Human body sign signal error code detection method and device and medium

Abstract

The invention discloses a human body sign signal error code detection method and device, and a medium. The method comprises the following steps: generating a first state vector according to a human body sign signal and a preset signal value; determining an estimated sign signal at the current moment according to the human body sign signal at the previous moment through a filtering model; determining a prediction signal interval at the current moment according to the human body sign signals in the preset time window through a constraint model; generating a second state vector based on the estimated sign signal and the predicted signal interval; and according to the first state vector and the second state vector, determining whether an error code exists in the human body sign signal at the current moment, and outputting a detection result. According to the scheme, error codes in the human body sign signals can be effectively detected, and the signal accuracy is guaranteed.

Description

Technical Field

[0001] The present application relates to the field of signal detection, and in particular to a method, device and medium for detecting error codes of human vital sign signals. Background Art

[0002] Error code detection refers to the detection of human vital signs signals through sensors. Due to the influence of noise, sensor performance, device wear, and other issues, the acquired human vital signs signals may not be actual signals. Error code detection is the detection of these erroneous signals and the output of corresponding error codes.

[0003] For example, various types of noise in the environment, including electromagnetic interference, mechanical vibration noise, etc., may be superimposed on the human vital sign signal, causing the originally pure signal to be distorted. Alternatively, the sensitivity of the sensor may decrease as the usage time increases, causing the collected signal to deviate from the true value. Alternatively, if the sensor is not worn correctly, resulting in displacement, etc., the collected signal may also be inaccurate. In this case, the human vital sign signal obtained is not real. Once it is regarded as valid data, it may mislead medical staff to make inappropriate treatment decisions. For example, it may lead to incorrect adjustment of drug dosage, change of treatment plan, etc., which will not only fail to effectively treat the disease, but may even worsen the patient's condition. Summary of the Invention

[0004] In order to solve the above problems, this application proposes a method for detecting error codes of human vital sign signals, including:

[0005] Generate a first state vector according to the human body vital sign signal and a preset signal value;

[0006] Determine the estimated vital sign signal at the current moment based on the human vital sign signal at the previous moment through a filtering model; determine the predicted signal interval at the current moment based on the estimated vital sign signal and the human vital sign signal within a preset time window through a constraint model;

[0007] generating a second state vector based on the estimated vital sign signal and the predicted signal interval;

[0008] Determine whether there is an error code in the human body vital sign signal at the current moment according to the first state vector and the second state vector, and output a detection result.

[0009] Optionally, determining the estimated vital sign signal at the current moment based on the human vital sign signal at the previous moment through a filtering model includes:

[0010] Linearizing the state equation of the filtering model to obtain a linear state equation;

[0011] The estimated vital sign signal at the current moment is obtained according to the optimal estimation result of the human vital sign signal at the previous moment through the linear state equation.

[0012] Optionally, determining the predicted signal interval at the current moment based on the human body vital signs signal within a preset time window through a constraint model includes:

[0013] The signal standard deviation and signal mean are calculated based on the human body sign signal within the preset time window;

[0014] The signal standard deviation, signal mean, human body vital sign signal at the previous moment and the estimated vital sign signal are input into the constraint model, and the constraint model is used to determine the predicted signal interval at the current moment.

[0015] Optionally, the predicted signal interval at the current moment includes a maximum critical value and a minimum critical value;

[0016] The calculation formula of the maximum critical value is:

[0017]

[0018] The calculation formula of the minimum critical value is:

[0019]

[0020] Among them, Pro_CgmSignal i-1 Ave_Pro_CgmSignal is the human body sign signal at the previous moment; N is the signal mean; Std_Pro_CgmSignal N is the signal standard deviation; is the estimated vital sign signal at the current moment; γ and β are preset coefficients.

[0021] Optionally, the preset signal value includes a first signal value, a second signal value, and a third signal value. Before generating the first state vector according to the human body vital sign signal and the preset signal value, the method further includes:

[0022] preprocessing the human body vital sign signal according to the first signal value, the second signal value, and the third signal value to obtain a preprocessed vital sign update signal;

[0023] Correspondingly, generating a first state vector according to the human body vital sign signal and the preset signal value includes:

[0024] A first state vector is generated according to the vital sign update signal, the first signal value, the second signal value, and the third signal value.

[0025] Optionally, preprocessing the human vital sign signal according to the first signal value, the second signal value, and the third signal value includes:

[0026] If the human body sign signal is greater than the first signal value, updating the human body sign signal to the first signal value;

[0027] If the human body sign signal is greater than the human body sign signal at the previous moment, and the difference is greater than the second signal value, updating the human body sign signal to the sum of the human body sign signal at the previous moment and the second signal value;

[0028] If the human body sign signal is smaller than the human body sign signal at the previous moment, and the absolute value of the difference is greater than the third signal value, the human body sign signal is updated to the difference between the human body sign signal at the previous moment and the third signal value.

[0029] Optionally, generating a first state vector according to the vital sign update signal, the first signal value, the second signal value, and the third signal value includes:

[0030] If the vital sign update signal is greater than or equal to the first signal value, or if the vital sign update signal is 0, determining the state value corresponding to the vital sign update signal as a first preset value;

[0031] If the vital sign update signal is greater than the human body vital sign signal at the previous moment, and the absolute value of the difference is greater than or equal to the second signal value, determining the state value corresponding to the vital sign update signal as the first preset value;

[0032] If the human body sign signal is less than the human body sign signal at the previous moment, and the absolute value of the difference is greater than or equal to the third signal value, determining the state value corresponding to the vital sign update signal as the first preset value;

[0033] Otherwise, the state value corresponding to the vital sign update signal is determined as a second preset value;

[0034] A first state vector is generated according to the state value of each vital sign update signal.

[0035] Optionally, generating a second state vector based on the estimated vital sign signal and the predicted signal interval includes:

[0036] If the estimated vital sign signal is within the predicted signal interval, determining the state value corresponding to the estimated vital sign signal as a second preset value;

[0037] If the estimated vital sign signal is not within the predicted signal interval, determining the state value corresponding to the estimated vital sign signal as a first preset value;

[0038] A second state vector is generated according to the state value of each estimated vital sign signal.

[0039] Optionally, determining whether an error code exists in the human vital sign signal at a current moment according to the first state vector and the second state vector includes:

[0040] If the state value of the first state vector corresponding to the estimated vital sign signal or the state value of the second state vector corresponding to the estimated vital sign signal is the first preset value, it is determined that an error code exists in the human vital sign signal at the current moment;

[0041] If the state value of the first state vector corresponding to the estimated vital sign signal is the second preset value and the state value of the second state vector is the second preset value, it is determined that the human vital sign signal at the current moment is a valid code.

[0042] Optionally, after determining whether an error code exists in the human vital sign signal at the current moment according to the first state vector and the second state vector, the method further includes:

[0043] Determine the optimal estimation result corresponding to the human body sign signal at the current moment, and collect and determine the number of consecutive occurrences of the human body sign signal at the current moment as a valid code;

[0044] If the number of consecutive occurrences is greater than or equal to a third preset value, outputting the human vital sign signal at the current moment as an unrepairable signal;

[0045] If the number of consecutive occurrences is less than the third preset value, the human body vital sign signal at the current moment is output as a repairable signal.

[0046] On the other hand, the present application also proposes a device for detecting error codes of human vital signs signals, comprising:

[0047] at least one processor; and,

[0048] a memory communicatively connected to the at least one processor; wherein,

[0049] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: detect the error code of the human vital sign signal as described in any of the above examples.

[0050] On the other hand, the present application also proposes a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured as: a method for detecting an error code of a human vital sign signal as described in any of the above examples.

[0051] The method for detecting error codes of human vital sign signals proposed in this application can bring the following beneficial effects:

[0052] The present application constructs a first state vector based on human vital signs signals and preset signal values, and a second state vector based on estimated vital signs signals and predicted signal intervals, thereby comprehensively considering the changing trends and expected ranges of human vital signs signals, thereby more accurately identifying abnormalities or error codes and improving signal accuracy; in addition, the filtering model is used to estimate the vital signs signals at the current moment, and the predicted signal interval is determined in combination with the constraint model, which can evaluate and detect human vital signs signals in real time without relying on a large amount of historical data, thereby improving the timeliness of error code detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0054] Figure 1 Schematic diagram of the flow of a method for detecting an error code of a human vital sign signal in an embodiment of the present application;

[0055] Figure 2 This is a schematic diagram of a method for detecting an error code of a human vital sign signal under one scenario in an embodiment of the present application;

[0056] Figure 3 This is a schematic diagram of a device for detecting error codes of human vital sign signals in an embodiment of the present application. DETAILED DESCRIPTION

[0057] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0058] The following describes in detail the technical solutions provided by various embodiments of the present application in conjunction with the accompanying drawings.

[0059] like Figure 1 As shown, the embodiment of the present application provides a method for detecting error codes of human vital sign signals, including:

[0060] S101: Generate a first state vector according to a human body vital sign signal and a preset signal value.

[0061] Vital sign signals refer to signals representing the user's vital signs that are collected by corresponding devices and sensors. For example, they can be blood glucose signals collected by a continuous glucose monitor (CGM) sensor implanted subcutaneously, or electrocardiogram (ECG) signals collected by an electrocardiograph, or blood pressure or blood oxygen signals collected by a sphygmomanometer or oximeter.

[0062] The causes of error codes can be roughly divided into the following categories: low current phenomenon caused by equipment failure, current saturation phenomenon caused by short circuit between equipment electrodes, current signal fluctuation phenomenon caused by equipment or during use, violent oscillation of current signal caused by electrode abnormality or during use, and continuous current decrease phenomenon caused by electrode performance degradation.

[0063] Taking blood glucose signals as an example, when collecting signals through a continuous blood glucose monitor, it is easily affected by noise, sensor performance drift, screen electrode breakage, calibration error, wearing and squeezing, etc., resulting in the current obtained on the working electrode not being the Faraday current generated by the actual glucose and enzyme reaction. By performing error code detection (also known as ErrorCode detection), the working current I of the effective and normal CGM sensor can be identified. w , improve the accuracy and reliability of CGM blood glucose monitoring and reduce the error rate, and facilitate the analysis and positioning of error codes.

[0064] Before executing step S101, it is necessary to perform initialization settings in advance and set the corresponding signal interval and preset signal value for the human body sign signal. The signal interval mainly refers to which intervals of the human body sign signal are normal signals, and which intervals are obviously abnormal signals. Of course, the signal interval can be further divided into multiple sub-intervals based on needs, or different signal interval division methods can be set based on different scenarios. The preset signal value includes a first signal value, a second signal value, and a third signal value, which are the critical values ​​of the corresponding signal intervals.

[0065] Specifically, for the signal value of the human vital sign signal, a first signal interval corresponding to the signal value is generated based on a preset conventional value interval and the sensitivity of the data detection sensor. The conventional value interval refers to the interval within which the human vital sign signal lies when the human body is normal, which can be obtained through corresponding medical standards or big data analysis.

[0066] Taking the human blood sugar value as an example, the conventional value interval is [Glu min ,Glu max] indicates that the conventional numerical interval of the signal value is preferably in the range of [3mmol / L, 30mmol / L]. This range is only an exemplary range under a conventional scenario. In actual implementation, it can be changed accordingly based on the change of the scenario (for example, according to the change of external conditions such as the user's age and the user's region). Unless otherwise specified, the ranges exemplified in the embodiments of this application are exemplary ranges and do not represent fixed values ​​for the corresponding intervals or values. They will not be described in detail later.

[0067] The sensitivity of the data detection sensor is represented by Ks, and the first signal interval can be [Glu min *Ks,Glu max *Ks], that is, the operating current I w range.

[0068] Similarly, for the change value of the human body sign signal, a second signal interval corresponding to the change value is generated according to a preset normal value interval. There are multiple second signal intervals, which correspond to at least rising values ​​and falling values ​​respectively.

[0069] Taking the human blood sugar value as an example, the human blood sugar drop value usually does not exceed 4-5mmol / L per hour. At this time, it is set according to 6mmol / L. The normal value range of the drop value [Glu_down_drift min ,Glu_down_drift max ] is set to [0,0.1mmol / L / min]. Similarly, the rise in blood sugar in the human body can usually reach 0.2mmol / L / min to 0.5mmol / L / min. The normal range of the rise can be [Glu_up_drift min ,Glu_up_drift max ] is set to [0, 0.5mmol / L / min]. At this time, for the rising value and the falling value, the corresponding normal value interval can be directly set to the corresponding second signal interval.

[0070] However, it is difficult to describe the influence of other factors in the actual scene during actual measurement only by using the conventional numerical interval and the conventional value interval. Therefore, for the first signal interval, the left endpoint is corrected to a fixed value lower than the current value, and the right endpoint is corrected to a fixed value greater than the current value, and the variable value is obtained by the current value and the first coefficient. For example, the left endpoint of the first signal interval is corrected to 0, and the right endpoint is corrected to Glu max*Ks*(1+α), where α is a non-zero positive value, preferably 20%, thereby expanding the range of the right endpoint. Of course, the right endpoint can also be represented in other ways, as long as the range of the right endpoint can be expanded, thereby expanding the first signal interval and increasing robustness. Correspondingly, the first signal value is set to Glu max *Ks*(1+α).

[0071] Similarly, for the second signal interval, the right endpoint is modified to be greater than the current value and a variable value obtained by multiplying the current value and the second coefficient. For example, the right endpoint of the second signal interval with a decreasing value is modified to Glu_down_drift max *(1+β), when Glu_down_drift max =0.1mmol / L / min, the second signal interval of the descending value is [0, 0.1*(1+β)mmol / L / min]. The right end point of the second signal interval of the ascending value is corrected to Glu_up_drift max *(1+λ), when Glu_up_drift max =0.5mmol / L / min, the second signal interval of the rising value is [0, 0.5*(1+λ)mmol / L / min]. Among them, β and λ are both non-zero positive values, which are preferably 30%, thereby expanding the range of the right endpoint. Of course, the right endpoint can also be represented by other methods, as long as the range of the right endpoint can be expanded, thereby expanding the second signal interval and increasing robustness. Correspondingly, the second signal value is set to Glu_up_drift max *(1+λ), set the third signal value to Glu_down_drift max *(1+β).

[0072] After the initialization, the corresponding human body sign signal is obtained, and the initialized signal interval and preset signal value are determined for the human body sign signal. For different human body sign signals, different signal intervals and preset signal values ​​can be initialized and set respectively.

[0073] like Figure 2 As shown, the human body sign signal is preprocessed based on the preset signal value, thereby updating the human body sign signal. The main purpose of preprocessing is to update the human body sign signal whose corresponding value exceeds the preset signal value to facilitate subsequent processing. Of course, the preprocessed signal can be marked accordingly to facilitate subsequent processing to determine whether the signal has been updated based on the mark.

[0074] Specifically, obtain the input human body sign signal CgmSignal i, where i refers to the i-th moment, if the signal value of the human body sign signal exceeds the first signal value, that is, CgmSignal i >Glu max *Ks*(1+α), then the first signal value Glu max *Ks*(1+α) is used as the updated value of the human body vital sign signal.

[0075] Based on human body signs, through ΔSignal i =CgmSignal i -CgmSignal i-1 Get the change value ΔSignal of the human body's vital signs signal i , CgmSignal i-1 is the human body sign signal at the i-1th moment.

[0076] Among them, the change value is divided into rising value and falling value. For rising value, if the change value of the human body sign signal exceeds the second signal value corresponding to the rising value, that is, ΔSignal i >Glu_up_drift max *(1+λ), then the human body sign signal CgmSignal i Updated to CgmSignal i-1 +Glu_up_drift max *(1+λ), of course, this value cannot exceed the first signal value Glu max *Ks*(1+α).

[0077] Similarly, for a decreasing value, if the change value of the human body sign signal exceeds the third signal value corresponding to the decreasing value, that is, ΔSignal i <-Glu_down_drift max *(1+β), then the human body sign signal CgmSignal i Updated to CgmSignal i-1 -Glu_down_drift max *(1+β), of course, this value needs to be greater than 0.

[0078] After preprocessing the human body vital sign signal to obtain a vital sign update signal, it meets the requirements of the preset signal value. At this time, a first state vector is generated based on the preprocessed human body vital sign signal and the preset signal value.

[0079] The vital sign update signal is represented in the form of a vector to obtain a signal vector. The first state vector mainly indicates whether the signal vector is updated due to exceeding a preset signal value.

[0080] Specifically, when the sign update signal CgmSignali ≥Glu max *Ks*(1+α), or CgmSignal i =0, or ΔSignal i ≥Glu_up_drift max *(1+λ), or ΔSignal i ≤-Glu_down_drift max *(1+β), it means that the vital sign update signal is updated because it exceeds the preset signal value. At this time, the corresponding first state vector CgmStatus i It is recorded as the first preset value 0, and at other times it can be recorded as the second preset value 1.

[0081] After the above processing, the human body sign signal obtains two sets of vector data, namely:

[0082] Pro_CgmSignal, the set of human body signs corresponding to the signal n =[Pro_CgmSignal1, Pro_CgmSignal2……Pro_CgmSignal n ], where Pro_CgmSignal i It refers to the updated vital signs signal after preprocessing, and n is the total number of moments.

[0083] The set CgmStatus corresponding to the first state vector n =[CgmStatus1, CgmStatus2...CgmStatus n ].

[0084] At this time, the signal vector and the first state vector are used as inputs of the filtering model and the constraint model to facilitate subsequent error code recognition.

[0085] S102: Determine the estimated vital sign signal at the current moment according to the human vital sign signal at the previous moment through a filtering model; determine the predicted signal interval at the current moment according to the human vital sign signal within a preset time window through a constraint model.

[0086] Taking blood glucose levels as an example, in real-world CGM signal systems, usage and interference can cause the collected blood glucose signals to be nonlinear. However, in the prediction process of the filtering model, the nonlinear system can be approximated as a linear system, resulting in more accurate prediction results.

[0087] Based on this, Figure 2As shown in the figure, in a nonlinear system, the filtering model performs Taylor series on the nonlinear state equation and observation equation around the filter value, and deletes the second-order and higher-order terms, thereby linearizing the state equation and approximating the nonlinear system to a linear system. The standard Kalman filtering algorithm is then used to estimate the signal vector of the human vital sign signal.

[0088] To expand on this, the standard Kalman filter technique is usually applicable to making the best estimate of the target state under the condition of a linear Gaussian model, and its state equation is: k+1 =f(x k )+W k , the observation equation is: k =h(x k )+v k Among them, the state equation f and the observation equation h are nonlinear functions, k is the discrete time, and the process noise W k-1 and observation noise v k are unrelated and satisfy the covariance Q k and R k Gaussian distribution.

[0089] Assume that the state estimate at time k is known and the estimated variance P k|k , perform Taylor series expansion on the state equation and observation equation, and ignore the high-order terms to obtain the state equation: The observation equation is: Among them, F k and H k The state equation f and the observation equation h are The Jacobian matrix at .

[0090] At this time, a linearized filter model is used for prediction, which includes: P k+1|k =F k P k F k T +Q k .in, It is the estimated characteristic signal x at time k+1 based on the information at time k k+1 The prediction, P k+1|k is the predicted covariance matrix, Q k is the covariance matrix of the process noise.

[0091] It should be noted that when the new input signal y k+1|kWhen a signal is determined to be valid, the state estimation needs to be updated to obtain the optimal estimation result corresponding to the input signal so that it can be applied to the signal detection at the next moment. The corresponding optimal estimation result determination process is as follows:

[0092] K k+1 =P k+1|k H k+1 T (H k+1 P k+1|k H k+1 T +R k+1 ) -1 ;

[0093]

[0094] P k+1|k+1 =(IK k+1 H k+1 )P k+1|k ;

[0095] Among them, K k+1 is the Kalman gain, is the updated state estimate, P k+1|k+1 is the updated covariance matrix, R k+1 is the covariance matrix of the observation noise.

[0096] Based on this, when using a filter model for prediction, we first determine the state equation f and observation equation h contained in the filter model and set the initial values ​​of the filter model parameters. The initial values ​​of the parameters required for the estimation process mainly include the initial distribution of the initial state and its covariance matrix, the process noise covariance matrix, and the initial distribution of the measurement noise covariance matrix.

[0097] Through the state equation, according to the optimal estimation result of the human body sign signal at the previous moment (moment k), the first predicted value of the human body sign signal at the current moment (moment k+1) is obtained.

[0098] The linearized state equation is obtained by obtaining the Jacobian matrix of the nonlinear state equation. Based on the linearized state equation and the error covariance matrix at the previous moment (time k), the second predicted value of the error covariance matrix at the current moment (time k+1) is obtained.

[0099] Based on the first and second predicted values, a filter gain is calculated, which is used to weigh the new and old information. Based on the filter gain and the measured value of the human vital sign signal at the previous moment (i.e., time k), the optimal estimate of the human vital sign signal at the current moment (time k+1) and the posterior estimate of the error covariance matrix are obtained. This process is repeated until the final moment is reached.

[0100] Of course, in addition to the standard Kalman filter, other filtering algorithms can also be used, such as the extended Kalman filter, the unscented Kalman filter, the particle filter, and other filtering algorithms. Some of these filtering algorithms can perform vector estimation without linearizing the state equation, which increases the estimation accuracy but also increases the algorithm complexity. The choice can be based on the actual situation.

[0101] Of course, in addition to filtering algorithms, for different scenarios, based on actual needs, time series analysis algorithms such as autoregressive moving average models, autoregressive integrated moving average models, or neural network algorithms such as recursive neural networks and long short-term memory networks can be used to estimate signal vectors.

[0102] The filtering model is mainly used to estimate human vital signs signals, while the constraint model is mainly used to constrain the prediction signal interval, so as to facilitate the subsequent signal processing process to determine whether there is an error code in the input signal.

[0103] Specifically, if Figure 2 As shown in the figure, the construction of constraint model by Shewhart control chart is taken as an example to explain.

[0104] First, a suitable time window value N is selected, and the corresponding mean and standard deviation of the human vital sign signal within the preset time window N are determined.

[0105] pass Calculated [Pro_CgmSignal i-N-1 ,Pro_CgmSignal i-1 ]The corresponding mean value Ave_Pro_CgmSignal in the time window N N .

[0106] pass Calculate Pro_CgmSignal i-N-1 ,Pro_CgmSignal i-1 ]The corresponding standard deviation Std_Pro_CgmSignal in the time window N N .

[0107] At least one of the mean and the standard deviation, and the human vital sign signal at the previous moment, are input into a constraint model based on the Shewhart control chart, and the maximum critical value and the minimum critical value of the predicted signal interval of the human vital sign signal at the current moment are output.

[0108] Specifically, a third preset coefficient and standard deviation are used to perform positive compensation on the human vital sign signal at the previous moment to obtain the maximum critical value of the predicted signal interval at the current moment. Furthermore, a fourth preset coefficient and standard deviation are used to perform negative compensation on the human vital sign signal at the previous moment to obtain the minimum critical value of the predicted signal interval at the current moment. The values ​​of the third and fourth preset coefficients are positively correlated with the human vital sign signal at the previous moment.

[0109] For example, the mean Ave_Pro_CgmSignal N and standard deviation Std_Pro_CgmSignal N , combined with the previous moment's human body sign signal Pro_CgmSignal i-1 Information and estimated vital signs at the current moment Input into the custom Shewhart control chart constraint model to obtain the current human body sign signal CgmSignal i The predicted signal interval.

[0110] Among them, the customized Shewhart control chart constraint model can be:

[0111]

[0112] Among them, the maximum critical value is:

[0113]

[0114] Minimum critical value:

[0115]

[0116] γ and β are the third and fourth preset coefficients respectively, and their coefficient values ​​need to be calculated based on Pro_CgmSignal i-1 To determine, when Pro_CgmSignal i-1 When it is smaller, the γ and β coefficient values ​​are narrowed. When Pro_CgmSignal i-1 When the value of the third and fourth preset coefficients is larger, the values ​​of the γ and β coefficients are amplified so that they show a positive relationship, and the γ and β coefficients are non-zero positive values. The values ​​of the third and fourth preset coefficients are not limited to the above formulas as long as they are positively correlated with the value of the human body vital sign signal at the previous moment and can achieve corresponding positive compensation and negative compensation.

[0117] Of course, in addition to the Shewhart control chart, similar functions can be achieved through the cumulative sum control chart, exponentially weighted moving average control chart, single value-moving range control chart, etc. to judge the upper and lower tracks of the signal interval.

[0118] Alternatively, based on the needs, the maximum critical value and the minimum critical value of the signal interval can be determined by using autoregressive models, neural networks, support vector regression, etc.

[0119] S103: Generate a second state vector based on the estimated vital sign signal and the predicted signal interval.

[0120] Correspondingly, if the estimated vital sign signal is in the predicted signal interval, the state value corresponding to the estimated vital sign signal is determined as the second preset value; if the estimated vital sign signal is not in the predicted signal interval, the state value corresponding to the estimated vital sign signal is determined as the first preset value; and a second state vector is generated according to the state value of each estimated vital sign signal.

[0121] Specifically, according to the filtering model, the optimal state estimate at the previous moment is used and the current measurement signal x k , find the prior estimate of the current moment judge Is it in the prediction signal interval [LowLimit_CgmSignal i ,upLimit_CgmSignal i ], if it is within the signal interval, the state value of the second state vector CgmInGap i Record as the second preset value 1, if not, record as the first preset value 0, thereby generating the second state vector [CgmInGap1, CgmInGap2, CgmInGap3……]

[0122] S104: Determine whether there is an error code in the human body vital sign signal at the current moment according to the first state vector and the second state vector, and output a detection result.

[0123] like Figure 2 As shown, if there is no abnormal signal, the human body sign signal is directly output. If there is an abnormal signal, it is further determined whether the abnormal signal is repairable. The determination of the abnormal signal can be determined based on whether the estimated signal vector is within the estimated signal interval. If not, an abnormality exists.

[0124] Specifically, for a human vital sign signal at a single moment, if its corresponding first state vector indicates that the change state in the preprocessing is unchanged (that is, it is recorded as 1 in the set corresponding to the first state vector), and its corresponding second state vector indicates that it is in the estimated signal interval (that is, it is recorded as 1 in the set corresponding to the second state vector), then the human vital sign signal at this single moment is regarded as a valid signal, and the valid sequence is recorded as CgmValid n =CgmStatus n∩CgmInGap n .

[0125]

[0126] Among them, CgmStatus i is the first state vector, CgmInGap i is the second state vector.

[0127] Based on this, set the vector XorCgmVaild = CgmValid⊕M, where vector M = [1, 1, 1…], and vector CgmValid is the valid signal CgmValid i Vector composed of.

[0128] If the number of consecutive 1s in the vector XorCgmVaild is not less than the preset threshold Err_Thd, it indicates that the signal is continuously being preprocessed and updated or that it does not hit the estimated signal interval. In this case, an unrecoverable error code is output. Otherwise, the error code is determined to be repairable, and no error code is output. The code repair process can be similar to the signal preprocessing process described above, that is, correcting excessively high or low signal values ​​to a reasonable range.

[0129] On the other hand, Figure 3 As shown, the embodiment of the present application further provides a device for detecting error codes of human vital sign signals, including:

[0130] at least one processor; and,

[0131] a memory communicatively connected to the at least one processor; wherein,

[0132] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: detect the error code of the human vital sign signal as described in any of the above embodiments.

[0133] An embodiment of the present application further provides a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured to be: a method for detecting an error code of a human vital sign signal as described in any of the above embodiments.

[0134] The various embodiments in this application are described in a progressive manner. Similar portions between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the device and medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simple. For relevant portions, refer to the descriptions of the method embodiments.

[0135] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects to their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0136] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0137] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0138] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0139] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0140] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0141] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0142] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0143] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0144] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for detecting error codes of human vital signs signals, characterized in that: include: Generate a first state vector according to the human body vital sign signal and a preset signal value; Determine the estimated vital sign signal at the current moment based on the human vital sign signal at the previous moment through a filtering model; Determining a predicted signal interval at a current moment based on the estimated vital sign signal and the human vital sign signal within a preset time window through a constraint model; generating a second state vector based on the estimated vital sign signal and the predicted signal interval; Determine whether there is an error code in the human body vital sign signal at the current moment according to the first state vector and the second state vector, and output a detection result.

2. The method according to claim 1, characterized in that The estimated vital sign signal at the current moment is determined based on the human vital sign signal at the previous moment through the filtering model, including: Linearizing the state equation of the filtering model to obtain a linear state equation; The estimated vital sign signal at the current moment is obtained according to the optimal estimation result of the human vital sign signal at the previous moment through the linear state equation.

3. The method according to claim 1, characterized in that Determining the predicted signal interval at the current moment according to the estimated vital sign signal and the human vital sign signal within a preset time window through a constraint model includes: The signal standard deviation and signal mean are calculated based on the human body sign signal within the preset time window; The signal standard deviation, signal mean, human body vital sign signal at the previous moment and the estimated vital sign signal are input into the constraint model, and the constraint model is used to determine the predicted signal interval at the current moment.

4. The method according to claim 3, characterized in that The predicted signal interval at the current moment includes a maximum critical value and a minimum critical value; The calculation formula of the maximum critical value is: The calculation formula of the minimum critical value is: Among them, Pro_CgmSignal i-1 Ave_Pro_CgmSignal is the human body sign signal at the previous moment; N is the signal mean; Std_Pro_CgmSignal N is the signal standard deviation; γ and β are preset coefficients.

5. The method according to claim 1, wherein The preset signal values ​​include a first signal value, a second signal value, and a third signal value. Before generating the first state vector according to the human body vital sign signal and the preset signal values, the method further includes: preprocessing the human body vital sign signal according to the first signal value, the second signal value, and the third signal value to obtain a preprocessed vital sign update signal; Correspondingly, generating a first state vector according to the human body vital sign signal and the preset signal value includes: A first state vector is generated according to the vital sign update signal, the first signal value, the second signal value, and the third signal value.

6. The method according to claim 5, characterized in that Preprocessing the human body vital sign signal according to the first signal value, the second signal value, and the third signal value includes: If the human body sign signal is greater than the first signal value, updating the human body sign signal to the first signal value; If the human body sign signal is greater than the human body sign signal at the previous moment, and the difference is greater than the second signal value, updating the human body sign signal to the sum of the human body sign signal at the previous moment and the second signal value; If the human body sign signal is smaller than the human body sign signal at the previous moment, and the absolute value of the difference is greater than the third signal value, the human body sign signal is updated to the difference between the human body sign signal at the previous moment and the third signal value.

7. The method according to claim 5, characterized in that Generating a first state vector according to the vital sign update signal, the first signal value, the second signal value, and the third signal value includes: If the vital sign update signal is greater than or equal to the first signal value, or if the vital sign update signal is 0, determining the state value corresponding to the vital sign update signal as a first preset value; If the vital sign update signal is greater than the human body vital sign signal at the previous moment, and the absolute value of the difference is greater than or equal to the second signal value, determining the state value corresponding to the vital sign update signal as the first preset value; If the human body sign signal is less than the human body sign signal at the previous moment, and the absolute value of the difference is greater than or equal to the third signal value, determining the state value corresponding to the vital sign update signal as the first preset value; Otherwise, the state value corresponding to the vital sign update signal is determined as a second preset value; A first state vector is generated according to the state value of each vital sign update signal.

8. The method according to claim 1, characterized in that Generating a second state vector based on the estimated vital sign signal and the predicted signal interval includes: If the estimated vital sign signal is within the predicted signal interval, determining the state value corresponding to the estimated vital sign signal as a second preset value; If the estimated vital sign signal is not within the predicted signal interval, determining the state value corresponding to the estimated vital sign signal as a first preset value; A second state vector is generated according to the state value of each estimated vital sign signal.

9. The method according to claim 1, characterized in that Determining whether an error code exists in a human body vital sign signal at a current moment according to the first state vector and the second state vector includes: If the state value of the first state vector corresponding to the estimated vital sign signal or the state value of the second state vector corresponding to the estimated vital sign signal is the first preset value, it is determined that an error code exists in the human vital sign signal at the current moment; If the state value of the first state vector corresponding to the estimated vital sign signal is the second preset value and the state value of the second state vector is the second preset value, it is determined that the human vital sign signal at the current moment is a valid code.

10. The method according to claim 9, characterized in that After determining whether an error code exists in the human vital sign signal at the current moment according to the first state vector and the second state vector, the method further includes: Determine the optimal estimation result corresponding to the human body sign signal at the current moment, and collect and determine the number of consecutive occurrences of the human body sign signal at the current moment as a valid code; If the number of consecutive occurrences is greater than or equal to a third preset value, outputting the human vital sign signal at the current moment as an unrepairable signal; If the number of consecutive occurrences is less than the third preset value, the human body vital sign signal at the current moment is output as a repairable signal.

11. A device for detecting error codes of human vital signs signals, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for detecting error codes of human vital sign signals as described in any one of claims 1 to 10.

12. A non-volatile computer storage medium storing computer executable instructions, characterized in that: The computer executable instructions are configured as: a method for detecting an error code of a human vital sign signal according to any one of claims 1 to 10.

Images