Blood pressure prediction method and electronic equipment

Abstract

The invention is applicable to the technical field of electronic equipment, and provides a blood pressure prediction method and electronic equipment.The method comprises the steps that in response to a blood pressure prediction instruction, a current photoplethysmography (PPG) signal of a user is obtained; performing feature extraction on the PPG signal to determine a plurality of blood pressure related features corresponding to the PPG signal; fusing the plurality of blood pressure related features to generate a target input feature corresponding to the PPG signal; and inputting the target input feature into a blood pressure prediction model to determine diastolic pressure and systolic pressure of the user. Therefore, the PPG signal detection module is integrated in the electronic equipment to collect the PPG signal, and the blood pressure is predicted according to the multiple signal characteristics related to the blood pressure and corresponding to the PPG signal, so that a user can conveniently measure the blood pressure at any time, the convenience of blood pressure measurement is improved, and the user experience is improved. And the accuracy and reliability of blood pressure prediction are ensured.

Description

Technical Field

[0001] The present application belongs to the technical field of electronic equipment, and in particular, relates to a blood pressure prediction method, electronic equipment, a chip system and a computer-readable storage medium. Background Art

[0002] Blood pressure refers to the pressure of blood ejected by the heart in the blood vessels. If normal blood pressure cannot be maintained, problems such as inability to provide adequate nutrition to the body and loss of organ function will arise. In particular, when blood pressure is too high, arteriosclerosis will occur in the blood vessels, which can cause a variety of diseases. Blood pressure is a key factor in determining health risks, and regular blood pressure checks are necessary, especially in the context of increasing life expectancy and an aging population. The traditional method of measuring blood pressure is to use a mercury sphygmomanometer or an electronic sphygmomanometer to measure blood pressure, but the disadvantage of the traditional method is that individuals need to go to the hospital or purchase measuring instruments to obtain blood pressure data, which is not only very inconvenient, but also costly.

[0003] With the widespread popularity and rapid development of electronic devices such as mobile phones, smart watches, and bracelets, the functions of electronic devices are becoming more and more powerful. Providing a blood pressure measurement function in such portable electronic devices so that users can conveniently measure their blood pressure at any time is an urgent problem to be solved. Summary of the invention

[0004] The embodiments of the present application provide a blood pressure prediction method, an electronic device, a chip system, a computer-readable storage medium, and a computer program product, which can solve the problem of urgently needing to provide a blood pressure measurement function in portable electronic devices commonly used by users, so that users can conveniently measure their blood pressure at any time, thereby improving the convenience of blood pressure measurement.

[0005] In a first aspect, an embodiment of the present application provides a blood pressure prediction method, comprising: in response to a blood pressure prediction instruction, obtaining a user's current photoplethysmography (PPG) signal; performing feature extraction on the PPG signal to determine a plurality of blood pressure-related features corresponding to the PPG signal; fusing the plurality of blood pressure-related features to generate a target input feature corresponding to the PPG signal; and inputting the target input feature into a blood pressure prediction model to determine the user's diastolic and systolic blood pressure.

[0006] In this way, the PPG signal of the user is collected by the PPG sensor in the electronic device, and multiple signal features are extracted from the PPG signal to determine multiple signal features related to the user's blood pressure, and then the multiple blood pressure related features are integrated as the input of the blood pressure prediction model to predict the user's blood pressure. Therefore, by integrating the PPG signal detection module in the electronic device to collect PPG signals, and predicting blood pressure based on multiple blood pressure related signal features corresponding to the PPG signal, it can not only make the user very convenient to measure blood pressure at any time, improve the convenience of blood pressure measurement, but also ensure the accuracy and reliability of blood pressure prediction.

[0007] In a possible implementation manner of the first aspect, the blood pressure-related characteristics include at least two of the following characteristics: morphological characteristics, spectral characteristics, time domain characteristics, and invasive continuous arterial blood pressure (ABP) characteristics corresponding to the PPG signal.

[0008] In this way, by extracting multiple signal features from the user's PPG signal, we can obtain the morphological features, spectral features, time domain features, ABP features and other signal features related to the user's blood pressure corresponding to the PPG signal, and input the fusion features of these features into the blood pressure prediction model to predict diastolic and systolic blood pressure. Since these signal features are closely related to the user's blood pressure characteristics, blood pressure prediction is performed using these features, which further improves the accuracy and reliability of blood pressure prediction.

[0009] Optionally, in another possible implementation of the first aspect, the blood pressure prediction model includes a backbone network, a first subnetwork, and a second subnetwork; accordingly, inputting the target input feature into the blood pressure prediction model to determine the diastolic blood pressure and systolic blood pressure of the user includes:

[0010] Input the target input features into the backbone network to generate shared output features corresponding to the PPG signal;

[0011] The shared output features are input into the first sub-network to determine the diastolic pressure;

[0012] The shared output features are fed into the second subnetwork to determine systolic blood pressure.

[0013] In this way, since human blood pressure measurement usually requires the prediction of diastolic and systolic blood pressure, and the connection between diastolic and systolic blood pressure and different features may be different, a blood pressure prediction model can be constructed based on a multi-task model, so that after shared feature extraction through the backbone network, different sub-networks can be used to predict diastolic and systolic blood pressure respectively, so that according to the two different prediction tasks of diastolic and systolic blood pressure prediction, further adaptive feature extraction is performed through different sub-networks to obtain more accurate diastolic and systolic blood pressure prediction results, which further improves the accuracy and reliability of blood pressure prediction.

[0014] Optionally, in another possible implementation of the first aspect, the backbone network includes N multi-scale modules, where N is a positive integer; accordingly, the step of inputting the target input feature into the backbone network to generate a shared output feature corresponding to the PPG signal includes:

[0015] The target input features are input into the backbone network, and each multi-scale module is used to extract multi-scale features of the target input features in turn, so as to perform N multi-scale feature extractions on the target input features and generate shared output features.

[0016] In this way, by stacking multiple multi-scale modules in the backbone network of the blood pressure prediction model to improve the network depth, and performing multi-scale feature extraction on the target input features, the model's ability to learn the key information of the input features is improved, thereby further improving the accuracy and reliability of blood pressure prediction.

[0017] Optionally, in yet another possible implementation of the first aspect, the target input feature is input into the backbone network, and each multi-scale module is used to sequentially perform multi-scale feature extraction on the target input feature, so as to perform N times of multi-scale feature extraction on the target input feature to generate a shared output feature, including:

[0018] The i-th intermediate feature is input into the i+1-th multi-scale module, and the i+1-th multi-scale feature extraction is performed on the target input feature to generate the i+1-th intermediate feature, where the 0th intermediate feature is the target input feature, the Nth intermediate feature is the shared output feature, and i is an integer greater than or equal to 0 and less than N.

[0019] In this way, by performing a residual connection with the original input features of each multi-scale module each time the multi-scale features are extracted, the model's ability to learn the original input features is improved, preventing the loss of key information in the original input features during the blood pressure prediction process, thereby further improving the accuracy and reliability of blood pressure prediction.

[0020] Optionally, in another possible implementation of the first aspect, each of the multi-scale modules includes multiple convolution kernels of different sizes, a first attention module, and a residual connection module; accordingly, the i-th intermediate feature is input into the i+1-th multi-scale module, and the target input feature is subjected to the i+1-th multi-scale feature extraction to generate the i+1-th intermediate feature, including:

[0021] The i-th intermediate feature is input into each convolution kernel of the i+1-th multi-scale module for convolution processing to generate convolution features of different sizes corresponding to the i-th intermediate feature;

[0022] Input each convolution feature into the first attention module of the i+1th multi-scale module to generate a first attention weight corresponding to each convolution feature, and fuse each convolution feature according to the first attention weight corresponding to each convolution feature to generate an i+1th multi-scale fusion feature;

[0023] The i-th intermediate feature and the i+1-th multi-scale fusion feature are input into the residual connection module of the i+1-th multi-scale module to generate the i+1-th intermediate feature.

[0024] In this way, multi-scale feature extraction is performed on the target input features through multiple convolution kernels of different sizes, and the weights corresponding to features of different scales are learned through the attention mechanism. The original input features of each multi-scale module are fused with the extracted multi-scale features through residual connections, so that higher weights are given to features with a higher correlation with blood pressure through the attention mechanism, and the network's learning ability of input features is enhanced through residual connections, thereby further improving the accuracy and reliability of blood pressure prediction.

[0025] Optionally, in another possible implementation of the first aspect, the size of each of the convolution kernels is determined according to the interval of the PPG signal.

[0026] In this way, by determining the size of each convolution kernel in the multi-scale module according to the interval of the PPG signal, the multi-scale features extracted by the multi-scale module are more matched with the key features of the PPG signal, thereby further improving the accuracy and reliability of blood pressure prediction.

[0027] Optionally, in another possible implementation of the first aspect, the first subnetwork includes a first hybrid attention module, a first convolutional layer and a first fully connected layer, and the second subnetwork includes a second hybrid attention module, a second convolutional layer and a second fully connected layer.

[0028] Optionally, in yet another possible implementation of the first aspect, the step of inputting the shared output feature into the first sub-network to determine the diastolic pressure includes:

[0029] Inputting the shared output feature into the first hybrid attention module to determine a first hybrid attention weight matrix corresponding to the shared output feature;

[0030] Weighting the shared output feature according to the first hybrid attention weight matrix to generate a first sub-output feature corresponding to the shared output feature;

[0031] The first sub-output feature is input into the first convolutional layer and the first fully connected layer to determine the diastolic pressure.

[0032] In this way, after extracting the shared output features corresponding to the PPG signal, the shared output features are input into the first sub-network for predicting diastolic pressure to further extract features from the shared output features, and the hybrid attention weight matrix of the shared output features in the diastolic pressure prediction task is determined through the hybrid attention mechanism, so that features with a higher correlation with diastolic pressure have a higher weight, thereby making the first output sub-feature contain more key information related to diastolic pressure, thereby further improving the accuracy and reliability of diastolic pressure prediction.

[0033] Optionally, in yet another possible implementation of the first aspect, the step of inputting the shared output feature into the second sub-network to determine the systolic blood pressure includes:

[0034] Inputting the shared output features into the second hybrid attention module to determine a second hybrid attention weight matrix corresponding to the shared output features;

[0035] Weighting the shared output feature according to the second mixed attention weight matrix to generate a second sub-output feature corresponding to the shared output feature;

[0036] The second sub-output features are input into the second convolutional layer and the second fully connected layer to determine the systolic blood pressure.

[0037] In this way, after extracting the shared output features corresponding to the PPG signal, the shared output features are input into the second sub-network for predicting systolic blood pressure to further extract features from the shared output features, and the hybrid attention weight matrix of the shared output features in the systolic blood pressure prediction task is determined through the hybrid attention mechanism, so that features with a higher correlation with systolic blood pressure have a higher weight, thereby making the second output sub-feature contain more key information related to systolic blood pressure, thereby further improving the accuracy and reliability of diastolic blood pressure prediction.

[0038] In a second aspect, an embodiment of the present application provides a blood pressure prediction device, comprising: a first acquisition module, used to obtain a user's current PPG signal in response to a blood pressure prediction instruction; a first determination module, used to extract features from the PPG signal to determine a plurality of blood pressure-related features corresponding to the PPG signal; a first generation module, used to fuse a plurality of blood pressure-related features to generate a target input feature corresponding to the PPG signal; and a second determination module, used to input the target input feature into a blood pressure prediction model to determine the user's diastolic and systolic blood pressure.

[0039] In this way, the PPG signal of the user is collected by the PPG sensor in the electronic device, and multiple signal features are extracted from the PPG signal to determine multiple signal features related to the user's blood pressure, and then the multiple blood pressure related features are integrated as the input of the blood pressure prediction model to predict the user's blood pressure. Therefore, by integrating the PPG signal detection module in the electronic device to collect PPG signals, and predicting blood pressure based on multiple blood pressure related signal features corresponding to the PPG signal, it can not only make the user very convenient to measure blood pressure at any time, improve the convenience of blood pressure measurement, but also ensure the accuracy and reliability of blood pressure prediction.

[0040] In a possible implementation manner of the second aspect, the blood pressure-related characteristics include at least two of the following characteristics: morphological characteristics, spectral characteristics, time domain characteristics, and ABP characteristics corresponding to the PPG signal.

[0041] In this way, by extracting multiple signal features from the user's PPG signal, we can obtain the morphological features, spectral features, time domain features, ABP features and other signal features related to the user's blood pressure corresponding to the PPG signal, and input the fusion features of these features into the blood pressure prediction model to predict diastolic and systolic blood pressure. Since these signal features are closely related to the user's blood pressure characteristics, blood pressure prediction is performed using these features, which further improves the accuracy and reliability of blood pressure prediction.

[0042] Optionally, in another possible implementation of the second aspect, the blood pressure prediction model includes a backbone network, a first subnetwork and a second subnetwork; accordingly, the second determination module includes:

[0043] A first generating unit, configured to input the target input feature into the backbone network to generate a shared output feature corresponding to the PPG signal;

[0044] A first determination unit, configured to input the shared output feature into the first sub-network to determine the diastolic pressure;

[0045] The second determination unit is used to input the shared output feature into the second sub-network to determine the systolic blood pressure.

[0046] In this way, since human blood pressure measurement usually requires the prediction of diastolic and systolic blood pressure, and the connection between diastolic and systolic blood pressure and different features may be different, a blood pressure prediction model can be constructed based on a multi-task model, so that after shared feature extraction through the backbone network, different sub-networks can be used to predict diastolic and systolic blood pressure respectively, so that according to the two different prediction tasks of diastolic and systolic blood pressure prediction, further adaptive feature extraction is performed through different sub-networks to obtain more accurate diastolic and systolic blood pressure prediction results, which further improves the accuracy and reliability of blood pressure prediction.

[0047] Optionally, in another possible implementation manner of the second aspect, the backbone network includes N multi-scale modules, where N is a positive integer; accordingly, the first generating unit is specifically configured to:

[0048] The target input features are input into the backbone network, and each multi-scale module is used to extract multi-scale features of the target input features in turn, so as to perform N multi-scale feature extractions on the target input features and generate shared output features.

[0049] In this way, by stacking multiple multi-scale modules in the backbone network of the blood pressure prediction model to improve the network depth, and performing multi-scale feature extraction on the target input features, the model's ability to learn the key information of the input features is improved, thereby further improving the accuracy and reliability of blood pressure prediction.

[0050] Optionally, in yet another possible implementation of the second aspect, the first generating unit is further configured to:

[0051] The i-th intermediate feature is input into the i+1-th multi-scale module, and the i+1-th multi-scale feature extraction is performed on the target input feature to generate the i+1-th intermediate feature, wherein the 0th intermediate feature is the target input feature, the Nth intermediate feature is the shared output feature, and i is an integer greater than or equal to 0 and less than N.

[0052] In this way, by performing a residual connection with the original input features of each multi-scale module each time the multi-scale features are extracted, the model's ability to learn the original input features is improved, preventing the loss of key information in the original input features during the blood pressure prediction process, thereby further improving the accuracy and reliability of blood pressure prediction.

[0053] Optionally, in yet another possible implementation of the second aspect, each of the multi-scale modules includes a plurality of convolution kernels of different sizes, a first attention module, and a residual connection module; accordingly, the first generation unit is further used to:

[0054] The i-th intermediate feature is input into each convolution kernel of the i+1-th multi-scale module for convolution processing to generate convolution features of different sizes corresponding to the i-th intermediate feature;

[0055] Input each convolution feature into the first attention module of the i+1th multi-scale module to generate a first attention weight corresponding to each convolution feature, and fuse each convolution feature according to the first attention weight corresponding to each convolution feature to generate an i+1th multi-scale fusion feature;

[0056] The i-th intermediate feature and the i+1-th multi-scale fusion feature are input into the residual connection module of the i+1-th multi-scale module to generate the i+1-th intermediate feature.

[0057] In this way, multi-scale feature extraction is performed on the target input features through multiple convolution kernels of different sizes, and the weights corresponding to features of different scales are learned through the attention mechanism. The original input features of each multi-scale module are fused with the extracted multi-scale features through residual connections, so that higher weights are given to features with a higher correlation with blood pressure through the attention mechanism, and the network's learning ability of input features is enhanced through residual connections, thereby further improving the accuracy and reliability of blood pressure prediction.

[0058] Optionally, in another possible implementation of the second aspect, the size of each of the convolution kernels is determined according to the interval of the PPG signal.

[0059] In this way, by determining the size of each convolution kernel in the multi-scale module according to the interval of the PPG signal, the multi-scale features extracted by the multi-scale module are more matched with the key features of the PPG signal, thereby further improving the accuracy and reliability of blood pressure prediction.

[0060] Optionally, in another possible implementation of the second aspect, the first subnetwork includes a first hybrid attention module, a first convolutional layer and a first fully connected layer, and the second subnetwork includes a second hybrid attention module, a second convolutional layer and a second fully connected layer.

[0061] Optionally, in yet another possible implementation manner of the second aspect, the first determining unit is specifically configured to:

[0062] Inputting the shared output feature into the first hybrid attention module to determine a first hybrid attention weight matrix corresponding to the shared output feature;

[0063] Weighting the shared output feature according to the first hybrid attention weight matrix to generate a first sub-output feature corresponding to the shared output feature;

[0064] The first sub-output feature is input into the first convolutional layer and the first fully connected layer to determine the diastolic pressure.

[0065] In this way, after extracting the shared output features corresponding to the PPG signal, the shared output features are input into the first sub-network for predicting diastolic pressure to further extract features from the shared output features, and the hybrid attention weight matrix of the shared output features in the diastolic pressure prediction task is determined through the hybrid attention mechanism, so that features with a higher correlation with diastolic pressure have a higher weight, thereby making the first output sub-feature contain more key information related to diastolic pressure, thereby further improving the accuracy and reliability of diastolic pressure prediction.

[0066] Optionally, in yet another possible implementation manner of the second aspect, the second determining unit is specifically configured to:

[0067] Inputting the shared output features into the second hybrid attention module to determine a second hybrid attention weight matrix corresponding to the shared output features;

[0068] Weighting the shared output feature according to the second mixed attention weight matrix to generate a second sub-output feature corresponding to the shared output feature;

[0069] The second sub-output features are input into the second convolutional layer and the second fully connected layer to determine the systolic blood pressure.

[0070] In this way, after extracting the shared output features corresponding to the PPG signal, the shared output features are input into the second sub-network for predicting systolic blood pressure to further extract features from the shared output features, and the hybrid attention weight matrix of the shared output features in the systolic blood pressure prediction task is determined through the hybrid attention mechanism, so that features with a higher correlation with systolic blood pressure have a higher weight, thereby making the second output sub-feature contain more key information related to systolic blood pressure, thereby further improving the accuracy and reliability of diastolic blood pressure prediction.

[0071] In a third aspect, an embodiment of the present application provides an electronic device, comprising: one or more processors, and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the electronic device to execute the blood pressure prediction method as described above.

[0072] In a fourth aspect, an embodiment of the present application provides a chip system, which is applied to an electronic device. The chip system includes one or more processors, and the one or more processors are used to call computer instructions so that the electronic device executes the blood pressure prediction method as described above.

[0073] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, which includes instructions. When the instructions are executed on an electronic device, the electronic device executes the blood pressure prediction method as described above.

[0074] In a sixth aspect, an embodiment of the present application provides a computer program product, which, when executed on an electronic device, enables the electronic device to execute the blood pressure prediction method as described above.

[0075] The technical effects obtained by the above-mentioned second, third, fourth, fifth and sixth aspects are similar to the technical effects obtained by the corresponding technical means in the above-mentioned first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art 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 drawings can be obtained based on these drawings without paying any creative work.

[0077] Figure 1 is a flow chart of a blood pressure prediction method provided in one embodiment of the present application;

[0078] Figure 2 is a flow chart of a blood pressure prediction method provided by another embodiment of the present application;

[0079] Figure 3 It is a structural schematic diagram of a blood pressure prediction model provided in one embodiment of the present application;

[0080] Figure 4 is a structural schematic diagram of a multi-scale module provided in one embodiment of the present application;

[0081] Figure 5 is a structural diagram of a hybrid attention module provided in one embodiment of the present application;

[0082] Figure 6 This is an overall algorithm flow chart of a blood pressure prediction method provided by an embodiment of the present application;

[0083] Figure 7 is a schematic diagram of the structure of a blood pressure prediction device provided in one embodiment of the present application;

[0084] Figure 8 It is a schematic diagram of the structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0085] The blood pressure prediction method, device, electronic device, chip system, storage medium and computer program provided in the present application are described in detail below with reference to the accompanying drawings.

[0086] Please refer to Figure 1 , Figure 1 : is a flow chart of a blood pressure prediction method provided by an embodiment of the present application, and the method may include some or all of the following contents:

[0087] Step 101, in response to a blood pressure prediction instruction, obtaining a user's current PPG signal.

[0088] It should be noted that the blood pressure prediction method of the embodiment of the present application can be performed by the blood pressure prediction device of the embodiment of the present application. The blood pressure prediction device of the embodiment of the present application can be configured in any electronic device to execute the blood pressure prediction method of the embodiment of the present application. For example, the blood pressure prediction device of the embodiment of the present application can be configured in electronic devices such as mobile phones, computers, wearable devices, etc., to measure the user's blood pressure. As an example, the blood pressure prediction device of the embodiment of the present application can be configured in a wearable device with a PPG signal detection function (such as a smart watch, a smart bracelet, etc.) to monitor the user's blood pressure in real time, or measure the user's blood pressure according to the user's operating instructions.

[0089] Among them, the blood pressure prediction instruction may refer to any instruction that can trigger the electronic device to activate the blood pressure prediction function.

[0090] As an example, assuming that the blood pressure prediction method of an embodiment of the present application is applied in a smart watch, if the smart watch can monitor the user's blood pressure at a preset frequency (such as once an hour, once a day, etc.) according to the default settings or user settings, then it can be determined that the blood pressure prediction instruction is obtained each time the measurement time is reached; if the smart watch can monitor the user's blood pressure at preset times (such as 8 o'clock and 22 o'clock every day, etc.) according to the default settings or user settings, then it can be determined that the blood pressure prediction instruction is obtained each time the preset time is reached; if there is a blood pressure prediction control in the smart watch or an application that provides a blood pressure prediction function (such as a health application, a sports application, etc.) is installed, it can also be determined that the blood pressure prediction instruction is obtained when the user triggers the blood pressure prediction control or starts the blood pressure prediction function in the application.

[0091] It should be noted that the above examples are only for illustrative purposes and cannot be regarded as limitations of the present application. In actual use, the type of blood pressure prediction instruction may be related to the function of the electronic device, the application scenario of the blood pressure prediction method of the embodiment of the present application, etc., and the embodiment of the present application does not limit this.

[0092] Among them, the photoplethysmography (PPG) method is portable and cheap, and can be used for blood pressure monitoring. PPG can use a light emitting diode (LED) to illuminate human skin, and use a photodiode to measure the change in reflected light intensity caused by blood flow. The resulting periodic waveform contains information about the pulsating changes in blood volume during the cardiac cycle. The blood volume is the largest when the heart contracts, and the diastolic volume is the smallest when the heart relaxes. Therefore, the systolic and diastolic pressures can be obtained through the relationship between the volume pulse blood flow information and the blood pressure. Therefore, in an embodiment of the present application, a PPG sensor can be configured in an electronic device to collect the user's PPG signal.

[0093] In an embodiment of the present application, when it is determined that a blood pressure prediction instruction has been obtained, the PPG sensor in the electronic device can be driven to collect the user's current PPG signal to predict the user's blood pressure using the user's current PPG signal.

[0094] Step 102: extract features from the PPG signal to determine a plurality of blood pressure related features corresponding to the PPG signal.

[0095] Among them, the blood pressure related features may include at least two of the following features: morphological features, spectrum features, time domain features, and ABP features corresponding to the PPG signal.

[0096] In an embodiment of the present application, after obtaining the user's current PPG signal, feature extraction can be performed on the PPG signal to obtain a variety of signal features related to the user's blood pressure, i.e., blood pressure-related features, so as to expand the diversity and richness of the input information subsequently input into the blood pressure prediction model, thereby further improving the accuracy and reliability of blood pressure prediction.

[0097] As a possible implementation, the morphological feature may include the waveform feature and the periodic feature of the PPG signal. As an example, the morphological feature may be obtained by calculating the recursive graph of the PPG signal, and the recursive graph may be calculated by the trajectory distance of the time series.

[0098] As a possible implementation, the spectral feature may include energy distribution and main frequency features of the PPG signal. As an example, the spectral feature may be obtained by calculating a spectrogram of the PPG signal, for example, the spectrogram may be obtained by calculating a short-time Fourier transform of the PPG signal.

[0099] As a possible implementation method, the time domain features can include a PPG signal, a first-order derivative and a second-order derivative corresponding to the PPG signal. The first-order derivative and the second-order derivative corresponding to the PPG signal contain characteristic points related to the physiological signal and blood pressure (for example, the zero point of the first-order derivative corresponds to the peak position of the original PPG signal), and are thus related to blood pressure prediction.

[0100] As a possible implementation method, the ABP feature is highly correlated with the blood pressure value to be predicted. An autoencoder from the PPG signal to the ABP feature can be constructed, and the autoencoder can be obtained by minimizing the reconstruction error training. After that, the PPG signal can be input into the trained autoencoder for encoding processing to generate latent features related to ABP, i.e., ABP features. As an example, the network structure of the above-mentioned autoencoder can be a U-net network structure, which is not limited in the embodiments of the present application.

[0101] It should be noted that the above-listed methods for calculating various blood pressure-related features are only exemplary and cannot be regarded as limitations on this application. In actual use, the specific method for extracting various blood pressure-related features can be determined according to actual needs and specific application scenarios, and this embodiment of the application does not limit this.

[0102] Step 103: fuse multiple blood pressure related features to generate a target input feature corresponding to the PPG signal.

[0103] In an embodiment of the present application, after extracting multiple blood pressure-related features corresponding to the PPG signal, the various blood pressure-related features can be fused to generate a target input feature corresponding to the PPG signal, which is input into a blood pressure prediction model to predict the user's diastolic and systolic blood pressure.

[0104] As a possible implementation method, each blood pressure related feature can be mapped to a unified dimension through convolution and fully connected layers to fuse the various blood pressure related features to generate the target input features of the blood pressure prediction model.

[0105] Step 104 , input the target input features into a blood pressure prediction model to determine the user's diastolic and systolic blood pressures.

[0106] In an embodiment of the present application, since human blood pressure can include two values: diastolic pressure and systolic pressure, a blood pressure prediction model that can predict the user's diastolic pressure and systolic pressure can be pre-trained, and after the target input features are input into the blood pressure prediction model, the blood pressure prediction model can output the user's diastolic pressure and systolic pressure.

[0107] As a possible implementation, after determining the user's diastolic and systolic blood pressures, the diastolic and systolic blood pressures may be notified to the user through screen display or voice announcement, so that the user can measure blood pressure very conveniently.

[0108] The blood pressure prediction method provided in the embodiment of the present application collects the user's PPG signal through the PPG sensor in the electronic device, and extracts multiple signal features from the PPG signal to determine multiple signal features related to the user's blood pressure, and then fuses the multiple blood pressure-related features as the input of the blood pressure prediction model to predict the user's blood pressure. Therefore, by integrating the PPG signal detection module in the electronic device to collect the PPG signal, and predicting the blood pressure based on the multiple blood pressure-related signal features corresponding to the PPG signal, the user can not only measure the blood pressure very conveniently at any time, which improves the convenience of blood pressure measurement, but also ensures the accuracy and reliability of blood pressure prediction.

[0109] Please refer to Figure 2 , Figure 2 : is a flow chart of a blood pressure prediction method provided by another embodiment of the present application, which method may include part or all of the following contents:

[0110] Step 201, in response to a blood pressure prediction instruction, obtaining a user's current PPG signal.

[0111] Step 202: extract features from the PPG signal to determine a plurality of blood pressure related features corresponding to the PPG signal.

[0112] Step 203: fuse multiple blood pressure related features to generate a target input feature corresponding to the PPG signal.

[0113] The specific implementation process and principle of the above steps 201-203 can be referred to the detailed description of the above embodiment, which will not be repeated here.

[0114] Step 204: input the target input features into the backbone network of the blood pressure prediction model to generate shared output features corresponding to the PPG signal.

[0115] As a possible implementation, Figure 3As shown, it is a structural schematic diagram of a blood pressure prediction model provided by an embodiment of the present application. The network structure of the blood pressure prediction model of the embodiment of the present application can be a deep neural network structure of multi-task learning. The blood pressure prediction model can include a backbone network, a first subnetwork and a second subnetwork; wherein the backbone network is used to extract shared features for blood pressure prediction, the first subnetwork is used to predict diastolic pressure, and the second subnetwork is used to predict systolic pressure. Since the blood pressure measurement of the human body usually requires the prediction of diastolic pressure and systolic pressure, and the connection between diastolic pressure and systolic pressure and different features may be different, a blood pressure prediction model can be constructed based on a multi-task model, so that after the shared feature extraction is performed through the backbone network and the shared output feature is obtained, different subnetworks can be used to predict diastolic pressure and systolic pressure respectively, so that according to the two different prediction tasks of diastolic pressure prediction and systolic pressure prediction, further adaptive feature extraction is performed through different subnetworks to obtain more accurate diastolic pressure and systolic pressure prediction results, further improving the accuracy and reliability of blood pressure prediction.

[0116] Furthermore, multiple multi-scale modules can be stacked in the backbone network of the blood pressure prediction model to improve the network depth, and multi-scale feature extraction can be performed on the target input features, thereby improving the model's ability to learn key information of the input features, so as to further improve the accuracy and reliability of blood pressure prediction. That is, in a possible implementation of the embodiment of the present application, the backbone network may include N multi-scale modules, where N is a positive integer; accordingly, the above step 204 may include:

[0117] The target input features are input into the backbone network, and each multi-scale module is used to extract multi-scale features of the target input features in turn, so as to perform N multi-scale feature extractions on the target input features and generate shared output features.

[0118] As a possible implementation, Figure 3 As shown, the backbone network of the blood pressure prediction model may include N multi-scale modules. After the target input features are input into the blood pressure prediction model, these N multi-scale modules may perform multi-scale feature extraction on the target input features in turn to generate shared output features.

[0119] Furthermore, it is also possible to perform a residual connection with the original input features of each multi-scale module during each multi-scale feature extraction to improve the model's learning ability for the original input features, prevent the loss of key information in the original input features during the blood pressure prediction process, and further improve the accuracy and reliability of blood pressure prediction. That is, in a possible implementation of the embodiment of the present application, the target input features are input into the backbone network, and each multi-scale module is used to perform multi-scale feature extraction on the target input features in turn, so as to perform N multi-scale feature extractions on the target input features to generate shared output features, which may include:

[0120] The i-th intermediate feature is input into the i+1-th multi-scale module, and the i+1-th multi-scale feature extraction is performed on the target input feature to generate the i+1-th intermediate feature, where the 0th intermediate feature is the target input feature, the Nth intermediate feature is the shared output feature, and i is an integer greater than or equal to 0 and less than N.

[0121] As a possible implementation method, after the target input feature is input into the blood pressure prediction model, the first multi-scale module of the backbone network can be first input to perform the first multi-scale feature extraction on the target input feature to generate the first intermediate feature, and then the intermediate feature can be input into the second multi-scale module, and the first intermediate feature can be extracted by multi-scale feature extraction to achieve the second multi-scale feature extraction of the target input feature; and so on, each time the intermediate feature output by the previous multi-scale module is used as the input of the next multi-scale module to achieve N times of multi-scale feature extraction of the target input feature and generate a shared output feature.

[0122] Furthermore, it is also possible to perform multi-scale feature extraction on the target input features through multiple convolution kernels of different sizes, learn the weights corresponding to features of different scales through the attention mechanism, and fuse the original input features of each multi-scale module with the extracted multi-scale features through the residual connection, so as to give higher weights to features with higher correlation with blood pressure through the attention mechanism, and improve the network's learning ability of input features through the residual connection, so as to further improve the accuracy and reliability of blood pressure prediction. That is, in a possible implementation method of the embodiment of the present application, each of the above multi-scale modules includes multiple convolution kernels of different sizes, a first attention module and a residual connection module; accordingly, the above inputs the i-th intermediate feature into the i+1-th multi-scale module, performs the i+1-th multi-scale feature extraction on the target input feature to generate the i+1-th intermediate feature, including:

[0123] The i-th intermediate feature is input into each convolution kernel of the i+1-th multi-scale module for convolution processing to generate convolution features of different sizes corresponding to the i-th intermediate feature;

[0124] Input each convolution feature into the first attention module of the i+1th multi-scale module to generate a first attention weight corresponding to each convolution feature, and fuse each convolution feature according to the first attention weight corresponding to each convolution feature to generate an i+1th multi-scale fusion feature;

[0125] The i-th intermediate feature and the i+1-th multi-scale fusion feature are input into the residual connection module of the i+1-th multi-scale module to generate the i+1-th intermediate feature.

[0126] As a possible implementation, Figure 4 As shown, it is a schematic diagram of the structure of a multi-scale module provided in an embodiment of the present application. Assume Figure 4 The multi-scale module in is the i+1th multi-scale module in the blood pressure prediction model, and its corresponding input feature is the i-th intermediate feature, and its corresponding output feature is the i+1th intermediate feature. In order to facilitate the expression, the input feature and output feature are used for expression in the following. After the input features are input into the multi-scale module, the input features can be convolved respectively by K (K is an integer greater than 1) convolution kernels of different sizes (convolution kernel 1...convolution kernel K) in the multi-scale module to generate K convolution features of different sizes (i.e., convolution feature 1...convolution feature K); then, the convolution features can be fused and input into the first attention module of the multi-scale module, so that each convolution feature can be pooled, fully connected and softmax connected through the first attention module to generate a first attention weight corresponding to each convolution feature; then, weighted summation is performed on each convolution feature according to the first attention weight corresponding to each convolution feature to generate a multi-scale fusion feature corresponding to the multi-scale module; finally, the multi-scale fusion feature is residually connected with the input feature of the multi-scale module to generate an output feature corresponding to the multi-scale module.

[0127] As an example, Figure 4 As shown, the first attention module in the multi-scale module may include a pooling layer (such as a global average pooling layer), a fully connected layer (such as a dense layer) and a softmax layer, but is not limited thereto.

[0128] As a possible implementation method, the size of each convolution kernel in the multi-scale module can be determined according to the interval of the PPG signal. By determining the size of each convolution kernel in the multi-scale module according to the interval of the PPG signal, the multi-scale features extracted by the multi-scale module are more matched with the key features of the PPG signal, thereby further improving the accuracy and reliability of blood pressure prediction.

[0129] Step 205 , input the shared output features into the first sub-network of the blood pressure prediction model to determine the diastolic pressure.

[0130] As a possible implementation, Figure 3 As shown, the first subnetwork of the blood pressure prediction model may include a first hybrid attention module, a first convolutional layer and a first fully connected layer, and the second subnetwork may include a second hybrid attention module, a second convolutional layer and a second fully connected layer.

[0131] Furthermore, after extracting the shared output features corresponding to the PPG signal, the shared output features can be input into the first sub-network for predicting diastolic pressure to further extract features from the shared output features, and the mixed attention weight matrix of the shared output features in the diastolic pressure prediction task can be determined through the mixed attention mechanism, so that features with a higher correlation with diastolic pressure have a higher weight, thereby making the first output sub-feature contain more key information related to diastolic pressure, thereby further improving the accuracy and reliability of diastolic pressure prediction. That is, in a possible implementation of the embodiment of the present application, the above step 205 can include:

[0132] Inputting the shared output feature into the first hybrid attention module to determine a first hybrid attention weight matrix corresponding to the shared output feature;

[0133] Weighting the shared output feature according to the first hybrid attention weight matrix to generate a first sub-output feature corresponding to the shared output feature;

[0134] The first sub-output feature is input into the first convolutional layer and the first fully connected layer to determine the diastolic pressure.

[0135] As a possible implementation, Figure 5 As shown, it is a schematic diagram of the structure of a hybrid attention module provided in an embodiment of the present application. Figure 5The hybrid attention module shown is the first hybrid attention module in the first sub-network. After the shared output feature is input into the first hybrid attention module of the first sub-network, the shared output feature can be globally averaged pooled in the channel dimension to determine the first channel attention weight matrix corresponding to the shared output feature, and the shared output feature is pointwise (PW) convolution operation is performed to determine the first spatial attention weight matrix corresponding to the shared output layer feature; then, the first channel attention weight matrix corresponding to the shared output feature is matrix multiplied with the first spatial attention weight matrix to generate the first hybrid attention weight matrix corresponding to the shared output feature, and the first hybrid attention weight matrix has the same dimension as the shared output feature, that is, the first hybrid attention weight matrix contains the hybrid attention weight corresponding to each element in the shared output feature; finally, each element in the shared output feature is weighted according to the first hybrid attention weight matrix to generate the first sub-output feature corresponding to the shared output feature; then, the first sub-output feature is input into the first convolutional layer and the first fully connected layer in the first sub-network to predict and output the user's diastolic blood pressure.

[0136] Step 206, input the shared output features into the second sub-network of the blood pressure prediction model to determine the systolic blood pressure.

[0137] As a possible implementation, after extracting the shared output features corresponding to the PPG signal, the shared output features can be input into the second sub-network for predicting systolic pressure to further extract features from the shared output features, and the hybrid attention weight matrix of the shared output features in the systolic pressure prediction task can be determined through the hybrid attention mechanism, so that features with a higher correlation with systolic pressure have a higher weight, thereby making the second output sub-feature contain more key information related to systolic pressure, thereby further improving the accuracy and reliability of diastolic pressure prediction. That is, in a possible implementation of the embodiment of the present application, the above step 206 can include:

[0138] Inputting the shared output features into the second hybrid attention module to determine a second hybrid attention weight matrix corresponding to the shared output features;

[0139] Weighting the shared output feature according to the second mixed attention weight matrix to generate a second sub-output feature corresponding to the shared output feature;

[0140] The second sub-output features are input into the second convolutional layer and the second fully connected layer to determine the systolic blood pressure.

[0141] As a possible implementation, Figure 5 As shown, assuming Figure 5The hybrid attention module shown is the second hybrid attention module in the second sub-network. After the shared output feature is input into the second hybrid attention module of the second sub-network, the shared output feature can be globally averaged pooled in the channel dimension to determine the second channel attention weight matrix corresponding to the shared output feature, and the shared output feature is subjected to a PW convolution operation to determine the second spatial attention weight matrix corresponding to the shared output layer feature; then, the second channel attention weight matrix corresponding to the shared output feature is matrix multiplied with the second spatial attention weight matrix to generate a second hybrid attention weight matrix corresponding to the shared output feature, and the second hybrid attention weight matrix has the same dimension as the shared output feature, that is, the second hybrid attention weight matrix contains the hybrid attention weight corresponding to each element in the shared output feature; finally, each element in the shared output feature is weighted according to the second hybrid attention weight matrix to generate a second sub-output feature corresponding to the shared output feature; then, the second sub-output feature is input into the second convolutional layer and the second fully connected layer in the second sub-network to predict and output the user's systolic blood pressure.

[0142] As an example, Figure 6 As shown, it is an overall algorithm flow chart of a blood pressure prediction method provided by an embodiment of the present application. After obtaining the current PPG signal of the user, firstly, a plurality of feature extractions are performed on the PPG signal to generate morphological features, spectral features, time domain features, and ABP features corresponding to the PPG signal. Then, these four features are fused and input into the backbone network in the blood pressure prediction model, so that the input features are subjected to N multi-scale feature extractions through the N multi-scale modules in the backbone network to generate shared output features; then, the shared output features are respectively input into the first sub-network and the second sub-network, so as to predict the user's diastolic pressure through the first sub-network, and the user's systolic pressure through the second sub-network. Among them, the first sub-network may include a first hybrid attention module, a first convolutional layer, and a first fully connected layer, and the second sub-network may include a second hybrid attention module, a second convolutional layer, and a second fully connected layer.

[0143] It should be noted that Figure 6 The embodiment shown is a specific implementation scheme proposed in the present application. The specific implementation process and principle can refer to the detailed description of the above embodiment, which will not be repeated here.

[0144] The blood pressure prediction method provided in the embodiment of the present application, since the blood pressure measurement of the human body usually requires the prediction of diastolic pressure and systolic pressure, and the connection between diastolic pressure and systolic pressure and different features may be different, therefore, a blood pressure prediction model can be constructed based on a multi-task model, so that after the shared features are extracted through the backbone network, different sub-networks can be used to predict the diastolic pressure and systolic pressure respectively, so that according to the two different prediction tasks of diastolic pressure prediction and systolic pressure prediction, further adaptive feature extraction is performed through different sub-networks to obtain more accurate diastolic pressure and systolic pressure prediction results, thereby further improving the accuracy and reliability of blood pressure prediction.

[0145] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0146] Corresponding to the blood pressure prediction method described in the above embodiment, Figure 7 A structural block diagram of a blood pressure prediction device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0147] Reference Figure 7 The device 70 comprises:

[0148] A first acquisition module 71 is used to obtain a current PPG signal of a user in response to a blood pressure prediction instruction;

[0149] A first determination module 72, configured to extract features from the PPG signal to determine a plurality of blood pressure related features corresponding to the PPG signal;

[0150] A first generating module 73, configured to fuse a plurality of blood pressure related features to generate a target input feature corresponding to the PPG signal;

[0151] The second determination module 74 is used to input the target input feature into the blood pressure prediction model to determine the user's diastolic blood pressure and systolic blood pressure.

[0152] In actual use, the blood pressure prediction device provided in the embodiment of the present application can be configured in any electronic device, especially a wearable device, to execute the aforementioned blood pressure prediction method.

[0153] The blood pressure prediction device provided in the embodiment of the present application collects the user's PPG signal through the PPG sensor in the electronic device, and extracts multiple signal features from the PPG signal to determine multiple signal features related to the user's blood pressure, and then fuses the multiple blood pressure-related features as the input of the blood pressure prediction model to predict the user's blood pressure. Therefore, by integrating the PPG signal detection module in the electronic device to collect the PPG signal, and predicting the blood pressure based on the multiple blood pressure-related signal features corresponding to the PPG signal, the user can not only measure the blood pressure at any time very conveniently, which improves the convenience of blood pressure measurement, but also ensures the accuracy and reliability of blood pressure prediction.

[0154] In a possible implementation of the present application, the above-mentioned blood pressure-related characteristics include at least two of the following characteristics: morphological characteristics, spectrum characteristics, time domain characteristics, and ABP characteristics corresponding to the PPG signal.

[0155] In this way, by extracting multiple signal features from the user's PPG signal, we can obtain the morphological features, spectral features, time domain features, ABP features and other signal features related to the user's blood pressure corresponding to the PPG signal, and input the fusion features of these features into the blood pressure prediction model to predict diastolic and systolic blood pressure. Since these signal features are closely related to the user's blood pressure characteristics, blood pressure prediction is performed using these features, which further improves the accuracy and reliability of blood pressure prediction.

[0156] Furthermore, in another possible implementation of the present application, the blood pressure prediction model includes a backbone network, a first sub-network and a second sub-network; accordingly, the second determination module 74 includes:

[0157] A first generating unit, configured to input the target input feature into the backbone network to generate a shared output feature corresponding to the PPG signal;

[0158] A first determination unit, configured to input the shared output feature into the first sub-network to determine the diastolic pressure;

[0159] The second determination unit is used to input the shared output feature into the second sub-network to determine the systolic blood pressure.

[0160] Furthermore, in another possible implementation of the present application, the backbone network includes N multi-scale modules, where N is a positive integer; accordingly, the first generation unit is specifically used to:

[0161] The target input features are input into the backbone network, and each multi-scale module is used to extract multi-scale features of the target input features in turn, so as to perform N multi-scale feature extractions on the target input features and generate shared output features.

[0162] Furthermore, in another possible implementation of the present application, the first generating unit is further configured to:

[0163] The i-th intermediate feature is input into the i+1-th multi-scale module, and the i+1-th multi-scale feature extraction is performed on the target input feature to generate the i+1-th intermediate feature, wherein the 0th intermediate feature is the target input feature, the Nth intermediate feature is the shared output feature, and i is an integer greater than or equal to 0 and less than N.

[0164] Furthermore, in another possible implementation of the present application, each of the multi-scale modules includes a plurality of convolution kernels of different sizes, a first attention module and a residual connection module; accordingly, the first generation unit is further used to:

[0165] The i-th intermediate feature is input into each convolution kernel of the i+1-th multi-scale module for convolution processing to generate convolution features of different sizes corresponding to the i-th intermediate feature;

[0166] Input each convolution feature into the first attention module of the i+1th multi-scale module to generate a first attention weight corresponding to each convolution feature, and fuse each convolution feature according to the first attention weight corresponding to each convolution feature to generate an i+1th multi-scale fusion feature;

[0167] The i-th intermediate feature and the i+1-th multi-scale fusion feature are input into the residual connection module of the i+1-th multi-scale module to generate the i+1-th intermediate feature.

[0168] Furthermore, in another possible implementation of the present application, the size of each of the above-mentioned convolution kernels is determined according to the interval of the PPG signal.

[0169] Furthermore, in another possible implementation of the present application, the first sub-network includes a first hybrid attention module, a first convolutional layer and a first fully connected layer, and the second sub-network includes a second hybrid attention module, a second convolutional layer and a second fully connected layer.

[0170] Furthermore, in another possible implementation of the present application, the first determining unit is specifically configured to:

[0171] Inputting the shared output feature into the first hybrid attention module to determine a first hybrid attention weight matrix corresponding to the shared output feature;

[0172] Weighting the shared output feature according to the first hybrid attention weight matrix to generate a first sub-output feature corresponding to the shared output feature;

[0173] The first sub-output feature is input into the first convolutional layer and the first fully connected layer to determine the diastolic pressure.

[0174] Furthermore, in another possible implementation of the present application, the second determining unit is specifically configured to:

[0175] Inputting the shared output features into the second hybrid attention module to determine a second hybrid attention weight matrix corresponding to the shared output features;

[0176] Weighting the shared output feature according to the second mixed attention weight matrix to generate a second sub-output feature corresponding to the shared output feature;

[0177] The second sub-output features are input into the second convolutional layer and the second fully connected layer to determine the systolic blood pressure.

[0178] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0179] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0180] In order to implement the above embodiments, the present application also proposes an electronic device.

[0181] Figure 8 A schematic diagram of the structure of an electronic device according to an embodiment of the present application.

[0182] See also Figure 8The electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc. Among them, the sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, an air pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, etc.

[0183] As a possible implementation manner, the electronic device of the embodiment of the present application may be a wearable device, such as a smart watch, a smart bracelet, etc., and the sensor module 180 may also include a PPG sensor for collecting the user's PPG signal.

[0184] It is to be understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0185] The processor 110 may include one or more processing units, for example, the processor 110 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.

[0186] The controller may be the nerve center and command center of the electronic device 100. The controller may generate an operation control signal according to the instruction operation code and the timing signal to complete the control of fetching and executing instructions.

[0187] The processor 110 may also be provided with a memory for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. The memory may store instructions or data that the processor 110 has just used or cyclically used. If the processor 110 needs to use the instruction or data again, it may be directly called from the memory. This avoids repeated access, reduces the waiting time of the processor 110, and thus improves the efficiency of the system.

[0188] In some embodiments, the processor 110 may include one or more interfaces, such as an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.

[0189] It is understandable that the interface connection relationship between the modules illustrated in the embodiment of the present application is only a schematic illustration and does not constitute a structural limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may also adopt different interface connection methods in the above embodiments, or a combination of multiple interface connection methods.

[0190] The internal memory 121 can be used to store computer executable program codes, which include instructions. The processor 110 executes various functional applications and data processing of the electronic device 100 by running the instructions stored in the internal memory 121. The internal memory 121 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc. The data storage area may store data created by the electronic device 100 during use (such as audio data, a phone book, etc.), etc. In addition, the internal memory 121 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc.

[0191] It should be noted that the implementation process and technical principles of the electronic device of this embodiment refer to the aforementioned explanation of the blood pressure prediction method of the embodiment of the present application, and will not be repeated here.

[0192] An embodiment of the present application also provides a chip system, which is applied to an electronic device. The chip system includes one or more processors, and the one or more processors are used to call computer instructions so that the electronic device implements the steps in the above-mentioned method embodiments.

[0193] An embodiment of the present application further provides a computer-readable storage medium, which includes instructions. When the instructions are executed on an electronic device, the electronic device implements the steps in the above-mentioned method embodiments.

[0194] The embodiments of the present application also provide a computer program product. When the computer program product is executed on an electronic device, the electronic device implements the steps in the above-mentioned method embodiments.

[0195] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the device / electronic device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electric carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0196] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0197] In the above-described embodiments, specific details such as specific system structures, technologies, etc. are provided for illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0198] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0199] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0200] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0201] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0202] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0203] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0204] In the embodiments provided in the present application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0205] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0206] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A blood pressure prediction method, characterized in that: include: In response to the blood pressure prediction instruction, obtaining the user's current photoplethysmogram (PPG) signal; performing feature extraction on the PPG signal to determine a plurality of blood pressure related features corresponding to the PPG signal; fusing the plurality of blood pressure related features to generate a target input feature corresponding to the PPG signal; The target input features are input into a blood pressure prediction model to determine the diastolic and systolic blood pressures of the user.

2. The method according to claim 1, characterized in that The blood pressure related features include at least two of the following features: morphological features, spectrum features, time domain features, and invasive continuous arterial blood pressure ABP features corresponding to the PPG signal.

3. The method according to claim 1 or 2, characterized in that The blood pressure prediction model includes a main network, a first sub-network and a second sub-network. Inputting the target input feature into the blood pressure prediction model to determine the diastolic blood pressure and the systolic blood pressure of the user includes: Inputting the target input feature into the backbone network to generate a shared output feature corresponding to the PPG signal; inputting the shared output features into the first subnetwork to determine the diastolic pressure; The shared output features are input into the second sub-network to determine the systolic blood pressure.

4. The method according to claim 3, characterized in that The backbone network includes N multi-scale modules, where N is a positive integer. The inputting the target input feature into the backbone network to generate a shared output feature corresponding to the PPG signal includes: The target input feature is input into the backbone network, and each of the multi-scale modules is used to sequentially perform multi-scale feature extraction on the target input feature, so as to perform N times of multi-scale feature extraction on the target input feature to generate the shared output feature.

5. The method according to claim 4, characterized in that The step of inputting the target input feature into the backbone network, and sequentially performing multi-scale feature extraction on the target input feature using each of the multi-scale modules, so as to perform N times of multi-scale feature extraction on the target input feature, and generating the shared output feature, comprises: The i-th intermediate feature is input into the i+1-th multi-scale module, and the i+1-th multi-scale feature extraction is performed on the target input feature to generate the i+1-th intermediate feature, wherein the 0th intermediate feature is the target input feature, the Nth intermediate feature is the shared output feature, and i is an integer greater than or equal to 0 and less than N.

6. The method according to claim 5, characterized in that Each of the multi-scale modules includes a plurality of convolution kernels of different sizes, a first attention module and a residual connection module, and the step of inputting the i-th intermediate feature into the i+1-th multi-scale module and performing the i+1-th multi-scale feature extraction on the target input feature to generate the i+1-th intermediate feature includes: Inputting the ith intermediate feature into each of the convolution kernels of the (i+1)th multi-scale module for convolution processing, so as to generate a plurality of convolution features of different sizes corresponding to the ith intermediate feature; Inputting each of the convolutional features into the first attention module of the i+1th multi-scale module to generate a first attention weight corresponding to each of the convolutional features, and fusing each of the convolutional features according to the first attention weight corresponding to each of the convolutional features to generate an i+1th multi-scale fused feature; The i-th intermediate feature and the i+1-th multi-scale fusion feature are input into the residual connection module of the i+1-th multi-scale module to generate the i+1-th intermediate feature.

7. The method according to claim 6, characterized in that The size of each of the convolution kernels is determined according to the interval of the PPG signal.

8. The method according to any one of claims 3 to 7, characterized in that: The first sub-network includes a first hybrid attention module, a first convolutional layer and a first fully connected layer, and the second sub-network includes a second hybrid attention module, a second convolutional layer and a second fully connected layer.

9. The method according to claim 8, characterized in that Inputting the shared output feature into the first sub-network to determine the diastolic pressure comprises: Inputting the shared output feature into the first hybrid attention module to determine a first hybrid attention weight matrix corresponding to the shared output feature; Weighting the shared output feature according to the first hybrid attention weight matrix to generate a first sub-output feature corresponding to the shared output feature; The first sub-output feature is input into the first convolutional layer and the first fully connected layer to determine the diastolic pressure.

10. The method according to claim 8, characterized in that Inputting the shared output feature into the second sub-network to determine the systolic blood pressure comprises: Inputting the shared output feature into the second hybrid attention module to determine a second hybrid attention weight matrix corresponding to the shared output feature; Weighting the shared output feature according to the second mixed attention weight matrix to generate a second sub-output feature corresponding to the shared output feature; The second sub-output feature is input into the second convolutional layer and the second fully connected layer to determine the systolic blood pressure.

11. An electronic device, characterized in that: The electronic device includes: one or more processors, and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the electronic device to execute the method as described in any one of claims 1-10.

12. A chip system, characterized in that: The chip system is applied to an electronic device, and the chip system includes one or more processors, and the one or more processors are used to call computer instructions so that the electronic device executes the method as described in any one of claims 1-10.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes instructions, and when the instructions are executed on an electronic device, the electronic device executes the method according to any one of claims 1 to 10.

Images