Exercise training course scoring method based on big data

Abstract

The invention relates to the technical field of big data analysis, in particular to an exercise training course scoring method based on big data, and the method comprises the steps: S1, collecting exercise data, target data and environment data of a user; s2, analyzing a target completion index of the user; s3, analyzing the physiological adaptation state of the user, and constructing a physiological adaptation index according to the physiological adaptation state of the user; s4, the environmental parameters are analyzed, the construction process of the physiological adaptation index is adjusted according to the environmental parameters, and the altitude collected in the monitoring period is the altitude collected at the end of the monitoring period; s5, analyzing gait features of the user; and S6, evaluating the motion state according to the analysis result of the target completion index, the construction result of the physiological adaptation index, the analysis result of the environmental parameters and the analysis result of the gait characteristics of the user in the monitoring period. The scoring efficiency of the exercise training course is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis, and in particular to a sports training course scoring method based on big data. Background Art

[0002] In recent years, with the improvement of health awareness and the development of science and technology, more and more sports enthusiasts have begun to pay attention to scientific training methods. Traditional sports training evaluation methods often rely on experience, lack of systematicity and scientificity, and cannot provide real-time feedback on the user's training status. Especially in endurance sports such as running, adaptability evaluation and data analysis are particularly important. In order to solve this problem, analysis methods based on big data have emerged. Through the widespread use of smart wearable devices, users can obtain multi-dimensional data on sports, body and environment in real time. This provides a foundation for the further development of sports science and promotes the formulation of personalized training plans.

[0003] Chinese patent publication number CN113449945A discloses a sports course scoring method and system, the sports course scoring method includes: playing a course film, obtaining the coach motion data of the corresponding course film, and obtaining the coach pane from the coach motion data; obtaining the student motion data through an inertial measurement unit, and obtaining the student pane from the student motion data, wherein the length of the student pane is greater than the length of the coach pane; finding the student segment in the student pane that is most similar to the coach pane; for the first type of exercise, calculating the exercise score according to the stability of the student segment and the coach pane; and for the second type of exercise, using a deduction mechanism and calculating the exercise score according to the difference between the student segment and the coach pane. In this way, different scoring methods are used for different types of exercise, so that the exercise score can be calculated more appropriately; it can be seen that when the scheme is used to score the sports course, the sports data in a complex environment is not analyzed, and there is a problem of low efficiency in sports course scoring. Summary of the invention

[0004] The object of the present invention is to provide a sports training course scoring method based on big data to solve at least one of the problems existing in the prior art.

[0005] To achieve the above object, the present invention adopts the following technical solutions: A sports training course scoring method based on big data, comprising: Step S1, collecting the user's motion data, target data and environment data; Step S2, analyzing the user's goal completion index based on the user's running distance, cumulative climb, average pace and goal data collected during the monitoring period; Step S3, constructing a heart rate index according to the user's heart rate collected during the monitoring period, constructing a recovery index according to the collected user's exercise recovery time, analyzing the user's physiological adaptation state according to the construction results of the heart rate index and the recovery index, and constructing a physiological adaptation index according to the user's physiological adaptation state; Step S4, analyzing environmental parameters according to the ambient temperature and altitude collected during the monitoring period, and adjusting the construction process of the physiological adaptation index according to the environmental parameters; Step S5, analyzing the user's gait characteristics according to the user's stride length and user's stride frequency collected during the monitoring period; Step S6, evaluating the motion state according to the analysis results of the user's goal completion index, the construction results of the physiological adaptation index, the analysis results of the environmental parameters and the analysis results of the gait characteristics during the monitoring period, and adjusting the motion state evaluation process according to the user's body movement amplitude collected during the monitoring period.

[0006] Furthermore, in step S2, when analyzing the target completion index, the user's running distance a0 collected during the monitoring period is compared with the target distance a1 to analyze the distance completion index; In the step S2, the user's cumulative climb b0 collected during the monitoring period is compared with the target climb b1 to analyze the climb completion index; In the step S2, the user pace c0 collected during the monitoring period is compared with the target pace c1 to analyze the pace completion index; In step S2, the target completion index is analyzed according to the analysis results of the distance completion index, the climbing completion index and the pace completion index to obtain the target completion index W.

[0007] Furthermore, the method for constructing the physiological adaptation index in step S3 includes: Step S31, constructing a heart rate index according to the user's heart rate collected during the monitoring period; Step S32, constructing a recovery index according to the collected user exercise recovery time; Step S33, analyzing the user's physiological adaptation state according to the construction results of the heart rate index and the recovery index, and constructing a physiological adaptation index according to the user's physiological adaptation state; The specific process of constructing the physiological adaptation index in step S33 is as follows: If XQ1×heart rate index+XQ2×recovery index≤u0, the user's physiological adaptation state is determined to be abnormal, and the physiological adaptation index is set to SS1; otherwise, the user's physiological adaptation state is determined to be normal, and the physiological adaptation index is set to SS2; Among them, XQ1 is the heart rate weight, XQ2 is the recovery time weight, and u0 is the preset physiological state threshold.

[0008] Furthermore, in step S4, when analyzing environmental parameters, the altitude h0 collected during the monitoring period is compared with the preset altitude h1 to obtain the altitude parameter; In step S4, the environmental parameter HC is analyzed according to the altitude parameter and the environmental temperature T0 collected during the monitoring period, and the construction process of the physiological adaptation index is adjusted according to the environmental parameter HC, and the adjusted preset physiological state threshold is set to u1.

[0009] Furthermore, the gait feature analysis method in step S5 includes: Step S51, analyzing the user's stride parameters according to the user's stride collected during the monitoring period; Step S52, analyzing the user's step frequency parameters according to the user's step frequency collected during the monitoring period; Step S53: analyzing the user's gait characteristics according to the user's stride length parameter and stride frequency parameter during the monitoring period.

[0010] Furthermore, when analyzing the user's stride parameters, step S51 compares the user's stride collected during the monitoring period with the preset stride f0 to analyze the abnormality of the user's stride, and analyzes the user's stride parameter BF based on the analysis result of the abnormality of the user's stride during the monitoring period.

[0011] Furthermore, in step S52, when analyzing the user's step frequency parameter, the user's step frequency collected during the monitoring period is compared with the preset step frequency p0 to analyze the abnormality of the user's step frequency, and the user's step frequency parameter BP is analyzed according to the analysis result of the abnormality of the user's step frequency during the monitoring period; The step S53 analyzes the user's gait characteristics according to the user's stride parameters and cadence parameters during the monitoring period, and sets the user's gait characteristics as BT.

[0012] Furthermore, the motion state evaluation method in step S6 includes: Step S61, evaluating the motion state according to the analysis results of the user's goal completion index, the construction results of the physiological adaptation index, the analysis results of the environmental parameters and the analysis results of the gait characteristics within the monitoring period; Step S62, analyzing the abnormality of the user's body movement amplitude according to the user's body movement amplitude collected during the monitoring period, and adjusting the motion state evaluation process according to the abnormality of the user's body movement amplitude; Step S63, analyzing the fluctuation state of the user's body movement amplitude according to the user's body movement amplitude collected during the monitoring period, and adjusting the analysis process of the abnormality of the user's body movement amplitude according to the fluctuation state of the user's body movement amplitude; The specific process of evaluating the motion state in step S61 is as follows: If g1×W+g2×physiological adaptation index-g3×BT≤E1, the user's exercise state in the current monitoring period is judged to be poor; If E1<g1×W+g2×physiological adaptation index-g3×BT<E2, it is determined that the user's exercise state in the current monitoring period is normal; If g1×W+g2×physiological adaptation index-g3×BT≥E2, the user's exercise status in the current monitoring period is determined to be excellent; Among them, g1 is the goal completion weight, g2 is the physiological adaptation weight, g3 is the gait weight, E1 is the first preset state threshold, and E2 is the second preset state threshold.

[0013] Furthermore, in the step S62, when analyzing the abnormality of the user's body movement amplitude, the average value of the user's body movement amplitude collected during the monitoring period is set to Dp, and the average value Dp of the user's body movement amplitude collected during the monitoring period is compared with the preset amplitude threshold d0 to adjust the motion state evaluation process. If the average value of the user's body movement amplitude collected during the monitoring period does not meet the threshold, the first preset state threshold is adjusted to E1', and the second preset state threshold is adjusted to E2'.

[0014] Furthermore, the step S63 constructs a fluctuation coefficient BD according to the user's body movement amplitude collected during the monitoring period, and compares the fluctuation coefficient BD with a preset fluctuation threshold by to analyze the fluctuation state of the user's body movement amplitude, the fluctuation state includes normal and abnormal, if the fluctuation state of the user's body movement amplitude is abnormal, the preset amplitude threshold is adjusted to d0'.

[0015] The beneficial effects of the present invention are as follows: by comprehensively collecting the user's motion data, target data and environmental data, the training effect is evaluated from multiple dimensions, and the user's personalized exercise experience is promoted. The method calculates the target completion index and the physiological adaptation index, and provides real-time feedback on the user's training status, helping them to implement a scientific and efficient training plan. In addition, the dynamic adjustment mechanism based on the body movement amplitude further improves the accurate evaluation of the motion status, provides users with timely and effective suggestions, and significantly improves the scoring efficiency of sports courses. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 It is a flowchart of the sports training course scoring method based on big data in this embodiment.

[0018] Figure 2 Schematic diagram of the process of constructing the physiological adaptation index of this embodiment.

[0019] Figure 3 Schematic diagram of the flow of the gait feature analysis method of this embodiment.

[0020] Figure 4 Schematic diagram of the flow of the motion state evaluation method of this embodiment. DETAILED DESCRIPTION

[0021] In order to more clearly illustrate the present invention, the present invention is further described below in conjunction with preferred embodiments and accompanying drawings. Similar components in the accompanying drawings are represented by the same reference numerals. It should be understood by those skilled in the art that the content specifically described below is illustrative rather than restrictive, and should not be used to limit the scope of protection of the present invention.

[0022] It should be noted that, although the terms first, second, third, etc. may be used to describe in the embodiments of the present application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0023] See also Figure 1 As shown, it is a flow chart of the sports training course scoring method based on big data in this embodiment, and the method includes: Step S1, collecting the user's motion data, target data and environmental data, the motion data including running distance, cumulative ascent, average pace, user heart rate, user stride, user step frequency, user motion recovery time and user body movement amplitude, the cumulative ascent is the total cumulative uphill climbing distance, the user motion recovery time is the time required for the user's heart rate to return to normal after completing an exercise training, the user's body movement amplitude is the movement amplitude of the user's body in the vertical direction during running, the target data includes target distance, target pace and target ascent, and the environmental data includes altitude and ambient temperature; in this embodiment, no specific limitation is made on the collection method of the user's motion data, target data and environmental data, and those skilled in the art can freely set it, as long as the collection requirements of the user's motion data, target data and environmental data are met, wherein the user's motion data and environmental data can be collected through smart wearable devices, and the target data can be collected through user interaction.

[0024] Please continue reading Figure 1 As shown, the sports training course scoring method based on big data also includes: Step S2, analyzing the user's goal completion index based on the user's running distance, cumulative ascent, average pace and goal data collected during the monitoring period.

[0025] Specifically, in step S2 of this embodiment, when analyzing the target completion index, the user's running distance a0 collected during the monitoring period is compared with the target distance a1 to analyze the distance completion index to quantify the completion of the exercise distance. If a0<a1, the distance completion index is set to JW1, and JW1=1-(a1-a0) / a1; if a0≥a1, the distance completion index is set to JW2, and JW2=1; The user's cumulative climb b0 collected during the monitoring period is compared with the target climb b1 to analyze the climb completion index to quantify the completion of the climb distance. If b0 < b1, the climb completion index is set to PW1, and PW1 is set to 1-(b1-b0) / b1; if b0 ≥ b1, the climb completion index is set to PW2, and PW2 is set to 1; The user pace c0 collected during the monitoring period is compared with the target pace c1 to analyze the pace completion index to quantify the pace completion. If c0≤c1, the pace completion index is set to SW1, setting: SW1=1-(c1-c0) / c1; if c0>c1, the pace completion index is set to SW2, setting: SW2=1; According to the analysis results of the distance completion index, the climbing completion index and the pace completion index, the target completion index W is analyzed to quantify the target completion degree, and the setting is: W=x1×distance completion index+x2×climbing completion index+x3×pace completion index; by constructing the distance completion index, the climbing completion index and the pace completion index to quantify the target completion degree, data support is provided for the sports state evaluation, thereby improving the efficiency of sports training scoring; Among them, x1 is the distance weight, x2 is the climbing weight, x3 is the pace weight, and x1+x2+x3=1.

[0026] It can be understood that the present embodiment does not specifically limit the setting of each weight, and those skilled in the art can freely set it as long as the setting requirements of each weight are met, among which the best value of x1 is 0.3, the best value of x2 is 0.3, and the best value of x3 is 0.4.

[0027] Specifically, the monitoring period described in this embodiment is the time it takes for a user to complete a training session.

[0028] Please continue reading Figure 1 As shown, the sports training course scoring method based on big data also includes: Step S3, constructing a heart rate index based on the user's heart rate collected during the monitoring period, constructing a recovery index based on the collected user's exercise recovery time, analyzing the user's physiological adaptation state based on the construction results of the heart rate index and the recovery index, and constructing a physiological adaptation index based on the user's physiological adaptation state.

[0029] See also Figure 2 As shown, it is a schematic diagram of the process of constructing the physiological adaptation index of this embodiment, including: Step S31, constructing a heart rate index according to the user's heart rate collected during a monitoring period.

[0030] Specifically, in step S31 of this embodiment, when constructing the heart rate index, the user heart rate data collected during the monitoring period are sorted in descending order, and the maximum value of the user's heart rate is recorded as Lmax. If |Lp-k1×Lmax| / (k1×Lmax)≤α, the heart rate index is set to XL1, and XL1=1 is set; if |Lp-k1×Lmax| / (k1×Lmax)>α, the heart rate index is set to XL2, and XL2=1-|Lp-k1×Lmax| / (k1×Lmax)+α; by standardizing the calculation of the heart rate data, the accuracy of the physiological adaptation state analysis is improved, thereby improving the efficiency of the sports training scoring; Wherein, k1 is the preset proportional coefficient, α is the preset offset coefficient, Lp is the average value of the user's heart rate collected during the monitoring period, , Li is the i-th user heart rate data collected during the monitoring period, and I is the number of user heart rate data collected during the monitoring period.

[0031] It can be understood that the present embodiment does not specifically limit the setting of the preset proportional coefficient and the preset offset coefficient, and those skilled in the art can freely set them as long as the setting requirements of the preset proportional coefficient and the preset offset coefficient are met, where the optimal value of k1 is 0.8, and the optimal value of α is 0.1.

[0032] Please continue reading Figure 2 As shown, the physiological adaptation index construction method also includes: Step S32: construct a recovery index according to the collected user exercise recovery time.

[0033] Specifically, in step S32 of this embodiment, when constructing the recovery index, the collected user exercise recovery time t0 is compared with the preset time t1. If t0≤t1, the recovery index is set to HF1, and HF1=1 is set; if t0>t1, the recovery index is set to HF2, and HF2=1-lg[3×(t0-t1) / t1+1] is set; through the quantitative analysis of the recovery time, the physical recovery state after training is quantitatively evaluated to improve the accuracy of the physiological adaptation state analysis, thereby improving the efficiency of the sports training scoring.

[0034] It is understandable that the present embodiment does not specifically limit the setting of the preset time length, and those skilled in the art can freely set it as long as the setting requirements of the preset time length are met, wherein the best value of t1 is 360 seconds.

[0035] Please continue reading Figure 2 As shown, the physiological adaptation index construction method also includes: Step S33: Analyze the user's physiological adaptation state according to the construction results of the heart rate index and the recovery index, and construct a physiological adaptation index according to the user's physiological adaptation state.

[0036] Specifically, the specific process of constructing the physiological adaptation index in step S33 of this embodiment is as follows: If XQ1×heart rate index+XQ2×recovery index≤u0, the user's physiological adaptation state is judged to be abnormal, and the physiological adaptation index is set to SS1, and SS1=exp{x1×heart rate index+x2×recovery index-u0}; otherwise, the user's physiological adaptation state is judged to be normal, and the physiological adaptation index is set to SS2, and SS2=1; the physiological adaptation index is constructed by combining the heart rate index and the recovery index to improve the accuracy of the user's physiological adaptability state analysis, thereby improving the efficiency of sports training scoring; Among them, XQ1 is the heart rate weight, XQ2 is the recovery time weight, XQ1+XQ2=1, and u0 is the preset physiological state threshold.

[0037] It can be understood that, in this embodiment, there is no specific limitation on the setting of each weight and preset physiological state threshold, and those skilled in the art can set it freely, as long as the setting requirements of each weight and preset physiological state threshold are met, among which, the optimal value of XQ1 is 0.6, the optimal value of XQ2 is 0.4, and the optimal value of u0 is 0.75.

[0038] Please continue reading Figure 1 As shown, the sports training course scoring method based on big data also includes: Step S4, analyzing environmental parameters according to the ambient temperature and altitude collected during the monitoring period, and adjusting the construction process of the physiological adaptation index according to the environmental parameters, wherein the altitude collected during the monitoring period is the altitude collected at the end of the monitoring period.

[0039] Specifically, in step S4 of this embodiment, when analyzing environmental parameters, the altitude h0 collected during the monitoring period is compared with the preset altitude h1 to obtain an altitude parameter: if h0≤h1, the altitude parameter is set to H1, and H1=0; otherwise, the altitude parameter is set to H2, and H2=exp[3×(h0-h1) / h1-3]; Analyze the environmental parameter HC according to the altitude parameter and the ambient temperature T0 collected during the monitoring period, and set HC=y1×|T0-T1| / (T0+T1)+y2×altitude parameter; The construction process of the physiological adaptation index is adjusted according to the environmental parameter HC, and the adjusted preset physiological state threshold is set as u1, and u1=u0×[1-β×ln(HC+1)] is set; the physiological adaptation index is adaptively adjusted by analyzing the environmental parameters according to the ambient temperature and the altitude, thereby improving the accuracy of the physiological adaptation index analysis, thereby improving the accuracy of the sports training score; Among them, y1 is the temperature weight, y2 is the altitude weight, y1+y2=1, T1 is the preset temperature threshold, and β is the preset adjustment ratio.

[0040] It can be understood that, in this embodiment, there is no specific limitation on the setting of the preset altitude, preset temperature threshold, preset adjustment ratio and each weight, and those skilled in the art can set them freely, as long as the setting requirements of the preset altitude, preset temperature threshold, preset adjustment ratio and each weight are met. Among them, the best value of y1 is 0.4, the best value of y2 is 0.6, the best value of T1 is 15°C, the best value of β is 0.18, and the best value of h1 is 500m.

[0041] Please continue reading Figure 1 As shown, the sports training course scoring method based on big data also includes: Step S5, analyzing the user's gait characteristics according to the user's stride length and user's stride frequency collected during the monitoring period.

[0042] See also Figure 3 As shown, it is a schematic diagram of the process of the gait feature analysis method of this embodiment, and the gait feature analysis method includes: Step S51, analyzing the user's stride parameters according to the user's stride collected during the monitoring period.

[0043] Specifically, in step S51 of this embodiment, when analyzing the stride parameters of the user, the stride of the user collected during the monitoring period is compared with the preset stride f0 to analyze the abnormality of the stride of the user. If fj≤f0, it is determined that the j-th stride data of the user collected during the monitoring period is normal. Otherwise, it is determined that the j-th stride data of the user collected during the monitoring period is abnormal. The user's stride parameter BF is analyzed according to the analysis results of the abnormality of the user's stride during the monitoring period, and BF=Y1 / Y0 is set; the accuracy of the stride parameter analysis is improved by identifying abnormal stride data, thereby improving the accuracy of the gait feature analysis, and further improving the accuracy of the motion state assessment; Among them, fj is the j-th stride data of the user collected during the monitoring period, Y1 is the number of abnormal stride data during the monitoring period, and Y0 is the number of stride data collected during the monitoring period.

[0044] It can be understood that the setting of the preset stride is not specifically limited in this embodiment, and those skilled in the art can freely set it as long as the setting requirements of the preset stride are met, wherein the best value of f0 is 1.3m.

[0045] Please continue reading Figure 3 As shown, the gait feature analysis method also includes: Step S52: analyzing the user's step frequency parameters according to the user's step frequency collected during the monitoring period.

[0046] Specifically, in step S52 of this embodiment, when analyzing the user's step frequency parameters, the user's step frequency collected during the monitoring period is compared with the preset step frequency p0 to analyze the abnormality of the user's step frequency. If pv≤p0, it is determined that the vth step frequency data of the user collected during the monitoring period is abnormal. Otherwise, it is determined that the vth step frequency data of the user collected during the monitoring period is normal. According to the analysis results of the abnormality of the user's cadence during the monitoring period, the user's cadence parameter BP is analyzed, and BP=Y3 / Y2 is set; by identifying abnormal cadence data to improve the accuracy of cadence parameter analysis, the accuracy of gait feature analysis is improved, and the accuracy of motion state assessment is further improved; Among them, pv is the vth cadence data of the user collected during the monitoring period, Y3 is the number of abnormal cadence data during the monitoring period, and Y2 is the number of cadence data collected during the monitoring period.

[0047] It can be understood that the present embodiment does not specifically limit the setting of the preset step frequency, and those skilled in the art can freely set it as long as the setting requirements of the preset step frequency are met, wherein the optimal value of p0 is 200 steps / minute.

[0048] Please continue reading Figure 3As shown, the gait feature analysis method also includes: Step S53: analyzing the user's gait characteristics according to the user's stride length parameter and stride frequency parameter during the monitoring period.

[0049] Specifically, step S53 described in this embodiment sets the user's gait characteristics as BT, setting BT=lg(BF×BP+1); the gait characteristics are analyzed by comprehensively analyzing the user's stride parameters and step frequency parameters to comprehensively evaluate the user's running gait, thereby improving the accuracy of the user's motion state analysis, thereby improving the scoring efficiency of the sports course.

[0050] Please continue reading Figure 1 As shown, the sports training course scoring method based on big data also includes: Step S6, evaluating the motion state according to the analysis results of the user's goal completion index, the construction results of the physiological adaptation index, the analysis results of the environmental parameters and the analysis results of the gait characteristics during the monitoring period, and adjusting the motion state evaluation process according to the user's body movement amplitude collected during the monitoring period.

[0051] See also Figure 4 As shown, it is a schematic diagram of the flow of the motion state evaluation method of this embodiment, and the motion state evaluation method includes: Step S61, evaluating the motion state according to the analysis results of the user's goal completion index, the construction results of the physiological adaptation index, the analysis results of the environmental parameters and the analysis results of the gait characteristics within the monitoring period.

[0052] Specifically, the specific process of evaluating the motion state in step S61 of this embodiment is as follows: If g1×W+g2×physiological adaptation index-g3×BT≤E1, the user's exercise state in the current monitoring period is judged to be poor; If E1<g1×W+g2×physiological adaptation index-g3×BT<E2, it is determined that the user's exercise state in the current monitoring period is normal; If g1×W+g2×physiological adaptation index-g3×BT≥E2, the user's exercise status in the current monitoring period is judged to be excellent; the exercise status is evaluated by comprehensively evaluating the goal completion index, physiological adaptation index, environmental parameters, and gait characteristics to accurately reflect the runner's training status, thereby providing data support for subsequent training adjustments, so that users can adjust their training plans in a timely manner; Among them, g1 is the goal completion weight, g2 is the physiological adaptation weight, g3 is the gait weight, g1+g2+g3=1, E1 is the first preset state threshold, E2 is the second preset state threshold, and E1<E2.

[0053] It can be understood that, in this embodiment, there is no specific limitation on the setting of each weight and each preset state threshold, and those skilled in the art can set them freely as long as the setting requirements of each weight and each preset state threshold are met. Among them, the best value of g1 is 0.5, the best value of g2 is 0.3, the best value of g3 is 0.2, the best value of E1 is 0.4, and the best value of E2 is 0.7.

[0054] See also Figure 4 As shown, the motion state assessment method further includes: Step S62, analyzing the abnormality of the user's body movement amplitude according to the user's body movement amplitude collected during the monitoring period, and adjusting the motion state evaluation process according to the abnormality of the user's body movement amplitude.

[0055] Specifically, in step S62 of this embodiment, when analyzing the abnormality of the user's body movement amplitude, the average value of the user's body movement amplitude collected during the monitoring period is set as Dp, and the value Dp is set as ,Dn is the nth user body movement amplitude data collected during the monitoring period, and N is the number of user body movement amplitude data collected during the monitoring period; The average value Dp of the user's body movement amplitude collected during the monitoring period is compared with the preset amplitude threshold d0 to adjust the motion state evaluation process. If Dp≤d0, it is determined that the average value of the user's body movement amplitude collected during the monitoring period meets the threshold and no adjustment is made. If Dp>d0, it is determined that the average value of the user's body movement amplitude collected during the monitoring period does not meet the threshold, and the first preset state threshold is set to E1', and E1'=E1×{1+3×[(Dp-d0) / (Dp+d0)] 2 -2×[(Dp-d0) / (Dp+d0)] 3}, set the second preset state threshold to E2', set E2'=E2×{1+3×[(Dp-d0) / (Dp+d0)] 2 -2×[(Dp-d0) / (Dp+d0)] 3}; By analyzing the abnormality of the user's body movement range, the stability and consistency of exercise training are evaluated, and the threshold is dynamically adjusted to make the exercise status assessment more accurate and efficient.

[0056] It can be understood that, in this embodiment, no specific limitation is imposed on the setting of the preset amplitude threshold, and those skilled in the art can freely set it as long as the setting requirements of the preset amplitude threshold are met, wherein the best value of d0 is 6 cm.

[0057] Please continue reading Figure 4 As shown, the motion state assessment method further includes: Step S63, analyzing the fluctuation state of the user's body movement amplitude according to the user's body movement amplitude collected during the monitoring period, and adjusting the analysis process of the abnormality of the user's body movement amplitude according to the fluctuation state of the user's body movement amplitude.

[0058] Specifically, step S63 in this embodiment constructs the fluctuation coefficient BD according to the user's body movement amplitude collected during the monitoring period, and sets: ; The fluctuation coefficient BD is compared with the preset fluctuation threshold by to analyze the fluctuation state of the user's body movement amplitude. If BD≤by, the fluctuation state of the user's body movement amplitude is determined to be normal and no adjustment is made. Otherwise, the fluctuation state of the user's body movement amplitude is determined to be abnormal, and the preset amplitude threshold is adjusted to d0', and d0'=d0×[1-η×(BD-by)] is set, where η is the preset optimization coefficient. The fluctuation state is analyzed according to the collected movement amplitude data to reduce the influence of the fluctuation state of the user's body movement amplitude on the abnormality analysis process of the user's body movement amplitude, thereby improving the accuracy of the motion state analysis and further improving the scoring efficiency of the sports course.

[0059] It can be understood that the present embodiment does not specifically limit the setting of the preset fluctuation threshold and the preset optimization coefficient, and those skilled in the art can freely set them as long as the setting requirements of the preset fluctuation threshold and the preset optimization coefficient are met, where the optimal value of by is 0.15, and the optimal value of η is 0.24.

[0060] Specifically, the sports training course scoring method based on big data described in this embodiment is applied to training evaluation and feedback in complex environments. By collecting user movement, goal and environmental data, analyzing the goal completion index and physiological adaptation index, and combining gait characteristics and environmental factors, a comprehensive evaluation and personalized optimization of the training status can be achieved to ensure safe and effective training.

[0061] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not limitations on the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is impossible to list all the embodiments here. All obvious changes or modifications derived from the technical solution of the present invention are still within the protection scope of the present invention.

Claims

1. A sports training course scoring method based on big data, characterized in that: include: Step S1, collecting the user's motion data, target data and environment data; Step S2, analyzing the user's goal completion index based on the user's running distance, cumulative climb, average pace and goal data collected during the monitoring period; Step S3, constructing a heart rate index according to the user's heart rate collected during the monitoring period, constructing a recovery index according to the collected user's exercise recovery time, analyzing the user's physiological adaptation state according to the construction results of the heart rate index and the recovery index, and constructing a physiological adaptation index according to the user's physiological adaptation state; Step S4, analyzing environmental parameters according to the ambient temperature and altitude collected during the monitoring period, and adjusting the construction process of the physiological adaptation index according to the environmental parameters; Step S5, analyzing the user's gait characteristics according to the user's stride length and user's stride frequency collected during the monitoring period; Step S6, evaluating the motion state according to the analysis results of the user's goal completion index, the construction results of the physiological adaptation index, the analysis results of the environmental parameters and the analysis results of the gait characteristics during the monitoring period, and adjusting the motion state evaluation process according to the user's body movement amplitude collected during the monitoring period.

2. The sports training course scoring method based on big data according to claim 1 is characterized in that: In step S2, when analyzing the target completion index, the user's running distance a0 collected during the monitoring period is compared with the target distance a1 to analyze the distance completion index; In the step S2, the user's cumulative climb b0 collected during the monitoring period is compared with the target climb b1 to analyze the climb completion index; In the step S2, the user pace c0 collected during the monitoring period is compared with the target pace c1 to analyze the pace completion index; In step S2, the target completion index is analyzed according to the analysis results of the distance completion index, the climbing completion index and the pace completion index to obtain the target completion index W.

3. The sports training course scoring method based on big data according to claim 2 is characterized in that: The method for constructing the physiological adaptation index in step S3 includes: Step S31, constructing a heart rate index according to the user's heart rate collected during the monitoring period; Step S32, constructing a recovery index according to the collected user exercise recovery time; Step S33, analyzing the user's physiological adaptation state according to the construction results of the heart rate index and the recovery index, and constructing a physiological adaptation index according to the user's physiological adaptation state; The specific process of constructing the physiological adaptation index in step S33 is as follows: If XQ1×heart rate index+XQ2×recovery index≤u0, the user's physiological adaptation state is determined to be abnormal, and the physiological adaptation index is set to SS1; otherwise, the user's physiological adaptation state is determined to be normal, and the physiological adaptation index is set to SS2; Among them, XQ1 is the heart rate weight, XQ2 is the recovery time weight, and u0 is the preset physiological state threshold.

4. The sports training course scoring method based on big data according to claim 3 is characterized in that: In step S4, when analyzing environmental parameters, the altitude h0 collected during the monitoring period is compared with the preset altitude h1 to obtain the altitude parameter; In step S4, the environmental parameter HC is analyzed according to the altitude parameter and the environmental temperature T0 collected during the monitoring period, and the construction process of the physiological adaptation index is adjusted according to the environmental parameter HC, and the adjusted preset physiological state threshold is set to u1.

5. The sports training course scoring method based on big data according to claim 4 is characterized in that: The gait feature analysis method in step S5 comprises: Step S51, analyzing the stride parameters of the user according to the stride of the user collected during the monitoring period; Step S52, analyzing the user's step frequency parameters according to the user's step frequency collected during the monitoring period; Step S53: analyzing the user's gait characteristics according to the user's stride length parameter and stride frequency parameter during the monitoring period.

6. The method for scoring sports training courses based on big data according to claim 5 is characterized in that: When analyzing the stride parameters of the user, the step S51 compares the stride of the user collected during the monitoring period with the preset stride f0 to analyze the abnormality of the user's stride, and analyzes the stride parameter BF of the user based on the analysis result of the abnormality of the user's stride during the monitoring period.

7. The method for scoring sports training courses based on big data according to claim 6, characterized in that: In step S52, when analyzing the user's step frequency parameter, the user's step frequency collected during the monitoring period is compared with the preset step frequency p0 to analyze the abnormality of the user's step frequency, and the user's step frequency parameter BP is analyzed according to the analysis result of the abnormality of the user's step frequency during the monitoring period; The step S53 analyzes the user's gait characteristics according to the user's stride parameters and cadence parameters during the monitoring period, and sets the user's gait characteristics as BT.

8. The sports training course scoring method based on big data according to claim 7 is characterized in that: The motion state evaluation method in step S6 includes: Step S61, evaluating the motion state according to the analysis results of the user's goal completion index, the construction results of the physiological adaptation index, the analysis results of the environmental parameters and the analysis results of the gait characteristics within the monitoring period; Step S62, analyzing the abnormality of the user's body movement amplitude according to the user's body movement amplitude collected during the monitoring period, and adjusting the motion state evaluation process according to the abnormality of the user's body movement amplitude; Step S63, analyzing the fluctuation state of the user's body movement amplitude according to the user's body movement amplitude collected during the monitoring period, and adjusting the analysis process of the abnormality of the user's body movement amplitude according to the fluctuation state of the user's body movement amplitude; The specific process of evaluating the motion state in step S61 is as follows: If g1×W+g2×physiological adaptation index-g3×BT≤E1, the user's exercise state in the current monitoring period is judged to be poor; If E1<g1×W+g2×physiological adaptation index-g3×BT<E2, it is determined that the user's exercise state in the current monitoring period is normal; If g1×W+g2×physiological adaptation index-g3×BT≥E2, the user's exercise status in the current monitoring period is determined to be excellent; Among them, g1 is the goal completion weight, g2 is the physiological adaptation weight, g3 is the gait weight, E1 is the first preset state threshold, and E2 is the second preset state threshold.

9. The method for scoring sports training courses based on big data according to claim 8, characterized in that: In the step S62, when analyzing the abnormality of the user's body movement amplitude, the average value of the user's body movement amplitude collected during the monitoring period is set to Dp, and the average value Dp of the user's body movement amplitude collected during the monitoring period is compared with the preset amplitude threshold d0 to adjust the evaluation process of the motion state. If the average value of the user's body movement amplitude collected during the monitoring period does not meet the threshold, the first preset state threshold is adjusted to E1', and the second preset state threshold is adjusted to E2'.

10. The sports training course scoring method based on big data according to claim 9, characterized in that: The step S63 constructs a fluctuation coefficient BD according to the user's body movement amplitude collected during the monitoring period, and compares the fluctuation coefficient BD with a preset fluctuation threshold by to analyze the fluctuation state of the user's body movement amplitude, the fluctuation state includes normal and abnormal. If the fluctuation state of the user's body movement amplitude is abnormal, the preset amplitude threshold is adjusted to d0'.

Images