Respiratory monitoring accuracy optimization method, device, computer equipment and storage medium

Abstract

The present application relates to a method, device, computer equipment and storage medium for optimizing respiratory monitoring accuracy. The method includes: obtaining first indicator values ​​corresponding to at least two physiological indicators respectively; each first indicator value is estimated based on the first PPG signal obtained by sampling the PPG sensor controlled by the sampling controller; based on each first indicator value, the predicted value of each physiological indicator in the next respiratory cycle is predicted; based on each first indicator value and each predicted value, the target sampling parameter of the next respiratory cycle when the estimation accuracy is the highest is determined; based on the target sampling parameter, the sampling controller is adjusted for sampling parameters, and when sampling the next respiratory cycle, the third indicator value of each physiological indicator is obtained based on the adjusted sampling parameter, and the prediction function parameters are updated based on the third indicator value; the prediction function parameters include the calculation parameters corresponding to blood oxygen, heart rate and respiration. The use of this method can improve the estimation accuracy when estimating the indicator value.

Description

Technical Field

[0001] The present application relates to the field of physiological indicator monitoring, and in particular to a method, device, computer equipment and storage medium for optimizing respiratory monitoring accuracy. Background Art

[0002] With the development of physiological index monitoring technology, sampling parameter optimization technology has emerged, which mainly optimizes sampling parameters through the index values ​​of physiological indicators.

[0003] In conventional technology, after the index value of the physiological index is estimated by the signal collected by the sensor, the sampling parameters are optimized according to the characteristics of the index value.

[0004] However, currently only the accuracy of single-dimensional physiological indicators (such as blood oxygen) can be optimized, and the optimization effect is poor, resulting in low accuracy of the indicator values ​​estimated after subsequent sampling. Summary of the invention

[0005] Based on this, it is necessary to provide a multi-feature network-controlled respiratory monitoring accuracy optimization method, device, computer equipment and storage medium that can improve the estimation accuracy when estimating index values ​​in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for optimizing respiratory monitoring accuracy, comprising:

[0007] Acquire first indicator values ​​corresponding to at least two physiological indicators respectively; each of the first indicator values ​​is estimated based on a first PPG signal sampled by a PPG sensor controlled by a sampling controller;

[0008] Predicting the predicted values ​​of the physiological indicators in the next respiratory cycle based on the first indicator values;

[0009] Based on each of the first indicator values ​​and each of the predicted values, determining a target sampling parameter for the next respiratory cycle when the estimation accuracy is the highest; the estimation accuracy is the accuracy of each second indicator value for the next respiratory cycle estimated based on the second PPG signal corresponding to the next respiratory cycle;

[0010] The sampling controller adjusts the sampling parameters based on the target sampling parameters, and when sampling in the next respiratory cycle, obtains the third indicator value of each physiological indicator based on the adjusted sampling parameters, and updates the prediction function parameters based on the third indicator value; the prediction function parameters include calculation parameters corresponding to blood oxygen, heart rate and respiration.

[0011] In one embodiment, each of the first indicator values ​​includes a first heart rate value, a first blood oxygen content, and a first respiratory characteristic value, the first respiratory characteristic value includes a first time interval when the respiratory movement is relatively static, the target sampling parameter also includes multiple sampling moments, and the target sampling parameter of the next respiratory cycle when the estimation accuracy is the highest is determined based on each of the first indicator values ​​and each of the predicted values. The parameter includes:

[0012] Taking the error estimation lower bound as the optimization target, determining each sampling time based on the end time of the first time interval, the sampling value at the end time, and the first blood oxygen content;

[0013] Based on each of the first indicator values ​​and each of the predicted values, the sampling frequency of the next respiratory cycle corresponding to each of the sampling moments when the estimation accuracy is the highest and the emission intensity of the emission unit of the PPG sensor are determined respectively.

[0014] In one embodiment, each of the predicted values ​​includes at least a second time interval in the next respiratory cycle when the respiratory movement is relatively static, and each of the sampling moments includes at least a first moment corresponding to the maximum signal strength of the next respiratory cycle and at least one second moment in the second time interval.

[0015] In one embodiment, each of the first indicator values ​​includes a first heart rate value, a first blood oxygen content and a first respiratory characteristic value, the first respiratory characteristic value includes a first respiratory signal characteristic value and a first time interval of respiratory movement when it is relatively static, and the predicted value of each of the physiological indicators in the next respiratory cycle predicted based on each of the first indicator values ​​includes:

[0016] Predicting a second respiratory signal characteristic value for the next respiratory cycle based on the first heart rate value, the first blood oxygen content, and the first respiratory signal characteristic value;

[0017] Predicting a second blood oxygen content for the next respiratory cycle based on the first blood oxygen content and the second respiratory signal characteristic value;

[0018] A second time interval of the next respiratory cycle when the respiratory movement is relatively static is predicted based on the first time interval and the first heart rate value.

[0019] In one embodiment, the method further comprises:

[0020] Acquire a second PPG signal sampled by the PPG sensor in the next respiratory cycle, and a second time interval of the predicted respiratory movement when it is relatively static;

[0021] determining a third time interval in the next respiratory cycle except the second time interval;

[0022] Based on the prior parameters corresponding to the physiological indicators, filtering the second PPG signal in the second time interval and the third time interval respectively;

[0023] The second indicator value of each of the physiological indicators is estimated based on the filtered second PPG signal.

[0024] In one embodiment, filtering the second PPG signal in the second time interval and the third time interval based on the prior parameters corresponding to each of the physiological indicators includes:

[0025] If there are two target physiological indicators that correspond to the second time interval at the same time among the at least two physiological indicators, respectively determine the correlation between each sampling data corresponding to the second time interval in the second PPG signal and each of the target physiological indicators;

[0026] Each sampled data is filtered based on the prior parameters corresponding to the target physiological index with the highest correlation.

[0027] In one embodiment, each of the second index values ​​includes a second heart rate value, a second blood oxygen content, and a second respiratory characteristic value, and the second index value of each of the physiological indicators estimated based on the filtered second PPG signal includes:

[0028] Extracting a breathing characteristic PPG signal corresponding to breathing, a blood oxygen characteristic PPG signal corresponding to blood oxygen, and a heart rate characteristic PPG signal corresponding to heart rate from the filtered second PPG signal respectively;

[0029] Determine the second respiratory characteristic value based on the respiratory characteristic PPG signal; the second respiratory characteristic value includes the second respiratory signal characteristic value and a fourth time interval when the respiratory movement is relatively static;

[0030] Determine the second blood oxygen content based on the fourth time interval and the blood oxygen characteristic PPG signal;

[0031] The second heart rate value is determined based on the fourth time interval and the heart rate characteristic PPG signal.

[0032] In a second aspect, the present application also provides a respiratory monitoring accuracy optimization device, comprising:

[0033] An acquisition module is used to obtain first indicator values ​​corresponding to at least two physiological indicators respectively; each of the first indicator values ​​is estimated based on a first PPG signal sampled by a PPG sensor controlled by a sampling controller;

[0034] A prediction module, used for predicting the predicted value of each of the physiological indicators in the next respiratory cycle based on each of the first indicator values;

[0035] an optimization module, for determining, based on each of the first indicator values ​​and each of the predicted values, a target sampling parameter of the next respiratory cycle when the estimation accuracy is the highest; the estimation accuracy is the accuracy of each second indicator value of the next respiratory cycle when the second PPG signal corresponding to the next respiratory cycle is estimated;

[0036] An updating module is used to adjust the sampling parameters of the sampling controller based on the target sampling parameters, and when sampling in the next respiratory cycle, obtain the third indicator value of each physiological indicator based on the adjusted sampling parameters, and update the prediction function parameters based on the third indicator value; the prediction function parameters include calculation parameters corresponding to blood oxygen, heart rate and respiration.

[0037] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0038] Acquire first indicator values ​​corresponding to at least two physiological indicators respectively; each of the first indicator values ​​is estimated based on a first PPG signal sampled by a PPG sensor controlled by a sampling controller;

[0039] Predicting the predicted values ​​of the physiological indicators in the next respiratory cycle based on the first indicator values;

[0040] Based on each of the first indicator values ​​and each of the predicted values, determining a target sampling parameter for the next respiratory cycle when the estimation accuracy is the highest; the estimation accuracy is the accuracy of each second indicator value for the next respiratory cycle estimated based on the second PPG signal corresponding to the next respiratory cycle;

[0041] The sampling controller adjusts the sampling parameters based on the target sampling parameters, and when sampling in the next respiratory cycle, obtains the third indicator value of each physiological indicator based on the adjusted sampling parameters, and updates the prediction function parameters based on the third indicator value; the prediction function parameters include calculation parameters corresponding to blood oxygen, heart rate and respiration.

[0042] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0043] Acquire first indicator values ​​corresponding to at least two physiological indicators respectively; each of the first indicator values ​​is estimated based on a first PPG signal sampled by a PPG sensor controlled by a sampling controller;

[0044] Predicting the predicted values ​​of the physiological indicators in the next respiratory cycle based on the first indicator values;

[0045] Based on each of the first indicator values ​​and each of the predicted values, determining a target sampling parameter for the next respiratory cycle when the estimation accuracy is the highest; the estimation accuracy is the accuracy of each second indicator value for the next respiratory cycle estimated based on the second PPG signal corresponding to the next respiratory cycle;

[0046] The sampling controller adjusts the sampling parameters based on the target sampling parameters, and when sampling in the next respiratory cycle, obtains the third indicator value of each physiological indicator based on the adjusted sampling parameters, and updates the prediction function parameters based on the third indicator value; the prediction function parameters include calculation parameters corresponding to blood oxygen, heart rate and respiration.

[0047] The above-mentioned respiratory monitoring accuracy optimization method, device, computer equipment and storage medium predict the predicted value of each physiological index in the next respiratory cycle through the index value prediction, and then determine the target sampling parameters of the next respiratory cycle when the estimation accuracy is the highest based on each first index value and each predicted value, and adjust the sampling controller based on this, and update the sampling parameters of each physiological index, and after sampling the next respiratory cycle, obtain the third index value of each physiological index based on the updated sampling parameter, and update the prediction function parameters based on the third index value; the prediction function parameters include the calculation parameters corresponding to blood oxygen, heart rate and breathing. Therefore, before sampling the sensor signal for the next respiratory cycle, the predicted value of each physiological index of the next respiratory cycle is first predicted, and the target sampling parameter is determined at least based on the predicted value. That is, the sampling parameters used for subsequent sampling are not determined only by the index value obtained by the current estimation, but also combined with the predicted value, so that the target sampling parameter is more suitable for use in the next respiratory cycle sampling, thereby improving the optimization effect. On this basis, after sampling the next respiratory cycle, the prediction function parameters are also updated according to the obtained third index value, so as to realize multi-feature network control, thereby improving the estimation accuracy when the index value is estimated. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 A schematic diagram of a flow chart of a method for optimizing respiratory monitoring accuracy in one embodiment;

[0050] Figure 2 is a graph showing a relationship between respiratory motion and PPG reflection signal intensity over time in one embodiment;

[0051] Figure 3 A schematic diagram of the distribution of each sampling time predicted in one embodiment;

[0052] Figure 4 A waveform diagram of respiratory movement in one embodiment;

[0053] Figure 5 is a waveform diagram after the second time interval and the characteristic signal are fused in one embodiment;

[0054] Figure 6 A schematic diagram of a flow chart of a respiratory monitoring joint optimization method in another embodiment;

[0055] Figure 7 It is a structural block diagram of a respiratory monitoring accuracy optimization device in one embodiment;

[0056] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0058] In an exemplary embodiment, Figure 1 As shown, a method for optimizing respiratory monitoring accuracy is provided, which is described by taking the method applied to a computer device as an example, and includes the following steps 102 to 108. The computer device may be a medical respiratory monitoring device, and the respiratory monitoring device may be a respiratory monitor, a tongue muscle stimulator, or a hypoglossal nerve stimulator.

[0059] It should be noted that the respiratory monitoring device can determine the quality of sleep breathing according to the index values ​​of various physiological indicators, and thereby determine whether to stimulate the tongue muscle or hypoglossal nerve to achieve the purpose of intervening in breathing during sleep. If it is determined that the quality of sleep breathing is low, the tongue muscle or hypoglossal nerve is stimulated to cause the movement of the tongue, thereby relieving upper airway obstruction and improving breathing quality. Among them:

[0060] Step 102, obtaining first indicator values ​​corresponding to at least two physiological indicators respectively; each first indicator value is estimated based on a first PPG signal sampled by a PPG sensor controlled by a sampling controller.

[0061] Among them, physiological indicators include but are not limited to respiration, heart rate and blood oxygen.

[0062] The PPG sensor is attached to the chest of the monitored object. The PPG sensor is a sensor that uses optical technology to measure changes in blood volume. It can collect PPG signals for detecting changes in the intensity of reflected light from the blood, thereby obtaining heart rate values, blood oxygen content, and respiratory characteristic values ​​corresponding to heart rate, blood oxygen, and respiration, including but not limited to heart rate, blood oxygen, and respiration.

[0063] Optionally, the first PPG signal is a correspondence between a moment and a received reflected light, wherein the intensity of the received reflected light is positively correlated with the amount of blood oxygen cells in the blood.

[0064] Optionally, when the sampling controller controls the PPG sensor to sample and obtain the first PPG signal, the sampling controller controls the sampling parameters, specifically, the sampling controller controls the PPG sensor to sample at the sampling time with the sampling frequency and emission intensity. The sampling parameters include but are not limited to the sampling time, sampling frequency and emission intensity.

[0065] Step 104: predicting the predicted value of each physiological index in the next respiratory cycle based on each first index value.

[0066] The next respiratory cycle is obtained by dividing the time series data of the first PPG signal into respiratory cycles. The time series data refers to a data sequence arranged in time order, and the time order is a sampling time order.

[0067] Furthermore, each first index value includes a first heart rate value, a first blood oxygen content and a first respiratory characteristic value, and the first respiratory characteristic value includes a first respiratory signal characteristic value and a first time interval of the respiratory movement when it is relatively static.

[0068] The first time interval refers to a sub-time interval in the time interval corresponding to the current respiratory cycle. Figure 2 As shown in FIG. 1 , during sleep breathing, the reciprocating motion of the chest cavity causes the reflection surface of the PPG signal in the detection node attached to the chest surface of the monitored object to change accordingly, resulting in the reflection signal intensity and the respiratory motion showing the following Figure 2 of relevance.

[0069] Specifically, when the monitored subject performs exhalation and inhalation movements, that is, breathing movements, the PPG reflection signal intensity changes periodically, that is, a breathing cycle is a change from the exhalation completion zone to the inhalation saturation zone, or from the inhalation saturation zone to the exhalation completion zone.

[0070] It can be understood that the current respiratory cycle is the respiratory cycle in which the monitored object is currently performing respiratory movement, which is reflected in the PPG signal being the respiratory cycle in which the intensity of the PPG reflection signal is measured most recently. Correspondingly, the next respiratory cycle is the respiratory cycle in which the monitored object has not yet performed respiratory movement.

[0071] Based on the prediction of each first indicator value, the predicted value of each physiological indicator in the next respiratory cycle is obtained, and the predicted value includes a second respiratory signal characteristic value, a second blood oxygen content, and a second time interval. The second respiratory signal characteristic value, the second blood oxygen content, and the second time interval predicted for the next respiratory cycle are described below:

[0072] The second respiratory signal characteristic value includes a second period, a second amplitude, and a second phase, wherein the second amplitude It can be predicted by the following formula:

[0073] (one)

[0074] in, is the first amplitude in the first respiratory signal characteristic value, and is the empirical formula, is the serial number of the current breathing cycle, are multiple heart rate values ​​of the current breathing cycle, It is the multiple blood oxygen content of the current respiratory cycle.

[0075] Accordingly, the second period and the second phase may be determined by a formula similar to Formula 1, which will not be described in detail herein.

[0076] Second blood oxygen content It can be predicted by the following formula:

[0077] (two)

[0078] in, is the serial number of the current breathing cycle; is the second amplitude, For the second cycle, is the second phase; Reason , and The vector formed; is a vector consisting of multiple first blood oxygen contents.

[0079] The second time interval may be determined by the second starting time and the second end moment Determine, where the second starting time It can be predicted by formula three:

[0080] (three)

[0081] in, is the first starting time of the first time interval; is the empirical formula, It is multiple heart rate values ​​of the current breathing cycle.

[0082] The second ending moment It can be predicted by formula 4:

[0083] (Four)

[0084] in, is the first end time of the first time interval; is the empirical formula, It is multiple heart rate values ​​of the current breathing cycle.

[0085] Step 106, based on each first indicator value and each predicted value, determine the target sampling parameters of the next respiratory cycle when the estimation accuracy is the highest; the estimation accuracy is the accuracy when the second indicator values ​​of the next respiratory cycle are estimated based on the second PPG signal corresponding to the next respiratory cycle; the target sampling parameters include the sampling frequency and the emission intensity of the transmitting unit of the PPG sensor.

[0086] The PPG sensor includes a transmitting unit and a receiving unit, the transmitting unit is used to transmit light, and the receiving unit is used to receive reflected light corresponding to the transmitted light.

[0087] Furthermore, the target sampling parameters also include multiple sampling moments. When determining the target sampling parameters of the next respiratory cycle when the estimation accuracy is highest based on the first indicator values ​​and the predicted values, the error estimation lower bound is first used as the optimization target, and each sampling moment is determined based on the end time of the first time interval, the sampling value at the end time, and the first blood oxygen content. Then, based on the first indicator values ​​and the predicted values, the sampling frequency of the next respiratory cycle when the estimation accuracy is highest and the emission intensity of the transmitting unit of the PPG sensor corresponding to each sampling moment are respectively determined.

[0088] The error estimation lower bound refers to the minimum value that the difference between the calculation result and the true value may reach. In this embodiment, the calculation result refers to each sampling moment.

[0089] Among them, each predicted value includes at least the second time interval when the respiratory movement is relatively static in the next respiratory cycle, and each sampling moment includes at least the first moment corresponding to the maximum signal strength of the next respiratory cycle and at least one second moment in the second time interval. That is, each sampling moment includes at least the moment in the second time interval corresponding to the heart rate or blood oxygen in the next respiratory cycle, and the moment in the time interval corresponding to the breathing in the next respiratory cycle, thereby taking into account the signal characteristics of the PPG signal in different characteristic time intervals, and improving the determination accuracy of each sampling moment.

[0090] It should be noted that the target sampling parameter is determined at the end of the current breathing cycle, that is, at the end of the first time interval.

[0091] Exemplarily, determining the sampling time is to predict the timing signal of the next respiratory cycle. When determining the sampling time, it can be determined by the following formula 5:

[0092] (five)

[0093] in, is the respiratory cycle number, is the predicted probability, is the probability calculation formula, is the sampling time, is the mean value of the PPG signal intensity in the prediction interval, is the signal distribution of the timing signal.

[0094] Accordingly, at the first sampling time after the end time of the predicted first time interval When It should be noted that the distribution parameters in the formula include and Affected by the blood oxygen content, the sampling time is predicted Before that, the distribution parameters need to be updated using the following formulas 6 and 7:

[0095] (six)

[0096] (seven)

[0097] in, is the mean value at the end of the first time interval, i.e., the sampling time The mean value of the previous sampling moment; is the signal distribution of the timing signal at the end time of the first time interval; and is the normal distribution of blood oxygen content.

[0098] like Figure 3 As shown, is the end time of the first time interval. Each sampling time may include - , the solid line in the prediction interval is drawn through the mean corresponding to each sampling time.

[0099] When determining the sampling frequency and emission intensity corresponding to each sampling moment, it can be determined by the following formula 8:

[0100] (eight)

[0101] in, is the maximum estimation accuracy, is the estimated accuracy calculation function, is the sampling time, is the sampling frequency, It should be noted that each first indicator value and each predicted value are known quantities, which are not shown in Formula 8.

[0102] For example, the target sampling parameters corresponding to each sampling time can be predicted by alternating prediction and sampling. After the corresponding target sampling parameters are obtained, the sampling controller controls the PPG sensor to perform sampling with the target sampling parameters, and after sampling, the range of the prediction interval is updated according to the sampling value, so as to make the estimation accuracy higher.

[0103] Step 108, adjusting the sampling parameters of the sampling controller based on the target sampling parameters, and obtaining the third indicator value of each physiological indicator based on the adjusted sampling parameters when sampling in the next respiratory cycle, and updating the prediction function parameters based on the third indicator value; the prediction function parameters include calculation parameters corresponding to blood oxygen, heart rate and respiration.

[0104] The calculation parameters are the parameters in the prediction function (ie, the above formulas 1 to 7) used in the above prediction process.

[0105] Optionally, the original sampling parameters in the sampling controller are updated and adjusted by the target sampling parameters, and then the sensor is controlled to sample and obtain the PPG signal by the adjusted sampling parameters, and then the third index value of each physiological index is obtained by the PPG signal, and the prediction function parameters are updated accordingly. That is, the prediction function parameters are updated by multi-feature network control in real time based on the corresponding index value after sampling, thereby improving the accuracy of the subsequent index value.

[0106] The above method predicts the predicted value of each physiological index in the next respiratory cycle through the index value, and then determines the target sampling parameter of the next respiratory cycle when the estimation accuracy is the highest based on each first index value and each predicted value, and adjusts the sampling controller based on this, and updates the sampling parameters of each physiological index, and after sampling the next respiratory cycle, obtains the third index value of each physiological index based on the updated sampling parameter, and updates the prediction function parameter based on the third index value; the prediction function parameter includes the calculation parameters corresponding to blood oxygen, heart rate and breathing. Thus, before sampling the sensor signal for the next respiratory cycle, the predicted value of each physiological index of the next respiratory cycle is first predicted, and the target sampling parameter is determined at least based on the predicted value. That is, the sampling parameter used for subsequent sampling is not determined only by the index value obtained by the current estimation, but also combined with the predicted value, so that the target sampling parameter is more suitable for use in the next respiratory cycle sampling, thereby improving the optimization effect. On this basis, after sampling the next respiratory cycle, the prediction function parameter is also updated according to the obtained third index value, so as to realize multi-feature network control, thereby improving the estimation accuracy when the index value is estimated.

[0107] In an exemplary embodiment, the above method further includes steps 202 to 208. Among them:

[0108] Step 202, obtaining a second PPG signal sampled by the PPG sensor in the next respiratory cycle, and a second time interval of the predicted respiratory movement when it is relatively static.

[0109] Step 204: determine a third time interval in the next respiratory cycle except the second time interval.

[0110] Step 206 , based on the prior parameters corresponding to the physiological indicators, filter the second PPG signal in the second time interval and the third time interval respectively.

[0111] Step 208: Estimating a second indicator value of each physiological indicator based on the filtered second PPG signal.

[0112] Among them, each physiological index has a different characteristic signal, that is, it has different characteristics on the PPG signal, and the characteristics correspond to the prior parameters of the characteristic signal.

[0113] Exemplarily, in order to avoid information loss, the signal segments corresponding to the second time interval and the third time interval are filtered by the prior parameters corresponding to the corresponding physiological indicators, rather than filtering the complete second PPG signal multiple times by the prior parameters corresponding to all physiological indicators.

[0114] For example, if at least two physiological indicators are respiration and blood oxygen, then when filtering the second PPG signal, the second PPG signal is filtered in the second time interval corresponding to respiration by using the prior parameters corresponding to respiration; and the second PPG signal is filtered in the third time interval corresponding to blood oxygen by using the prior parameters corresponding to blood oxygen. If there are time intervals 1 and 2 on the second PPG signal, where time interval 1 corresponds to respiration and time interval 2 corresponds to blood oxygen, the prior parameters corresponding to respiration are used to filter the signal segment of the second PPG signal corresponding to time interval 1; and the prior parameters corresponding to blood oxygen are used to filter the signal segment of the second PPG signal corresponding to time interval 2.

[0115] It should be noted that after filtering the second PPG signal, characteristic PPG signals corresponding to various physiological indicators can be extracted therefrom.

[0116] It should be noted that when calculating the index values ​​corresponding to the heart rate and blood oxygen, the signal segment corresponding to the time interval of the respiratory movement in the second PPG signal when it is relatively static is generally used for calculation. The index value calculated by this signal segment has a higher accuracy.

[0117] Because of this, the third time interval corresponding to the heart rate and blood oxygen may be the same, and the third time interval is a time interval in a respiratory cycle other than the second time interval corresponding to breathing. Figure 4 As shown, Figure 4 is the waveform of the characteristic PPG signal corresponding to breathing, wherein the first time interval corresponding to breathing includes t o_start -t o_stop and t i_start -t i_stop , the first time interval corresponding to heart rate and blood oxygen is t o_stop -t i_start .

[0118] In one embodiment, if there are common parts in the time intervals corresponding to at least two physiological indicators, the common parts of the time intervals can be divided into intervals at a certain ratio so that the corresponding physiological indicators correspond to different divided intervals. For example, if there are common parts of time interval 3 in time interval 1 corresponding to respiration and time interval 2 corresponding to blood oxygen, then time interval 3 is divided into two equal parts, corresponding to respiration and blood oxygen respectively.

[0119] In another embodiment, based on the prior parameters corresponding to the physiological indicators, filtering is performed on the second PPG signal in the second time interval and the third time interval, respectively, which specifically includes:

[0120] If there are two target physiological indicators that correspond to the second time interval at the same time among the at least two physiological indicators, the correlation between each sampling data corresponding to the second time interval in the second PPG signal and each target physiological indicator is determined respectively; and each sampling data is filtered based on the prior parameters corresponding to the target physiological indicator with the highest correlation.

[0121] It should be noted that the second PPG signal is actually composed of a plurality of sampling data, and its waveform is formed by connecting points corresponding to sampling values ​​corresponding to the sampling data.

[0122] The correlation refers to the matching degree between the sampled data and the prior parameters corresponding to each physiological index.

[0123] Exemplarily, each sampled data has a different correlation with different physiological indicators. When each sampled data is filtered using the prior parameters corresponding to the physiological indicator with the highest correlation, more information of the sampled data can be retained, thereby improving the accuracy of the subsequent estimation of the first indicator value.

[0124] In this embodiment, when determining the index value through the PPG signal, considering that the features corresponding to different physiological indicators are interrelated, the overall PPG signal is not subjected to various filterings respectively, but segmented filtering is implemented through corresponding time intervals. That is, the PPG signal corresponding to each time interval is only subjected to filtering corresponding to one physiological indicator, rather than filtering corresponding to all physiological indicators, thereby avoiding the loss of information in the PPG signal and improving the accuracy of each index value.

[0125] On the basis of the above embodiments, each second index value includes a second heart rate value, a second blood oxygen content, and a second respiratory characteristic value, and the second index value of each physiological index estimated based on the filtered second PPG signal includes the following steps 302 to 308. Among them:

[0126] Step 302: Extract a breathing characteristic PPG signal corresponding to respiration, a blood oxygen characteristic PPG signal corresponding to blood oxygen, and a heart rate characteristic PPG signal corresponding to heart rate from the filtered second PPG signal.

[0127] Among them, each characteristic PPG signal is estimated by calculating the correlation between the filtered second PPG signal and the corresponding characteristic signal, that is, the characteristic signal corresponding to breathing can be estimated to obtain the breathing characteristic PPG signal, the characteristic signal corresponding to blood oxygen can be estimated to obtain the blood oxygen characteristic PPG signal, and the characteristic signal corresponding to heart rate can be estimated to obtain the heart rate characteristic PPG signal.

[0128] Step 304, determining a second respiratory characteristic value based on the respiratory characteristic PPG signal; the second respiratory characteristic value includes the second respiratory signal characteristic value and a fourth time interval when the respiratory movement is relatively static.

[0129] The second breathing signal characteristic value includes a second period, a second amplitude and a second phase.

[0130] Optionally, the second respiratory characteristic value can be directly identified from a waveform corresponding to the respiratory characteristic PPG signal.

[0131] like Figure 4 As shown, Figure 4 is the waveform corresponding to the breathing characteristic PPG signal. i cycle, the exhalation interval t can be identified from the respiratory characteristic PPG signal o_start -t o_stop , inhalation interval t i_start -t i_stop , and t o_stop -t i_start This is the fourth time interval when the state is relatively static.

[0132] Step 306: determine a second blood oxygen content based on the fourth time interval and the blood oxygen characteristic PPG signal.

[0133] like Figure 5 As shown, the fourth time interval is fused with the blood oxygen characteristic PPG signal, and the signal segment of the blood oxygen characteristic PPG signal corresponding to the fourth time interval can be determined in the blood oxygen characteristic PPG signal, that is, t o_stop -t i_start The corresponding signal segment is then used to determine the second blood oxygen content.

[0134] Furthermore, when determining the second blood oxygen content through the signal segment, sampling data is obtained from the signal segment; and then the second blood oxygen content is calculated through the sampling data.

[0135] The calculation process is: determining the first AC component and the first DC component of the red light signal in the sampling data, and the second AC component and the second DC component of the infrared signal; and obtaining the second blood oxygen content based on the first AC component, the first DC component, the second AC component and the second DC component.

[0136] See the following formula 9, the second blood oxygen content Spo 2 can be calculated by formula 9:

[0137] (Nine)

[0138] in, is the first AC component of the red light signal, is the first DC component of the red light signal, is the second AC component of the infrared signal, It is the second DC component of the infrared signal.

[0139] Step 308: Determine a second heart rate value based on the fourth time interval and the heart rate characteristic PPG signal.

[0140] Likewise, if Figure 5 As shown, by fusing the fourth time interval with the heart rate characteristic PPG signal, the signal segment of the heart rate characteristic PPG signal corresponding to the fourth time interval can be determined in the heart rate characteristic PPG signal, that is, t o_stop -t i_start The corresponding signal segment is then used to determine the second heart rate value.

[0141] In an exemplary embodiment, if Figure 6 As shown, the overall process of the method may include steps 1 to 16. Among them:

[0142] Step 1: Based on the sampling controller, the PPG sensor (including the PPG transmitting unit and the PPG receiving unit) is controlled to sample and obtain the PPG signal with the sampling time, sampling frequency and emission intensity, and the PPG signal is input into the PPG feature extractor. Among them, the PPG sensor, as a respiratory monitoring node, can be attached to the chest of the monitored object or placed in its chest cavity.

[0143] Step 2: Perform prior processing and filtering on the PPG signal.

[0144] Step 3: Extract the breathing feature PPG.

[0145] Step 4: Extract the blood oxygen feature PPG.

[0146] Step 5: Extract the heart rate feature PPG.

[0147] Step 6: Perform respiratory motion detection based on the respiratory feature PPG to obtain a first respiratory signal characteristic value and a first time interval of the respiratory motion when it is relatively static.

[0148] Step 7: Calculate the blood oxygen content based on the blood oxygen feature PPG and the first time interval obtained in the subsequent step 9.

[0149] Step 8: Calculate the heart rate value based on the heart rate characteristic PPG and the first time interval obtained in the subsequent step 9.

[0150] Step 9: Input the first time interval into the blood oxygen content calculation module and the heart rate calculation module, so that the blood oxygen content calculation module calculates the first blood oxygen content, and the heart rate calculation module calculates the first heart rate value.

[0151] Step 10: Input a first time interval into the breathing prediction module; provide the breathing prediction module with a second time interval for relatively static breathing movement of the next breathing cycle based on the first blood oxygen content obtained in step 11, the first heart rate value obtained in step 12, and the first time interval to predict a second breathing signal characteristic value for the next breathing cycle.

[0152] Step 11: input the first blood oxygen content into the blood oxygen prediction module, and the blood oxygen prediction module predicts the second blood oxygen content of the next respiratory cycle based on the first blood oxygen content and the second respiratory signal characteristic value obtained in the subsequent step 13.

[0153] Step 12: Input the first heart rate value to the breathing prediction module.

[0154] Step 13: The breathing prediction module inputs the second breathing signal characteristic value to the blood oxygen prediction module.

[0155] Step 14: Input the second respiratory signal characteristic value and the second time interval predicted by the respiratory prediction module into the estimation accuracy optimizer. The estimation accuracy optimizer performs estimation accuracy optimization based on each index value and the predicted value to obtain the target sampling parameter. The estimation accuracy optimizer also obtains the predicted values ​​of other physiological indicators of the next respiratory cycle.

[0156] Step 15: Input the predicted value obtained in the prediction process, such as the second time interval, into the PPG feature extractor.

[0157] Step 16: Input the target sampling parameters to the sampling controller for the sampling controller to adjust the sampling parameters, and when sampling in the next respiratory cycle, obtain the third indicator value of each physiological indicator based on the adjusted sampling parameters, and update the prediction function parameters based on the third indicator value; the prediction function parameters include the calculation parameters corresponding to blood oxygen, heart rate and respiration.

[0158] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0159] Based on the same inventive concept, the embodiment of the present application also provides a respiratory monitoring accuracy optimization device for implementing the respiratory monitoring accuracy optimization method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more respiratory monitoring accuracy optimization device embodiments provided below can refer to the limitations of the respiratory monitoring accuracy optimization method above, and will not be repeated here.

[0160] In an exemplary embodiment, Figure 7 As shown, a respiratory monitoring accuracy optimization device is provided, including: a collection module 702, a prediction module 704, an optimization module 706 and an update module 708, wherein:

[0161] The acquisition module 702 is used to obtain first indicator values ​​corresponding to at least two physiological indicators respectively; each of the first indicator values ​​is estimated based on a first PPG signal sampled by a PPG sensor controlled by a sampling controller;

[0162] A prediction module 704, configured to predict a predicted value of each of the physiological indicators in the next respiratory cycle based on each of the first indicator values;

[0163] an optimization module 706, for determining, based on each of the first indicator values ​​and each of the predicted values, a target sampling parameter for the next respiratory cycle when the estimation accuracy is the highest; the estimation accuracy is the accuracy of each second indicator value for the next respiratory cycle when the second PPG signal corresponding to the next respiratory cycle is estimated;

[0164] The updating module 708 is used to adjust the sampling parameters of the sampling controller based on the target sampling parameters, and when sampling in the next respiratory cycle, obtain the third indicator value of each physiological indicator based on the adjusted sampling parameters, and update the prediction function parameters based on the third indicator value; the prediction function parameters include calculation parameters corresponding to blood oxygen, heart rate and respiration.

[0165] In one embodiment, the optimization module 706 includes:

[0166] A first determining unit, configured to determine each of the sampling moments based on an end moment of the first time interval, a sampling value at the end moment, and the first blood oxygen content, taking an error estimation lower bound as an optimization target;

[0167] The second determination unit is used to determine the sampling frequency of the next respiratory cycle corresponding to each sampling moment when the estimation accuracy is the highest and the emission intensity of the emission unit of the PPG sensor based on each of the first indicator values ​​and each of the predicted values.

[0168] In one embodiment, each of the predicted values ​​includes at least a second time interval in the next respiratory cycle when the respiratory movement is relatively static, and each of the sampling moments includes at least a first moment corresponding to the maximum signal strength of the next respiratory cycle and at least one second moment in the second time interval.

[0169] In one embodiment, the prediction module 704 includes:

[0170] A first prediction unit, configured to predict a second respiratory signal characteristic value for a next respiratory cycle based on the first heart rate value, the first blood oxygen content, and the first respiratory signal characteristic value;

[0171] a second prediction unit, configured to predict a second blood oxygen content in a next respiratory cycle based on the first blood oxygen content and the second respiratory signal characteristic value;

[0172] The third prediction unit is used to predict a second time interval of the respiratory movement of the next respiratory cycle when it is relatively static based on the first time interval and the first heart rate value.

[0173] In one embodiment, the respiratory monitoring accuracy optimization device further comprises:

[0174] An acquisition module is used to acquire a second PPG signal sampled by the PPG sensor in the next respiratory cycle, and a second time interval of the predicted respiratory movement when it is relatively static;

[0175] A determination module, configured to determine a third time interval in the next respiratory cycle except the second time interval;

[0176] a filtering module, configured to filter the second PPG signal in the second time interval and the third time interval respectively based on the prior parameters corresponding to the physiological indicators;

[0177] The estimation module is used to estimate the second indicator value of each of the physiological indicators based on the filtered second PPG signal.

[0178] In one embodiment, the filtering module comprises:

[0179] a third determining unit, configured to respectively determine a correlation between each sampling data corresponding to the second time interval in the second PPG signal and each of the target physiological indicators if there are two target physiological indicators that simultaneously correspond to the second time interval among the at least two physiological indicators;

[0180] The filtering unit is used to filter each sampled data based on the priori parameters corresponding to the target physiological index with the highest correlation.

[0181] In one embodiment, the estimation module comprises:

[0182] an extraction unit, used to extract respectively from the filtered second PPG signal a breathing characteristic PPG signal corresponding to respiration, a blood oxygen characteristic PPG signal corresponding to blood oxygen, and a heart rate characteristic PPG signal corresponding to heart rate;

[0183] a fourth determining unit, configured to determine the second respiratory characteristic value based on the respiratory characteristic PPG signal; the second respiratory characteristic value comprising a second respiratory signal characteristic value and a fourth time interval when the respiratory motion is relatively static;

[0184] a fifth determining unit, configured to determine the second blood oxygen content based on the fourth time interval and the blood oxygen characteristic PPG signal;

[0185] A sixth determination unit is used to determine the second heart rate value based on the fourth time interval and the heart rate characteristic PPG signal.

[0186] Each module in the above-mentioned respiratory monitoring accuracy optimization device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0187] In an exemplary embodiment, a computer device is provided, which may be a respiratory monitoring device, and its internal structure diagram may be as shown in FIG. Figure 8 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through Bluetooth, WIFI, a mobile cellular network, near field communication (Near Field Communication, NFC) or other technologies. When the computer program is executed by the processor, a method for optimizing the accuracy of respiratory monitoring is implemented.

[0188] Those skilled in the art will understand that Figure 8The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0189] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0190] Acquire first indicator values ​​corresponding to at least two physiological indicators respectively; each of the first indicator values ​​is estimated based on a first PPG signal sampled by a PPG sensor controlled by a sampling controller;

[0191] Predicting the predicted values ​​of the physiological indicators in the next respiratory cycle based on the first indicator values;

[0192] Based on each of the first indicator values ​​and each of the predicted values, determining a target sampling parameter for the next respiratory cycle when the estimation accuracy is the highest; the estimation accuracy is the accuracy of each second indicator value for the next respiratory cycle estimated based on the second PPG signal corresponding to the next respiratory cycle;

[0193] The sampling controller adjusts the sampling parameters based on the target sampling parameters, and when sampling in the next respiratory cycle, obtains the third indicator value of each physiological indicator based on the adjusted sampling parameters, and updates the prediction function parameters based on the third indicator value; the prediction function parameters include calculation parameters corresponding to blood oxygen, heart rate and respiration.

[0194] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0195] Taking the error estimation lower bound as the optimization target, determining each sampling time based on the end time of the first time interval, the sampling value at the end time, and the first blood oxygen content;

[0196] Based on each of the first indicator values ​​and each of the predicted values, the sampling frequency of the next respiratory cycle corresponding to each of the sampling moments when the estimation accuracy is the highest and the emission intensity of the emission unit of the PPG sensor are determined respectively.

[0197] In one embodiment, each of the predicted values ​​includes at least a second time interval in the next respiratory cycle when the respiratory movement is relatively static, and each of the sampling moments includes at least a first moment corresponding to the maximum signal strength of the next respiratory cycle and at least one second moment in the second time interval.

[0198] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0199] Predicting a second respiratory signal characteristic value for the next respiratory cycle based on the first heart rate value, the first blood oxygen content, and the first respiratory signal characteristic value;

[0200] Predicting a second blood oxygen content for the next respiratory cycle based on the first blood oxygen content and the second respiratory signal characteristic value;

[0201] A second time interval of the next respiratory cycle when the respiratory movement is relatively static is predicted based on the first time interval and the first heart rate value.

[0202] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0203] Acquire a second PPG signal sampled by the PPG sensor in the next respiratory cycle, and a second time interval of the predicted respiratory movement when it is relatively static;

[0204] determining a third time interval in the next respiratory cycle except the second time interval;

[0205] Based on the prior parameters corresponding to the physiological indicators, filtering the second PPG signal in the second time interval and the third time interval respectively;

[0206] The second indicator value of each of the physiological indicators is estimated based on the filtered second PPG signal.

[0207] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0208] If there are two target physiological indicators that correspond to the second time interval at the same time among the at least two physiological indicators, respectively determine the correlation between each sampling data corresponding to the second time interval in the second PPG signal and each of the target physiological indicators;

[0209] Each sampled data is filtered based on the prior parameters corresponding to the target physiological index with the highest correlation.

[0210] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0211] Extracting a breathing characteristic PPG signal corresponding to breathing, a blood oxygen characteristic PPG signal corresponding to blood oxygen, and a heart rate characteristic PPG signal corresponding to heart rate from the filtered second PPG signal respectively;

[0212] Determine the second respiratory characteristic value based on the respiratory characteristic PPG signal; the second respiratory characteristic value includes the second respiratory signal characteristic value and a fourth time interval when the respiratory movement is relatively static;

[0213] Determine the second blood oxygen content based on the fourth time interval and the blood oxygen characteristic PPG signal;

[0214] The second heart rate value is determined based on the fourth time interval and the heart rate characteristic PPG signal.

[0215] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0216] Acquire first indicator values ​​corresponding to at least two physiological indicators respectively; each of the first indicator values ​​is estimated based on a first PPG signal sampled by a PPG sensor controlled by a sampling controller;

[0217] Predicting the predicted values ​​of the physiological indicators in the next respiratory cycle based on the first indicator values;

[0218] Based on each of the first indicator values ​​and each of the predicted values, determining a target sampling parameter for the next respiratory cycle when the estimation accuracy is the highest; the estimation accuracy is the accuracy of each second indicator value for the next respiratory cycle estimated based on the second PPG signal corresponding to the next respiratory cycle;

[0219] The sampling controller adjusts the sampling parameters based on the target sampling parameters, and when sampling in the next respiratory cycle, obtains the third indicator value of each physiological indicator based on the adjusted sampling parameters, and updates the prediction function parameters based on the third indicator value; the prediction function parameters include calculation parameters corresponding to blood oxygen, heart rate and respiration.

[0220] In one embodiment, the computer program, when executed by a processor, implements the following steps:

[0221] Taking the error estimation lower bound as the optimization target, determining each sampling time based on the end time of the first time interval, the sampling value at the end time, and the first blood oxygen content;

[0222] Based on each of the first indicator values ​​and each of the predicted values, the sampling frequency of the next respiratory cycle corresponding to each of the sampling moments when the estimation accuracy is the highest and the emission intensity of the emission unit of the PPG sensor are determined respectively.

[0223] In one embodiment, each of the predicted values ​​includes at least a second time interval in the next respiratory cycle when the respiratory movement is relatively static, and each of the sampling moments includes at least a first moment corresponding to the maximum signal strength of the next respiratory cycle and at least one second moment in the second time interval.

[0224] In one embodiment, the computer program, when executed by a processor, implements the following steps:

[0225] Predicting a second respiratory signal characteristic value for the next respiratory cycle based on the first heart rate value, the first blood oxygen content, and the first respiratory signal characteristic value;

[0226] Predicting a second blood oxygen content for the next respiratory cycle based on the first blood oxygen content and the second respiratory signal characteristic value;

[0227] A second time interval of the next respiratory cycle when the respiratory movement is relatively static is predicted based on the first time interval and the first heart rate value.

[0228] In one embodiment, the computer program, when executed by a processor, implements the following steps:

[0229] Acquire a second PPG signal sampled by the PPG sensor in the next respiratory cycle, and a second time interval of the predicted respiratory movement when it is relatively static;

[0230] determining a third time interval in the next respiratory cycle except the second time interval;

[0231] Based on the prior parameters corresponding to the physiological indicators, filtering the second PPG signal in the second time interval and the third time interval respectively;

[0232] The second indicator value of each of the physiological indicators is estimated based on the filtered second PPG signal.

[0233] In one embodiment, the computer program, when executed by a processor, implements the following steps:

[0234] If there are two target physiological indicators that correspond to the second time interval at the same time among the at least two physiological indicators, respectively determine the correlation between each sampling data corresponding to the second time interval in the second PPG signal and each of the target physiological indicators;

[0235] Each sampled data is filtered based on the prior parameters corresponding to the target physiological index with the highest correlation.

[0236] In one embodiment, the computer program, when executed by a processor, implements the following steps:

[0237] Extracting a breathing characteristic PPG signal corresponding to breathing, a blood oxygen characteristic PPG signal corresponding to blood oxygen, and a heart rate characteristic PPG signal corresponding to heart rate from the filtered second PPG signal respectively;

[0238] Determine the second respiratory characteristic value based on the respiratory characteristic PPG signal; the second respiratory characteristic value includes the second respiratory signal characteristic value and a fourth time interval when the respiratory movement is relatively static;

[0239] Determine the second blood oxygen content based on the fourth time interval and the blood oxygen characteristic PPG signal;

[0240] The second heart rate value is determined based on the fourth time interval and the heart rate characteristic PPG signal.

[0241] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0242] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0243] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0244] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for optimizing respiratory monitoring accuracy, characterized in that: The method comprises: Acquire first indicator values ​​corresponding to at least two physiological indicators respectively; each of the first indicator values ​​is estimated based on a first PPG signal sampled by a PPG sensor controlled by a sampling controller; Based on each of the first indicator values, a prediction function is used to predict a predicted value of each of the physiological indicators in the next respiratory cycle; wherein each of the predicted values ​​at least includes a second time interval when the respiratory movement in the next respiratory cycle is relatively static; Based on each of the first indicator values ​​and each of the predicted values, determining a target sampling parameter for the next respiratory cycle when the estimation accuracy is the highest; the estimation accuracy is the accuracy of each second indicator value for the next respiratory cycle estimated based on the second PPG signal corresponding to the next respiratory cycle; The sampling controller is adjusted for sampling parameters based on the target sampling parameters, and when sampling in the next respiratory cycle, a third indicator value of each of the physiological indicators is obtained based on the adjusted sampling parameters, and a prediction function parameter is updated based on the third indicator value; the prediction function parameter includes calculation parameters corresponding to blood oxygen, heart rate and respiration; Acquire a second PPG signal sampled by the PPG sensor in the next respiratory cycle, and a second time interval of the predicted respiratory movement when it is relatively static; determining a third time interval in the next respiratory cycle except the second time interval; Based on the prior parameters corresponding to the physiological indicators, filtering the second PPG signal in the second time interval and the third time interval respectively; A second indicator value of each of the physiological indicators is estimated based on the filtered second PPG signal.

2. The method according to claim 1, characterized in that Each of the first indicator values ​​includes a first heart rate value, a first blood oxygen content, and a first respiratory characteristic value, the first respiratory characteristic value includes a first time interval when the respiratory movement is relatively static, the target sampling parameter also includes multiple sampling moments, and the target sampling parameter of the next respiratory cycle when the estimation accuracy is the highest is determined based on each of the first indicator values ​​and each of the predicted values. The parameter includes: Taking the error estimation lower bound as the optimization target, determining each sampling time based on the end time of the first time interval, the sampling value at the end time, and the first blood oxygen content; Based on each of the first indicator values ​​and each of the predicted values, the sampling frequency of the next respiratory cycle corresponding to each of the sampling moments when the estimation accuracy is the highest and the emission intensity of the emission unit of the PPG sensor are determined respectively.

3. The method according to claim 2, characterized in that Each of the sampling moments includes at least a first moment corresponding to the maximum signal strength of the next respiratory cycle and at least one second moment in the second time interval.

4. The method according to claim 1, characterized in that: Each of the first indicator values ​​includes a first heart rate value, a first blood oxygen content, and a first respiratory characteristic value, the first respiratory characteristic value includes a first respiratory signal characteristic value and a first time interval of respiratory movement when it is relatively static, and the predicted value of each of the physiological indicators in the next respiratory cycle obtained based on each of the first indicator values ​​includes: Predicting a second respiratory signal characteristic value for the next respiratory cycle based on the first heart rate value, the first blood oxygen content, and the first respiratory signal characteristic value; Predicting a second blood oxygen content for the next respiratory cycle based on the first blood oxygen content and the second respiratory signal characteristic value; A second time interval of the next respiratory cycle when the respiratory movement is relatively static is predicted based on the first time interval and the first heart rate value.

5. The method according to claim 1, characterized in that The filtering of the second PPG signal in the second time interval and the third time interval based on the priori parameters corresponding to the physiological indicators includes: If there are two target physiological indicators that correspond to the second time interval at the same time among the at least two physiological indicators, respectively determine the correlation between each sampling data corresponding to the second time interval in the second PPG signal and each of the target physiological indicators; Each sampled data is filtered based on the prior parameters corresponding to the target physiological index with the highest correlation.

6. The method according to claim 5, characterized in that Each of the second index values ​​includes a second heart rate value, a second blood oxygen content, and a second respiratory characteristic value. The second index value of each of the physiological indicators estimated based on the filtered second PPG signal includes: Extracting a breathing characteristic PPG signal corresponding to breathing, a blood oxygen characteristic PPG signal corresponding to blood oxygen, and a heart rate characteristic PPG signal corresponding to heart rate from the filtered second PPG signal respectively; Determine the second respiratory characteristic value based on the respiratory characteristic PPG signal; the second respiratory characteristic value includes the second respiratory signal characteristic value and a fourth time interval when the respiratory movement is relatively static; Determine the second blood oxygen content based on the fourth time interval and the blood oxygen characteristic PPG signal; The second heart rate value is determined based on the fourth time interval and the heart rate characteristic PPG signal.

7. A respiratory monitoring accuracy optimization device, characterized in that: The device comprises: An acquisition module is used to obtain first indicator values ​​corresponding to at least two physiological indicators respectively; each of the first indicator values ​​is estimated based on a first PPG signal sampled by a PPG sensor controlled by a sampling controller; A prediction module, used to predict the predicted value of each of the physiological indicators in the next respiratory cycle based on the first indicator values ​​using a prediction function; wherein each of the predicted values ​​at least includes a second time interval when the respiratory movement is relatively static in the next respiratory cycle; an optimization module, for determining, based on each of the first indicator values ​​and each of the predicted values, a target sampling parameter of the next respiratory cycle when the estimation accuracy is the highest; the estimation accuracy is the accuracy of each second indicator value of the next respiratory cycle when the second PPG signal corresponding to the next respiratory cycle is estimated; An updating module, configured to adjust the sampling parameters of the sampling controller based on the target sampling parameters, and obtain the third indicator value of each of the physiological indicators based on the adjusted sampling parameters during the next respiratory cycle sampling, and update the prediction function parameters based on the third indicator value; the prediction function parameters include calculation parameters corresponding to blood oxygen, heart rate and respiration; An acquisition module is used to acquire a second PPG signal sampled by the PPG sensor in the next respiratory cycle, and a second time interval of the predicted respiratory movement when it is relatively static; A determination module, configured to determine a third time interval in the next respiratory cycle except the second time interval; a filtering module, configured to filter the second PPG signal in the second time interval and the third time interval respectively based on the prior parameters corresponding to the physiological indicators; The estimation module is used to estimate the second indicator value of each of the physiological indicators based on the filtered second PPG signal.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images