Sports service management platform of smart community

Abstract

The invention relates to the technical field, and particularly discloses a sports service management platform of a smart community, comprising: a user identification unit arranged on each training facility and used for identifying a user identity before each training; the database is used for storing basic information of each user; the user data monitoring unit is used for monitoring physiological parameter information of a user in real time; the training data monitoring unit is used for monitoring training information of each training item of the user in real time; the training content recommendation unit is used for recommending the next training item and the corresponding strength thereof according to the basic information of the user and the physiological parameter information and training information of the user in the previous training item; and the early warning unit is used for carrying out early warning on the state of the user according to the basic information of the user and the physiological parameter information and training information of the user in the previous training item. The training process can be dynamically adjusted according to the actual state of the user.

Description

Technical Field

[0001] The present invention relates to the technical field of sports service management, and specifically to a sports service management platform for smart communities. Background Art

[0002] With the development and application of Internet of Things technology and intelligent devices, in the process of sports service management, more and more smart communities adopt digital management platforms. By integrating monitoring terminals on sports facilities, intelligent reservation, equipment intelligent management, social interaction and personalized service processes are realized.

[0003] Among them, in the process of monitoring the user's exercise process, the existing solutions are mainly assisted by professional coaching staff. Through the coaching staff's understanding of the user's state during training and the completion state of training, the training plan is continuously adjusted adaptively to meet the exercise assistance process of different users in different states. When the function of assisted training is assisted by intelligent devices, the existing technology mainly monitors the user's physiological parameters and issues a warning when a certain parameter of the user exceeds the standard range. In this way, abnormalities in the user's exercise process can be detected and warned in time to avoid physical harm caused by improper exercise.

[0004] In the existing sports service management, although the use of intelligent assistance means can monitor the user's state and collect the user's exercise data, compared with professional coaching staff, it cannot realize the function of dynamically adjusting the training process according to the user's actual state. Therefore, how to dynamically adjust the training process according to the user's actual state is one of the fundamental problems to be solved by the present invention. Summary of the Invention

[0005] The purpose of the present invention is to provide a sports service management platform for smart communities, and solve the following technical problems:

[0006] How to dynamically adjust the training process according to the user's actual state.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A sports service management platform for smart communities, comprising:

[0009] A user identification unit, arranged on each training facility, for identifying the user's identity before each training;

[0010] A database, for storing the basic information of each user;

[0011] A user data monitoring unit, for real-time monitoring of the user's physiological parameter information;

[0012] A training data monitoring unit for real-time monitoring of the training information of each training item of the user;

[0013] A training content recommendation unit for recommending the next training item and its corresponding intensity based on the user's basic information, the user's physiological parameter information and training information in the previous training item;

[0014] An early warning unit for warning the user's status based on the user's basic information, the user's physiological parameter information and training information in the previous training item.

[0015] Through the above technical solution, based on the monitoring of the user's training information and physiological parameter information, it is possible to recommend the next training item according to the training information of each training item and the user's physiological parameter information. This recommendation process comprehensively considers the user's physical state and training state factors during the completion of the previous training item. Therefore, it is possible to improve the completion degree and completion effect of training on the premise of ensuring the user's physical health, and give an early warning through the early warning unit when the user's physical state is abnormal, and then timely handle the problems existing in the user's body, realizing the dynamic adjustment of the training process according to the user's actual state.

[0016] Further, the process of the training content recommendation unit recommending the next training item and its corresponding intensity includes:

[0017] Input the user's basic information into the AI model to obtain a preset training plan;

[0018] Determine the body state coefficient and the training completion degree of the previous training item according to the user's physiological parameter information and training information in the previous training item;

[0019] Determine the next training item and its corresponding intensity according to the body state coefficient and the training completion degree of the previous training item.

[0020] Through the above technical solution, it is possible to dynamically recommend subsequent training items to the user according to the user's actual state, and improve the training effect on the premise of ensuring the user's physical health.

[0021] Further, the calculation process of the training completion degree includes:

[0022] Calculate the training completion degree C through formulas (1)-(3);

[0023] C = ρ1 * C Y + ρ2 * C X (1)

[0024]

[0025] Among them, ρ1 and ρ2 are training item judgment coefficients. When the training item is continuous exercise, ρ1 = 0 and ρ2 = 1; when the training item is intermittent exercise, ρ1 = 0 and ρ2 = 0; C Y is the completion degree of intermittent exercise, and C X is the completion degree of continuous exercise; Q is the number of training times, and Q0 is the planned number of training times in the preset training plan. is the average intermittent duration, and t s is the reference amount of intermittent duration in the preset training plan. P is the training intensity level, P0 is the reference training intensity in the preset training plan, and μ1 and μ2 are the first preset adjustment coefficients; t is the duration of continuous exercise, and t0 is the reference amount of continuous exercise in the preset training plan. is the average speed of continuous exercise, Δv is the maximum speed difference of continuous exercise, γ is the correction coefficient, v0 is the reference speed of continuous exercise in the preset training plan, L is the continuous exercise level, L0 is the reference continuous exercise level in the preset training plan, and λ1 and λ2 are the second preset adjustment coefficients.

[0026] Through the above technical solutions, the completion status of the user's training can be quantified. During the quantification process, not only the completion ratio of the main parameters of the training item (such as the time of aerobic training and the number of anaerobic training times) is considered, but also the influences of different exercise intensities, intermittent times, and training speeds are taken into account. Therefore, the obtained training completion degree can more objectively reflect the user's training status.

[0027] Furthermore, the calculation process of the body state coefficient includes:

[0028] The body state coefficient y is calculated through the formula ;

[0029] where m is the number of physiological parameter monitoring items in the physiological parameter information, i is a positive integer and i ∈ [1, m]; χ i is the influence coefficient of the i-th physiological parameter, g i is the value of the i-th physiological parameter, gm i is the critical risk value of the i-th physiological parameter, gt i is the standard reference value of the i-th physiological parameter, gl i is the reference unit amount of the i-th physiological parameter, and x1 and x2 are weight coefficients.

[0030] Through the above technical solutions, the body load status of the user can be judged based on the magnitude of the body state coefficient, and the subsequent training process can be dynamically adjusted according to the magnitude of the body state coefficient. Therefore, the risk of the user's body appearing abnormal in the subsequent training can be reduced.

[0031] Furthermore, the process of the warning unit warning the user's status includes:

[0032] Compare the user's physical state coefficient y with the user's preset critical state threshold interval [yt1, yt2]:

[0033] If y > yt2, give an early warning;

[0034] If y < yt1, do not give an early warning;

[0035] If y ∈ [yt1, yt2], determine whether to give an early warning according to the user's historical training items and the corresponding completion degrees.

[0036] Through the above technical solution, it is possible to realize the judgment of early warning by the early warning center.

[0037] Furthermore, the process of determining whether to give an early warning when y ∈ [yt1, yt2] includes:

[0038] Through the formula Calculate the cumulative training amount R;

[0039] Compare R with the user's training threshold Rt:

[0040] If R < Rt, give an early warning;

[0041] Where n is the user's historical training items, j is a positive integer and j ∈ [1, n], K j is the cumulative training amount of the jth item, C j is the training completion degree of the jth item, tp j is the time difference between the training completion time of the jth item and the current time point, and f is a preset attenuation function, which is a decreasing function.

[0042] Through the above technical solution, it is possible to more accurately judge the physical state and reduce problems such as misjudgment and missed judgment.

[0043] Furthermore, the process of determining the next training item and its corresponding intensity according to the physical state coefficient and the training completion degree of the previous training item includes:

[0044] When y < yt1, compare the training completion degree C with the completion degree threshold C1:

[0045] If C < C1, recommend the next training item as a training item of the same type as the previous training item, and determine the corresponding intensity of the next training item according to the size of C1 - C;

[0046] If C ≥ C1, recommend the next training item according to the preset training plan;

[0047] When y ∈ [yt1, yt2] and no early warning has been given, recommend the next training item according to the preset training plan;

[0048] If the warning unit issues a warning, the training process will be stopped.

[0049] Through the above technical solution, it is possible to dynamically adjust the training process according to the training completion degree of each training item of the user and the physical state coefficient, and improve the training completion degree and completion effect on the premise of ensuring that the user's body is in a healthy state.

[0050] Furthermore, the basic information includes the user's age, gender, BMI, medical history information, and historical training information;

[0051] The physiological parameter monitoring items include heart rate, blood oxygen saturation, body temperature, and blood pressure.

[0052] Through the above technical solution, it is possible to provide a relatively accurate reference basis in the process of generating the preset training plan. At the same time, the physiological parameter detection items can be monitored through smart wearable devices during the training process and can reflect the user's physical state, which has better implementability.

[0053] Advantages of the present invention:

[0054] (1) Based on the monitoring of the user's training information and physiological parameter information, the present invention can recommend the next training item according to the training information of each training item and the user's physiological parameter information. This recommendation process comprehensively considers the user's physical state and training state factors during the completion process of the previous training item. Therefore, it is possible to improve the training completion degree and completion effect on the premise of ensuring that the user's body is in a healthy state, and issue a warning through the warning unit when the user's physical state is abnormal, so as to timely handle the problems existing in the user's body and realize the dynamic adjustment of the training process according to the actual state of the user.

[0055] (2) Through the calculation process of the training completion degree, the present invention can quantify the completion state of the user's training. And in the quantification process, not only the completion ratio of the main parameters of the training item (such as the time of aerobic training and the number of anaerobic training) is considered, but also the influence of factors such as different exercise intensities, intermittent times, and training speeds is considered. Therefore, the obtained training completion degree can more objectively reflect the user's training situation; through the calculation process of the user's physical state coefficient, it is possible to judge the user's body load state according to the size of the physical state coefficient and dynamically adjust the subsequent training process according to the size of the physical state coefficient, so as to reduce the risk of the user's body appearing abnormal in the subsequent training. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The present invention will be further described below with reference to the accompanying drawings.

[0057] Figure 1 It is the logic block diagram of the sports service management platform of the intelligent community of the present invention. Detailed implementation manners

[0058] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0059] Please refer to Figure 1 As shown, in one embodiment, a sports service management platform for a smart community is provided, including a user identification unit, a database, a user data monitoring unit, a training data monitoring unit, a training content recommendation unit, and an early warning unit. Among them, the database stores the basic information of each user, including the user's age, gender, height, weight, medical record information, etc. By obtaining the basic information, it can be used as a reference when formulating a training plan later, and then a suitable training plan can be determined according to the user's physical condition. In addition, the user identification unit is used to identify the user's identity before each training. It is set on each training facility and can identify the user through face recognition or user ID card recognition, etc., so as to facilitate obtaining the user's training information. The user data monitoring unit is used to monitor the user's physiological parameter information in real time. It can obtain the common real-time monitorable physiological parameters of the user by setting a bracelet on the user's arm. The training data monitoring unit is used to monitor the training information of each training item of the user in real time. It can communicate directly with the intelligent terminal set on the training facility to monitor the training information of each training item of the user. Then, the training content recommendation unit recommends the next training item and its corresponding intensity according to the user's basic information, the user's physiological parameter information and training information in the previous training item, and the early warning unit warns the user's state according to the user's basic information, the user's physiological parameter information and training information in the previous training item. Through the above technical solutions, based on the monitoring of the user's training information and physiological parameter information, the next training item can be recommended according to the training information of each training item and the user's physiological parameter information. This recommendation process comprehensively considers the user's physical state and training state factors during the completion of the previous training item. Therefore, it can improve the completion degree and completion effect of training on the premise of ensuring the user's physical health, and warn through the early warning unit when the user's physical state is abnormal, so as to timely handle the problems existing in the user's body and realize the dynamic adjustment of the training process according to the user's actual state.

[0060] In one embodiment, a process for a training content recommendation unit to recommend the next training item and its corresponding intensity is provided, including: inputting the user's basic information into the AI model to obtain a preset training plan. The AI model can be selected according to the accuracy of the test data. Then, determine the body state coefficient and the training completion degree of the previous training item based on the user's physiological parameter information and training information in the previous training item. The body state coefficient reflects the body load state of the user during the training process, and the training completion degree reflects the degree of meeting the exercise standards of the user during the previous training item. Therefore, determining the next training item and its corresponding intensity based on the body state coefficient and the training completion degree of the previous training item can dynamically recommend subsequent training items according to the actual state of the user, and improve the training effect on the premise of ensuring the user's body is in a healthy state.

[0061] In one embodiment, a calculation process for the training completion degree is provided, including: calculating the training completion degree C through formulas (1)-(3);

[0062] C = ρ1 * C Y + ρ2 * C X (1)

[0063]

[0064] Among them, the training process is divided into continuous exercise and intermittent exercise. Continuous exercise is aerobic exercise. The training completion degree model provided in this embodiment is applicable to common aerobic exercise facilities, such as treadmills, elliptical machines, spinning bikes, etc.; intermittent exercise is anaerobic exercise. The training completion degree model provided in the embodiment is applicable to common pushing and pulling strength training equipment. ρ1 and ρ2 in the formula are training item judgment coefficients. When the training item is continuous exercise, only continuous exercise factors are considered, so ρ1 = 0 and ρ2 = 1; when the training item is intermittent exercise, only intermittent exercise factors are considered, so ρ1 = 1 and ρ2 = 1; C Y is the intermittent exercise completion degree, C X is the continuous exercise completion degree; Q is the number of training times, Q0 is the planned number of training times in the preset training plan, is the average intermittent duration, t s is the intermittent duration reference quantity in the preset training plan, P is the training intensity level, P0 is the reference training intensity in the preset training plan, μ1 and μ2 are the first preset adjustment coefficients, and the first preset adjustment coefficients are obtained by fitting the test data of different training items; t is the continuous exercise duration, t0 is the continuous exercise reference quantity in the preset training plan, For the continuous motion average speed, Δv is the maximum speed difference of continuous motion, γ is the correction coefficient, which is obtained by fitting the test data of different types of training items, v0 is the reference quantity of continuous motion speed in the preset training plan, L is the continuous motion level, L0 is the reference continuous motion level in the preset training plan, λ1 and λ2 are the second preset adjustment coefficients, which are obtained by fitting the test data of different training items. Therefore, through the calculation process of the above formula, the completion status of the user's training can be quantified. And in the quantification process, not only the completion ratio of the main parameters of the training item (such as the time of aerobic training and the number of anaerobic training) is considered, but also the influence of factors such as different exercise intensities, intermittent times, and training speeds is considered. Furthermore, the training completion degree obtained can more objectively reflect the user's training status.

[0065] In one embodiment, a calculation process of a body state coefficient is given, including: through the formula calculate to obtain the body state coefficient y; where m is the number of physiological parameter monitoring items in the physiological parameter information, i is a positive integer and i ∈ [1, m]; χ i is the influence coefficient of the i-th physiological parameter, and the influence coefficient is set according to the authority of different physiological parameters, g i is the value of the i-th physiological parameter, gm i is the critical risk value of the i-th physiological parameter, gt i is the standard reference value of the i-th physiological parameter, gl i is the reference unit quantity of the i-th physiological parameter, where the critical risk value, standard reference value, and reference unit quantity are all set according to the user's basic information and empirical data of the corresponding physiological parameters, which will not be elaborated here. x1 and x2 are weight coefficients, which are set by fitting empirical data. Through the above calculation process of the user's body state coefficient, the body load state of the user can be judged by the size of the body state coefficient, and the subsequent training process can be dynamically adjusted according to the size of the body state coefficient. Furthermore, the risk of the user's body appearing abnormal can be reduced in the subsequent training.

[0066] In one embodiment, the process of the warning unit warning the user status is given, including: comparing the user's physical state coefficient y with the user's preset critical state threshold range [yt1, yt2], where the user's preset critical state threshold range [yt1, yt2] is set by fitting based on empirical data. If y > yt2, it indicates that the user's physiological parameters exceed the normal standard too much, so a warning is issued. If y < yt1, it indicates that the user's physiological parameters are within the normal standard, so no warning is issued. If y ∈ [yt1, yt2], it indicates that the user's physiological parameters slightly exceed the normal standard, so further judgment is needed, that is, to judge whether to give a warning according to the user's historical training items and the corresponding completion degrees. The process of judging whether to give a warning when y ∈ [yt1, yt2] includes:

[0067] Calculate the training cumulative amount R through the formula where n is the user's historical training items, j is a positive integer and j ∈ [1, n], K j is the training cumulative amount of the j-th item, C j is the training completion degree of the j-th item, tp j is the time difference between the training completion time of the j-th item and the current time point, f is a preset attenuation function, which is a decreasing function and satisfies f < 1, and is set by fitting according to test data. By calculating the training cumulative amount R, it is possible to judge the rationality of the slightly higher physical state coefficient y according to the size of the training cumulative amount R. When the training cumulative amount R is large, it indicates that the slightly higher physical state coefficient y is caused by a higher training volume, so it indicates that the physical state coefficient y is not abnormal. When the training cumulative amount R is small, it indicates that the slightly higher situation of the physical state coefficient y is not caused by a higher training volume, so it indicates that there is a health risk to the body. Therefore, by comparing R with the user's training threshold Rt, where the user's training threshold Rt is set according to empirical data, if R < Rt, a warning is issued. Through the above process, it is possible to more accurately judge the physical state and reduce problems such as misjudgment and missed judgment.

[0068] In addition, this embodiment gives a process for determining the next training item and its corresponding intensity according to the physical state coefficient and the training completion degree of the previous training item, including:

[0069] When y < yt1, it indicates that the user's physical condition is relatively good. Therefore, it is necessary to ensure the user's training volume. At this time, the training completion degree C is compared with the completion degree threshold C1, and the completion degree threshold C1 is set according to empirical data. Therefore, when C < C1, it means that the completion degree of the user's previous training item is insufficient. Then, the next training item is recommended as a training item of the same type as the previous training item, and the corresponding intensity of the next training item is determined according to the size of C1 - C. When C ≥ C1, it means that the user has completed the previous training item. Therefore, the next training item is recommended according to the preset training plan; when y ∈ [yt1, yt2] and no warning is issued, it means that the user's physical condition is in a high-load state. Therefore, it is not suitable for the current training process. Then, the next training item is recommended according to the preset training plan; if the warning unit issues a warning, the training process is stopped. Through the above process, the training process can be dynamically adjusted according to the training completion degree of each training item of the user and the physical condition coefficient, and the training completion degree and completion effect can be improved on the premise of ensuring the user's physical health.

[0070] In one embodiment, the basic information includes the user's age, gender, BMI, medical record information, and historical training information. The above basic information can provide a relatively accurate reference basis in the generation process of the preset training plan; the physiological parameter monitoring items include heart rate, blood oxygen saturation, body temperature, and blood pressure. The above physiological parameter detection items can be monitored by intelligent wearable devices during the training process and can reflect the user's physical condition, with relatively good implementability.

[0071] The above has described a detailed description of an embodiment of the present invention, but the content described is only a preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. A sports service management platform for a smart community, characterized in that, including: a user identification unit, which is set on each training facility and is used to identify the user's identity before each training; a database, which is used to store the basic information of each user; a user data monitoring unit, which is used to monitor the user's physiological parameter information in real time; a training data monitoring unit, which is used to monitor the training information of each training item of the user in real time; a training content recommendation unit, which is used to recommend the next training item and its corresponding intensity according to the user's basic information, the user's physiological parameter information and training information in the previous training item; a warning unit, which is used to give a warning about the user's state according to the user's basic information, the user's physiological parameter information and training information in the previous training item.

2. The sports service management platform of an intelligent community according to claim 1, characterized in that The process of the training content recommendation unit recommending the next training item and its corresponding intensity includes: inputting the user's basic information into the AI model to obtain a preset training plan; determining the body state coefficient and the training completion degree of the previous training item according to the user's physiological parameter information and training information in the previous training item; determining the next training item and its corresponding intensity according to the body state coefficient and the training completion degree of the previous training item.

3. The sports service management platform for an intelligent community according to claim 2, characterized in that, The calculation process of the training completion degree includes: calculating the training completion degree C through formulas (1)-(3); C = ρ1 * C Y + ρ2 * C X (1) Among them, ρ1 and ρ2 are training item judgment coefficients. When the training item is continuous exercise, ρ1 = 0 and ρ2 = 1; when the training item is intermittent exercise, ρ1 = 1 and ρ2 = 0; C Y is the completion degree of intermittent exercise, C X is the completion degree of continuous exercise; Q is the number of training sessions, Q0 is the planned number of training sessions in the preset training plan, is the average intermittent duration, t s is the reference intermittent duration in the preset training plan, P is the training intensity level, P0 is the reference training intensity in the preset training plan, μ1 and μ2 are the first preset adjustment coefficients; t is the duration of continuous exercise, t0 is the reference continuous exercise amount in the preset training plan, is the average speed of continuous exercise, Δv is the maximum speed difference of continuous exercise, γ is the correction coefficient, v0 is the reference continuous exercise speed in the preset training plan, L is the continuous exercise level, L0 is the reference continuous exercise level in the preset training plan, λ1 and λ2 are the second preset adjustment coefficients.

4. The sports service management platform for a smart community according to claim 3, characterized in that, The calculation process of the body state coefficient includes: Obtained through the formula Calculate to obtain the physical state coefficient y; Among them, m is the number of physiological parameter monitoring items in the physiological parameter information, i is a positive integer and i ∈ [1, m]; χ i is the influence coefficient of the i-th physiological parameter, g i is the value of the i-th physiological parameter, gm i is the critical risk value of the i-th physiological parameter, gt i is the standard reference value of the i-th physiological parameter, gl i is the reference unit quantity of the i-th physiological parameter, and x1, x2 are weight coefficients.

5. The sports service management platform of an intelligent community according to claim 4, characterized in that, The process of the warning unit warning about the user's state includes: comparing the user's body state coefficient y with the user's preset critical state threshold interval [yt1, yt2]: if y > yt2, then give a warning; if y < yt1, then do not give a warning; if y ∈ [yt1, yt2], then judge whether to give a warning according to the user's historical training items and corresponding completion degrees.

6. The sports service management platform of an intelligent community according to claim 5, characterized in that, The process of judging whether to give a warning when y ∈ [yt1, yt2] includes: Obtained by the formula Calculate the training cumulative amount R; comparing R with the user's training threshold Rt: if R < Rt, then give a warning; Among them, n is the user's historical training item, j is a positive integer and j ∈ [1, n], K j is the cumulative training volume of the j-th item, C j is the training completion degree of the j-th item, tp j is the time difference between the training completion time of the j-th item and the current time point, and f is a preset attenuation function, which is a decreasing function.

7. The sports service management platform of an intelligent community according to claim 6, characterized in that The process of determining the next training item and its corresponding intensity according to the body state coefficient and the training completion degree of the previous training item includes: when y < yt1, comparing the training completion degree C with the completion degree threshold C1: if C < C1, then recommend the next training item as a training item of the same type as the previous training item, and determine the corresponding intensity of the next training item according to the size of C1 - C; if C ≥ C1, then recommend the next training item according to the preset training plan; when y ∈ [yt1, yt2] and no warning is given, then recommend the next training item according to the preset training plan; if the warning unit gives a warning, then stop the training process.

8. The sports service management platform for a smart community according to claim 7, characterized in that, The basic information includes the user's age, gender, BMI, medical record information and historical training information; The physiological parameter monitoring items include heart rate, blood oxygen saturation, body temperature and blood pressure.

Images