Physiological signal processing method and device

Abstract

The invention discloses a physiological signal processing method and device. The method comprises the following steps: acquiring multi-type physiological signal information; the multi-type physiological signal information comprises M pieces of physiological signal information; m is a positive integer not less than 4; pre-processing the multi-type physiological signal information to obtain target processing signal information; the target processing signal information comprises M pieces of processing physiological signal information; performing evaluation processing on the target processing signal information by using a signal evaluation model to obtain target evaluation result information; the signal evaluation model comprises a feature extraction sub-model and a feature evaluation sub-model. Therefore, comprehensive processing of various physiological signals can be realized, and the accuracy and efficiency of signal evaluation can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of signal processing, and in particular, to a physiological signal processing method and apparatus. Background Art

[0002] With the accelerating pace of modern society, people are facing increasing pressure, leading to increasingly prominent mental health problems. For the personnel staying in special environments such as polar regions, plateaus, deep seas, and high altitudes, due to the particularity of their working and living conditions, they face higher psychological pressure and challenges. However, there are many problems in traditional mental signal processing methods, such as time / location limitations and shortages of professional doctor resources. Therefore, based on the research results of auxiliary diagnosis in the aspect of physiological signals carried out by the national natural science foundation project "Research on the diagnosis technology and neural mechanism of fear of disease progression based on traditional Chinese medicine eye diagnosis", the present application provides a physiological signal processing method and apparatus to achieve comprehensive processing of various physiological signals and improve the accuracy and efficiency of signal evaluation. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a physiological signal processing method and apparatus that are conducive to achieving comprehensive processing of various physiological signals and improving the accuracy and efficiency of signal evaluation.

[0004] To solve the above technical problem, in the first aspect of an embodiment of the present invention, a physiological signal processing method is disclosed, and the method includes:

[0005] Obtain multi-type physiological signal information; the multi-type physiological signal information includes M pieces of physiological signal information; M is a positive integer not less than 4;

[0006] Perform preprocessing on the multi-type physiological signal information to obtain target processed signal information; the target processed signal information includes the M pieces of processed physiological signal information;

[0007] Use a signal evaluation model to perform evaluation processing on the target processed signal information to obtain target evaluation result information; the signal evaluation model includes a feature extraction sub-model and a feature evaluation sub-model.

[0008] As an optional implementation manner, in the first aspect of an embodiment of the present invention, the physiological signal information includes electroencephalogram signal information, and / or electrocardiogram signal information, and / or facial signal information, and / or eye signal information;

[0009] The obtaining of the multi-type physiological signal information includes:

[0010] Set the sampling frequencies and sampling time intervals of the first signal acquisition device, the second signal acquisition device, the third signal acquisition device, and the fourth signal acquisition device of the signal evaluation system in sequence;

[0011] Play a signal trigger video at the first device end of the signal evaluation system; the video duration corresponding to the signal trigger video is not greater than the time interval length of the sampling time interval.

[0012] Based on the sampling frequency of the first signal acquisition device, collect signals of the user's electroencephalogram activity within the sampling time interval to obtain the electroencephalogram signal information.

[0013] Based on the sampling frequency of the second signal acquisition device, collect signals of the user's cardiac activity within the sampling time interval to obtain the electrocardiogram signal information.

[0014] Based on the sampling frequency of the third signal acquisition device, collect signals of the user's facial activity within the sampling time interval to obtain the facial signal information.

[0015] Based on the sampling frequency of the fourth signal acquisition device, collect signals of the user's eye activity within the sampling time interval to obtain the eye signal information.

[0016] As an optional implementation manner, in the first aspect of the embodiments of the present invention, the preprocessing of the multi-type physiological signal information to obtain the target processed signal information includes:

[0017] For any one of the physiological signal information, obtain the frequency adjustment information corresponding to the physiological signal information.

[0018] Based on the frequency adjustment information, perform interpolation smoothing processing on the physiological signal information to obtain the first processed signal information corresponding to the physiological signal information.

[0019] Obtain the filtering parameter information corresponding to the physiological signal information; the filtering parameter information corresponding to any two of the physiological signal information is inconsistent.

[0020] Based on the filtering parameter information, perform filtering processing on the first processed signal information to obtain the second processed signal information corresponding to the physiological signal information.

[0021] Perform signal amplification processing on the second processed signal information to obtain the third processed signal information corresponding to the physiological signal information.

[0022] Perform discretization processing on the third processed signal information to obtain the processed physiological signal information corresponding to the physiological signal information.

[0023] As an alternative implementation, in the first aspect of the embodiments of the present invention, the evaluation processing of the target processed signal information using the signal evaluation model to obtain the target evaluation result information includes:

[0024] Performing feature extraction processing on the target processed signal information using the feature extraction sub-model to obtain target signal feature information;

[0025] Performing evaluation processing on the target signal feature information using the feature evaluation sub-model to obtain the target evaluation result information; the feature evaluation sub-model includes a first convolution module, the first feature evaluation sub-model, the second feature evaluation sub-model, a first fusion module, a second fusion module, and a third fusion module.

[0026] As an alternative implementation, in the first aspect of the embodiments of the present invention, the evaluation processing of the target signal feature information using the feature evaluation sub-model to obtain the target evaluation result information includes:

[0027] Performing convolution processing on the target signal feature information using the first convolution module to obtain target convolution feature information;

[0028] Processing the target convolution feature information using the first feature evaluation sub-model to obtain first feature evaluation information;

[0029] Performing fusion processing on the target convolution feature information and the first feature evaluation information using the first fusion module to obtain first fusion feature information;

[0030] Processing the first fusion feature information using the second feature evaluation sub-model to obtain second feature evaluation information;

[0031] Performing fusion processing on the first fusion feature information and the second feature evaluation information using the second fusion module to obtain second fusion feature information;

[0032] Performing fusion processing on the target convolution feature information and the second fusion feature information using the third fusion module to obtain the target evaluation result information.

[0033] As an alternative implementation, in the first aspect of the embodiments of the present invention, the first feature evaluation sub-model includes a first pooling layer, a second pooling layer, a first activation module, a second activation module, a third activation module, a fourth activation module, a first fully connected layer, a second fully connected layer, a third fully connected layer, a fourth fully connected layer, and a first neural network;

[0034] The second feature evaluation sub-model includes a third pooling layer, a fourth pooling layer, a second convolution module, and a fifth activation module.

[0035] As an alternative implementation, in the first aspect of the embodiments of the present invention, the input end of the first convolution module is connected to the model input, and the output end of the first convolution module is respectively connected to the input end of the first pooling layer, the input end of the second pooling layer, the input end of the first fusion module, and the input end of the third fusion module; the output end of the first pooling layer is connected to the input end of the first fully-connected layer; the output end of the first fully-connected layer is connected to the input end of the first activation module; the output end of the first activation module is connected to the input end of the second fully-connected layer; the output end of the second fully-connected layer is connected to the input end of the second activation module; the output end of the second pooling layer is connected to the input end of the third fully-connected layer; the output end of the third fully-connected layer is connected to the input end of the third activation module; the output end of the third activation module is connected to the input end of the fourth fully-connected layer; the output end of the fourth fully-connected layer is connected to the input end of the fourth activation module; the input end of the first neural network is respectively connected to the output end of the second activation module and the output end of the fourth activation module; the output end of the first neural network is connected to the input end of the first fusion module; the output end of the first fusion module is respectively connected to the input end of the third pooling layer, the input end of the fourth pooling layer, and the input end of the second fusion module; the output ends of the third pooling layer and the fourth pooling layer are both connected to the input end of the second convolution module; the output end of the second convolution module is connected to the input end of the fifth activation module; the output end of the fifth activation module is connected to the input end of the second fusion module; the input end of the second fusion module is connected to the input end of the third fusion module; the output end of the third fusion module is connected to the model output.

[0036] The second aspect of the embodiments of the present invention discloses a physiological signal processing device, the device includes:

[0037] An acquisition module, configured to acquire multi-type physiological signal information; the multi-type physiological signal information includes M physiological signal information; M is a positive integer not less than 4;

[0038] A first processing module, configured to perform preprocessing on the multi-type physiological signal information to obtain target processed signal information; the target processed signal information includes the M processed physiological signal information;

[0039] A second processing module, configured to perform evaluation processing on the target processed signal information by using a signal evaluation model to obtain target evaluation result information; the signal evaluation model includes a feature extraction sub-model and a feature evaluation sub-model.

[0040] The third aspect of the present invention discloses another physiological signal processing device, the device includes:

[0041] A memory storing executable program code;

[0042] A processor coupled to the memory;

[0043] The processor calls the executable program code stored in the memory and executes some or all of the steps in the physiological signal processing method disclosed in the first aspect of the embodiments of the present invention.

[0044] The fourth aspect of the present invention discloses a computer-readable storage medium storing computer instructions, which are used to execute some or all of the steps in the physiological signal processing method disclosed in the first aspect of the embodiments of the present invention when the computer instructions are called.

[0045] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0046] In the embodiments of the present invention, multi-type physiological signal information is acquired; the multi-type physiological signal information includes M pieces of physiological signal information; M is a positive integer not less than 4; the multi-type physiological signal information is pre-processed to obtain target processed signal information; the target processed signal information includes M pieces of processed physiological signal information; the target processed signal information is evaluated using a signal evaluation model to obtain target evaluation result information; the signal evaluation model includes a feature extraction sub-model and a feature evaluation sub-model. It can be seen that the present application is conducive to realizing the comprehensive processing of multiple physiological signals and improving the accuracy and efficiency of signal evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0048] Figure 1 is a flowchart of a physiological signal processing method disclosed in an embodiment of the present invention;

[0049] Figure 2 is a structural diagram of a physiological signal processing device disclosed in an embodiment of the present invention;

[0050] Figure 3 is a structural diagram of another physiological signal processing device disclosed in an embodiment of the present invention;

[0051] Figure 4 is a structural diagram of a signal evaluation model disclosed in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0052] To enable those skilled in the art to better understand the solution of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0053] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or equipment.

[0054] Referring to "embodiments" herein means that the specific features, structures or characteristics described in connection with the embodiments can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0055] The present invention discloses a physiological signal processing method and device, which are beneficial to realizing the comprehensive processing of various physiological signals and improving the accuracy and efficiency of signal evaluation. The following will be described in detail respectively.

[0056] Embodiment 1

[0057] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a physiological signal processing method disclosed in an embodiment of the present invention. Among them, Figure 1 the described physiological signal processing method is applied in a signal management system, such as a local server or a cloud server for physiological signal processing management, etc., which is not limited in the embodiments of the present invention. As Figure 1 shown, the physiological signal processing method may include the following operations:

[0058] 101. Obtain multi-type physiological signal information.

[0059] In the embodiments of the present invention, the multi-type physiological signal information includes M pieces of physiological signal information; M is a positive integer not less than 4.

[0060] 102. Preprocess multi-type physiological signal information to obtain target processed signal information.

[0061] In the embodiments of the present invention, the target processed signal information includes M processed physiological signal information.

[0062] 103. Use a signal evaluation model to evaluate and process the target processed signal information to obtain target evaluation result information.

[0063] In the embodiments of the present invention, the signal evaluation model includes a feature extraction sub-model and a feature evaluation sub-model.

[0064] It should be noted that the method of the present application can analyze and interpret signals such as facial micro-expressions, eye movements, electrocardiograms, and electroencephalograms, and carry out more accurate and comprehensive signal state detection and evaluation.

[0065] It can be seen that implementing the physiological signal processing method described in the embodiments of the present invention is conducive to realizing the comprehensive processing of multiple physiological signals and improving the accuracy and efficiency of signal evaluation.

[0066] In an alternative embodiment, the above physiological signal information includes electroencephalogram signal information, and / or electrocardiogram signal information, and / or facial signal information, and / or eye signal information;

[0067] Obtain multi-type physiological signal information, including:

[0068] Set the sampling frequencies and sampling time intervals of the first signal acquisition device, the second signal acquisition device, the third signal acquisition device, and the fourth signal acquisition device of the signal evaluation system in sequence;

[0069] Play a signal trigger video at the first device end of the signal evaluation system; the video duration corresponding to the signal trigger video is not greater than the time interval length of the sampling time interval;

[0070] Based on the sampling frequency of the first signal acquisition device, collect signal of the user's electroencephalogram activity within the sampling time interval to obtain electroencephalogram signal information;

[0071] Based on the sampling frequency of the second signal acquisition device, collect signal of the user's cardiac activity within the sampling time interval to obtain electrocardiogram signal information;

[0072] Based on the sampling frequency of the third signal acquisition device, collect signal of the user's facial activity within the sampling time interval to obtain facial signal information;

[0073] Based on the sampling frequency of the fourth signal acquisition device, collect signal of the user's eye activity within the sampling time interval to obtain eye signal information.

[0074] It should be noted that the above-mentioned different types of signal data can be collected at each time point according to the sampling frequency within the sampling time interval, so as to obtain the corresponding electroencephalogram (EEG) signal information, and / or electrocardiogram (ECG) signal information, and / or facial signal information, and / or eye signal information.

[0075] It should be noted that the above-mentioned first signal acquisition device can be a wireless dry electrode EEG acquisition device. By placing a dry electrode device on the user's head, the EEG activity of the user can be recorded and measured in real time to obtain the corresponding EEG signal information. The EEG signal information can provide important information about brain activity and nerve function, such as attention level, cognitive process, and emotional changes, etc.

[0076] It should be noted that the above-mentioned second signal acquisition device can be an ECG signal acquisition device, which acquires the user's ECG signal to obtain the corresponding ECG signal information. The ECG signal information can provide important indicators about heart function and the state of the cardiovascular system, such as heart rate, heart rhythm, and electrocardiogram waveform, etc.

[0077] It should be noted that the above-mentioned third signal acquisition device can be a high-frame-rate camera, which acquires the user's facial image information, captures the user's facial expressions and movements, so as to obtain facial signal information related to emotions.

[0078] It should be noted that the above-mentioned fourth signal acquisition device can be an eye tracker, which records the user's eye movement behavior, such as blinking, gazing, and fixation points, etc., so as to obtain eye signal information to provide information related to attention and visual attention.

[0079] It can be seen that implementing the physiological signal processing method described in the embodiments of the present invention is beneficial to realizing the comprehensive processing of multiple physiological signals and improving the accuracy and efficiency of signal evaluation.

[0080] In another optional embodiment, preprocessing the multi-type physiological signal information to obtain target processed signal information, including:

[0081] For any physiological signal information, obtain the frequency adjustment information corresponding to this physiological signal information;

[0082] Based on the frequency adjustment information, perform interpolation smoothing processing on this physiological signal information to obtain the first processed signal information corresponding to this physiological signal information;

[0083] Obtain the filtering parameter information corresponding to this physiological signal information; the filtering parameter information corresponding to any two physiological signal information is inconsistent;

[0084] Based on the filtering parameter information, perform filtering processing on the first processed signal information to obtain the second processed signal information corresponding to this physiological signal information;

[0085] Perform signal amplification processing on the second processed signal information to obtain the third processed signal information corresponding to the physiological signal information;

[0086] Perform discretization processing on the third processed signal information to obtain the processed physiological signal information corresponding to the physiological signal information.

[0087] It should be noted that the frequency adjustment information corresponding to the above physiological signal information can be set by the user or generated by the system according to historical data, which is not limited in the embodiments of the present invention. Further, the above interpolation smoothing processing of the physiological signal information based on the frequency adjustment information is to perform interpolation at the time position corresponding to the frequency adjustment information, and then perform curve fitting on all values to make the data smoother.

[0088] It should be noted that the above filtering parameters are used to adjust the parameter information of the filter, and the unnecessary impurity data of the first processed signal information can be filtered through the filter.

[0089] It should be noted that the above signal amplification processing can enhance the amplitude of the signal, making it easier to analyze and process.

[0090] It should be noted that the above discretization processing is to convert a continuous data curve into individual data points, such as converting a continuous analog signal into a discrete digital signal.

[0091] It can be seen that implementing the physiological signal processing method described in the embodiments of the present invention is beneficial to realizing the comprehensive processing of various physiological signals and improving the accuracy and efficiency of signal evaluation.

[0092] Such as Figure 4 As shown, in another optional embodiment, use a signal evaluation model to perform evaluation processing on the target processed signal information to obtain target evaluation result information, including:

[0093] Use a feature extraction sub-model to perform feature extraction processing on the target processed signal information to obtain target signal feature information;

[0094] Use a feature evaluation sub-model to perform evaluation processing on the target signal feature information to obtain target evaluation result information; the feature evaluation sub-model includes a first convolution module, a first feature evaluation sub-model, a second feature evaluation sub-model, a first fusion module, a second fusion module, and a third fusion module.

[0095] It should be noted that the above first fusion module, second fusion module, and third fusion module are constructed based on residual connections.

[0096] It should be noted that the above-mentioned feature evaluation sub-model includes 4 feature extraction modules arranged in parallel and 1 feature fusion module. Further, the above-mentioned feature extraction modules are respectively used to process electroencephalogram signal information, electrocardiogram signal information, facial signal information, and eye signal information.

[0097] It should be noted that the above-mentioned feature extraction module sequentially includes a 3*3 convolutional layer and a residual multi-head attention module.

[0098] It should be noted that the above-mentioned feature fusion module is a multi-head mutual attention module.

[0099] It should be noted that through the feature extraction and fusion processing of the above 4 feature extraction modules arranged in parallel and the cross-modal feature fusion module, the deep fusion of different modal feature information can be realized.

[0100] It can be seen that implementing the physiological signal processing method described in the embodiments of the present invention is beneficial to realizing the comprehensive processing of multiple physiological signals and improving the accuracy and efficiency of signal evaluation.

[0101] In another optional embodiment, the feature evaluation sub-model is used to evaluate the target signal feature information to obtain the target evaluation result information, including:

[0102] Using the first convolutional module to perform convolutional processing on the target signal feature information to obtain the target convolutional feature information;

[0103] Using the first feature evaluation sub-model to process the target convolutional feature information to obtain the first feature evaluation information;

[0104] Using the first fusion module to perform fusion processing on the target convolutional feature information and the first feature evaluation information to obtain the first fusion feature information;

[0105] Using the second feature evaluation sub-model to process the first fusion feature information to obtain the second feature evaluation information;

[0106] Using the second fusion module to perform fusion processing on the first fusion feature information and the second feature evaluation information to obtain the second fusion feature information;

[0107] Using the third fusion module to perform fusion processing on the target convolutional feature information and the second fusion feature information to obtain the target evaluation result information.

[0108] It should be noted that the features corresponding to the above first feature evaluation information and second feature evaluation information have 2-dimensional numerical values of 1.

[0109] It can be seen that implementing the physiological signal processing method described in the embodiments of the present invention is beneficial to realizing the comprehensive processing of multiple physiological signals and improving the accuracy and efficiency of signal evaluation.

[0110] In an optional embodiment, the above-mentioned first feature evaluation sub-model includes a first pooling layer, a second pooling layer, a first activation module, a second activation module, a third activation module, a fourth activation module, a first fully connected layer, a second fully connected layer, a third fully connected layer, a fourth fully connected layer, and a first neural network;

[0111] The second feature evaluation sub-model includes a third pooling layer, a fourth pooling layer, a second convolution module, and a fifth activation module.

[0112] It should be noted that the above-mentioned first pooling layer and third pooling layer are max pooling layers. Further, the above-mentioned second pooling layer and fourth pooling layer are average pooling layers.

[0113] It should be noted that the above-mentioned first activation module and third activation module are constructed based on the ReLU function. Further, the above-mentioned second activation module, fourth activation module, and fifth activation module are constructed based on softmax.

[0114] It should be noted that the above-mentioned first neural network is a feed-forward neural network.

[0115] It should be noted that the above-mentioned second convolution module includes a 7*7 convolution operation and a splicing and fusion unit.

[0116] It can be seen that implementing the physiological signal processing method described in the embodiments of the present invention is conducive to realizing the comprehensive processing of various physiological signals and improving the accuracy and efficiency of signal evaluation.

[0117] In another alternative embodiment, the input end of the first convolution module is connected to the model input, and the output end of the first convolution module is respectively connected to the input end of the first pooling layer, the input end of the second pooling layer, the input end of the first fusion module, and the input end of the third fusion module; the output end of the first pooling layer is connected to the input end of the first fully connected layer; the output end of the first fully connected layer is connected to the input end of the first activation module; the output end of the first activation module is connected to the input end of the second fully connected layer; the output end of the second fully connected layer is connected to the input end of the second activation module; the output end of the second pooling layer is connected to the input end of the third fully connected layer; the output end of the third fully connected layer is connected to the input end of the third activation module; the output end of the third activation module is connected to the input end of the fourth fully connected layer; the output end of the fourth fully connected layer is connected to the input end of the fourth activation module; the input end of the first neural network is respectively connected to the output end of the second activation module and the output end of the fourth activation module; the output end of the first neural network is connected to the input end of the first fusion module; the output end of the first fusion module is respectively connected to the input end of the third pooling layer, the input end of the fourth pooling layer, and the input end of the second fusion module; the output ends of the third pooling layer and the fourth pooling layer are both connected to the input end of the second convolution module; the output end of the second convolution module is connected to the input end of the fifth activation module; the output end of the fifth activation module is connected to the input end of the second fusion module; the input end of the second fusion module is connected to the input end of the third fusion module; the output end of the third fusion module is connected to the model output.

[0118] It can be seen that implementing the physiological signal processing method described in the embodiments of the present invention is conducive to realizing the comprehensive processing of various physiological signals and improving the accuracy and efficiency of signal evaluation.

[0119] Embodiment 2

[0120] Please refer to Figure 2 , Figure 2 which is a schematic structural diagram of a physiological signal processing device disclosed in the embodiments of the present invention. Among them, Figure 2 the described device can be applied to a signal management system, such as a local server or a cloud server for physiological signal processing management, etc., which is not limited in the embodiments of the present invention. As Figure 2 shown, the device may include:

[0121] An acquisition module 201, configured to acquire multi-type physiological signal information; the multi-type physiological signal information includes M physiological signal information; M is a positive integer not less than 4;

[0122] A first processing module 202, configured to perform preprocessing on the multi-type physiological signal information to obtain target processed signal information; the target processed signal information includes M processed physiological signal information;

[0123] The second processing module 203 is configured to evaluate and process the target processing signal information by using a signal evaluation model to obtain target evaluation result information; the signal evaluation model includes a feature extraction sub-model and a feature evaluation sub-model.

[0124] It can be seen that implementing Figure 2 the described physiological signal processing device is conducive to realizing the comprehensive processing of various physiological signals and improving the accuracy and efficiency of signal evaluation.

[0125] In another optional embodiment, as Figure 2 shown, the physiological signal information includes electroencephalogram signal information, and / or electrocardiogram signal information, and / or facial signal information, and / or eye signal information;

[0126] The acquisition module 201 acquires multi-type physiological signal information, including:

[0127] Sequentially set the sampling frequencies and sampling time intervals of the first signal acquisition device, the second signal acquisition device, the third signal acquisition device, and the fourth signal acquisition device of the signal evaluation system;

[0128] Play a signal trigger video at the first device end of the signal evaluation system; the video duration corresponding to the signal trigger video is not greater than the time interval length of the sampling time interval;

[0129] Based on the sampling frequency of the first signal acquisition device, collect signal of the user's electroencephalogram activity within the sampling time interval to obtain electroencephalogram signal information;

[0130] Based on the sampling frequency of the second signal acquisition device, collect signal of the user's cardiac activity within the sampling time interval to obtain electrocardiogram signal information;

[0131] Based on the sampling frequency of the third signal acquisition device, collect signal of the user's facial activity within the sampling time interval to obtain facial signal information;

[0132] Based on the sampling frequency of the fourth signal acquisition device, collect signal of the user's eye activity within the sampling time interval to obtain eye signal information.

[0133] It can be seen that implementing Figure 2 the described physiological signal processing device is conducive to realizing the comprehensive processing of various physiological signals and improving the accuracy and efficiency of signal evaluation.

[0134] In yet another optional embodiment, as Figure 2 shown, the first processing module 202 performs pre-processing on the multi-type physiological signal information to obtain target processing signal information, including:

[0135] For any physiological signal information, obtain the frequency adjustment information corresponding to the physiological signal information;

[0136] Based on the frequency adjustment information, perform interpolation smoothing processing on the physiological signal information to obtain the first processed signal information corresponding to the physiological signal information;

[0137] Obtain the filtering parameter information corresponding to the physiological signal information; the filtering parameter information corresponding to any two physiological signal information is inconsistent;

[0138] Based on the filtering parameter information, perform filtering processing on the first processed signal information to obtain the second processed signal information corresponding to the physiological signal information;

[0139] Perform signal amplification processing on the second processed signal information to obtain the third processed signal information corresponding to the physiological signal information;

[0140] Perform discretization processing on the third processed signal information to obtain the processed physiological signal information corresponding to the physiological signal information.

[0141] It can be seen that implementing Figure 2 the described physiological signal processing device is conducive to realizing the comprehensive processing of various physiological signals and improving the accuracy and efficiency of signal evaluation.

[0142] In another alternative embodiment, as Figure 2 shown, the second processing module 203 uses a signal evaluation model to evaluate the target processed signal information to obtain target evaluation result information, including:

[0143] Use a feature extraction sub-model to perform feature extraction processing on the target processed signal information to obtain target signal feature information;

[0144] Use a feature evaluation sub-model to perform evaluation processing on the target signal feature information to obtain target evaluation result information; the feature evaluation sub-model includes a first convolution module, a first feature evaluation sub-model, a second feature evaluation sub-model, a first fusion module, a second fusion module, and a third fusion module.

[0145] It can be seen that implementing Figure 2 the described physiological signal processing device is conducive to realizing the comprehensive processing of various physiological signals and improving the accuracy and efficiency of signal evaluation.

[0146] In another alternative embodiment, as Figure 2 shown, the second processing module 203 uses a feature evaluation sub-model to perform evaluation processing on the target signal feature information to obtain target evaluation result information, including:

[0147] Use the first convolution module to perform convolution processing on the target signal feature information to obtain target convolution feature information;

[0148] Process the target convolutional feature information using the first feature evaluation sub-model to obtain the first feature evaluation information;

[0149] Fuse and process the target convolutional feature information and the first feature evaluation information using the first fusion module to obtain the first fusion feature information;

[0150] Process the first fusion feature information using the second feature evaluation sub-model to obtain the second feature evaluation information;

[0151] Fuse and process the first fusion feature information and the second feature evaluation information using the second fusion module to obtain the second fusion feature information;

[0152] Fuse and process the target convolutional feature information and the second fusion feature information using the third fusion module to obtain the target evaluation result information.

[0153] It can be seen that implementing Figure 2 the described physiological signal processing device is conducive to realizing the comprehensive processing of various physiological signals and improving the accuracy and efficiency of signal evaluation.

[0154] In another optional embodiment, as Figure 2 shown, the first feature evaluation sub-model includes a first pooling layer, a second pooling layer, a first activation module, a second activation module, a third activation module, a fourth activation module, a first fully connected layer, a second fully connected layer, a third fully connected layer, a fourth fully connected layer, and a first neural network;

[0155] The second feature evaluation sub-model includes a third pooling layer, a fourth pooling layer, a second convolutional module, and a fifth activation module.

[0156] It can be seen that implementing Figure 2 the described physiological signal processing device is conducive to realizing the comprehensive processing of various physiological signals and improving the accuracy and efficiency of signal evaluation.

[0157] In another optional embodiment, as Figure 2As shown, the input end of the first convolution module is connected to the model input, and the output end of the first convolution module is respectively connected to the input end of the first pooling layer, the input end of the second pooling layer, the input end of the first fusion module, and the input end of the third fusion module; the output end of the first pooling layer is connected to the input end of the first fully connected layer; the output end of the first fully connected layer is connected to the input end of the first activation module; the output end of the first activation module is connected to the input end of the second fully connected layer; the output end of the second fully connected layer is connected to the input end of the second activation module; the output end of the second pooling layer is connected to the input end of the third fully connected layer; the output end of the third fully connected layer is connected to the input end of the third activation module; the output end of the third activation module is connected to the input end of the fourth fully connected layer; the output end of the fourth fully connected layer is connected to the input end of the fourth activation module; the input end of the first neural network is respectively connected to the output end of the second activation module and the output end of the fourth activation module; the output end of the first neural network is connected to the input end of the first fusion module; the output end of the first fusion module is respectively connected to the input end of the third pooling layer, the input end of the fourth pooling layer, and the input end of the second fusion module; the output ends of the third pooling layer and the fourth pooling layer are both connected to the input end of the second convolution module; the output end of the second convolution module is connected to the input end of the fifth activation module; the output end of the fifth activation module is connected to the input end of the second fusion module; the input end of the second fusion module is connected to the input end of the third fusion module; the output end of the third fusion module is connected to the model output.

[0158] It can be seen that implementing Figure 2 the described physiological signal processing device is conducive to realizing the comprehensive processing of various physiological signals and improving the accuracy and efficiency of signal evaluation.

[0159] Embodiment III

[0160] Please refer to Figure 3 , Figure 3 which is a schematic structural diagram of another physiological signal processing device disclosed in the embodiments of the present invention. Among them, Figure 3 the described device can be applied to a signal management system, such as a local server or a cloud server for physiological signal processing management, etc., which is not limited in the embodiments of the present invention. As Figure 3 shown, the device may include:

[0161] A memory 301 storing executable program code;

[0162] A processor 302 coupled to the memory 301;

[0163] The processor 302 calls the executable program code stored in the memory 301 to execute the steps in the physiological signal processing method described in Embodiment I.

[0164] Embodiment IV

[0165] An embodiment of the present invention discloses a computer-readable storage medium that stores a computer program for electronic data exchange. The computer program causes a computer to execute the steps in the physiological signal processing method described in Embodiment 1.

[0166] Embodiment 5

[0167] An embodiment of the present invention discloses a computer program product. The computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps in the physiological signal processing method described in Embodiment 1.

[0168] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative work.

[0169] Through the above specific descriptions of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, and the storage medium includes Read-Only Memory (ROM), Random Access Memory (RAM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), One-time Programmable Read-Only Memory (OTPROM), Electrically-Erasable Programmable Read-Only Memory (EEPROM), Compact Disc Read-Only Memory (CD-ROM) or other optical disc memories, magnetic disk memories, tape memories, or any other computer-readable medium that can be used to carry or store data.

[0170] Finally, it should be noted that: What is disclosed by a physiological signal processing method and device disclosed in the embodiments of the present invention is only the preferred embodiments of the present invention, which are only used to illustrate the technical solutions of the present invention, rather than limiting them; Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A physiological signal processing method, characterized in that, The method includes: Obtaining multi-type physiological signal information; the multi-type physiological signal information includes M pieces of physiological signal information; M is a positive integer not less than 4; Performing preprocessing on the multi-type physiological signal information to obtain target processed signal information; the target processed signal information includes the M pieces of processed physiological signal information; Using a signal evaluation model to perform evaluation processing on the target processed signal information to obtain target evaluation result information; the signal evaluation model includes a feature extraction sub-model and a feature evaluation sub-model.

2. The physiological signal processing method according to claim 1, wherein The physiological signal information includes electroencephalogram signal information, and / or electrocardiogram signal information, and / or facial signal information, and / or eye signal information; The obtaining of the multi-type physiological signal information includes: Sequentially setting the sampling frequencies and sampling time intervals of the first signal acquisition device, the second signal acquisition device, the third signal acquisition device, and the fourth signal acquisition device of the signal evaluation system; Playing a signal trigger video at the first device end of the signal evaluation system; the video duration corresponding to the signal trigger video is not greater than the time interval length of the sampling time interval; Based on the sampling frequency of the first signal acquisition device, collecting signals of the user's electroencephalogram activity within the sampling time interval to obtain the electroencephalogram signal information; Based on the sampling frequency of the second signal acquisition device, collecting signals of the user's cardiac activity within the sampling time interval to obtain the electrocardiogram signal information; Based on the sampling frequency of the third signal acquisition device, collecting signals of the user's facial activity within the sampling time interval to obtain the facial signal information; Based on the sampling frequency of the fourth signal acquisition device, collecting signals of the user's eye activity within the sampling time interval to obtain the eye signal information.

3. The physiological signal processing method according to claim 2, wherein The performing of preprocessing on the multi-type physiological signal information to obtain target processed signal information includes: For any one of the physiological signal information, obtaining the frequency adjustment information corresponding to the physiological signal information; Performing interpolation smoothing processing on the physiological signal information based on the frequency adjustment information to obtain the first processed signal information corresponding to the physiological signal information; Obtaining the filtering parameter information corresponding to the physiological signal information; the filtering parameter information corresponding to any two pieces of physiological signal information is inconsistent; Based on the filtering parameter information, performing filtering processing on the first processed signal information to obtain the second processed signal information corresponding to the physiological signal information; Performing signal amplification processing on the second processed signal information to obtain the third processed signal information corresponding to the physiological signal information; Performing discretization processing on the third processed signal information to obtain the processed physiological signal information corresponding to the physiological signal information.

4. The physiological signal processing method according to claim 1, wherein The using of the signal evaluation model to perform evaluation processing on the target processed signal information to obtain target evaluation result information includes: Using the feature extraction sub-model to perform feature extraction processing on the target processed signal information to obtain target signal feature information; The target signal feature information is evaluated by using the feature evaluation sub-model to obtain target evaluation result information; the feature evaluation sub-model includes a first convolution module, the first feature evaluation sub-model, the second feature evaluation sub-model, a first fusion module, a second fusion module, and a third fusion module.

5. The physiological signal processing method according to claim 4, wherein The step of using the feature evaluation sub-model to evaluate the target signal feature information to obtain target evaluation result information includes: Performing convolution processing on the target signal feature information by using the first convolution module to obtain target convolution feature information; Processing the target convolution feature information by using the first feature evaluation sub-model to obtain first feature evaluation information; Performing fusion processing on the target convolution feature information and the first feature evaluation information by using the first fusion module to obtain first fusion feature information; Processing the first fusion feature information by using the second feature evaluation sub-model to obtain second feature evaluation information; Performing fusion processing on the first fusion feature information and the second feature evaluation information by using the second fusion module to obtain second fusion feature information; Performing fusion processing on the target convolution feature information and the second fusion feature information by using the third fusion module to obtain target evaluation result information.

6. The physiological signal processing method according to claim 4, characterized in that The first feature evaluation sub-model includes a first pooling layer, a second pooling layer, a first activation module, a second activation module, a third activation module, a fourth activation module, a first fully connected layer, a second fully connected layer, a third fully connected layer, a fourth fully connected layer, and a first neural network; The second feature evaluation sub-model includes a third pooling layer, a fourth pooling layer, a second convolution module, and a fifth activation module.

7. The physiological signal processing method according to claim 6, wherein, The input end of the first convolution module is connected to the model input, and the output end of the first convolution module is respectively connected to the input end of the first pooling layer, the input end of the second pooling layer, the input end of the first fusion module, and the input end of the third fusion module; the output end of the first pooling layer is connected to the input end of the first fully-connected layer; the output end of the first fully-connected layer is connected to the input end of the first activation module; the output end of the first activation module is connected to the input end of the second fully-connected layer; the output end of the second fully-connected layer is connected to the input end of the second activation module; the output end of the second pooling layer is connected to the input end of the third fully-connected layer; the output end of the third fully-connected layer is connected to the input end of the third activation module; the output end of the third activation module is connected to the input end of the fourth fully-connected layer; the output end of the fourth fully-connected layer is connected to the input end of the fourth activation module; the input end of the first neural network is respectively connected to the output end of the second activation module and the output end of the fourth activation module; the output end of the first neural network is connected to the input end of the first fusion module; the output end of the first fusion module is respectively connected to the input end of the third pooling layer, the input end of the fourth pooling layer, and the input end of the second fusion module; the output ends of the third pooling layer and the fourth pooling layer are both connected to the input end of the second convolution module; the output end of the second convolution module is connected to the input end of the fifth activation module; the output end of the fifth activation module is connected to the input end of the second fusion module; the input end of the second fusion module is connected to the input end of the third fusion module; the output end of the third fusion module is connected to the model output.

8. A physiological signal processing device, characterized in that, The device includes: An acquisition module, configured to acquire multi-type physiological signal information; the multi-type physiological signal information includes M physiological signal information; M is a positive integer not less than 4; A first processing module, configured to perform preprocessing on the multi-type physiological signal information to obtain target processed signal information; the target processed signal information includes the M processed physiological signal information; A second processing module, configured to perform evaluation processing on the target processed signal information by using a signal evaluation model to obtain target evaluation result information; the signal evaluation model includes a feature extraction sub-model and a feature evaluation sub-model.

9. A physiological signal processing device, characterized in that, The device includes: A memory storing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory and executes the physiological signal processing method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, which are used to execute the physiological signal processing method according to any one of claims 1-7 when being called.

Images