Risk level determination method, device, electronic device and storage medium

Abstract

The present invention discloses a method, device, electronic device and storage medium for determining risk level, wherein the method comprises: obtaining a to-be-processed ECG signal of a target user, and filtering the to-be-processed ECG signal based on a preset signal processing method to obtain a target ECG signal; extracting features from the target ECG signal to obtain target heart rate information, and determining the risk level of the target user based on the target heart rate information. The problem that the detection of the heart rate information of high-altitude workers is not accurate enough, resulting in inaccurate risk assessment results for the workers based on the heart rate information and the existence of safety risks, is solved. By performing amplitude filtering and minimum mean square value filtering on the ECG signal of the workers, a more accurate ECG signal is obtained, and more accurate heart rate information is obtained based on the processed ECG signal, thereby achieving a more accurate result of risk assessment for the workers.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a risk level determination method, device, electronic device and storage medium. Background Art

[0002] When workers are performing high-altitude operations, there is a risk of falling from a height, which may even endanger their lives.

[0003] At present, in order to ensure the safety of workers during high-altitude operations, risk assessment of high-altitude operations is usually carried out based on expert experience or theoretical analysis, or risk warning is given verbally by managers. However, such risk warning methods do not take into account the influencing factors in the actual operation process, resulting in inaccurate risk assessment and the inability to provide timely safety protection when workers are at risk.

[0004] In order to solve the above problems, it is necessary to conduct risk assessment when the staff is working, so as to take corresponding safety protection measures in time according to the corresponding risk level of the staff. Summary of the invention

[0005] The present invention provides a risk level determination method, device, electronic device and storage medium to solve the problem that the heart rate information detection of high-altitude workers is not accurate enough, resulting in inaccurate risk assessment results of the workers based on the heart rate information, and there are safety risks.

[0006] In a first aspect, an embodiment of the present invention provides a risk level determination method, comprising:

[0007] Acquire the target user's to-be-processed ECG signal, and filter the to-be-processed ECG signal based on a preset signal processing method to obtain a target ECG signal; wherein the preset signal processing method includes an amplitude filtering method and a minimum mean square value filtering method;

[0008] Feature extraction is performed on the target electrocardiogram signal to obtain target heart rate information, and based on the target heart rate information, the risk level of the target user is determined.

[0009] In a second aspect, an embodiment of the present invention further provides a risk level determination device, comprising:

[0010] An ECG signal determination module is used to obtain the target user's ECG signal to be processed, and filter the ECG signal to be processed based on a preset signal processing method to obtain a target ECG signal; wherein the preset signal processing method includes an amplitude filtering method and a minimum mean square value filtering method;

[0011] The risk level determination module is used to extract features from the target electrocardiogram signal to obtain target heart rate information, and determine the risk level of the target user based on the target heart rate information.

[0012] In a third aspect, an embodiment of the present invention further provides an electronic device, including:

[0013] at least one processor; and

[0014] a memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the risk level determination method described in any embodiment of the present invention.

[0016] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the risk level determination method described in any embodiment of the present invention when executed.

[0017] The technical solution of the embodiment of the present invention obtains the target user's to-be-processed ECG signal, and filters the to-be-processed ECG signal based on a preset signal processing method to obtain the target ECG signal. By filtering the to-be-processed ECG signal by amplitude filtering and minimum mean square filtering, an accurate target ECG signal can be obtained. Further, feature extraction is performed on the target ECG signal to obtain target heart rate information, and based on the target heart rate information, the risk level of the target user is determined. According to the heart rate interval corresponding to the target heart rate information, the risk level corresponding to the target user can be determined. The problem of inaccurate detection of the heart rate information of high-altitude workers, which leads to inaccurate risk assessment results of the workers based on the heart rate information and the existence of safety risks, is solved. A more accurate ECG signal is obtained by performing amplitude filtering and minimum mean square filtering on the ECG signal of the workers, so that more accurate heart rate information is obtained based on the processed ECG signal, thereby achieving a more accurate result of risk assessment of the workers.

[0018] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] 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.

[0020] Figure 1 is a flow chart of a risk level determination method provided according to Embodiment 1 of the present invention;

[0021] Figure 2 is a schematic diagram of performing risk assessment on a staff member according to Embodiment 1 of the present invention;

[0022] Figure 3 is a flow chart of a risk level determination method provided according to Embodiment 2 of the present invention;

[0023] Figure 4 is a schematic diagram of filtering an electrocardiogram signal according to a second embodiment of the present invention;

[0024] Figure 5 is a schematic diagram of the structure of a risk level determination device provided according to Embodiment 3 of the present invention;

[0025] Figure 6 It is a structural schematic diagram of an electronic device for implementing the risk level determination method of an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein.

[0028] Before elaborating on the technical solution in detail, the application scenarios of the technical solution are briefly introduced in order to more clearly understand the technical solution. When workers are performing high-altitude operations, in order to ensure the safety of the workers and avoid high-altitude falling accidents, it is necessary to conduct risk assessments on the workers in real time, and issue corresponding risk warnings in a timely manner when risks are detected. In the actual operation process, risk assessments need to consider many factors, such as environmental factors, weather factors, whether the workers wear safety protection equipment, and the physical condition of the workers. Among them, when conducting safety assessments, the assessment of the physical condition of the workers is very important, and the assessment of the physical condition can be achieved by collecting the electrocardiogram signals of the workers during the actual operation process, and analyzing and processing the electrocardiogram signals to obtain heart rate information, so as to determine the risk level corresponding to the workers based on the heart rate information.

[0029] It should be noted that the ECG signal is a low-frequency weak electrical signal generated by myocardial contraction, with an amplitude of about 10μV to 5mV and a frequency of about 0.05 to 100Hz. In order to ensure that the heart rate information corresponding to the staff is obtained based on the ECG signal, the tracking of the ECG signal is required to be sufficiently accurate when processing the ECG signal. It is understandable that the most obvious feature in the ECG signal is the QRS wave, and the algorithms used for QRS wave detection mainly include: empirical mode decomposition, wavelet transform method, differential threshold method and artificial neural network algorithm. Among them, the differential threshold method has the advantages of fast detection speed and simple application, but due to the presence of varying degrees of noise interference in the ECG signal, the actual application effect of the differential threshold method is not ideal. The wavelet transform method can maintain good time-frequency characteristics in ECG signal detection and can effectively detect the characteristics of the ECG signal, but the noise in the signal can easily cause the method to have false detection and missed detection. The artificial neural network algorithm can effectively process noise, but it requires a large number of sample training and a large amount of calculation, and cannot be used for real-time calculation.

[0030] In order to solve the above problems, the present technical solution proposes an adaptive filtering algorithm based on the minimum mean square value to detect the QRS wave in the ECG signal, and then obtain more accurate heart rate information based on the QRS wave in the ECG signal.

[0031] Embodiment 1

[0032] Figure 1A flowchart of a risk level determination method is provided for the first embodiment of the present invention. This embodiment can be applied to situations where, when the workers are performing high-altitude operations, the electrocardiogram signals of the workers are collected and filtered to obtain more accurate heart rate information based on the filtered electrocardiogram signals, and the risk of the workers is assessed based on the heart rate information. The method can be executed by a risk level determination device, which can be implemented in the form of hardware and / or software, and can be configured in a computing device that can execute the risk level determination method.

[0033] like Figure 1 As shown, the method includes:

[0034] S110 , obtaining a target user's to-be-processed ECG signal, and filtering the to-be-processed ECG signal based on a preset signal processing method to obtain a target ECG signal.

[0035] In the present technical solution, the target user refers to a worker who is performing high-altitude operations, such as a worker who is performing pole tower operations. The ECG signal to be processed can be understood as the ECG signal of the target user during high-altitude operations collected by the ECG acquisition device. The preset signal processing method includes an amplitude filtering method and a minimum mean square value filtering method. After filtering the ECG signal to be processed based on the preset signal processing method, the target ECG signal can be obtained. It can be understood that the characteristics of the QRS wave in the target ECG signal are clearer, so it is more accurate when tracking the target ECG signal, so that the QRS wave can be detected more conveniently to obtain more accurate heart rate information.

[0036] In actual applications, in order to monitor the physical state of the target user in real time during high-altitude operations, the target user is required to wear an electrocardiogram detection device when performing high-altitude operations, so as to obtain the target user's electrocardiogram signal to be processed during the operation based on the electrocardiogram detection device. After obtaining the electrocardiogram signal to be processed, the electrocardiogram signal to be processed is filtered by amplitude filtering and minimum mean square filtering to obtain the target electrocardiogram signal, so as to determine the target heart rate information corresponding to the target user based on the target electrocardiogram signal.

[0037] S120 , extracting features of the target electrocardiogram signal to obtain target heart rate information, and determining the risk level of the target user based on the target heart rate information.

[0038] Among them, the target heart rate information can be used as one of the important indicators to measure the physical condition of the target user during the operation. The risk level can be used to characterize the risk level of the target user during the work process. The higher the risk level, the higher the danger level of the target user. When conducting risk assessment on the target user, various influencing factors can be considered comprehensively, such as environmental factors, safety protection status factors and the physical condition of the target user. In this technical solution, the physical condition of the target user is mainly characterized based on the target heart rate information, and it is used as an important measurement indicator to reflect the physical condition of the target user.

[0039] Generally speaking, for workers working at heights, if they are inexperienced, they may be highly nervous during work. At this time, the heart rate information of the workers is significantly higher than that of the normal state. When the workers are too nervous, the risk level during the work will increase. Alternatively, when the workers are in poor physical condition, the heart rate information is also significantly higher than that of the normal state. Therefore, the target heart rate information based on the target user can more intuitively reflect the physical condition of the target user during the work.

[0040] Specifically, when the target ECG signal is obtained, the target ECG signal is detected based on the QRS wave detection method to obtain the target heart rate information. Currently, the methods for detecting the QRS wave of the ECG signal include differential method, bandpass filtering method, wavelet transform, morphological operation, length and energy transformation artificial neural network and genetic algorithm, etc. The target heart rate information can be obtained by extracting the QRS wave of the target ECG signal, and then the risk level of the target user can be determined according to the target heart rate information.

[0041] Optionally, determining the risk level of the target user based on the target heart rate information includes: determining a target heart rate interval corresponding to the target heart rate information; determining the risk level corresponding to the target heart rate interval based on a target mapping table, and determining the risk level corresponding to the target user.

[0042] In practical applications, in order to determine the risk level based on the target heart rate information, a target mapping table can be constructed in advance according to the correspondence between the heart rate interval and the risk level. After determining the target heart rate information, the corresponding risk level can be determined through the target mapping table according to the target heart rate interval corresponding to the target heart rate information. The target mapping table includes at least one heart rate interval and the risk level corresponding to each heart rate interval.

[0043] Exemplarily, the target mapping table is shown in Table 1:

[0044] Table 1 Mapping table of heart rate interval and risk level

[0045] Risk Level Heart rate range (beats / min-1) Level 1 (160, 180] or (40, 45] Level 2 (100, 160] or (45, 60] Level 3 (60，100]

[0046] Optionally, if the risk level is greater than a preset risk level, the anti-fall device of the target user is controlled to start safety protection measures to provide safety protection for the target user.

[0047] Among them, in order to carry out effective safety protection during the actual operation of the target user, by counting the heart rate information of a large number of workers in the actual operation process, it can be determined that different heart rate information corresponds to different risk levels. For example, the larger the heart rate information, the more nervous the worker's state is, and accordingly, the higher the degree of danger. Based on this, the corresponding preset risk level can be set in advance.

[0048] During the actual operation process, the target user needs to wear corresponding safety protection measures according to the protection requirements for high-altitude operations, such as wearing a fall protection device. When the target user's risk level is greater than the preset risk level, the fall protection device can be turned on to provide safety protection for the target user.

[0049] In order to introduce the technical solution more clearly, a specific example is used to introduce the technical solution. Take the target user's tower operation as an example. Figure 2 As shown in the figure, in the actual operation process, the assessment of the risk level of the target user depends on many safety factors, including (1) the unsafe state of objects, such as failure to use safety protection measures correctly; (2) unsafe behavior of people, which in this technical solution is mainly manifested as the physical condition of the target user; (3) unsafe state of the environment, such as adverse weather conditions such as rain and wind. Among them, this technical solution mainly elaborates on the risk assessment of the physical condition of the target user.

[0050] Specifically, the physical condition of the target user can be reflected by various physiological indicators, such as body temperature, heart rate, blood pressure, work intensity, fear of heights and other factors. Taking into account the actual working scenario, the physical state and behavior of the target user are prone to change. This technical solution mainly conducts risk assessment through the heart rate information of the target user during the actual operation process, and determines the corresponding risk level of the target user. As shown in Table 2, in terms of human unsafe behavior, it can be reflected by the following physiological indicators, and different indicator weights can be set for different physiological indicators, so as to make more comprehensive considerations in the subsequent risk assessment of the target user.

[0051] Table 2 Physiological indicators and corresponding weights

[0052]

[0053] It can be seen from Table 2 that when the target user conducts risk assessment during the pole tower operation, the risk ratio of unsafe human behavior is 0.39, and this factor can be more finely divided into multiple secondary indicators, that is, the factors affecting the physical condition of the target user, and the corresponding secondary weight indicators are set for each influencing factor. In this technical solution, a detailed risk assessment is mainly conducted on the physical condition of the target user. Specifically, this technical solution determines the target heart rate information of the target user as the main measurement indicator of the physical condition of the target user.

[0054] It should be noted that although many influencing factors need to be considered when conducting risk assessment on the target user, which is equivalent to each influencing factor occupying a certain weight when conducting security assessment, the risk assessment attributes of the target user under each influencing factor can be obtained by calculation, and finally the target risk assessment attributes of the target user can be obtained by superimposing each risk assessment attribute. However, in this process, the physical condition of the target user is uncontrollable and cannot be directly set. Therefore, it is necessary to evaluate according to the actual physical condition of the target user, and other influencing factors can be obtained by pre-setting risk assessment attributes. Therefore, this technical solution mainly elaborates on the risk assessment of the influencing factor of the actual physical condition of the target user under the premise of determining other influencing factors.

[0055] The technical solution of the embodiment of the present invention obtains the target user's to-be-processed ECG signal, and filters the to-be-processed ECG signal based on a preset signal processing method to obtain the target ECG signal. By filtering the to-be-processed ECG signal by amplitude filtering and minimum mean square filtering, an accurate target ECG signal can be obtained. Further, feature extraction is performed on the target ECG signal to obtain target heart rate information, and based on the target heart rate information, the risk level of the target user is determined. According to the heart rate interval corresponding to the target heart rate information, the risk level corresponding to the target user can be determined. The problem of inaccurate detection of the heart rate information of high-altitude workers, which leads to inaccurate risk assessment results of the workers based on the heart rate information and the existence of safety risks, is solved. A more accurate ECG signal is obtained by performing amplitude filtering and minimum mean square filtering on the ECG signal of the workers, so that more accurate heart rate information is obtained based on the processed ECG signal, thereby achieving a more accurate result of risk assessment of the workers.

[0056] Embodiment 2

[0057] Figure 3 A flow chart of a risk level determination method provided in Embodiment 2 of the present invention, optionally, obtaining a target user's pending ECG signal, filtering the pending ECG signal based on a preset signal processing method, and refining the target ECG signal.

[0058] like Figure 3 As shown, the method includes:

[0059] S210: Obtain the target user's electrocardiogram signal to be processed.

[0060] S220 . Based on the amplitude filtering condition, perform amplitude filtering on the electrocardiograph signal to be processed to obtain a first filtered signal.

[0061] The amplitude filtering condition can be understood as a detection condition for filtering the ECG signal to be processed, and the amplitude filtering condition in this technical solution includes an upper limit ECG amplitude and a lower limit ECG amplitude. The first filtered signal can be understood as a signal after filtering the ECG signal to be processed based on the amplitude filtering condition.

[0062] In practical applications, the corresponding amplitude filtering conditions are set according to the normal floating range of the human ECG signal, and the ECG signal to be processed is filtered based on the amplitude filtering conditions to filter out the noise signal outside the normal range of the human ECG signal to obtain the first filtered signal.

[0063] Exemplarily, the upper limit ECG amplitude in the amplitude filtering condition is 5mv, and the lower limit ECG amplitude is 3mv. In the acquired target user's to-be-processed ECG signal, there may be ECG signals greater than 5mv or less than 3mv. At this time, the to-be-processed ECG signal is filtered based on the amplitude filtering condition, and the ECG signals greater than the upper limit ECG amplitude and less than the lower limit ECG amplitude in the to-be-processed ECG signal can be filtered out. At this time, the ECG signal that meets the amplitude filtering condition is the first filtered signal.

[0064] S230 , performing secondary filtering on the first filtered signal to obtain a second filtered signal, and obtaining a signal error to be processed based on the second filtered signal and a corresponding expected filtered signal.

[0065] Among them, the expected filtered signal can be understood as the second filtered signal corresponding to the historical moment adjacent to the current moment. It can be understood that the target user's to-be-processed ECG signal can float within a certain range, rather than a fixed value. Correspondingly, the second filtered signal obtained by filtering the target user's to-be-processed ECG signal twice can also float within a certain signal range. Specifically, based on the difference between the second filtered signal at the current moment and the corresponding expected filtered signal, the error of the to-be-processed signal can be obtained.

[0066] It should be noted that although the first filtered signal is an ECG signal within the normal range of the human body, there may be interference information from other factors in the first filtered signal, such as interference signals caused by muscle contraction, breathing, and body shaking of the target user during activities, or interference factors caused by the device when the ECG acquisition device collects signals. Based on this, in order to obtain more accurate heart rate information corresponding to the target user based on the ECG signal to be processed, it is necessary to first perform secondary filtering on the first filtered signal to obtain the second filtered signal.

[0067] Specifically, the error of the signal to be processed can be obtained based on the difference between the second filtered signal and the expected filtered signal of the target user. Under normal circumstances, when the error of the signal to be processed fluctuates within a certain range, it is a normal signal fluctuation. If the error of the signal to be processed exceeds the preset signal floating range, it indicates that the filter to be adjusted is abnormal during signal tracking, and inaccurate ECG signal detection may occur, resulting in inaccurate heart rate information detection results. Based on this, the technical solution constructs a target filter based on the error of the signal to be processed.

[0068] S240, adjusting the filter to be adjusted according to the error of the signal to be processed to obtain a target filter, and correcting the second filtered signal based on the target filter to obtain a target ECG signal.

[0069] Among them, in the process of processing the ECG signal of the target user, the filter needs to be adjusted in real time according to the error of the signal to be processed. It can be understood that in this technical solution, the filter that processes the first filtered signal at the current moment is the target filter. For the moment corresponding to the target filter, the filter at the previous moment can be regarded as the filter to be adjusted. In practical applications, the second filtered signal can be obtained by filtering the first filtered signal based on the filter to be adjusted. When it is detected that the error of the signal to be processed between the second filtered signal and the expected filtered signal is large, it is necessary to adjust the weight coefficient of the filter to be adjusted according to the error of the signal to be processed to obtain the target filter, so as to correct the second filtered signal based on the target filter to obtain the target ECG signal.

[0070] Optionally, the filter to be adjusted is adjusted according to the error of the signal to be processed to obtain a target filter, and the second filtered signal is filtered based on the target filter to obtain a target ECG signal, including: determining whether the error of the signal to be processed is less than a preset signal error; if so, determining that the filter to be adjusted is the target filter; if not, determining the weight coefficient to be used corresponding to the filter to be adjusted, and adjusting the filter to be adjusted based on the weight coefficient to be used to obtain the target filter.

[0071] Among them, the weight coefficient to be used can be understood as the weight vector with the smallest error of the signal to be processed, which is obtained by adjusting the filter parameters based on an adaptive algorithm. That is to say, when the error of the signal to be processed between the second filtered signal and the corresponding expected filtered signal is large, the weight vector of the filter to be adjusted is adjusted by the weight coefficient to be used to obtain the target filter. At this time, the second filtered signal is corrected based on the target filter so that the error of the signal to be processed corresponding to the corrected second filtered signal is the minimum error.

[0072] For example, Figure 4 As shown, the ECG signal to be processed is obtained, and the ECG signal to be processed is filtered for the first time based on the amplitude filtering condition in the bandpass filter to obtain a first filtered signal. Then, the first filtered signal is input into the LMS adaptive filter (i.e., the filter to be adjusted) to obtain a second filtered signal based on the LMS adaptive filter. Among them, the LMS adaptive filter is a filter based on the least mean square algorithm (LMS). If the error of the signal to be processed corresponding to the second filtered signal is less than the preset signal error, it indicates that the tracking result of the filter to be adjusted for the first filtered signal is more accurate. At this time, the filter to be adjusted can be used as the target filter, and the next first filtered signal can be filtered based on the target filter.

[0073] On the contrary, if the error of the signal to be processed is greater than the preset signal error, it indicates that the tracking result of the filter to be adjusted for the first filtered signal is inaccurate and there is a large error. At this time, it is necessary to adjust the weight coefficient to be used of the filter to be adjusted to obtain the target filter, so as to filter the next first filtered signal based on the adjusted target filter. Exemplarily, the first filtered signal at the current moment is x(n), and x(n) is filtered based on the filter to be processed to obtain the second filtered signal y(n), and the expected filtered signal d(n) at the historical moment adjacent to the current moment is obtained. Based on the difference between the expected filtered signal and the second filtered signal, the error of the signal to be processed e(n) can be obtained. Specifically, the error of the signal to be processed can be obtained based on the following formula:

[0074] e(n)=d(n)-y(n)

[0075] Wherein, e(n) represents the error of the signal to be processed, d(n) represents the desired filtered signal, and y(n) represents the second filtered signal.

[0076] Among them, y(n) can be expressed by the following formula:

[0077] y(n)=ω T (n)x(n)

[0078] Wherein, ω(n) represents the weight coefficient vector of the filter to be adjusted, ω(n)=[ω0(n), ω0(n-1), ..., ω n-1 (n-1)] T , T is the transposed sign, n is the filter order of the filter to be adjusted, x(n) represents the first filtered signal, and y(n) represents the second filtered signal.

[0079] Based on this, when e(n) is greater than the preset signal error, the weight coefficient vector of the filter to be adjusted needs to be adjusted to obtain the target filter with the smallest error of the signal to be processed, and the second filtered signal is corrected based on the target filter to obtain the target ECG signal.

[0080] Specifically, the weight coefficients to be used corresponding to the filter to be adjusted are determined, and the filter to be adjusted is adjusted based on the weight coefficients to be used to obtain a target filter, including: setting the weight coefficients to be determined, and determining the weight coefficients to be adjusted corresponding to at least one historical filtering signal according to the weight coefficients to be determined; adjusting the weight coefficients of the filter to be adjusted based on each weight coefficient to be adjusted to obtain a target filter.

[0081] Among them, the weight coefficients to be determined can be understood as a custom-set weight coefficient vector. In the present technical solution, in order to obtain the target filter, the weight coefficients of the historical filtering signals at at least one historical signal filtering moment can be adjusted based on the weight coefficients to be determined, so as to adjust the weight coefficients of the filter to be adjusted based on the weight coefficients of the second filtering signals at each historical moment and the current moment, and obtain the target filter.

[0082] Specifically, the filter to be adjusted in the technical solution adopts the least mean square filtering method to filter the first filtered signal. The reason is that the least mean square algorithm (LMS) is the most representative adaptive algorithm. The LMS algorithm makes the value of the cost function tend to the minimum value by stochastic gradient descent, that is, the updated time weight vector moves along the negative direction of the gradient estimation of the error performance surface. Assuming that the time is n, the input signal vector, that is, the first filtered signal x(n) = [x1(n), x2(n),…, x n (n)] T It can be expressed by the following formula:

[0083]

[0084] Where h represents the iterative step size of the LMS algorithm; represents the instantaneous gradient, ω(n) represents the weight coefficient vector of the filter to be adjusted at the current moment, and ω(n+1) represents the weight coefficient vector corresponding to the target filter.

[0085] By simply transforming the above formula, we can get the following formula:

[0086]

[0087] in, represents the instantaneous gradient, ω(n) represents the weight coefficient vector of the filter to be adjusted at the current moment, e(n) represents the error of the signal to be processed, and x(n) represents the first filtered signal.

[0088] Let the filter step size of the filter to be adjusted be Combining the above two formulas, we can get the following formula:

[0089] ω(n+1)=ω(n)+2μe(n)x(n)

[0090] Among them, ω(n+1) represents the weight coefficient vector corresponding to the target filter, ω(n) represents the weight coefficient vector of the filter to be adjusted at the current moment, h represents the filtering step size of the filter to be adjusted, e(n) represents the error of the signal to be processed, and x(n) represents the first filtered signal.

[0091] In order to determine the weight coefficient to be used that best matches the adjustment filter, the weight coefficient ρ to be determined can be set, and the weight coefficient vector ω(n+1) of the filter to be adjusted at the next moment is determined based on the weight coefficient to be determined. Specifically, ω(n+1) can be determined by the following formula:

[0092] ω(n+1)=ω(n)+2μe(n)x(n)+ρ[ω(n)-ω(n-1)]

[0093] +ρ 2 [ω(n-2)-ω(n-1)]+ρ 3 [ω(n-3)-ω(n-1)]

[0094] Wherein, ρ represents the weight coefficient to be determined, μ represents the filtering step size of the filter to be adjusted, x(n) represents the first filtered signal, and e(n) represents the error of the signal to be processed.

[0095] Among them, ω(n) represents the weight coefficient vector of the filter to be adjusted at the current moment, ω(nt) represents the weight coefficient vector corresponding to the filter to be adjusted at at least one historical moment adjacent to the current moment, t=1, 2,….

[0096] The advantage of such a setting is that when determining the weight coefficient vector ω(n+1) of the filter to be adjusted at the next moment in the technical solution, the three dynamic weight items are conditioned on the weight coefficient vector corresponding to each historical moment obtained based on the weight coefficient ρ to be determined, which serves to reduce the sensitivity of the LMS algorithm to the dispersion of the eigenvalues ​​of the input signal matrix. The parameter ρ affects the degree of influence of the dynamic weight item. The larger ρ is, the greater the correlation between the updated weight and the previous weights is, and the smaller ρ is, the smaller the correlation between the updated weight and the previous weights is.

[0097] Optionally, determine the maximum eigenvalue corresponding to the second filtered signal; based on the step size determination function, process the maximum eigenvalue and the weight coefficient to be determined to obtain a target filtering step size, so as to use the target filtering step size as the filtering step size of the target filtering function.

[0098] The step length determination function may be understood as a function for determining a filtering step length corresponding to a target filter. The target filtering step length may be understood as a filtering step length used by the target filter when modifying the second filtered signal.

[0099] Specifically, the step size determination function can be expressed by the following formula:

[0100]

[0101] Among them, k represents the target filtering step size of the filter to be adjusted, ρ represents the weight coefficient to be determined, and λ ma x represents the maximum eigenvalue of the autocorrelation matrix of the second filtered signal.

[0102] The advantage of this setting is that after determining the target filter step size corresponding to the target filter based on the weight coefficient to be determined and the maximum eigenvalue of the autocorrelation matrix of the first filtered signal, the noise resistance of the target filter can be improved to more accurately track the second filtered signal, thereby obtaining a more accurate target ECG signal.

[0103] S250: extract features from the target ECG signal to obtain target heart rate information, and determine the risk level of the target user based on the target heart rate information.

[0104] The technical solution of the embodiment of the present invention obtains the target user's to-be-processed ECG signal, and filters the to-be-processed ECG signal based on a preset signal processing method to obtain the target ECG signal. By filtering the to-be-processed ECG signal by amplitude filtering and minimum mean square filtering, an accurate target ECG signal can be obtained. Further, feature extraction is performed on the target ECG signal to obtain target heart rate information, and based on the target heart rate information, the risk level of the target user is determined. According to the heart rate interval corresponding to the target heart rate information, the risk level corresponding to the target user can be determined. The problem of inaccurate detection of the heart rate information of high-altitude workers, which leads to inaccurate risk assessment results of the workers based on the heart rate information and the existence of safety risks, is solved. A more accurate ECG signal is obtained by performing amplitude filtering and minimum mean square filtering on the ECG signal of the workers, so that more accurate heart rate information is obtained based on the processed ECG signal, thereby achieving a more accurate result of risk assessment of the workers.

[0105] Embodiment 3

[0106] Figure 5 This is a schematic diagram of the structure of a risk level determination device provided in Embodiment 3 of the present invention. Figure 5 As shown, the device includes: an electrocardiogram signal determination module 310 and a risk level determination module 320 .

[0107] The ECG signal determination module 310 is used to obtain the target user's ECG signal to be processed, and filter the ECG signal to be processed based on a preset signal processing method to obtain a target ECG signal; wherein the preset signal processing method includes an amplitude filtering method and a minimum mean square value filtering method;

[0108] The risk level determination module 320 is used to extract features from the target ECG signal to obtain target heart rate information, and determine the risk level of the target user based on the target heart rate information.

[0109] The technical solution of the embodiment of the present invention obtains the target user's to-be-processed ECG signal, and filters the to-be-processed ECG signal based on a preset signal processing method to obtain the target ECG signal. By filtering the to-be-processed ECG signal by amplitude filtering and minimum mean square filtering, an accurate target ECG signal can be obtained. Further, feature extraction is performed on the target ECG signal to obtain target heart rate information, and based on the target heart rate information, the risk level of the target user is determined. According to the heart rate interval corresponding to the target heart rate information, the risk level corresponding to the target user can be determined. The problem of inaccurate detection of the heart rate information of high-altitude workers, which leads to inaccurate risk assessment results of the workers based on the heart rate information and the existence of safety risks, is solved. A more accurate ECG signal is obtained by performing amplitude filtering and minimum mean square filtering on the ECG signal of the workers, so that more accurate heart rate information is obtained based on the processed ECG signal, thereby achieving a more accurate result of risk assessment of the workers.

[0110] Optionally, the ECG signal determination module includes: a first filter signal determination submodule, which is used to perform amplitude filtering on the ECG signal to be processed based on the amplitude filtering condition to obtain a first filtered signal; wherein the amplitude filtering condition includes an upper limit ECG amplitude and a lower limit ECG amplitude;

[0111] A signal error determination submodule, configured to perform secondary filtering on the first filtered signal to obtain a second filtered signal, and obtain a signal error to be processed based on the second filtered signal and a corresponding expected filtered signal; wherein the second filtered signal is an electrocardiogram signal obtained by filtering based on the minimum mean square value filtering method;

[0112] The ECG signal determination submodule is used to adjust the filter to be adjusted according to the error of the signal to be processed to obtain a target filter, and to correct the second filtered signal based on the target filter to obtain a target ECG signal.

[0113] Optionally, the ECG signal determination submodule includes: an error judgment unit, used to determine whether the error of the signal to be processed is less than a preset signal error;

[0114] The first unit is used for determining that the filter to be adjusted is a target filter if yes;

[0115] The second unit is configured to, if not, determine the weight coefficients to be used corresponding to the filter to be adjusted, and adjust the filter to be adjusted based on the weight coefficients to be used to obtain a target filter.

[0116] Optionally, the second unit includes: a weight coefficient determination subunit, which is used to set the weight coefficient to be determined, and determine the weight coefficient to be adjusted corresponding to at least one historical filtering signal according to the weight coefficient to be determined;

[0117] The filter determination subunit is used to adjust the weight coefficient of the filter to be adjusted based on each weight coefficient to be adjusted to obtain a target filter.

[0118] Optionally, the second unit further includes: a maximum eigenvalue determining subunit, configured to determine a maximum eigenvalue corresponding to the second filtered signal;

[0119] Based on the step size determination function, the maximum eigenvalue and the weight coefficient to be determined are processed to obtain a target filtering step size, so as to use the target filtering step size as the filtering step size of the target filtering function.

[0120] Optionally, the risk level determination module includes: a heart rate interval determination submodule, used to determine a target heart rate interval corresponding to the target heart rate information;

[0121] The risk level determination submodule is used to determine the risk level corresponding to the target heart rate interval based on the target mapping table, and determine the risk level corresponding to the target user; wherein the target mapping table includes at least one heart rate interval and the risk level corresponding to each heart rate interval.

[0122] Optionally, the risk level determination device is also used to control the target user's anti-fall device to initiate safety protection measures to provide safety protection for the target user if the risk level is greater than a preset risk level.

[0123] The risk level determination device provided in the embodiment of the present invention can execute the risk level determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0124] Embodiment 4

[0125] Figure 6 A schematic diagram of the structure of an electronic device 10 of an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0126] like Figure 6As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0127] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0128] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the risk level determination method.

[0129] In some embodiments, the risk level determination method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the risk level determination method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the risk level determination method in any other appropriate manner (e.g., by means of firmware).

[0130] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0131] The computer programs for implementing the risk level determination method of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0132] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0133] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0134] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0135] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0136] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0137] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining a risk level, characterized in that: include: Acquire the target user's to-be-processed ECG signal, and filter the to-be-processed ECG signal based on a preset signal processing method to obtain a target ECG signal; wherein the preset signal processing method includes an amplitude filtering method and a minimum mean square value filtering method; Extracting features of the target electrocardiogram signal to obtain target heart rate information, and determining the risk level of the target user based on the target heart rate information; The filtering of the to-be-processed ECG signal based on a preset signal processing method to obtain a target ECG signal includes: Based on the amplitude filtering condition, the to-be-processed ECG signal is subjected to amplitude filtering to obtain a first filtered signal; wherein the amplitude filtering condition includes an upper limit ECG amplitude and a lower limit ECG amplitude; Perform secondary filtering on the first filtered signal to obtain a second filtered signal, and obtain a signal error to be processed based on the second filtered signal and a corresponding expected filtered signal; wherein the second filtered signal is an electrocardiogram signal filtered based on the minimum mean square value filtering method; and the expected filtered signal is a second filtered signal corresponding to a historical moment adjacent to the current moment; Adjusting the filter to be adjusted according to the error of the signal to be processed to obtain a target filter, and correcting the second filtered signal based on the target filter to obtain a target ECG signal; The method of adjusting the filter to be adjusted according to the error of the signal to be processed to obtain a target filter, and correcting the second filtered signal based on the target filter to obtain a target electrocardiogram signal includes: Determining whether the error of the signal to be processed is less than a preset signal error; If so, determining that the filter to be adjusted is the target filter; If not, determining the weight coefficients to be used corresponding to the filter to be adjusted, and adjusting the filter to be adjusted based on the weight coefficients to be used to obtain a target filter; The step of determining the weight coefficients to be used corresponding to the filter to be adjusted, and adjusting the filter to be adjusted based on the weight coefficients to be used to obtain a target filter includes: Setting a weight coefficient to be determined, and determining a weight coefficient to be adjusted corresponding to at least one historical filtering signal respectively according to the weight coefficient to be determined; The weight coefficient of the filter to be adjusted is adjusted based on each weight coefficient to obtain a target filter; The step of determining the weight coefficients to be adjusted corresponding to at least one historical filter signal according to the weight coefficients to be determined includes: determining the weight coefficient vector ω(n+1) of the filter to be adjusted at the next moment based on the weight coefficients to be determined by the following formula: ， Among them, ρ represents the weight coefficient to be determined, μ represents the filtering step size of the filter to be adjusted, x(n) represents the first filtered signal, e(n) represents the error of the signal to be processed; ω(n) represents the weight coefficient vector of the filter to be adjusted at the current moment, ω(nt) represents the weight coefficient vector corresponding to at least one historical moment adjacent to the current moment of the filter to be adjusted, t=1,2,….

2. The method according to claim 1, characterized in that Also includes: determining a maximum eigenvalue corresponding to the second filtered signal; Based on the step size determination function, the maximum eigenvalue and the weight coefficient to be determined are processed to obtain a target filtering step size, so as to use the target filtering step size as the filtering step size of the target filtering function.

3. The method according to claim 1, characterized in that The determining the risk level of the target user based on the target heart rate information includes: Determining a target heart rate interval corresponding to the target heart rate information; Based on the target mapping table, the risk level corresponding to the target heart rate interval is determined, and the risk level corresponding to the target user is determined; wherein the target mapping table includes at least one heart rate interval and the risk level corresponding to each heart rate interval.

4. The method according to claim 1, characterized in that: Also includes: If the risk level is greater than a preset risk level, the anti-fall device of the target user is controlled to start safety protection measures to provide safety protection for the target user.

5. A risk level determination device, characterized in that: include: An ECG signal determination module is used to obtain the target user's ECG signal to be processed, and filter the ECG signal to be processed based on a preset signal processing method to obtain a target ECG signal; wherein the preset signal processing method includes an amplitude filtering method and a minimum mean square value filtering method; A risk level determination module, configured to extract features from the target ECG signal to obtain target heart rate information, and determine the risk level of the target user based on the target heart rate information; The ECG signal determination module includes: a first filter signal determination submodule, which is used to perform amplitude filtering on the ECG signal to be processed based on the amplitude filtering condition to obtain a first filtered signal; wherein the amplitude filtering condition includes an upper limit ECG amplitude and a lower limit ECG amplitude; A signal error determination submodule, configured to perform secondary filtering on the first filtered signal to obtain a second filtered signal, and obtain a signal error to be processed based on the second filtered signal and a corresponding expected filtered signal; wherein the second filtered signal is an electrocardiogram signal filtered based on the minimum mean square value filtering method; and the expected filtered signal is a second filtered signal corresponding to a historical moment adjacent to the current moment; The ECG signal determination submodule is used to adjust the filter to be adjusted according to the error of the signal to be processed to obtain a target filter, and to correct the second filtered signal based on the target filter to obtain a target ECG signal; Wherein, the ECG signal determination submodule includes: an error judgment unit, used to determine whether the error of the signal to be processed is less than a preset signal error; The first unit is used for determining that the filter to be adjusted is a target filter if yes; The second unit is configured to determine the weight coefficients to be used corresponding to the filter to be adjusted if no, and adjust the filter to be adjusted based on the weight coefficients to be used to obtain a target filter; The second unit includes: a weight coefficient determination subunit, which is used to set the weight coefficient to be determined, and determine the weight coefficient to be adjusted corresponding to at least one historical filtering signal according to the weight coefficient to be determined; A filter determination subunit, configured to adjust the weight coefficient of the filter to be adjusted based on each weight coefficient to be adjusted, so as to obtain a target filter; The weight coefficient determination subunit is further used to determine the weight coefficient vector ω(n+1) of the filter to be adjusted at the next moment based on the weight coefficient to be determined by the following formula: ， Among them, ρ represents the weight coefficient to be determined, μ represents the filtering step size of the filter to be adjusted, x(n) represents the first filtered signal, e(n) represents the error of the signal to be processed; ω(n) represents the weight coefficient vector of the filter to be adjusted at the current moment, ω(nt) represents the weight coefficient vector corresponding to at least one historical moment adjacent to the current moment of the filter to be adjusted, t=1,2,….

6. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the risk level determination method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the risk level determination method according to any one of claims 1 to 4 when executed.

Images