulative load score of the current user is obtained, the time cumulative load score = ln(motion duration), and a value calculated by (real-time heart rate at time t-initial heart rate) / initial heart rate x corresponding preset weight coefficient + time cumulative load score x corresponding preset weight coefficient is set as the fatigue index.

[0027] Preferably, the analysis process of the linkage control module is as follows: the basic physiological data of the current user is called, the initial maximum heart rate threshold of the current user is calculated based on the formula: initial maximum heart rate initial value = 220-age, the comprehensive state index of the current user is called, and a value calculated by initial maximum heart rate threshold x (1-preset correction coefficient x comprehensive state index) is set as the maximum heart rate threshold.

[0028] Preferably, the theoretical heart rate range under the current motion intensity of the user is obtained based on the constructed heart rate-motion intensity correlation model.

[0029] Real-time heart rate of the current user is acquired, and the real-time heart rate is compared with a theoretical heart rate range; if the real-time heart rate is within the theoretical heart rate range, it is determined that the matching degree is normal, if the real-time heart rate is higher than the maximum value in the theoretical heart rate range and does not exceed the maximum heart rate threshold, it is determined that the matching degree is slightly abnormal, then a first-level early warning signal is generated, if the real-time heart rate exceeds the maximum heart rate threshold or is lower than the minimum value in the theoretical heart rate range, it is determined that the matching degree is severely abnormal, then a second-level early warning signal is generated.

[0030] Preferably, the analysis process of the feedback evaluation unit is as follows:

[0031] The historical feedback data of the current user is acquired, and the historical feedback data includes the total number of false alarms, the total number of missed alarms, the average false alarm interval time length and the average missed alarm interval time length;

[0032] It is determined whether the total number of false alarms and the total number of missed alarms exist at least one of continuous false alarms or missed alarms for more than 2 times, if yes, a feedback optimization signal is generated, if no, a regular signal is generated.

[0033] Preferably, when the regular signal is generated, the average false alarm interval time length and the average missed alarm interval time length are determined, if the average false alarm interval time length is less than a preset average false alarm interval time length threshold, and the average missed alarm interval time length is less than a preset average missed alarm interval time length threshold, a mild influence signal is generated, if the average false alarm interval time length is greater than or equal to the preset average false alarm interval time length threshold, or the average missed alarm interval time length is greater than or equal to the preset average missed alarm interval time length threshold, a severe influence signal is generated.

[0034] The beneficial effects of the present application are as follows:

[0035] (1) The present application acquires heart rate data, basic physiological data, current exercise type information and exercise intensity parameters under the corresponding exercise type in the user's exercise, covers the core data related to heart rate, body state and exercise characteristics in the exercise scene, avoids analysis deviation caused by data loss, constructs a heart rate-exercise intensity correlation model based on data processing, ensures that the model has reliable prediction performance for different subgroups, and provides a scientific model basis for personalized exercise intensity evaluation and early warning of different user groups;

[0036] (2) The present application makes the early warning trigger more in line with the actual state of the user through comprehensive evaluation, and facilitates dynamic adjustment of the heart rate threshold according to the real-time physical state and exercise duration of the user, solves the problem of overstrictness in the early stage of exercise and lag in the late stage of exercise of the traditional static threshold, provides accurate judgment basis for subsequent early warning trigger, accurately identifies the heart rate abnormal state through real-time heart rate monitoring + exercise intensity correlation analysis, realizes closed-loop management of accurate judgment-classification early warning-effective response, significantly improves exercise safety, and continuously improves the accuracy and reliability of system early warning, avoids long-term use deviation caused by device performance solidification, and prolongs the system application life cycle. BRIEF DESCRIPTION OF DRAWINGS

[0037] The present application will be further described below in conjunction with the accompanying drawings;

[0038] Fig. 1 is a system flowchart of the present application;

[0039] Fig. 2 is a partial reference diagram of embodiment one of the present application;

[0040] Fig. 3 is a partial reference diagram of embodiment two of the present application. DETAILED DESCRIPTION

[0041] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying 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. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0042] In this document, reference to“an embodiment” means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of one another;

[0043] Embodiment one:

[0044] Please refer to Figs. 1 to 3As shown, the application is a motion heart rate monitoring and intensity linkage early warning system, which comprises a linkage early warning center, a multi-dimensional motion module, a data processing module, a body state evaluation module, a linkage control module, a feedback evaluation unit and a warning execution module, the linkage early warning center is in bidirectional communication connection with the multi-dimensional motion module and the body state evaluation module, the multi-dimensional motion module is in unidirectional communication connection with the data processing module, the data processing module and the body state evaluation module are in unidirectional communication connection with the linkage control module, the linkage control module is in unidirectional communication connection with the warning execution module, the linkage early warning center is in unidirectional communication connection with the feedback evaluation unit, and the feedback evaluation unit is in unidirectional communication connection with the warning execution module;

[0045] The multi-dimensional motion module is used for collecting heart rate data, basic physiological data, current motion type information and motion intensity parameters under corresponding motion types in a user motion period in real time and sending them to the linkage early warning center for storage;

[0046] The heart rate data includes instantaneous heart rate, heart rate change trend and heart rate variability, etc.

[0047] The basic physiological data includes age, gender, maximum heart rate threshold, target heart rate interval, etc.

[0048] The motion type information includes cycling, running, etc.

[0049] The motion intensity parameters include motion speed, motion resistance, motion frequency and motion amplitude, etc.

[0050] The data processing module is used for constructing a heart rate-motion intensity correlation model and accompanying verification feedback analysis, and the specific analysis process is as follows:

[0051] S1: The collected heart rate data, basic physiological data, current motion type information and motion intensity parameters under corresponding motion types are preprocessed to obtain standardized multi-dimensional data, and the preprocessing includes cleaning, enhancement, etc.

[0052] S2: The standardized multi-dimensional data is divided into a training set and a test set according to a preset proportion, and a heart rate-motion intensity correlation model is constructed based on the training set;

[0053] S3: The heart rate-motion intensity correlation model is verified to obtain a verification result (including qualified and unqualified);

[0054] S4: The verification result is discriminated, if the verification is passed, the final heart rate-motion intensity correlation model is obtained, if the verification is not passed, steps S1-S4 are re-executed until the final heart rate-motion intensity correlation model is obtained;

[0055] The heart rate-motion intensity correlation model is sent to the linkage control module for storage;

[0056] Through the above discrimination process, the prediction performance of the model for different subgroups can be accurately evaluated, ensuring that the system can provide reliable heart rate prediction in various user scenarios, providing a scientific basis for exercise intensity adjustment and early warning.

[0057] The targeted verification analysis process is as follows:

[0058] The standardized multi-dimensional data is divided into subgroups according to age (such as under 18 years old, 18-30 years old, 31-45 years old, 46-60 years old, and over 61 years old), exercise type (such as running, cycling, swimming, etc.), exercise ability (primary: exercise frequency <1 time / week, intermediate: exercise frequency 1-3 times / week, advanced: exercise frequency >3 times / week), and health status (healthy population, obese population: BMI ≥28, etc.);

[0059] According to the preset proportion, all sample data of each subgroup is extracted;

[0060] The heart rate-exercise intensity correlation model is input into the heart rate-exercise intensity correlation model to obtain the output predicted heart rate value, and the heart rate mean absolute error M is calculated based on the predicted heart rate value YC and the actual heart rate value SJ;

[0061] That is, M = ∑|SJ-YC| / N, where N is the sample size of the subgroup;

[0062] The heart rate mean absolute error M is discriminated, if there is any subgroup with a heart rate mean absolute error M less than the preset heart rate mean absolute error threshold, it is determined to be unqualified, if there is no subgroup with a heart rate mean absolute error M less than the preset heart rate mean absolute error threshold, it is determined to be qualified;

[0063] Through this verification method of directly inputting subgroup data into the model, the adaptability of the model to specific user groups can be objectively evaluated, avoiding the masking of prediction bias for specific groups due to model averaging, and providing accurate basis for subsequent personalized optimization.

[0064] Embodiment two:

[0065] The physical state evaluation module is used for continuous motion state evaluation analysis of the collected current user's exercise original data, and the specific continuous motion state evaluation analysis process is as follows:

[0066] The current user's exercise original data is obtained, which includes physiological state index, fatigue index, and environmental influence factor (a value obtained by weighted calculation of the difference between the environmental temperature value and the preset reference temperature and the difference between the environmental humidity value and the preset reference humidity);

[0067] That is, (environmental temperature value - preset reference temperature) x corresponding preset weight coefficient + (environmental humidity value - preset reference humidity) x corresponding preset weight coefficient = environmental influence factor;

[0068] The real-time heart rate, resting heart rate, real-time body temperature, normal body temperature and blood oxygen concentration of the current user are obtained, and a value calculated by real-time heart rate / resting heart rate x a1 + (1-blood oxygen concentration) x a2 + (real-time body temperature-normal body temperature) x a3 is set as a physiological state index, wherein a1, a2 and a3 are all preset weight coefficients, and a1, a2 and a3 are all greater than zero.

[0069] The real-time heart rate at time t in the current user's exercise period and the initial heart rate at the start of exercise are obtained, t is a natural number greater than zero, the time cumulative load score of the current user is also obtained, time cumulative load score = ln(exercise duration), and a value calculated by (real-time heart rate at time t-initial heart rate) / initial heart rate x corresponding preset weight coefficient + time cumulative load score x corresponding preset weight coefficient is set as a fatigue index.

[0070] The physiological state index, fatigue index and environmental influence factor are weighted to obtain a comprehensive state index (the higher the comprehensive state index value, the lower the tolerance);

[0071] The comprehensive state index is sent to the linkage warning center for storage;

[0072] That is, physiological state index x preset physiological state index weight coefficient + fatigue index x preset fatigue index weight coefficient + environmental influence factor x preset environmental influence factor weight coefficient = comprehensive state index;

[0073] Through comprehensive evaluation, the warning trigger is more in line with the actual state of the user, and the heart rate threshold can be dynamically adjusted according to the real-time physical state of the user and the exercise duration, solving the problem of excessive strictness in the early stage of exercise and lag in the later stage of exercise of the traditional static threshold, so that the warning is more in line with the actual tolerance of the user;

[0074] The linkage control module is used for real-time comparative analysis of the matching degree of the current real-time heart rate and the theoretical heart rate range, and for judging whether the current real-time heart rate exceeds the maximum heart rate threshold or deviates from the theoretical heart rate interval, and the specific analysis process is as follows:

[0075] SS1: Retrieve the basic physiological data of the current user, calculate the initial maximum heart rate threshold of the current user based on the formula: initial maximum heart rate initial value = 220-age, retrieve the comprehensive state index of the current user, and set the value calculated by initial maximum heart rate threshold x (1-preset correction coefficient x comprehensive state index) as the maximum heart rate threshold;

[0076] SS2: obtaining a theoretical heart rate range of the user under the current exercise intensity based on the constructed heart rate-exercise intensity correlation model;

[0077] SS3: obtaining the real-time heart rate of the current user in real time, comparing the real-time heart rate with the theoretical heart rate range: if the real-time heart rate is within the theoretical heart rate range, determining that the matching degree is normal, if the real-time heart rate is higher than the maximum value in the theoretical heart rate range and does not exceed the maximum heart rate threshold, determining that the matching degree is mildly abnormal, then generating a first warning signal, if the real-time heart rate exceeds the maximum heart rate threshold or is lower than the minimum value in the theoretical heart rate range (indicating insufficient exercise intensity or physical abnormalities), determining that the matching degree is severely abnormal, then generating a second warning signal;

[0078] The warning execution module is used to respond to the first warning signal or the second warning signal, and immediately perform the preset warning operation corresponding to the first warning signal or the second warning signal, for example: if the first warning signal is issued, a running speed reduction voice prompt is accompanied by vibration, and if the second warning signal is issued, a running pause speed voice prompt is accompanied by light flashing;

[0079] It should be noted that the warning degree of the first warning signal is less than that of the second warning signal.

[0080] Through real-time heart rate monitoring and exercise intensity correlation analysis, the heart rate abnormal state is accurately identified, combined with hierarchical linkage adjustment (such as automatic speed reduction, pause exercise) and multi-mode warning, the exercise risk is maximally reduced, and it is especially suitable for middle-aged and old users or exercise population with underlying diseases.

[0081] The feedback evaluation unit is used for warning evaluation feedback analysis on the collected historical feedback data of the user, and the specific warning evaluation feedback analysis process is as follows:

[0082] The historical feedback data of the current user is obtained, and the historical feedback data includes the total number of false alarms, the total number of missed alarms, the average false alarm interval time length, and the average missed alarm interval time length;

[0083] It is determined whether the total number of false alarms and the total number of missed alarms exist at least one of continuous false alarms or missed alarms for more than 2 times, if yes, a feedback optimization signal is generated, if not, a normal signal is generated;

[0084] When the normal signal is generated, the average false alarm interval time length and the average missed alarm interval time length are discriminated and processed, if the average false alarm interval time length is less than a preset average false alarm interval time length threshold, and the average missed alarm interval time length is less than a preset average missed alarm interval time length threshold, a mild influence signal is generated, if the average false alarm interval time length is greater than or equal to the preset average false alarm interval time length threshold, or the average missed alarm interval time length is greater than or equal to the preset average missed alarm interval time length threshold, a severe influence signal is generated;

[0085] The early warning execution module is used for displaying preset early warning words corresponding to the feedback optimization signal or the slight influence signal or the severe influence signal in response to the feedback optimization signal or the slight influence signal or the severe influence signal, so as to make an optimization decision feedback to the current device based on the feedback information, and improve the early warning performance of the current device.

[0086] In summary, the application collects heart rate data, basic physiological data, current exercise type information and exercise intensity parameters under corresponding exercise types in real time, covers core data related to heart rate, body state and exercise characteristics in the exercise scene, avoids analysis deviation caused by data loss, constructs a heart rate-exercise intensity correlation model based on data processing, ensures reliable prediction performance of the model for different subgroups through targeted verification design, provides a scientific model basis for personalized exercise intensity evaluation and early warning of different user groups, and through comprehensive evaluation, the early warning trigger is more suitable for the actual state of the user, and the heart rate threshold can be dynamically adjusted according to the real-time body state and exercise duration, thereby solving the problems of too strict in the initial exercise and lag in the later exercise of the traditional static threshold, providing accurate judgment basis for subsequent early warning triggering, accurately identifying the heart rate abnormal state through real-time heart rate monitoring and exercise intensity correlation analysis, realizing closed-loop management of accurate judgment, graded early warning and effective response, significantly improving exercise safety, and continuously improving the accuracy and reliability of system early warning, avoiding long-term use deviation caused by fixed device performance, and prolonging the system application life cycle.

[0087] The threshold is set for result comparison and analysis to determine whether it is good or bad, and the size of the threshold is determined by combining large model analysis of sample data and artificial experience to set the input storage, and can be appropriately adjusted by seasonal or rational influence conditions;

[0088] The size of the coefficient is a specific numerical value obtained by quantifying each parameter for subsequent comparison, and the size of the coefficient depends on the amount of sample data and the corresponding running coefficient preliminarily set by the person skilled in the art for each group of sample data; as long as the proportional relationship between the parameter and the quantized numerical value is not affected.

[0089] The above is only a preferred specific embodiment of the application, but the protection scope of the application is not limited thereto, and any person skilled in the art can make equivalent replacement or change according to the technical solution and the inventive concept of the application within the technical range disclosed by the application, which should be covered within the protection scope of the application.

Claims

1. A system for monitoring heart rate and intensity of exercise and providing a warning, characterized in that, The system comprises a linkage early warning center, a multidimensional motion module, a data processing module, a physical state evaluation module, a linkage control module, a feedback evaluation unit and an early warning execution module. The multidimensional motion module is configured to collect heart rate data, basic physiological data, current motion type information and motion intensity parameters corresponding to the current motion type during a motion period of a user in real time and send the data to the linkage early warning center for storage. The data processing module is configured to construct a heart rate-motion intensity correlation model and perform verification and feedback analysis. The physical state evaluation module is configured to perform continuous motion state evaluation analysis on the collected motion original data of the user, and perform weighted calculation on the physiological state index, the fatigue index and the environmental influence factor to obtain a comprehensive state index. The linkage control module is configured to compare and analyze the matching degree between the current real-time heart rate and the theoretical heart rate range in real time, determine whether the current real-time heart rate exceeds the maximum heart rate threshold or deviates from the theoretical heart rate range, and output a first-level early warning signal or a second-level early warning signal. The feedback evaluation unit is configured to perform early warning evaluation feedback analysis on the collected historical feedback data of the user to obtain a feedback optimization signal, a mild influence signal or a severe influence signal.

2. The motion heart rate monitoring and intensity linkage warning system according to claim 1, wherein, The analysis process of the data processing module is as follows: S1: preprocessing the collected heart rate data, basic physiological data, current motion type information and motion intensity parameters corresponding to the current motion type to obtain standardized multidimensional data; S2: dividing the standardized multidimensional data into a training set and a test set according to a preset proportion, and constructing a heart rate-motion intensity correlation model based on the training set; S3: performing targeted verification on the heart rate-motion intensity correlation model to obtain a verification result; S4: performing discrimination processing on the verification result, if the verification is passed, obtaining the final heart rate-motion intensity correlation model, if the verification is not passed, re-executing steps S1-S4 until the final heart rate-motion intensity correlation model is obtained.

3. The motion heart rate monitoring and intensity linkage warning system according to claim 2, wherein, The targeted verification analysis process is as follows: The standardized multidimensional data is divided into subgroups according to age, motion type, motion ability and health status; According to a preset proportion, all sample data of each subgroup is extracted; The all sample data of each subgroup is input into the heart rate-motion intensity correlation model to obtain the output predicted heart rate value, and the heart rate average absolute error M is calculated based on the predicted heart rate value YC and the actual heart rate value SJ; The heart rate average absolute error M is discriminated to obtain the discrimination results of unqualified and qualified.

4. The motion heart rate monitoring and intensity linkage warning system according to claim 1, wherein, The analysis process of the physical state evaluation module is as follows: The motion original data of the current user is obtained, which includes the physiological state index, the fatigue index and the environmental influence factor (a value obtained by weighting the difference between the environmental temperature value and the preset reference temperature and the difference between the environmental humidity value and the preset reference humidity); The comprehensive state index is calculated by the physiological state index x preset physiological state index weight coefficient + fatigue index x preset fatigue index weight coefficient + environmental influence factor x preset environmental influence factor weight coefficient.

5. The motion heart rate monitoring and intensity linkage warning system according to claim 4, wherein, Obtaining the real-time heart rate, resting heart rate, real-time body temperature, normal body temperature and blood oxygen concentration of the current user, and setting a value calculated by real-time heart rate / resting heart rate×a1+(1-blood oxygen concentration)×a2+(real-time body temperature-normal body temperature)×a3 as the physiological state index, wherein a1, a2 and a3 are all preset weight coefficients, and a1, a2 and a3 are all greater than zero; Obtaining the real-time heart rate at t time in the current user's exercise period and the initial heart rate at the start time of exercise, t being a natural number greater than zero, and simultaneously obtaining the time cumulative load score of the current user, the time cumulative load score=ln(exercise duration), and setting a value calculated by (real-time heart rate at t time-initial heart rate) / initial heart rate×corresponding preset weight coefficient+time cumulative load score×corresponding preset weight coefficient as the fatigue index.

6. The motion heart rate monitoring and intensity linkage warning system according to claim 1, wherein, The analysis process of the linkage control module is as follows: obtaining the basic physiological data of the current user, calculating the initial maximum heart rate threshold of the current user based on the formula: initial maximum heart rate threshold=220-age, obtaining the comprehensive state index of the current user, and setting a value calculated by initial maximum heart rate threshold×(1-preset correction coefficient×comprehensive state index) as the maximum heart rate threshold.

7. The motion heart rate monitoring and intensity linkage warning system according to claim 6, wherein, Based on the constructed heart rate-exercise intensity correlation model, the theoretical heart rate range under the current exercise intensity of the user is obtained. Real-time heart rate of the current user is obtained in real time, and the real-time heart rate is compared with the theoretical heart rate range: if the real-time heart rate is within the theoretical heart rate range, it is determined that the matching degree is normal, if the real-time heart rate is higher than the maximum value in the theoretical heart rate range and does not exceed the maximum heart rate threshold, it is determined that the matching degree is slightly abnormal, then a first-level warning signal is generated, if the real-time heart rate exceeds the maximum heart rate threshold or is lower than the minimum value in the theoretical heart rate range, it is determined that the matching degree is severely abnormal, then a second-level warning signal is generated.

8. The motion heart rate monitoring and intensity linkage warning system according to claim 1, wherein, The analysis process of the feedback evaluation unit is as follows: Obtaining the historical feedback data of the current user, the historical feedback data including the total number of false alarms, the total number of missed alarms, the average false alarm interval length and the average missed alarm interval length; Discriminating whether the total number of false alarms and the total number of missed alarms exist at least one of continuous false alarms or missed alarms for more than 2 times, if yes, a feedback optimization signal is generated, if no, a regular signal is generated.

9. The motion heart rate monitoring and intensity linkage warning system according to claim 8, wherein, When the regular signal is generated, the average false alarm interval length and the average missed alarm interval length are discriminated, if the average false alarm interval length is less than the preset average false alarm interval length threshold, and the average missed alarm interval length is less than the preset average missed alarm interval length threshold, a mild influence signal is generated, if the average false alarm interval length is greater than or equal to the preset average false alarm interval length threshold, or the average missed alarm interval length is greater than or equal to the preset average missed alarm interval length threshold, a severe influence signal is generated.

Images