Blood oxygen saturation detection method and device, noise reduction equipment, storage medium and product

Abstract

The invention discloses an oxyhemoglobin saturation detection method and device, noise reduction equipment, a storage medium and a product, and relates to the technical field of artificial intelligence. The oxyhemoglobin saturation detection method comprises the steps that an initial pulse wave signal collected by photoplethysmography detection equipment is received, and whether a noise signal exists in the initial pulse wave signal or not is judged; if the noise signal exists in the initial pulse wave signal, the initial pulse wave signal is input into a noise reduction model to obtain a target pulse wave signal, and the noise reduction model is obtained through training by taking a historical pulse wave signal as input data and taking the denoised historical pulse wave signal as a label; the target pulse wave signal is sent to the photoplethysmography detection equipment, and the photoplethysmography detection equipment carries out blood oxygen concentration detection based on the target pulse wave signal. The accuracy of blood oxygen saturation detection is improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a blood oxygen saturation detection method, device, noise reduction equipment, storage medium and product. Background Art

[0002] Pulse oximetry (PPG, Photoplethysmogram) detection is a non-invasive method to measure human blood oxygen saturation. It detects small changes in the skin or nail bed through infrared sensors or fluorescent sensors to obtain blood oxygen saturation information. However, in practical applications, pulse wave signals are easily interfered by ambient light, electromyographic signals, etc., which affect the accurate detection of blood oxygen saturation.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide a blood oxygen saturation detection method, device, noise reduction equipment, storage medium and product, aiming to solve the technical problem that the pulse wave signal is easily interfered with, which affects the accurate detection of blood oxygen saturation and the effect of blood oxygen saturation detection.

[0005] To achieve the above-mentioned purpose, the present application provides a blood oxygen saturation detection method, the blood oxygen saturation detection method is applied to a noise reduction device, the noise reduction device is communicatively connected with a photoplethysmography detection device, and the blood oxygen saturation detection method includes:

[0006] receiving an initial pulse wave signal collected by the photoplethysmography detection device, and determining whether a noise signal exists in the initial pulse wave signal;

[0007] If the noise signal exists in the initial pulse wave signal, the initial pulse wave signal is input into a noise reduction model to obtain a target pulse wave signal, wherein the noise reduction model is trained using a historical pulse wave signal as input data and the noise-reduced historical pulse wave signal as a label;

[0008] The target pulse wave signal is sent to the photoplethysmography detection device, wherein the photoplethysmography detection device performs blood oxygen concentration detection based on the target pulse wave signal.

[0009] In one embodiment, the step of inputting the initial pulse wave signal into the noise reduction model to obtain a target pulse wave signal comprises:

[0010] Filtering the initial pulse wave signal to obtain a filtered pulse wave signal of a target frequency band, wherein the target frequency band is a frequency band corresponding to a human heart rate range;

[0011] The filtered pulse wave signal is input into the noise reduction model to obtain a target pulse wave signal.

[0012] In one embodiment, the denoising model includes an encoder, a recurrent neural network, an attention mechanism module, a decoder and a fully connected layer, and the step of inputting the filtered pulse wave signal into the denoising model to obtain a target pulse wave signal includes:

[0013] Inputting the filtered pulse wave signal into the encoder for processing to obtain a first processing result;

[0014] Inputting the first processing result into the recurrent neural network module for processing to obtain a second processing result, wherein when the first processing result is processed by the recurrent neural network module, the result obtained by processing the previous frame processing result by the recurrent neural network module is the result obtained by the encoder processing the previous frame signal of the initial pulse wave signal;

[0015] Inputting the second processing result into the decoder for processing to obtain a third processing result;

[0016] Inputting the first processing result and the third processing result into the attention mechanism module for processing to obtain a fourth processing result;

[0017] The third processing result and the fourth processing result are connected, and the connected result is input into the fully connected layer for processing to obtain a target pulse wave signal.

[0018] In one embodiment, the attention mechanism module includes a weight calculation block and a weighted processing block, and the step of inputting the first processing result and the third processing result into the attention mechanism module for processing to obtain a fourth processing result includes:

[0019] Inputting the first processing result and the third processing result into the weight calculation block for processing to obtain an attention weight matrix;

[0020] The attention weight matrix and the first processing result are input into the weighted processing block for processing to obtain a fourth processing result.

[0021] In one embodiment, the step of determining whether a noise signal exists in the initial pulse wave signal comprises:

[0022] Extracting features of the initial pulse wave signal to obtain signal waveform features, and determining a target interference type of the initial pulse wave signal based on the signal waveform features;

[0023] If the target interference type is a non-physiological interference type, determining that a noise signal exists in the initial pulse wave signal;

[0024] If the target interference type is a physiological interference type, it is determined that the noise signal does not exist in the initial pulse wave signal.

[0025] In one embodiment, the signal waveform feature includes a signal variance and a baseline offset; the step of determining the target interference type of the initial pulse wave signal based on the signal waveform feature includes:

[0026] If the signal variance is greater than a preset variance threshold and the baseline offset is greater than a preset offset, determining that the target interference type of the initial pulse wave signal is physiological interference;

[0027] If the signal variance is greater than the preset variance threshold and the baseline offset is less than or equal to the preset offset, it is determined that the target interference type is non-physiological interference.

[0028] To achieve the above-mentioned purpose, the present application further provides a blood oxygen saturation detection device, which is applied to a noise reduction device, the noise reduction device is communicatively connected with a photoplethysmography detection device, and the blood oxygen saturation detection device comprises:

[0029] A judgment module, used for receiving the initial pulse wave signal collected by the photoplethysmography detection device, and judging whether there is a noise signal in the initial pulse wave signal;

[0030] A denoising module, for inputting the initial pulse wave signal into a denoising model to obtain a target pulse wave signal if the noise signal exists in the initial pulse wave signal, wherein the denoising model is trained with a historical pulse wave signal as input data and the denoised historical pulse wave signal as a label;

[0031] A sending module is used to send the target pulse wave signal to the photoplethysmography detection device, wherein the photoplethysmography detection device performs blood oxygen concentration detection based on the target pulse wave signal.

[0032] To achieve the above-mentioned purpose, the present application also provides a noise reduction device, which includes: a memory, a processor, and a blood oxygen saturation detection program stored in the memory and executable on the processor, wherein the blood oxygen saturation detection program implements the steps of the blood oxygen saturation detection method as described above when executed by the processor.

[0033] In addition, to achieve the above-mentioned purpose, the present application also proposes a computer-readable storage medium, on which a blood oxygen saturation detection program is stored. When the blood oxygen saturation detection program is executed by a processor, the steps of the blood oxygen saturation detection method as described above are implemented.

[0034] In the present application, by receiving the initial pulse wave signal collected by the photoplethysmography detection device, it is determined whether there is a noise signal in the initial pulse wave signal; if the noise signal exists in the initial pulse wave signal, the initial pulse wave signal is input into a noise reduction model to obtain a target pulse wave signal, wherein the noise reduction model is trained with a historical pulse wave signal as input data and the denoised historical pulse wave signal as a label; the target pulse wave signal is sent to the photoplethysmography detection device, wherein the photoplethysmography detection device performs blood oxygen concentration detection based on the target pulse wave signal.

[0035] The present application introduces a noise reduction model to identify and remove the noise signal in the initial pulse wave signal, thereby extracting a purer target pulse wave signal and reducing the interference of noise on the pulse wave signal. Therefore, blood oxygen concentration detection based on the processed target pulse wave signal can more accurately reflect the blood oxygen saturation of the human body, thereby improving the accuracy of blood oxygen detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0038] Figure 1 A flow chart of the first embodiment of the blood oxygen saturation detection method of the present application;

[0039] Figure 2 A schematic diagram of a flow chart provided for Embodiment 2 of the blood oxygen saturation detection method of the present application;

[0040] Figure 3 A structural diagram of a deep neural network involved in an embodiment of the present application;

[0041] Figure 4 This is a schematic diagram of the module structure of the blood oxygen saturation detection device according to an embodiment of the present application;

[0042] Figure 5Schematic diagram of the device structure of the hardware operating environment involved in the blood oxygen saturation detection method in the embodiment of the present application.

[0043] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0044] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0045] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0046] The main solution of the embodiment of the present application is: receiving the initial pulse wave signal collected by the photoplethysmography detection device, and determining whether there is a noise signal in the initial pulse wave signal; if the noise signal exists in the initial pulse wave signal, inputting the initial pulse wave signal into a noise reduction model to obtain a target pulse wave signal, wherein the noise reduction model is trained with a historical pulse wave signal as input data and the noise-reduced historical pulse wave signal as a label; sending the target pulse wave signal to the photoplethysmography detection device, wherein the photoplethysmography detection device performs blood oxygen concentration detection based on the target pulse wave signal.

[0047] In this embodiment, for the convenience of description, the following description is made with the noise reduction device as the execution subject.

[0048] Pulse oximetry is a non-invasive method for measuring human blood oxygen saturation. It detects small changes in the skin or nail bed through infrared sensors or fluorescent sensors to obtain blood oxygen saturation information. However, in practical applications, pulse wave signals are easily interfered by ambient light, electromyographic signals, etc., which affect the accurate detection of blood oxygen saturation.

[0049] The present application introduces a noise reduction model to identify and remove the noise signal in the initial pulse wave signal, thereby extracting a purer target pulse wave signal and reducing the interference of noise on the pulse wave signal. Therefore, blood oxygen concentration detection based on the processed target pulse wave signal can more accurately reflect the blood oxygen saturation of the human body, thereby improving the accuracy of blood oxygen detection.

[0050] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device, a noise reduction device, etc. that can realize the above functions. The following is an example of a noise reduction device to illustrate this embodiment and the following embodiments. It should be noted that in this embodiment, the noise reduction device is communicatively connected to the photoplethysmography detection device, and a noise reduction model is deployed in the noise reduction device.

[0051] Based on this, the present application embodiment provides a blood oxygen saturation detection method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the blood oxygen saturation detection method of the present application.

[0052] In this embodiment, the noise reduction device is connected to the photoplethysmography detection device for communication, and the blood oxygen saturation detection method includes steps S10 to S30:

[0053] Step S10, receiving the initial pulse wave signal collected by the photoplethysmography detection device, and determining whether there is a noise signal in the initial pulse wave signal;

[0054] Receive the initial pulse wave signal collected by the photoplethysmography (PPG) detection device. PPG technology monitors pulse waves by measuring changes in blood volume under the skin. The PPG device illuminates the skin through a light-emitting diode (LED) and uses a photoelectric sensor to receive reflected or transmitted light signals. The changes in the light signal are proportional to the changes in blood volume, thereby generating a pulse wave signal.

[0055] It is understandable that the initial pulse wave signal received may contain various noises, such as ambient light interference, device noise, motion artifacts, etc. Signal processing technology (such as threshold detection and spectrum analysis) is used to preliminarily determine whether there is significant noise in the signal. The specific judgment process will not be repeated here.

[0056] Step S20, if the noise signal exists in the initial pulse wave signal, inputting the initial pulse wave signal into a noise reduction model to obtain a target pulse wave signal, wherein the noise reduction model is trained using a historical pulse wave signal as input data and the noise-reduced historical pulse wave signal as a label;

[0057] If there is noise in the initial pulse wave signal, the signal is denoised using a pre-trained denoising model. The denoising model is trained based on the historical pulse wave signal (containing noise) and its corresponding denoised signal, and can identify and remove noise, thereby obtaining a purer target pulse wave signal. The denoising model uses deep learning algorithms, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs). During the model training phase, a large number of noisy historical pulse wave signals are input, and corresponding denoised label data is provided. The model parameters are adjusted through optimization algorithms (such as gradient descent) so that the model can accurately predict the denoised signal.

[0058] By inputting the noisy initial pulse wave signal into the trained denoising model and outputting the denoised target pulse wave signal, the signal-to-noise ratio of the pulse wave signal can be significantly improved and the error can be reduced. The denoising model can adapt to noises from different sources and types and improve generalization ability.

[0059] Step S30: sending the target pulse wave signal to the photoplethysmography detection device, wherein the photoplethysmography detection device performs blood oxygen concentration detection based on the target pulse wave signal.

[0060] The noise-reduced target pulse wave signal is sent back to the PPG detection device for further blood oxygen concentration detection. Blood oxygen concentration is one of the important indicators for evaluating human health, and is usually calculated by analyzing specific features in the pulse wave signal (such as pulsation amplitude, frequency, etc.).

[0061] It is understandable that the target pulse wave signal has a higher signal-to-noise ratio than the initial signal and can more accurately reflect changes in blood volume. The PPG device can calculate the blood oxygen saturation (SpO2) value by analyzing the absorption spectrum characteristics in the signal, and display the calculation results to the user or transmit them to other medical devices for further analysis, providing more reliable data support for clinical diagnosis and treatment.

[0062] In one feasible implementation, the step S10: determining whether there is a noise signal in the initial pulse wave signal comprises:

[0063] Step S101, extracting features from the initial pulse wave signal to obtain signal waveform features, and determining a target interference type of the initial pulse wave signal based on the signal waveform features;

[0064] The initial pulse wave signal is subjected to feature extraction. These features usually include waveform features such as the frequency, amplitude, period, and morphology of the signal. The features are used to describe the basic properties of the pulse wave signal and are provided as input data to the preset interference recognition model. The interference recognition model is trained based on historical data and machine learning algorithms, and can identify and classify different types of interference. It should be noted that the feature extraction process is not limited here, and key waveform features can be extracted from the initial pulse wave signal using methods such as Fourier transform, wavelet transform, and filtering.

[0065] Feature extraction is performed on the initial pulse wave signal to obtain signal waveform features. The specific method is not limited here. For example, the signal waveform features may be input into a preset interference recognition model to obtain a target interference type, wherein the interference recognition model is trained using the signal features of historical pulse wave signals as input data and the interference types of the historical pulse wave signals as training labels; the signal waveform features are input into a preset interference recognition model to obtain a target interference type.

[0066] Through feature extraction and interference identification, the type of interference in the pulse wave signal can be automatically and accurately determined, avoiding the subjectivity and inefficiency of manual judgment, improving the efficiency and accuracy of signal processing, and providing reliable input data for subsequent steps.

[0067] Step S102, if the target interference type is a non-physiological interference type, determining that a noise signal exists in the initial pulse wave signal;

[0068] According to the output of the interference recognition model, it is determined whether the target interference type is non-physiological interference. Non-physiological interference usually includes motion artifacts, equipment noise, electromagnetic interference, etc. These interferences will significantly affect the quality of the pulse wave signal, thereby affecting the subsequent blood oxygen concentration detection. Therefore, when non-physiological interference is detected, it is determined that there is a noise signal in the initial pulse wave signal.

[0069] Step S103: If the target interference type is a physiological interference type, it is determined that the noise signal does not exist in the initial pulse wave signal.

[0070] If the interference type output by the interference recognition model does not include non-physiological interference types but physiological interference (such as respiratory fluctuations, heart rhythm changes, etc.), it is determined that there is no noise signal that requires special processing in the initial pulse wave signal. Physiological interference reflects that normal physiological activities of the human body usually do not have a significant impact on blood oxygen concentration detection.

[0071] It can be understood that by reducing unnecessary noise reduction processing steps, the efficiency of signal processing is improved and the physiological information in the pulse wave signal is retained, which helps to improve the efficiency of blood oxygen concentration detection.

[0072] In one feasible implementation, the signal waveform feature includes a signal variance and a baseline offset; the step S101, the step of determining the target interference type of the initial pulse wave signal based on the signal waveform feature, includes:

[0073] Step S1011, if the signal variance is greater than a preset variance threshold and the baseline offset is greater than a preset offset, determining that the target interference type of the initial pulse wave signal is physiological interference;

[0074] In this embodiment, whether the initial pulse wave signal is affected by physiological interference is determined based on the joint judgment of signal variance and baseline offset. Specifically, the variance of the initial pulse wave signal is calculated and compared with the preset variance threshold. If the signal variance is greater than the threshold, it means that there is a large fluctuation in the signal; the baseline offset of the signal is calculated and compared with the preset offset threshold. If the baseline offset is also greater than the threshold, it means that the baseline of the signal has been significantly offset, and physiological interference is considered to exist. It can be understood that by jointly judging the signal variance and baseline offset, physiological interference can be identified more accurately, the possibility of misjudgment can be reduced, the efficiency and accuracy of signal processing can be improved, and more reliable input data can be provided for subsequent steps.

[0075] Step S1012: If the signal variance is greater than the preset variance threshold and the baseline offset is less than or equal to the preset offset, determining that the target interference type is non-physiological interference.

[0076] When the signal variance is greater than the preset variance threshold but the baseline offset is less than or equal to the preset offset, it means that there is a large fluctuation in the signal but the baseline has not significantly shifted, and the target interference type of the initial pulse wave signal is determined to be non-physiological interference.

[0077] It can be understood that by jointly determining the signal variance and the baseline offset, the physiological interference and non-physiological interference types in the initial pulse wave signal can be more accurately identified, providing reliable input data and decision-making basis for subsequent steps.

[0078] This embodiment introduces a noise reduction model to identify and remove noise signals in the initial pulse wave signal, thereby extracting a purer target pulse wave signal and reducing the interference of noise on the pulse wave signal. Therefore, blood oxygen concentration detection based on the processed target pulse wave signal can more accurately reflect the blood oxygen saturation of the human body, thereby improving the accuracy of blood oxygen detection.

[0079] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 Step S20: Inputting the filtered pulse wave signal into the noise reduction model to obtain a target pulse wave signal, comprising:

[0080] Step S201, filtering the initial pulse wave signal to obtain a filtered pulse wave signal of a target frequency band, wherein the target frequency band is a frequency band corresponding to a human heart rate range;

[0081] The initial pulse wave signal is filtered to extract the signal components related to the target frequency band (the frequency band corresponding to the human heart rate range). The filtering process can remove the noise and interference that are not in the target frequency band, thereby obtaining a clearer pulse wave signal.

[0082] Specifically, the frequency band corresponding to the human heart rate range is pre-set. Generally speaking, the normal heart rate range of an adult is between 60 and 100 beats per minute, and the corresponding frequency range is 1 to 1.67 Hz (assuming that the heart rate is regular and each heartbeat cycle is constant). It can be understood that in actual applications, since the heart rate may vary due to individual differences, exercise status and other factors, the target frequency band may be appropriately adjusted according to the specific situation; determine the target filter, and use the filter to extract the filtered pulse signal wave signal.

[0083] It can be understood that through filtering, the noise and interference in the initial pulse wave signal that are not within the target frequency band can be removed, the signal-to-noise ratio of the signal can be improved, and the pulse wave signal after filtering is clearer, which is conducive to the subsequent noise reduction model processing and the accuracy of blood oxygen concentration detection.

[0084] Step S202: input the filtered pulse wave signal into the noise reduction model to obtain a target pulse wave signal.

[0085] The filtered pulse wave signal is subjected to noise elimination processing by a deep neural network combined with an attention mechanism, and the result obtained is referred to as a first signal for distinction. In this embodiment, the filtered pulse wave signal features extracted by the deep neural network are weighted based on the attention weight through the attention mechanism, and the higher the similarity between the filtered pulse wave signal features and the filtered pulse wave signal features after denoising, the greater the attention weight, so that the deep neural network can focus on important information in the filtered pulse wave signal through the weighted processing of the attention mechanism during the processing of the filtered pulse wave signal, thereby making the deep neural network more accurate in eliminating noise from the filtered pulse wave signal.

[0086] In a specific implementation, the noise reduction device can perform frame processing on the received pulse wave signal, and perform blood oxygen saturation detection processing on each frame of the received pulse wave signal in sequence. In this implementation, the currently processed frame of the received pulse wave signal is used as the initial pulse wave signal.

[0087] This embodiment introduces an attention mechanism into the deep neural network, and performs weighted processing on the filtered pulse wave signal features extracted by the deep neural network based on the attention weight through the attention mechanism. The higher the similarity between the filtered pulse wave signal features and the filtered pulse wave signal features after denoising, the greater the attention weight. In this way, the deep neural network can focus on important information in the filtered pulse wave signal through the weighted processing of the attention mechanism during the processing of the filtered pulse wave signal, thereby making the deep neural network more accurate in eliminating noise of the filtered pulse wave signal, thereby achieving the blood oxygen saturation detection effect in which the pulse wave signal is easily interfered with and the accurate detection of blood oxygen saturation is affected.

[0088] In one feasible implementation, the deep neural network includes an encoder, an attention mechanism module, a decoder and a fully connected layer, and the steps of step S202 include:

[0089] Step S2021, inputting the filtered pulse wave signal into the encoder for processing to obtain a first processing result;

[0090] In this embodiment, the preset deep neural network may include an encoder, a recurrent neural network module, an attention mechanism module, a decoder and a fully connected layer. Among them, the encoder layer is used to extract data features and downsample the input initial pulse wave signal; the recurrent neural network module is used to process the results output by the encoder layer, and the results of processing the initial pulse wave signal of the previous frame will be used in the processing process, so as to use the information of the historical frame to eliminate noise in the current frame and improve the blood oxygen saturation detection effect; the attention mechanism module is used to focus on the key signals in the initial pulse wave signal, that is, the signals in the target frequency band; the decoder is used to upsample the results output by the recurrent neural network; the fully connected layer is used to process the results output by the decoder and output the signal after noise elimination. The deep neural network can be trained in advance through a training data set, and the training method can adopt a conventional neural network training method, which will not be repeated here.

[0091] In one feasible implementation, the encoder and decoder can refer to the encoder-decoder structure in the U-net network, that is, the decoder is used to implement the crossover and upsampling of data features. The noise reduction device inputs the filtered pulse wave signal in the initial pulse wave signal into the encoder for processing to obtain a processing result corresponding to the target initial pulse wave signal (hereinafter referred to as the first processing result for distinction).

[0092] Step S2022, inputting the first processing result into the recurrent neural network module for processing to obtain a second processing result, wherein when the first processing result is processed by the recurrent neural network module, the result obtained by processing the previous frame processing result by the recurrent neural network module is the result obtained by the encoder processing the previous frame signal of the initial pulse wave signal;

[0093] When the noise reduction device is performing noise elimination, it processes the received initial pulse wave signal in a time sequence. In this embodiment, the previous frame signal of the currently processed initial pulse wave signal is called the previous frame signal, and the processing result of the encoder on the previous frame signal is called the previous frame processing result.

[0094] In this embodiment, the first processing result is input into the recurrent neural network module for processing to obtain the second processing result. It can be understood that when the first processing result is processed by the recurrent neural network module, the result obtained by processing the previous frame processing result using the recurrent neural network module.

[0095] Step S2023, inputting the second processing result into the decoder for processing to obtain a third processing result;

[0096] The second processing result is input to the decoder for processing, and the obtained result is called the third processing result for distinction.

[0097] Step S2024, inputting the first processing result and the third processing result into the attention mechanism module for processing to obtain a fourth processing result;

[0098] The first processing result and the third processing result are input into the attention mechanism module for processing, and the obtained result is called the fourth processing result for distinction.

[0099] In a specific implementation, an attention weight matrix representing the degree of attention to information in the first processing result may be calculated based on the first processing result and the third processing result, and the first processing result may be weighted by the attention weight matrix to obtain the fourth processing result.

[0100] The attention mechanism module performs weighted processing on the first processing result to achieve weight allocation of features in the first processing result, thereby screening out important information in the first processing result and enhancing important information, so that the deep neural network focuses on key information during the decoding process, that is, the signal of the target frequency band corresponding to the heart rate, thereby improving the accuracy of noise elimination.

[0101] Step S2025, connecting the third processing result and the fourth processing result, and inputting the connected result into the fully connected layer for processing to obtain a target pulse wave signal.

[0102] The third processing result and the fourth processing result are connected, and the connected result is input into the fully connected layer for processing to obtain the target pulse wave signal.

[0103] like Figure 3 As shown, a schematic diagram of the structure of the deep neural network in this embodiment is drawn, in which R_rnn represents a recurrent neural network, and the encoder may include multiple encoding layers (such as Figure 3 The decoder may include multiple decoding layers ( Figure 3 Three decoding layers are drawn in the figure), the decoding layer can be used for deconvolution (deconv), the number of attention mechanism modules is the same as the number of encoder layers (that is, the number of decoder layers), each layer of the encoder and decoder is connected to the attention mechanism module respectively, and the output data of the attention mechanism module is connected to the output data of the decoder as the input data of the next layer.

[0104] Among them, the encoding layer can use one-dimensional convolution (1D-conv, that is, Figure 3 conv)+downsampling+activation function as shown in , downsampling can use 2*2 pooling layer, and the activation function can use LeakyRelu.

[0105] Further, in a feasible implementation manner, the attention mechanism module includes a weight calculation block and a weighted processing block, and the step S2024: inputting the first processing result and the third processing result into the attention mechanism module for processing to obtain a fourth processing result includes:

[0106] Step S20241, inputting the first processing result and the third processing result into the weight calculation block for processing to obtain an attention weight matrix;

[0107] In this embodiment, the first processing result and the third processing result are input into the weight calculation block for processing to obtain the attention weight matrix. The specific method of calculating the attention weight matrix is ​​not limited in this embodiment.

[0108] Step S20242, input the attention weight matrix and the first processing result into the weighted processing block for processing to obtain a fourth processing result.

[0109] The attention weight matrix and the first processing result are input into the weighted processing block for processing to obtain a fourth processing result.

[0110] Further, in a feasible implementation, the weight calculation block includes three convolution layers, one dot product layer and two activation functions. The first processing result and the third processing result are input into the weight calculation block for processing. The process of obtaining the attention weight matrix can be: the first processing result is input into the first convolution layer for convolution operation to obtain the first convolution result, and the third processing result is input into the second convolution layer for convolution operation to obtain the second convolution result; the first convolution result and the second convolution result are input into the first dot product layer to calculate the first dot product result, and the first dot product result is input into the first activation function for processing to obtain the first activation result; the first activation result is input into the third convolution layer for convolution operation to obtain the third convolution result, and the third convolution result is input into the second activation function for processing to obtain the attention weight matrix. It should be noted that the first convolution weight, the second convolution weight and the third convolution weight can be obtained in the model training stage, and the training process is not described in detail here. In this implementation, feature enhancement is performed through convolution operation, and nonlinear factors are added through activation functions to improve the expression ability of deep neural networks for models.

[0111] Furthermore, in a feasible implementation, the weighted processing block includes a convolution layer and a dot product layer, and the process of inputting the attention weight matrix and the first processing result into the weighted processing block for processing to obtain a fourth processing result may be: inputting the first processing result into the fourth convolution layer for convolution operation to obtain a fourth convolution result; inputting the fourth convolution result and the attention weight matrix into the second dot product layer to calculate and obtain the fourth processing result.

[0112] In the process of training a deep neural network using a recurrent neural network layer, back propagation can be used to calculate the gradient of each parameter and update each parameter based on the gradient.

[0113] In this embodiment, the first processing result is weighted by introducing an attention mechanism module to achieve weight allocation of features in the first processing result, thereby screening out important information in the first processing result and enhancing the important information, so that the deep neural network focuses on key information during the decoding process, thereby improving the accuracy of noise elimination.

[0114] For example, in order to help understand the implementation process of the blood oxygen saturation detection method obtained by combining this embodiment with the above-mentioned embodiment 1:

[0115] a. Data preprocessing: To address the noise and electromyographic signal interference in the original pulse wave signal, filtering, noise reduction and other means are used for preprocessing to improve the signal quality. Specific methods include: Butterworth filtering, wavelet transform, adaptive filtering, etc.

[0116] b. Feature extraction: Extract distinguishing features from the preprocessed pulse wave signal to reflect the essential characteristics of the interference waveform. Specific features include: time domain features (such as mean, standard deviation, kurtosis), frequency domain features (power spectral density, Fourier transform coefficients, etc.) and time-frequency features (Hilbert-Huang transform coefficients, etc.).

[0117] c. Machine learning algorithm: A neural network (NN) machine learning algorithm is used to classify and identify the extracted features to obtain candidate interference types, and parameter tuning is performed to improve recognition accuracy (i.e., feature extraction is performed on the initial pulse wave signal to obtain signal waveform features, and the target interference type of the initial pulse wave signal is determined based on the signal waveform features).

[0118] d. Deep learning algorithm: A convolutional neural network (CNN) deep learning algorithm is used to further identify candidate interference types and obtain the final interference waveform type. The deep learning algorithm can adaptively learn feature representations to improve recognition accuracy and robustness (i.e., receiving the initial pulse wave signal collected by the photoplethysmography detection device, determining whether there is a noise signal in the initial pulse wave signal; if there is the noise signal in the initial pulse wave signal, inputting the initial pulse wave signal into the noise reduction model to obtain the target pulse wave signal).

[0119] e. Adaptive adjustment: According to the recognition results, the preprocessing and feature extraction methods are dynamically adjusted to meet the interference waveform recognition requirements in different environments and usage scenarios. For example, when the recognition accuracy is low, the order of the filter can be increased or a more complex feature extraction method can be used.

[0120] f. Real-time optimization: For application scenarios with high real-time requirements, it supports the use of optimized algorithms and hardware platforms, such as FPGA, ASIC, etc., to improve the real-time performance of interference waveform recognition.

[0121] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the blood oxygen saturation detection method of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0122] The present application also provides a blood oxygen saturation detection device, which is applied to a noise reduction device, and the noise reduction device is connected to a photoplethysmography detection device for communication. Figure 4 , the blood oxygen saturation detection device comprises:

[0123] A judgment module 10 is used to receive the initial pulse wave signal collected by the photoplethysmography detection device and judge whether there is a noise signal in the initial pulse wave signal;

[0124] A denoising module 20, for inputting the initial pulse wave signal into a denoising model to obtain a target pulse wave signal if the noise signal exists in the initial pulse wave signal, wherein the denoising model is trained with a historical pulse wave signal as input data and the denoised historical pulse wave signal as a label;

[0125] The sending module 30 is used to send the target pulse wave signal to the photoplethysmography detection device, wherein the photoplethysmography detection device performs blood oxygen concentration detection based on the target pulse wave signal.

[0126] Optionally, the noise reduction module 20 is used to:

[0127] Filtering the initial pulse wave signal to obtain a filtered pulse wave signal of a target frequency band, wherein the target frequency band is a frequency band corresponding to a human heart rate range;

[0128] The filtered pulse wave signal is input into the noise reduction model to obtain a target pulse wave signal.

[0129] Optionally, the denoising model includes an encoder, a recurrent neural network, an attention mechanism module, a decoder and a fully connected layer, and the denoising module 20 is used to:

[0130] Inputting the filtered pulse wave signal into the encoder for processing to obtain a first processing result;

[0131] Inputting the first processing result into the recurrent neural network module for processing to obtain a second processing result, wherein when the first processing result is processed by the recurrent neural network module, the result obtained by processing the previous frame processing result by the recurrent neural network module is the result obtained by the encoder processing the previous frame signal of the initial pulse wave signal;

[0132] Inputting the second processing result into the decoder for processing to obtain a third processing result;

[0133] Inputting the first processing result and the third processing result into the attention mechanism module for processing to obtain a fourth processing result;

[0134] The third processing result and the fourth processing result are connected, and the connected result is input into the fully connected layer for processing to obtain a target pulse wave signal.

[0135] Optionally, the attention mechanism module includes a weight calculation block and a weighted processing block, and the noise reduction module 20 is used to:

[0136] Inputting the first processing result and the third processing result into the weight calculation block for processing to obtain an attention weight matrix;

[0137] The attention weight matrix and the first processing result are input into the weighted processing block for processing to obtain a fourth processing result.

[0138] Optionally, the judging module 10 is used to:

[0139] Extracting features of the initial pulse wave signal to obtain signal waveform features, and determining a target interference type of the initial pulse wave signal based on the signal waveform features;

[0140] If the target interference type is a non-physiological interference type, determining that a noise signal exists in the initial pulse wave signal;

[0141] If the target interference type is a physiological interference type, it is determined that the noise signal does not exist in the initial pulse wave signal.

[0142] Optionally, the signal waveform characteristics include signal variance and baseline offset; the judgment module 10 is used to:

[0143] If the signal variance is greater than a preset variance threshold and the baseline offset is greater than a preset offset, determining that the target interference type of the initial pulse wave signal is physiological interference;

[0144] If the signal variance is greater than the preset variance threshold and the baseline offset is less than or equal to the preset offset, it is determined that the target interference type is non-physiological interference.

[0145] The blood oxygen saturation detection device provided by the present application adopts the blood oxygen saturation detection method in the above embodiment, which can solve the technical problem that the pulse wave signal is easily interfered with, affecting the blood oxygen saturation detection effect. Compared with the prior art, the beneficial effects of the blood oxygen saturation detection device provided by the present application are the same as the beneficial effects of the blood oxygen saturation detection method provided by the above embodiment, and the other technical features of the blood oxygen saturation detection device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0146] The present application provides a noise reduction device, which includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the blood oxygen saturation detection method in the above-mentioned embodiment 1.

[0147] Reference below Figure 5, which shows a schematic diagram of the structure of a noise reduction device suitable for implementing the embodiment of the present application. The noise reduction device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The noise reduction device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0148] like Figure 5 As shown, the noise reduction device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the noise reduction device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the noise reduction device to communicate with other devices wirelessly or wired to exchange data. Although the figure shows a noise reduction device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0149] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0150] The noise reduction device provided by the present application adopts the blood oxygen saturation detection method in the above embodiment, which can solve the technical problem that the pulse wave signal is easily interfered with, affecting the accurate detection of blood oxygen saturation. Compared with the prior art, the beneficial effects of the noise reduction device provided by the present application are the same as the beneficial effects of the blood oxygen saturation detection method provided by the above embodiment, and the other technical features in the noise reduction device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0151] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0152] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0153] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the blood oxygen saturation detection method in the above-mentioned embodiment.

[0154] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0155] The computer-readable storage medium may be included in the noise reduction device; or may exist independently without being assembled into the noise reduction device.

[0156] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the noise reduction device, the noise reduction device: receives the initial pulse wave signal collected by the photoplethysmography detection device, and determines whether there is a noise signal in the initial pulse wave signal; if the noise signal exists in the initial pulse wave signal, inputs the initial pulse wave signal into a noise reduction model to obtain a target pulse wave signal, wherein the noise reduction model is trained using a historical pulse wave signal as input data and the noise-reduced historical pulse wave signal as a label; sends the target pulse wave signal to the photoplethysmography detection device, wherein the photoplethysmography detection device performs blood oxygen concentration detection based on the target pulse wave signal.

[0157] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0158] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0159] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0160] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned blood oxygen saturation detection method, and can solve the technical problem that the pulse wave signal is easily interfered with, which affects the accurate detection of blood oxygen saturation. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the blood oxygen saturation detection method provided by the above-mentioned embodiment, and will not be repeated here.

[0161] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned blood oxygen saturation detection method when executed by a processor.

[0162] The computer program product provided by the present application can solve the technical problem that the pulse wave signal is easily interfered with, which affects the accurate detection of blood oxygen saturation. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the blood oxygen saturation detection method provided by the above embodiment, which will not be repeated here.

[0163] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for detecting blood oxygen saturation, characterized in that: The blood oxygen saturation detection method is applied to a noise reduction device, the noise reduction device is communicatively connected with a photoplethysmography detection device, and the blood oxygen saturation detection method includes: receiving an initial pulse wave signal collected by the photoplethysmography detection device, and determining whether a noise signal exists in the initial pulse wave signal; If the noise signal exists in the initial pulse wave signal, the initial pulse wave signal is input into a noise reduction model to obtain a target pulse wave signal, wherein the noise reduction model is trained using a historical pulse wave signal as input data and the noise-reduced historical pulse wave signal as a label; The target pulse wave signal is sent to the photoplethysmography detection device, wherein the photoplethysmography detection device performs blood oxygen concentration detection based on the target pulse wave signal.

2. The method for detecting blood oxygen saturation as claimed in claim 1, characterized in that: The step of inputting the initial pulse wave signal into the noise reduction model to obtain a target pulse wave signal comprises: Filtering the initial pulse wave signal to obtain a filtered pulse wave signal of a target frequency band, wherein the target frequency band is a frequency band corresponding to a human heart rate range; The filtered pulse wave signal is input into the noise reduction model to obtain a target pulse wave signal.

3. The method for detecting blood oxygen saturation as claimed in claim 2, characterized in that: The denoising model includes an encoder, a recurrent neural network, an attention mechanism module, a decoder and a fully connected layer. The step of inputting the filtered pulse wave signal into the denoising model to obtain a target pulse wave signal includes: Inputting the filtered pulse wave signal into the encoder for processing to obtain a first processing result; Inputting the first processing result into the recurrent neural network module for processing to obtain a second processing result, wherein when the first processing result is processed by the recurrent neural network module, the result obtained by processing the previous frame processing result by the recurrent neural network module is the result obtained by the encoder processing the previous frame signal of the initial pulse wave signal; Inputting the second processing result into the decoder for processing to obtain a third processing result; Inputting the first processing result and the third processing result into the attention mechanism module for processing to obtain a fourth processing result; The third processing result and the fourth processing result are connected, and the connected result is input into the fully connected layer for processing to obtain a target pulse wave signal.

4. The method for detecting blood oxygen saturation as claimed in claim 3, characterized in that: The attention mechanism module includes a weight calculation block and a weighted processing block, and the step of inputting the first processing result and the third processing result into the attention mechanism module for processing to obtain a fourth processing result includes: Inputting the first processing result and the third processing result into the weight calculation block for processing to obtain an attention weight matrix; The attention weight matrix and the first processing result are input into the weighted processing block for processing to obtain a fourth processing result.

5. The method for detecting blood oxygen saturation according to any one of claims 1 to 4, characterized in that: The step of determining whether there is a noise signal in the initial pulse wave signal comprises: Extracting features of the initial pulse wave signal to obtain signal waveform features, and determining a target interference type of the initial pulse wave signal based on the signal waveform features; If the target interference type is a non-physiological interference type, determining that a noise signal exists in the initial pulse wave signal; If the target interference type is a physiological interference type, it is determined that the noise signal does not exist in the initial pulse wave signal.

6. The method for detecting blood oxygen saturation as claimed in claim 5, characterized in that: The signal waveform characteristics include signal variance and baseline offset; the step of determining the target interference type of the initial pulse wave signal based on the signal waveform characteristics includes: If the signal variance is greater than a preset variance threshold and the baseline offset is greater than a preset offset, determining that the target interference type of the initial pulse wave signal is physiological interference; If the signal variance is greater than the preset variance threshold and the baseline offset is less than or equal to the preset offset, it is determined that the target interference type is non-physiological interference.

7. A blood oxygen saturation detection device, characterized in that: The blood oxygen saturation detection device is applied to a noise reduction device, the noise reduction device is communicatively connected with a photoplethysmography detection device, and the blood oxygen saturation detection device comprises: A judgment module, used for receiving the initial pulse wave signal collected by the photoplethysmography detection device, and judging whether there is a noise signal in the initial pulse wave signal; A denoising module, for inputting the initial pulse wave signal into a denoising model to obtain a target pulse wave signal if the noise signal exists in the initial pulse wave signal, wherein the denoising model is trained with a historical pulse wave signal as input data and the denoised historical pulse wave signal as a label; A sending module is used to send the target pulse wave signal to the photoplethysmography detection device, wherein the photoplethysmography detection device performs blood oxygen concentration detection based on the target pulse wave signal.

8. A noise reduction device, characterized in that: The noise reduction device includes: a memory, a processor, and a blood oxygen saturation detection program stored in the memory and executable on the processor. When the blood oxygen saturation detection program is executed by the processor, the steps of the blood oxygen saturation detection method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a blood oxygen saturation detection program, and when the blood oxygen saturation detection program is executed by the processor, the steps of the blood oxygen saturation detection method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the blood oxygen saturation detection method according to any one of claims 1 to 6 are implemented.

Images