Human health monitoring method and system based on bio-electricity signal acquisition technology

Abstract

The invention belongs to the technical field of bioelectricity monitoring, and provides a human health monitoring method and system based on a bioelectricity signal acquisition technology, and the method comprises the steps: respectively extracting electromyographic signals during the training of athletes in each historical test period in a plurality of historical test periods, carrying out the continuous integrity analysis, screening out an easy-to-lose stage, and carrying out the detection of the easy-to-lose stage; the method comprises the following steps: establishing an easy-to-lose sequence, analyzing each easy-to-lose stage in the easy-to-lose sequence, screening out a special easy-to-lose time period in the easy-to-lose stage, and identifying a special loss type of the special easy-to-lose time period. The physiological states of the muscles of the athlete in different exercise stages and the interactive influence between the exercise states can be deeply known, a basis is provided for more accurately interpreting the bio-electricity signals, and the muscle fatigue degree and the potential injury risk of the athlete in the training process can be evaluated.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of bioelectricity monitoring, and particularly relates to a human health monitoring method and system based on bioelectric signal acquisition technology. BACKGROUND

[0002] With the continuous development of bioelectric signal acquisition technology, electromyography signal, as an important bioelectric signal capable of reflecting the muscle activity state, can directly reflect the muscle contraction strength, fatigue degree and functional state of the neuromuscular system. Through the acquisition and analysis of electromyography signals during the training process of athletes, important basis can be provided for coaches to formulate scientific and reasonable training plans and evaluate the physical condition of athletes.

[0003] In the prior art, there is often a lack of effective analysis of the continuous integrity of electromyography signals. During the training process of athletes, electromyography signals often lose due to rapid changes in the movement state, limitations of the acquisition device and other factors. Moreover, the prior art does not further screen out special loss periods and identify special loss types. In the training process, the electromyography signals of different stages may have different causes and characteristics, and these special cases cannot be distinguished, so it is not possible to accurately determine whether the signal loss is due to unreasonable device threshold setting or device acquisition accuracy, thereby it is not possible to adjust and optimize the acquisition device in a targeted manner, which limits the accuracy and reliability of electromyography signal acquisition.

[0004] Therefore, the present application provides a human health monitoring method and system based on bioelectric signal acquisition technology. SUMMARY

[0005] In order to make up for the deficiencies of the prior art and solve at least one technical problem raised in the background art.

[0006] The technical scheme adopted by the present application to solve its technical problems is: A human health monitoring method based on bioelectric signal acquisition technology, comprising the following steps: In a plurality of historical test periods, electromyography signals of athletes during training in each historical test period are extracted respectively, and continuous integrity analysis is performed to construct a loss-prone sequence; Each loss-prone stage in the loss-prone sequence is analyzed respectively, a special loss-prone period in the loss-prone stage is screened out, and a special loss type of the special loss-prone period is identified; Based on the identified special loss type, stability analysis is performed on the special loss-prone period to evaluate whether the loss-prone type in the special loss-prone period is an overrun loss type or a non-overrun loss type; If the easy-to-lose type is an overrun loss type, an acquisition intensity adjustment amount is obtained to adjust and optimize the acquisition signal intensity of the electromyographic signal acquisition device, and if the easy-to-lose type is a non-overrun loss type, an adjacent acquisition interval length is obtained to obtain an acquisition frequency adjustment amount to adjust and optimize the acquisition frequency of the electromyographic signal acquisition device.

[0007] As a preferred scheme, the process of constructing the easy-to-lose sequence is as follows: The historical test period is divided into a historical test start phase, a historical test uniform speed phase, and a historical test sprint phase, the electromyographic intensity values collected in the historical test start phase are sorted in time sequence, and integrated into a start electromyographic intensity set; In the start electromyographic intensity set, adjacent sorted electromyographic intensity values are obtained, corresponding signal acquisition nodes are extracted, and the time length between the corresponding signal acquisition nodes is obtained as the adjacent sorting length, if the adjacent sorting length is not equal to the adjacent acquisition length, it is displayed as a collection loss signal, and the proportion of the number of collection loss signals in the total number of displayed signals is calculated to obtain the collection loss number ratio; The collection loss number ratios corresponding to the historical test start phase, the historical test uniform speed phase and the historical test sprint phase are extracted, the historical test phase corresponding to the maximum collection loss number ratio is taken as the easy-to-lose phase, the easy-to-lose phase corresponding to each historical test period is extracted, and the number of coincidences is compared, and sorted in descending order to construct the easy-to-lose sequence.

[0008] As a preferred scheme, the screening process of the special easy-to-lose period is as follows: An easy-to-lose phase is randomly selected as a target analysis phase, and an easy-to-lose period is randomly selected as a target analysis period in the target analysis phase; The signal acquisition nodes corresponding to the electromyographic intensity values not collected in the target analysis period and the signal acquisition nodes at the end of the target analysis period are extracted; If any two signal acquisition nodes in the target analysis period are located in the same historical test phase, and the other signal acquisition node exists in the target analysis period of other historical test phases, it is marked as a special easy-to-lose period.

[0009] As a preferred scheme, the special loss type identification process is as follows: The electromyographic intensity values in the easy-to-lose phase with the special easy-to-lose period are input into a two-dimensional coordinate system according to the time sequence corresponding to the signal acquisition nodes, an easy-to-lose curve is constructed, an electromyographic signal intensity threshold is marked on the Y axis, and a straight line parallel to the X axis is taken as the electromyographic intensity threshold line; extract the signal acquisition nodes corresponding to the start and end of the special easy-to-lose period respectively, and obtain the coordinate points of the signal acquisition node at the start of the special easy-to-lose period and the signal acquisition node at the end of the special easy-to-lose period on the easy-to-lose curve as the special easy-to-lose start coordinate and the special easy-to-lose end coordinate; If at least one of the special easy-to-lose start coordinate and the special easy-to-lose end coordinate is located on the electromyographic intensity threshold line, it is identified as an out-of-limit loss type, and the special easy-to-lose period corresponding to the out-of-limit loss type is identified as an out-of-limit loss period; If neither the special easy-to-lose start coordinate nor the special easy-to-lose end coordinate is located on the electromyographic intensity threshold line, it is identified as a non-out-of-limit loss type, and the special easy-to-lose period corresponding to the non-out-of-limit loss type is identified as a non-out-of-limit loss period.

[0010] As a preferred solution, the stability of the special easy-to-lose period is analyzed, and the process is as follows: Extract the special easy-to-lose period in each historical test period, and obtain the special loss type corresponding to each special easy-to-lose period; Extract all historical test periods with the out-of-limit loss type as the out-of-limit loss period, and calculate the proportion of the number of out-of-limit loss periods in the total number of historical test periods to obtain the out-of-limit loss number ratio; In the out-of-limit loss period, the adjacent ordering duration corresponding to each out-of-limit loss period is extracted, and the difference between the adjacent ordering duration and the adjacent acquisition duration is calculated, and then summed to obtain the out-of-limit loss duration; Calculate the standard deviation of the out-of-limit loss duration corresponding to each out-of-limit loss period to obtain the out-of-limit loss duration standard deviation; Calculate the ratio of the out-of-limit loss number ratio and the out-of-limit loss duration standard deviation to output the easy-to-lose type value.

[0011] As a preferred solution, the easy-to-lose type in the special easy-to-lose period is evaluated to be an out-of-limit loss type or a non-out-of-limit loss type, and the process is as follows: If the easy-to-lose type value is greater than the easy-to-lose type threshold value, the non-out-of-limit loss type is displayed as the easy-to-lose type; If the easy-to-lose type value is less than or equal to the easy-to-lose threshold value, the out-of-limit loss type is displayed as the easy-to-lose type.

[0012] As a preferred solution, the acquisition intensity adjustment amount is obtained in the following way: If the easy-to-lose type is an out-of-limit loss type, the adjacent ordering duration corresponding to each out-of-limit loss period in each historical test period is extracted, and the difference between the adjacent ordering duration and the adjacent acquisition duration is calculated to obtain a unit out-of-limit amount; All unit out-of-limit amounts are mean value calculated to output the acquisition intensity adjustment amount.

[0013] As a preferred scheme, the acquisition process of the adjacent collection interval length is as follows: If the easy-to-lose type is a non-overrun loss type, the standard deviation of the length corresponding to each non-overrun loss period in each historical test period is calculated, and the non-overrun loss length standard deviation is output. If the non-overrun loss length standard deviation is greater than the non-overrun loss length standard deviation threshold, it indicates that the length corresponding to the non-overrun loss period is relatively large, and a non-overrun loss length fluctuation signal is displayed. The length corresponding to each non-overrun loss period is compared in size, and the length corresponding to the maximum non-overrun loss period and the length corresponding to the minimum non-overrun loss period are selected. After the sum mean value calculation, the difference between the adjacent collection length is obtained, and the adjacent collection interval length is obtained. If the non-overrun loss length standard deviation is less than or equal to the non-overrun loss length standard deviation threshold, it indicates that the length corresponding to the non-overrun loss period is relatively small, and a non-overrun loss length stability signal is displayed. After the sum mean value calculation of the length corresponding to each non-overrun loss period, the difference between the adjacent collection length is obtained, and the adjacent collection interval length is obtained.

[0014] As a preferred scheme, the acquisition process of the collection frequency adjustment amount is as follows: The reciprocal of the adjacent collection interval length is taken as the collection frequency adjustment amount.

[0015] In a second aspect, a human health monitoring coefficient based on bioelectric signal collection technology includes the following modules: The sequence construction module: in multiple historical test periods, the electromyographic signals of the athletes during training in each historical test period are extracted respectively, and the continuity analysis is performed to construct the easy-to-lose sequence. The type analysis module: each easy-to-lose stage in the easy-to-lose sequence is analyzed respectively, the special easy-to-lose period in the easy-to-lose stage is screened out, and the special loss type of the special easy-to-lose period is identified. The easy-to-lose identification module: based on the identified special loss type, the stability of the special easy-to-lose period is analyzed, and it is evaluated whether the easy-to-lose type in the special easy-to-lose period is an overrun loss type or a non-overrun loss type. The adjustment and optimization module: if the easy-to-lose type is an overrun loss type, the collection intensity adjustment amount is obtained, the collection signal intensity of the electromyographic signal collection device is adjusted and optimized, and if the easy-to-lose type is a non-overrun loss type, the adjacent collection interval length is obtained, the collection frequency adjustment amount is obtained, and the collection frequency of the electromyographic signal collection device is adjusted and optimized.

[0016] The beneficial effects of the present application are as follows: The application extracts the electromyographic signals of the athletes during training in each historical test period respectively, and performs continuous integrity analysis, screens out the easy loss stages, constructs the easy loss sequences, analyzes each easy loss stage in the easy loss sequences respectively, screens out the special easy loss period in the easy loss stage, and identifies the special loss type of the special easy loss period, so that whether the electromyographic signal intensity exceeds the preset maximum value of the collection device is determined, and whether the electromyographic intensity threshold in the electromyographic signal collection device needs to be reset or the collection accuracy of the electromyographic signal collection device needs to be optimized is diagnosed, the physiological state of the muscles of the athletes in different movement stages and the interaction between the physiological state and the movement state are further understood, the biological electric signal is more accurately interpreted, the muscle fatigue degree and the potential damage risk of the athletes in the training process are evaluated, and the muscle fatigue degree and the potential damage risk of the athletes in the training process are evaluated. The application performs stability analysis on the special easy loss period according to the identified special loss type, obtains a collection intensity adjustment amount if the easy loss type is an overrun loss type, adjusts and optimizes the collection signal intensity of the electromyographic signal collection device, obtains a collection frequency adjustment amount if the easy loss type is a non-overrun loss type, adjusts and optimizes the collection frequency of the electromyographic signal collection device, and obtains the collection frequency adjustment amount in order to adjust and optimize the collection frequency of the electromyographic signal collection device, avoid signal loss or inaccuracy due to inappropriate collection frequency, and thus guarantee the accuracy and integrity of the monitoring of the muscle state of the athletes, and obtains the collection intensity adjustment amount in order to adjust the threshold of the collection signal intensity of the electromyographic signal collection device, so that the device can adapt to the sharp increase of the muscle force intensity of the athletes in a specific movement stage, and help to find problems such as muscle fatigue accumulation, excessive force or improper movement skills of the athletes in time, and avoid muscle strains of the athletes caused by muscle fatigue accumulation, excessive force or improper movement skills. BRIEF DESCRIPTION OF DRAWINGS

[0017] The application will be further described below with reference to the drawings.

[0018] Figure 1 is a step flow chart of a human health monitoring method based on a biological electric signal collection technology of the application; Figure 2 is a judgment flow chart in a human health monitoring method based on a biological electric signal collection technology of the application; Figure 3 is a schematic diagram of a human health monitoring system based on a biological electric signal collection technology of the application. DETAILED DESCRIPTION

[0019] In order to make the technical means, creative features, purposes and effects of the application easy to understand, the application will be further described below with reference to the specific embodiments.

[0020] Embodiment 1:

[0021] Since the muscle strength of the athlete exists a state of switching from a low load warm-up state to a maximum power output state (from the start to the sprint stage during the running training), the amplitude of the electromyographic signal collected by the bioelectric signal collection technology will fluctuate several times or even dozens of times in a short time, which is easy to exceed the dynamic range of the collection device, thereby causing the collected electromyographic signal to appear over-saturation phenomenon, ultimately causing the collection parameters to be lost, and further interfering with the muscle fatigue assessment of the athlete during training, and unable to avoid the muscle injury of the athlete during training in time; Therefore, referring to Figure 1 Figure 2 The human health monitoring method based on the bioelectric signal collection technology provided by the embodiment of the present application comprises the following steps: Step 1: In a plurality of historical test periods, the electromyographic signal of the athlete during training in each historical test period is extracted respectively, and a continuous integrity analysis is performed to screen out an easy loss stage and construct an easy loss sequence; It should be noted that the historical test period is the process of collecting the electromyographic signal of the athlete in real time during the running training, which can be understood as the time period of the entire running training of the athlete; In some embodiments, the historical test period is divided into a historical test start stage, a historical test constant speed stage and a historical test sprint stage; In the historical test start stage, the collected electromyographic intensity values are sorted according to the time sequence and integrated into a start electromyographic intensity set; Similarly, the collected electromyographic intensity values in the historical test constant speed stage and the historical test sprint stage are sorted according to the time sequence, and a constant speed electromyographic intensity set and a sprint electromyographic intensity set are integrated; Specifically, the electromyographic signal intensity acquisition method is as follows: For example, the historical test start stage is equally divided into a plurality of signal collection nodes, the interval time length between adjacent signal collection nodes is equal, the electromyographic signal intensity at each signal collection node is obtained as the electromyographic intensity value; It should be noted that the collected electromyographic intensity values in the historical test constant speed stage and the historical test sprint stage are consistent with the collected electromyographic intensity values in the historical test start stage; In the start electromyographic intensity set, the electromyographic intensity values of adjacent sorting are obtained, the corresponding signal collection nodes are extracted respectively, and the time length between the corresponding signal collection nodes is obtained as the adjacent sorting time length; ​If the adjacent ordering duration is equal to the adjacent collection duration, it indicates that the adjacent ordering electromyogram intensity values analyzed are continuous and complete in the collection time dimension, which is displayed as no signal loss in collection; If the adjacent ordering duration is not equal to the adjacent collection duration, it indicates that the adjacent ordering electromyogram intensity values analyzed are not continuous and complete in the collection time dimension, which is displayed as signal loss in collection, and the signal collection nodes corresponding to the adjacent ordering electromyogram intensity values analyzed are extracted, and the time period between the corresponding signal collection nodes is taken as the easy-to-lose period; It should be noted that the adjacent collection duration is the interval duration between adjacent signal collection nodes, which is not only applicable to the judgment in the historical test starting stage, but also applicable to the judgment in the historical test uniform speed stage and the historical test sprint stage; The number of signals displayed as loss in collection is counted, and the proportion of the number of signals lost in collection in the total number of signals displayed is calculated to obtain the collection loss number ratio; For example, the total number of signals displayed represents the sum of the displayed signals lost in collection and the actual signals not lost in collection in the historical test starting stage, which is not only applicable to the historical test starting stage, but also applicable to the historical test uniform speed stage and the historical test sprint stage; In the historical test period, the collection loss number ratio corresponding to the historical test starting stage, the historical test uniform speed stage and the historical test sprint stage is extracted respectively, and a size comparison is made, and the historical test stage corresponding to the maximum collection loss number ratio is taken as the easy-to-lose stage; The easy-to-lose stage corresponding to each historical test period is extracted, and a coincidence number comparison is made, and the easy-to-lose sequence is constructed in descending order of number; Among them, the purpose of constructing the easy-to-lose sequence is: Purpose one: Since the muscle strength of the athlete during running training is quickly switched from low load warm-up to maximum power output, which exceeds the collection threshold of the collection device, resulting in parameter loss, therefore, by constructing the easy-to-lose sequence, it is clear that parameter loss phenomenon occurs in which monitoring stage, so as to optimize and adjust the collection function of the collection device for the easy-to-lose stage; Purpose two: The construction of the easy-to-lose sequence helps to reflect the changes of the muscle state of the athlete in each stage, as well as the fatigue degree of the athlete's muscle in different training stages, which provides strong support for dynamically adjusting the training plan and evaluating the muscle fatigue degree; Step two: Each easy-to-lose stage in the easy-to-lose sequence is analyzed respectively, the special easy-to-lose period in the easy-to-lose stage is screened out, and the special loss type of the special easy-to-lose period is identified; It should be noted that the special easy-to-lose period can be: the last signal acquisition node does not collect the electromyogram signal intensity in the historical test starting stage, the second-to-last signal acquisition node collects the electromyogram signal intensity in the historical test starting stage, and the first signal acquisition node collects the electromyogram signal intensity in the historical test uniform speed stage, or the last signal acquisition node does not collect the electromyogram signal intensity in the historical test uniform speed stage, the second-to-last signal acquisition node collects the electromyogram signal intensity in the historical test uniform speed stage, and the first signal acquisition node collects the electromyogram signal intensity in the historical test sprint stage; It can also be: the last signal acquisition node collects the electromyogram signal intensity in the historical test starting stage, the first signal acquisition node does not collect the electromyogram signal intensity in the historical test uniform speed stage, and the second signal acquisition node collects the electromyogram signal intensity in the historical test uniform speed stage, or the last signal acquisition node collects the electromyogram signal intensity in the historical test uniform speed stage, the first signal acquisition node does not collect the electromyogram signal intensity in the historical test sprint stage, and the second signal acquisition node collects the electromyogram signal intensity in the historical test sprint stage; It should be further explained that, for the special easy-to-lose period belonging to which easy-to-lose stage, the rule for judgment is: in the special easy-to-lose period, the historical test stage (including: the historical test starting stage, the historical test uniform speed stage and the historical test sprint stage) where the signal acquisition point that does not collect the electromyogram signal intensity is located is regarded as the easy-to-lose stage; In some embodiments, the screening process of the special easy-to-lose period is as follows: Arbitrarily select one easy-to-lose stage as the target analysis stage, and in the target analysis stage, arbitrarily select one easy-to-lose period as the target analysis period; Extract the signal acquisition nodes in the target analysis period that do not collect the electromyogram intensity value, and the signal acquisition nodes at the end of the target analysis period; Among them, the signal acquisition nodes at the end of the target analysis period are the signal acquisition nodes corresponding to the starting end and the terminating end of the target analysis period, respectively; If there are any two signal acquisition nodes in the target analysis period located in the same historical test stage, and the other signal acquisition node exists in the target analysis period of other historical test stages, it is marked as a special easy-to-lose period; If there are no any two signal acquisition nodes in the target analysis period located in the same historical test stage, and the other signal acquisition node is not located in the target analysis period of other historical test stages, it is marked as a special non-easy-to-lose period; The purpose of screening is: Objective one: Because there are some easy-to-lose periods that appear at the junction of different training stages, screening them as special easy-to-lose periods helps to accurately locate the problem of easy-to-lose parameters in the process of training stage transition; Objective two: Special easy-to-lose periods reflect the muscle state of athletes in the process of motion state transition, which helps to understand the interaction between physiological state and motion state, and provides a basis for more accurate interpretation of bioelectric signals; The special loss type identification process is as follows: Taking the X-axis as time and the Y-axis as the electromyography intensity value, the electromyography intensity value in the easy-to-lose stage with special easy-to-lose periods is input into the two-dimensional coordinate system according to the time sequence of the signal acquisition nodes to construct an easy-to-lose curve; Mark the electromyography signal intensity threshold on the Y-axis of the easy-to-lose curve, and draw a straight line parallel to the X-axis as the electromyography intensity threshold line; Respectively extract the signal acquisition nodes corresponding to the start and end of the special easy-to-lose period; Get the coordinate point of the signal acquisition node at the start of the special easy-to-lose period on the easy-to-lose curve as the special easy-to-lose start coordinate; Similarly, get the coordinate point of the signal acquisition node at the end of the special easy-to-lose period on the easy-to-lose curve as the special easy-to-lose end coordinate; If at least one of the special easy-to-lose start coordinate and the special easy-to-lose end coordinate is located on the electromyography intensity threshold line, it means that the electromyography signal intensity exceeds the preset maximum value of the electromyography signal intensity acquisition device during the acquisition process, and it is identified as an over-limit loss type. Identify the special easy-to-lose period corresponding to the over-limit loss type as the over-limit loss period; If neither the special easy-to-lose start coordinate nor the special easy-to-lose end coordinate is located on the electromyography intensity threshold line, it means that the electromyography signal intensity does not exceed the preset maximum value of the electromyography signal intensity acquisition device during the acquisition process, and it is identified as a non-over-limit loss type. Identify the special easy-to-lose period corresponding to the non-over-limit loss type as the non-over-limit loss period; The purpose of special loss type identification is: Objective one: By determining whether the electromyography signal intensity exceeds the preset maximum value of the acquisition device, it can be analyzed and diagnosed whether the electromyography intensity threshold in the electromyography signal acquisition device needs to be reset or the acquisition accuracy of the electromyography signal acquisition device needs to be optimized; Objective two: It can deeply understand the physiological state of athletes' muscles in different exercise stages and the interaction between physiological state and motion state, and provide a basis for more accurate interpretation of bioelectric signals, which helps to evaluate the muscle fatigue degree and potential injury risk of athletes in the training process; The specific implementation of the embodiment is: in a plurality of historical test periods, the electromyographic signals of the athletes during training in each historical test period are extracted respectively, and a continuous integrity analysis is performed to screen out an easy loss stage, construct an easy loss sequence, analyze each easy loss stage in the easy loss sequence respectively, screen out a special easy loss period in the easy loss stage, and identify a special loss type of the special easy loss period. Not only can it be determined whether the electromyographic signal intensity exceeds the preset maximum value of the collection device, and whether the electromyographic signal intensity threshold in the electromyographic signal collection device needs to be reset or the collection accuracy of the electromyographic signal collection device needs to be optimized and adjusted, but also the physiological state of the muscles of the athletes in different movement stages and the interaction between the physiological state and the movement state can be understood in depth, which provides a basis for more accurate interpretation of the bioelectric signal and helps to evaluate the muscle fatigue degree and potential injury risk of the athletes during training.

[0022] Embodiment 2

[0023] Please refer to Figure 1 - Figure 2 As shown in the figure, the human health monitoring method based on the bioelectric signal collection technology comprises the following steps: Step three: based on the identified special loss type, stability analysis is performed on the special easy loss period to evaluate whether the easy loss type in the special easy loss period is an overrun loss type or a non-overrun loss type; In some embodiments, the special easy loss period in each historical test period is extracted, and the special loss type corresponding to each special easy loss period is obtained; All historical test periods with the overrun loss type are extracted as overrun loss periods, and the proportion of the number of overrun loss periods in the total number of historical test periods is counted to obtain an overrun loss quantity ratio; In the overrun loss period, the adjacent ordering duration corresponding to each overrun loss period is extracted, and the adjacent collection duration is subtracted to obtain the overrun loss duration; The standard deviation of the overrun loss duration corresponding to each overrun loss period is calculated to obtain an overrun loss duration standard deviation; The overrun loss quantity ratio and the overrun loss duration standard deviation are calculated by ratio to output an easy loss type value; It can be understood that the meaning represented by the easy loss type value is: on the one hand, the overrun loss quantity ratio reflects the frequency of the serious loss condition that the electromyographic signal intensity exceeds the preset maximum value of the collection device in the entire historical test process, and on the other hand, the overrun loss duration standard deviation reflects the dispersion degree of the overrun loss duration, thereby reflecting the problem that the human electromyographic signal intensity collection device needs to be adjusted and optimized in the collection process; The process is as follows: If the easy-to-lose type value is greater than the easy-to-lose type threshold value, it indicates that the out-of-limit loss phenomenon not only occurs less frequently, but also is less stable in the out-of-limit loss duration, and the non-out-of-limit loss type is the easy-to-lose type. If the easy-to-lose type value is less than or equal to the easy-to-lose threshold value, it indicates that the out-of-limit loss phenomenon not only occurs more frequently, but also is more stable in the out-of-limit loss duration, and the out-of-limit loss type is the easy-to-lose type. The purpose of evaluating the easy-to-lose type is that, from the perspective of device optimization, if the easy-to-lose type is identified as the out-of-limit loss type, it indicates that the electromyographic signal intensity exceeds the preset maximum value of the collection device, and it is urgent to adjust the threshold value of the device for collecting electromyographic signal intensity. If the easy-to-lose type is identified as the non-out-of-limit loss type, it indicates that there is a problem with the accuracy of the electromyographic signal collection device itself, and it is urgent to adjust and optimize the accuracy of the device for collecting electromyographic signals. Secondly, from the perspective of the muscle state of the athlete, if the easy-to-lose type is identified as the out-of-limit loss type, it indicates that the muscle strength of the athlete in a specific exercise phase increases sharply, exceeding the normal range, which may be related to factors such as muscle fatigue accumulation, excessive force, or improper exercise technique, resulting in muscle fatigue during training, and even potential muscle strain risk. If the easy-to-lose type is identified as the non-out-of-limit loss type, it indicates that there are other physiological changes in the muscle during the exercise state transition, such as muscle coordination changes and neural control adjustments. Therefore, it is helpful to adjust the training plan in a timely manner to avoid muscle damage caused by excessive training of the athlete, and to ensure the physical health and training effect of the athlete. Step four: if the easy-to-lose type is the out-of-limit loss type, obtain the collection intensity adjustment amount and adjust and optimize the collection signal intensity of the electromyographic signal collection device; if the easy-to-lose type is the non-out-of-limit loss type, obtain the adjacent collection interval duration and obtain the collection frequency adjustment amount to adjust and optimize the collection frequency of the electromyographic signal collection device. In some embodiments, if the easy-to-lose type is the out-of-limit loss type, the adjacent ordering duration corresponding to each out-of-limit loss period in each historical test period is subtracted from the adjacent collection duration to obtain a unit out-of-limit amount. All unit out-of-limit amounts are subjected to mean value calculation to output the collection intensity adjustment amount. If the easy-to-lose type is the non-out-of-limit loss type, the duration corresponding to each non-out-of-limit loss period in each historical test period is subjected to standard deviation calculation to output the non-out-of-limit loss duration standard deviation. If the non-out-of-limit loss duration standard deviation is greater than the non-out-of-limit loss duration standard deviation threshold value, it indicates that the duration corresponding to the non-out-of-limit loss period has a large deviation, and it is displayed as a non-out-of-limit loss duration fluctuation signal. If the standard deviation of the non-overrun loss duration is less than or equal to the non-overrun loss duration standard deviation threshold, it indicates that the duration deviation of the non-overrun loss period is small, and a non-overrun loss duration stability signal is displayed. Based on the non-overrun loss duration fluctuation signal, the duration of each non-overrun loss period is compared in size, the duration of the maximum non-overrun loss period and the duration of the minimum non-overrun loss period are selected, and the sum is calculated. After the mean value is calculated, the difference is subtracted from the adjacent collection duration to obtain the adjacent collection interval duration. Based on the non-overrun loss duration stability signal, the duration of each non-overrun loss period is calculated by summing and averaging, and the difference is subtracted from the adjacent collection duration to obtain the adjacent collection interval duration. The reciprocal of the adjacent collection interval duration is used as the collection frequency adjustment amount. The specific scheme of the embodiment is: based on the identified special loss type, the stability of the special easy-to-lose period is analyzed, if the easy-to-lose type is an overrun loss type, the collection intensity adjustment amount is obtained, the collection signal intensity of the electromyographic signal collection device is adjusted and optimized, if the easy-to-lose type is a non-overrun loss type, the collection frequency adjustment amount is obtained, the collection frequency of the electromyographic signal collection device is adjusted and optimized, the collection frequency adjustment amount is obtained to adjust and optimize the collection frequency of the electromyographic signal collection device, avoid signal loss or inaccuracy due to inappropriate collection frequency, and thus ensure the accuracy and integrity of the monitoring of the muscle state of the athlete, and the collection intensity adjustment amount is obtained to adjust the threshold of the signal intensity collected by the electromyographic signal collection device, so that the device can adapt to the case that the muscle exertion intensity of the athlete increases sharply in a specific exercise stage, which helps to timely find out the problems such as muscle fatigue accumulation, excessive force or improper exercise skill of the athlete, and avoid muscle strain caused by muscle fatigue accumulation, excessive force or improper exercise skill of the athlete.

[0024] Please refer to Figure 2 As shown in the figure, the human health monitoring method based on bioelectric signal collection technology comprises the following modules: Sequence construction module: in a plurality of historical test periods, the electromyographic signals of the athletes during training in each historical test period are extracted respectively, and the continuity and integrity are analyzed to construct an easy-to-lose sequence; Type analysis module: each easy-to-lose stage in the easy-to-lose sequence is analyzed respectively, the special easy-to-lose period in the easy-to-lose stage is screened out, and the special loss type of the special easy-to-lose period is identified; Easy-to-lose identification module: based on the identified special loss type, the stability of the special easy-to-lose period is analyzed, and it is evaluated whether the easy-to-lose type in the special easy-to-lose period is an overrun loss type or a non-overrun loss type; The adjustment optimization module: if the easy loss type is an out-of-limit loss type, an acquisition intensity adjustment amount is obtained to adjust and optimize the acquisition signal intensity of the electromyographic signal acquisition device; if the easy loss type is a non-out-of-limit loss type, an adjacent acquisition interval duration is obtained to obtain an acquisition frequency adjustment amount to adjust and optimize the acquisition frequency of the electromyographic signal acquisition device.

[0025] The basic principles, main features and advantages of the present application are shown and described above. Those skilled in the art should understand that the present application is not limited to the above-mentioned embodiments, and the above-mentioned embodiments and descriptions in the specification are only to illustrate the principles of the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the claimed present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. A human health monitoring method based on bioelectrical signal acquisition technology, characterized by: include: In multiple historical test cycles, the electromyographic signals of athletes during training in each historical test cycle are extracted, and continuous integrity analysis is performed to construct easy-to-miss sequences; Analyze each loss-prone stage in the loss-prone sequence separately, screen out the special loss-prone periods in the loss-prone stages, and identify the special loss types in the special loss-prone periods; Based on the identified special loss types, stability analysis is conducted for the special loss-prone period to assess whether the loss type during the special loss-prone period is an excessive loss type or a non-excess loss type. If the easy-to-loss type is an over-limit loss type, the acquisition intensity adjustment amount is obtained, and the acquisition signal intensity of the electromyographic signal acquisition device is adjusted and optimized. If the easy-to-loss type is a non-over-limit loss type, the length of the adjacent acquisition interval is obtained, and the acquisition frequency adjustment amount is obtained, and the acquisition frequency of the electromyographic signal acquisition device is adjusted and optimized.

2. The human health monitoring method based on bioelectrical signal acquisition technology according to claim 1, characterized in that: The process of constructing the easy-to-miss sequence is as follows: The historical test cycle is divided into the historical test startup phase, the historical test constant speed phase, and the historical test sprint phase. The electromyographic intensity values ​​collected during the historical test startup phase are sorted according to the time series and integrated into the startup electromyographic intensity set. In the starting EMG intensity set, randomly obtain adjacent sorted EMG intensity values, extract the corresponding signal acquisition nodes respectively, and obtain the time length between the corresponding signal acquisition nodes as the adjacent sorting duration. If the adjacent sorting duration is not equal to the adjacent acquisition duration, it is displayed as an acquisition loss signal, and the ratio of the number of acquisition loss signals to the total number of displayed signals is calculated to obtain the acquisition loss ratio; The acquisition loss ratios corresponding to the historical test startup phase, the historical test uniform speed phase, and the historical test sprint phase are extracted respectively. The historical test phase corresponding to the maximum acquisition loss ratio is taken as the prone-to-loss phase. The prone-to-loss phase corresponding to each historical test cycle is extracted, and the overlapping number is compared. The phases are sorted from large to small to construct a prone-to-loss sequence.

3. The human health monitoring method based on bioelectrical signal acquisition technology according to claim 1, characterized in that: The screening process for special vulnerable periods is as follows: Randomly select a loss-prone phase as the target analysis phase, and within the target analysis phase, randomly select a loss-prone period as the target analysis period; Extracting signal acquisition nodes corresponding to the myoelectric strength values ​​not acquired during the target analysis period, and signal acquisition nodes at the end of the target analysis period; If any two signal acquisition nodes are located in the same historical test phase within the target analysis period, and another signal acquisition node exists in the target analysis period of another historical test phase, it is marked as a special loss-prone period.

4. The human health monitoring method based on bioelectrical signal acquisition technology according to claim 1, characterized in that: The process of identifying special loss types is as follows: The myoelectric strength values ​​in the prone-to-loss phase with special prone-to-loss periods are input into a two-dimensional coordinate system according to the time sequence corresponding to the signal acquisition node, and a prone-to-loss curve is constructed. The myoelectric signal strength threshold is marked on the Y-axis and drawn as a straight line parallel to the X-axis as the myoelectric strength threshold line; Extract the signal acquisition nodes corresponding to the start and end of the special easy-to-loss period respectively, and obtain the coordinates of the signal acquisition node at the start of the special easy-to-loss period and the signal acquisition node at the end of the special easy-to-loss period on the easy-to-loss curve as the special easy-to-loss start coordinates and the special easy-to-loss end coordinates; If at least one of the special easy-to-lose start coordinate and the special easy-to-lose end coordinate is located on the myoelectric intensity threshold line, it is identified as an excessive loss type, and the special easy-to-lose period corresponding to the excessive loss type is marked as the excessive loss period; If the special easy-to-lose starting coordinates and the special easy-to-lose ending coordinates are not located on the myoelectric intensity threshold line, it is identified as a non-exceeding loss type, and the special easy-to-lose period corresponding to the non-exceeding loss type is identified as a non-exceeding loss period.

5. The human health monitoring method based on bioelectrical signal acquisition technology according to claim 1, characterized in that: The stability analysis of special loss-prone periods is carried out as follows: Extract the special loss-prone periods in each historical test cycle and obtain the special loss type corresponding to each special loss-prone period; Extract all historical test cycles with excessive loss types as excessive loss cycles, and calculate the ratio of the number of excessive loss cycles to the total number of historical test cycles to obtain the excessive loss ratio. During the over-limit loss period, the adjacent sorting duration corresponding to each over-limit loss period is extracted, and the difference between the adjacent collection durations is added to obtain the over-limit loss duration. Calculate the standard deviation of the over-limit loss duration corresponding to each over-limit loss cycle to obtain the standard deviation of the over-limit loss duration; The ratio of the number of excessive losses to the standard deviation of the excessive loss duration is calculated and the output is the easy-to-lose type value.

6. The human health monitoring method based on bioelectrical signal acquisition technology according to claim 5, characterized in that: The process of evaluating whether the loss type during a special loss-prone period is an excessive loss type or a non-excess loss type is as follows: If the easy-to-lose type value is greater than the easy-to-lose type threshold, the non-exceeding loss type is displayed as the easy-to-lose type; If the value of the prone-to-loss type is less than or equal to the prone-to-loss threshold, the excessive loss type is displayed as the prone-to-loss type.

7. The human health monitoring method based on bioelectrical signal acquisition technology according to claim 1, characterized in that: The acquisition intensity adjustment amount is obtained as follows: If the prone loss type is the over-limit loss type, the adjacent sorting duration corresponding to each over-limit loss period in each historical test cycle is subtracted from the adjacent collection duration to obtain the unit over-limit amount; All unit excess values ​​are averaged and the acquisition intensity adjustment value is output.

8. The human health monitoring method based on bioelectrical signal acquisition technology according to claim 1, characterized in that: The process of obtaining the duration of adjacent collection intervals is as follows: If the prone loss type is a non-excessive loss type, the standard deviation of the duration corresponding to each non-excessive loss period in each historical test cycle is calculated and the standard deviation of the non-excessive loss duration is output; If the standard deviation of the non-excessive loss duration is greater than the standard deviation threshold, a non-excessive loss duration fluctuation signal is displayed. The duration corresponding to each non-excessive loss period is compared, and the duration corresponding to the maximum non-excessive loss period and the duration corresponding to the minimum non-excessive loss period are selected. The sum and average are calculated, and the difference is taken from the adjacent collection duration to obtain the adjacent collection interval duration. If the standard deviation of the non-limit loss duration is less than or equal to the standard deviation threshold of the non-limit loss duration, a non-limit loss duration stability signal is displayed. The duration corresponding to each non-limit loss period is summed and averaged, and then subtracted from the adjacent collection duration to obtain the adjacent collection interval duration.

9. The human health monitoring method based on bioelectrical signal acquisition technology according to claim 1, characterized in that: The acquisition process of the acquisition frequency adjustment amount is as follows: The reciprocal of the interval between adjacent collections is used as the collection frequency adjustment amount.

10. A human health monitoring system based on bioelectrical signal acquisition technology, characterized by: Includes the following modules: Sequence construction module: extracts the EMG signals of athletes during training in each historical test period, performs continuous integrity analysis, and constructs easily lost sequences; Type analysis module: Analyzes each loss-prone stage in the loss-prone sequence, screens out special loss-prone periods within the loss-prone stages, and identifies special loss types in special loss-prone periods; The vulnerable loss identification module: Based on the identified special loss types, it conducts stability analysis on the special vulnerable loss period and evaluates whether the vulnerable loss type in the special vulnerable loss period is an excessive loss type or a normal loss type. Adjustment and optimization module: If the easy loss type is the over-limit loss type, the acquisition intensity adjustment amount is obtained, and the acquisition signal intensity of the electromyographic signal acquisition device is adjusted and optimized. If the easy loss type is the non-over-limit loss type, the adjacent acquisition interval length is obtained, and the acquisition frequency adjustment amount is obtained, and the acquisition frequency of the electromyographic signal acquisition device is adjusted and optimized.

Images