Deep brain electrophysiological signal processing method, device and equipment, storage medium and program product

Abstract

The invention relates to a deep brain electrophysiological signal processing method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring a first brain deep electrophysiological signal to be processed, and determining artifact type information of the first brain deep electrophysiological signal based on a pre-trained artifact type identification model; determining a first artifact processing strategy according to the artifact type information, and performing first artifact processing on the first brain deep electrophysiological signal based on the first artifact processing strategy to obtain a second brain deep electrophysiological signal after artifact processing; and performing artifact detection on the second deep brain electrophysiological signal according to a pre-trained artifact detection model, and performing second artifact processing on the second deep brain electrophysiological signal by adopting a second artifact processing strategy under the condition that a detection result indicates that artifacts exist in the second deep brain electrophysiological signal so as to obtain a target deep brain electrophysiological signal. By adopting the method, the accuracy of artifact processing can be improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus, computer device, computer-readable storage medium, and computer program product for processing deep brain electrophysiological signals. Background Technology

[0002] Deep brain electrophysiological signals refer to bioelectrical signals recorded from deep brain nuclei or white matter pathways that reflect the electrical activity state of neuronal clusters, such as local field potentials and single-neuron action potentials. Because the acquisition of deep brain electrophysiological signals is easily affected by various artifacts, the quality of the acquired signals is often poor, impacting the accuracy of subsequent analysis.

[0003] In existing technologies, most methods employ filtering algorithms to process artifacts from the acquired deep brain electrophysiological signals in order to improve the quality of these signals and thus enhance the accuracy of subsequent analysis.

[0004] However, this method of artifact processing based on filtering algorithms for the acquired deep brain electrophysiological signals suffers from poor accuracy in artifact processing, resulting in poor quality of the deep brain electrophysiological signals and consequently affecting the accuracy of subsequent analysis of these signals. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for processing deep brain electrophysiological signals that can improve the accuracy of artifact processing, in order to address the above-mentioned technical problems.

[0006] In a first aspect, this application provides a method for processing deep brain electrophysiological signals, including:

[0007] The first deep brain electrophysiological signal to be processed is acquired, and the artifact type information of the first deep brain electrophysiological signal is determined based on a pre-trained artifact type recognition model, which is a multi-branch deep network model.

[0008] The first artifact processing strategy is determined based on the artifact type information, and the first deep brain electrophysiological signal is processed based on the first artifact processing strategy to obtain the second deep brain electrophysiological signal after artifact processing.

[0009] The second deep brain electrophysiological signal is subjected to artifact detection based on a pre-trained artifact detection model. If the detection results indicate the presence of artifacts in the second deep brain electrophysiological signal, a second artifact processing strategy is adopted to process the second deep brain electrophysiological signal to obtain the target deep brain electrophysiological signal.

[0010] In one embodiment, the artifact type identification model includes a first branch network and a second branch network. Based on the pre-trained artifact type identification model, artifact type information of the first deep brain electrophysiological signal is determined, including: determining the time-frequency domain features of the first deep brain electrophysiological signal based on the first branch network; determining the time domain features of the first deep brain electrophysiological signal based on the second branch network; and determining the artifact type information of the first deep brain electrophysiological signal based on the time-frequency domain features and the time domain features.

[0011] In one embodiment, the artifact type information of the first deep brain electrophysiological signal is determined based on time-frequency domain features and time-domain features, including: performing feature fusion processing on the time-frequency domain features and time-domain features to obtain initial artifact type information of the first deep brain electrophysiological signal; and performing correction processing on the initial artifact type information based on a multi-window voting correction algorithm to obtain artifact type information of the first deep brain electrophysiological signal.

[0012] In one embodiment, determining a first artifact processing strategy based on artifact type information includes: if the artifact type information includes an electrical impulse artifact type, determining the artifact processing strategy corresponding to the electrical impulse artifact type from multiple artifact processing strategies as the first artifact processing strategy, the first artifact processing strategy being used to instruct the first artifact processing of the first deep brain electrophysiological signal based on an adaptive filtering algorithm; if the artifact type information includes an electrocardiogram artifact type, determining the artifact processing strategy corresponding to the electrocardiogram artifact type from multiple artifact processing strategies as the first artifact processing strategy, the first artifact processing strategy being used to instruct the first artifact processing of the first deep brain electrophysiological signal based on a correlation analysis algorithm; if the artifact type information includes a body motion artifact type, determining the artifact processing strategy corresponding to the body motion artifact type from multiple artifact processing strategies as the first artifact processing strategy, the first artifact processing strategy being used to instruct the first artifact processing of the first deep brain electrophysiological signal based on a label removal method.

[0013] In one embodiment, a first artifact processing strategy is determined based on artifact type information, and a first artifact processing strategy is applied to a first deep brain electrophysiological signal to obtain a second deep brain electrophysiological signal after artifact processing. This includes: when the artifact type information includes multiple artifact types, determining the artifact processing strategy corresponding to the multiple artifact types as the first artifact processing strategy from the multiple artifact processing strategies; determining the processing priority information of the multiple artifact types, and applying the first artifact processing strategy and the processing priority information to the first deep brain electrophysiological signal to obtain a second deep brain electrophysiological signal.

[0014] In one embodiment, determining the processing priority information for multiple artifact types includes: determining whether the multiple artifact types include body motion artifact types; if so, determining the processing priority information for body motion artifact types as high processing priority; if not, determining whether the multiple artifact types include electrical pulse artifact types; if so, determining the processing priority information for electrical pulse artifact types as high processing priority.

[0015] Secondly, this application also provides a device for processing deep brain electrophysiological signals, comprising:

[0016] The acquisition module is used to acquire the first deep brain electrophysiological signal to be processed, and to determine the artifact type information of the first deep brain electrophysiological signal based on a pre-trained artifact type recognition model. The artifact type recognition model is a multi-branch deep network model.

[0017] The determination module is used to determine a first artifact processing strategy based on artifact type information, and to perform first artifact processing on the first deep brain electrophysiological signal based on the first artifact processing strategy to obtain a second deep brain electrophysiological signal after artifact processing.

[0018] The execution module is used to perform artifact detection on the second deep brain electrophysiological signal according to the pre-trained artifact detection model, and when the detection result indicates that there are artifacts in the second deep brain electrophysiological signal, it uses a second artifact processing strategy to perform second artifact processing on the second deep brain electrophysiological signal to obtain the target deep brain electrophysiological signal.

[0019] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in any of the embodiments of the first aspect above.

[0020] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any of the embodiments of the first aspect above.

[0021] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any of the embodiments of the first aspect above.

[0022] The aforementioned method, apparatus, computer equipment, computer-readable storage medium, and computer program product for processing deep brain electrophysiological signals first acquire a first deep brain electrophysiological signal to be processed, and determine the artifact type information of the first deep brain electrophysiological signal based on a pre-trained artifact type recognition model. The artifact type recognition model is a multi-branch deep network model. Then, a first artifact processing strategy is determined based on the artifact type information, and the first deep brain electrophysiological signal is processed based on the first artifact processing strategy to obtain a second deep brain electrophysiological signal after artifact processing. Finally, artifact detection is performed on the second deep brain electrophysiological signal according to a pre-trained artifact detection model. If the detection result indicates that there are artifacts in the second deep brain electrophysiological signal, a second artifact processing strategy is used to process the second deep brain electrophysiological signal to obtain the target deep brain electrophysiological signal. The method for processing deep brain electrophysiological signals provided in this application first determines the artifact type information of the deep brain electrophysiological signals, and then uses different artifact processing strategies for different types of artifacts to improve the accuracy of artifact processing, thereby improving the quality of deep brain electrophysiological signals and avoiding affecting the accuracy of subsequent analysis of deep brain electrophysiological signals. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart illustrating a method for processing deep brain electrophysiological signals in one embodiment;

[0025] Figure 2 This is a flowchart illustrating a method for determining artifact type information of a first deep brain electrophysiological signal based on a pre-trained artifact type recognition model, as an example.

[0026] Figure 3 This is a flowchart illustrating a method for determining artifact type information of a first deep brain electrophysiological signal based on time-frequency domain features and time-domain features in one embodiment.

[0027] Figure 4 This is a flowchart illustrating a method for determining a first artifact processing strategy based on artifact type information in one embodiment.

[0028] Figure 5 This is a flowchart illustrating a method for obtaining a second deep brain electrophysiological signal after artifact processing in one embodiment.

[0029] Figure 6 This is a flowchart illustrating a method for determining processing priority information for multiple artifact types in one embodiment.

[0030] Figure 7 This is a flowchart illustrating a method for processing deep brain electrophysiological signals in another embodiment;

[0031] Figure 8 This is a structural block diagram of a device for processing deep brain electrophysiological signals in one embodiment;

[0032] Figure 9 This is an internal structural diagram of a computer device in one embodiment;

[0033] Figure 10 This is a diagram of the internal structure of a computer device in another embodiment;

[0034] Figure 11 This is a schematic diagram of an artifact type recognition model in one embodiment. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0036] It should be noted that the terms "comprising" and "having," and any variations thereof, as used in this application, are intended to cover non-exclusive inclusion. The term "multiple" as used in this application refers to two or more. The term "and / or" as used in this application refers to one of the solutions, or any combination of multiple solutions.

[0037] Deep brain electrophysiological signals refer to bioelectrical signals recorded from deep brain nuclei or white matter pathways that reflect the electrical activity state of neuronal clusters, such as local field potentials (LFP) and single-neuron action potentials. Due to the susceptibility to various artifacts during the acquisition of deep brain electrophysiological signals, the quality of the acquired signals is often poor, affecting the accuracy of subsequent analysis.

[0038] In existing technologies, most methods employ filtering algorithms to process artifacts from the acquired deep brain electrophysiological signals in order to improve the quality of these signals and thus enhance the accuracy of subsequent analysis.

[0039] However, this method of artifact processing based on filtering algorithms for the acquired deep brain electrophysiological signals suffers from poor accuracy in artifact processing, resulting in poor quality of the deep brain electrophysiological signals and consequently affecting the accuracy of subsequent analysis of these signals.

[0040] In view of this, this application provides a method for processing deep brain electrophysiological signals. First, the artifact type information of the deep brain electrophysiological signals is determined. Different artifact processing strategies are used for different types of artifacts to improve the accuracy of artifact processing, thereby improving the quality of deep brain electrophysiological signals and avoiding affecting the accuracy of subsequent analysis of deep brain electrophysiological signals.

[0041] The method for processing deep brain electrophysiological signals provided in this application can be executed by a computer device, which can be a terminal or a server.

[0042] In one exemplary embodiment, such as Figure 1 As shown, a method for processing deep brain electrophysiological signals is provided, which includes the following steps:

[0043] Step 101: Obtain the first deep brain electrophysiological signal to be processed, and determine the artifact type information of the first deep brain electrophysiological signal based on the pre-trained artifact type recognition model.

[0044] Among them, the artifact type identification model is a multi-branch deep network model.

[0045] Optionally, the first deep brain electrophysiological signal can be a raw, unprocessed deep brain electrophysiological signal. Specifically, the first deep brain electrophysiological signal can be a local field potential, a single neuron action potential, etc.

[0046] Artifact type information can be used to indicate the type of artifacts in the first deep brain electrophysiological signal. Artifact type information can include electrical impulse artifact types, electrocardiogram artifact types, body movement artifact types, and mixed artifact types.

[0047] For example, electrical pulse artifacts are directly generated by the therapeutic electrical pulses released when the deep brain stimulator is working, and are directly related to the stimulation parameters of the deep brain stimulator; electrocardiogram artifacts originate from the electrocardiogram signals formed by the electrical activity of the heart, which are conducted to the recording electrodes in the brain through the conductivity of human tissue, and manifest as periodic interference consistent with the heartbeat rhythm; body movement artifacts are caused by the active / passive movement of the patient's head or body, which causes the contact position between the recording electrodes and brain tissue to shift or the wires to sway, thereby generating non-periodic noise interference.

[0048] In some exemplary embodiments, the computer device may first acquire a first deep brain electrophysiological signal to be processed.

[0049] Specifically, computer equipment can use deep brain electrophysiological signal acquisition equipment to obtain the first deep brain electrophysiological signal.

[0050] Furthermore, after acquiring the first deep brain electrophysiological signal to be processed, the computer device can determine the artifact type information of the first deep brain electrophysiological signal based on a pre-trained artifact type recognition model.

[0051] Specifically, the computer equipment can first perform signal preprocessing on the first deep brain electrophysiological signal to obtain a preprocessed first deep brain electrophysiological signal. For example, bandpass filtering can be used to remove baseline drift and high-frequency noise interference in the first deep brain electrophysiological signal. In an optional approach, the computer equipment can also resample the first deep brain electrophysiological signal according to actual needs to unify the sampling frequency.

[0052] After obtaining the first deep brain electrophysiological signal after signal preprocessing, the computer equipment can input the preprocessed first deep brain electrophysiological signal into a pre-trained artifact type recognition model to obtain artifact type information of the first deep brain electrophysiological signal.

[0053] Step 102: Determine the first artifact processing strategy based on the artifact type information, and perform first artifact processing on the first deep brain electrophysiological signal based on the first artifact processing strategy to obtain the second deep brain electrophysiological signal after artifact processing.

[0054] Optionally, the first artifact processing strategy serves as the basis for performing first artifact processing on the first deep brain electrophysiological signal.

[0055] In some exemplary embodiments, after obtaining the first deep brain electrophysiological signal, the computer device can determine a first artifact processing strategy based on artifact type information.

[0056] Specifically, the computer device can use the spoofing type information-spoofing processing strategy mapping relationship list to determine the spoofing processing strategy corresponding to the spoofing type information as the first spoofing processing strategy. This spoofing type information-spoofing processing strategy mapping relationship list can be used to indicate the mapping relationship between different spoofing type information and different spoofing processing strategies. This spoofing type information-spoofing processing strategy mapping relationship list is shown in Table 1.

[0057] Table 1

[0058]

[0059] Furthermore, after determining the first artifact processing strategy based on the artifact type information, the computer device can perform first artifact processing on the first deep brain electrophysiological signal based on the first artifact processing strategy to obtain the second deep brain electrophysiological signal after artifact processing.

[0060] Specifically, the computer device can perform first artifact processing on the first deep brain electrophysiological signal according to the instructions of the first artifact processing strategy to obtain the second deep brain electrophysiological signal after artifact processing.

[0061] Step 103: Perform artifact detection on the second deep brain electrophysiological signal according to the pre-trained artifact detection model, and if the detection result indicates that there are artifacts in the second deep brain electrophysiological signal, use the second artifact processing strategy to perform second artifact processing on the second deep brain electrophysiological signal to obtain the target deep brain electrophysiological signal.

[0062] For example, the artifact detection model can be the same model as the artifact type recognition model, or it can be a different model. The artifact detection model is a multi-branch deep network model. Artifact detection can be used to detect the presence of artifacts in second brain deep electrophysiological signals.

[0063] The second artifact removal strategy can be a strategy pre-set by technicians according to actual needs. For example, the second artifact removal strategy can be to remove artifacts in the second deep brain electrophysiological signal using linear interpolation or fragment deletion.

[0064] In some exemplary embodiments, after obtaining the second deep brain electrophysiological signal after artifact processing, the computer device can perform artifact detection on the second deep brain electrophysiological signal according to a pre-trained artifact detection model.

[0065] Specifically, computer equipment can input second brain deep electrophysiological signals into the artifact detection model to obtain the detection results output by the artifact detection model.

[0066] Furthermore, after determining the detection results, if the detection results indicate that there are artifacts in the second deep brain electrophysiological signal, the computer equipment can use a second artifact processing strategy to process the second deep brain electrophysiological signal to obtain the target deep brain electrophysiological signal.

[0067] If the test results indicate that there are no artifacts in the second deep brain electrophysiological signal, then the second deep brain electrophysiological signal can be directly identified as the target deep brain electrophysiological signal.

[0068] The above-mentioned method for processing deep brain electrophysiological signals first acquires a first deep brain electrophysiological signal to be processed, and determines the artifact type information of the first deep brain electrophysiological signal based on a pre-trained artifact type recognition model. The artifact type recognition model is a multi-branch deep network model. Then, a first artifact processing strategy is determined based on the artifact type information, and the first deep brain electrophysiological signal is processed based on the first artifact processing strategy to obtain a second deep brain electrophysiological signal after artifact processing. Finally, artifact detection is performed on the second deep brain electrophysiological signal according to a pre-trained artifact detection model. If the detection result indicates that there are artifacts in the second deep brain electrophysiological signal, a second artifact processing strategy is used to process the second deep brain electrophysiological signal to obtain the target deep brain electrophysiological signal. The method for processing deep brain electrophysiological signals provided in this application first determines the artifact type information of the deep brain electrophysiological signals, and then uses different artifact processing strategies for different types of artifacts to improve the accuracy of artifact processing, thereby improving the quality of deep brain electrophysiological signals and avoiding affecting the accuracy of subsequent analysis of deep brain electrophysiological signals.

[0069] Furthermore, the deep brain electrophysiological signal processing method provided in this application, after artifact processing of the deep brain electrophysiological signal, will also detect whether artifacts still exist in the processed deep brain electrophysiological signal. If they do exist, further processing will be performed to improve the accuracy of artifact processing.

[0070] In one exemplary embodiment, such as Figure 2 As shown, the artifact type recognition model includes a first branch network and a second branch network. Based on the pre-trained artifact type recognition model, the artifact type information of the first deep brain electrophysiological signal is determined, including the following steps:

[0071] Step 201: Determine the time-frequency domain characteristics of the first deep brain electrophysiological signal based on the first branch network.

[0072] Optionally, the first branch network refers to a specific branch structure in the artifact type recognition model used to extract time-frequency domain features from the first deep brain electrophysiological signal. This first branch network can be a convolutional neural network. Time-frequency domain features refer to signal features that simultaneously fuse the time and frequency dimensions.

[0073] In some exemplary embodiments, after acquiring the first deep brain electrophysiological signal to be processed, the computer device can determine the time-frequency domain characteristics of the first deep brain electrophysiological signal based on the first branch network.

[0074] Specifically, the structure of the forgery type recognition model can be as follows: Figure 11As shown, the computer device can input the first deep brain electrophysiological signal into the first branch network to obtain the time-frequency domain characteristics of the first deep brain electrophysiological signal output by the first branch network.

[0075] Step 202: Determine the temporal characteristics of the first deep brain electrophysiological signal based on the second branch network.

[0076] Optionally, the second branch network refers to a specific branch structure in the artifact type recognition model, used to extract temporal features from the first deep brain electrophysiological signal. This second branch network can be a convolutional neural network. Temporal features refer to parameters that describe the characteristics of the first deep brain electrophysiological signal from a time dimension, reflecting the dynamic changes of the first deep brain electrophysiological signal over time.

[0077] In some exemplary embodiments, after acquiring the first deep brain electrophysiological signal to be processed, the computer device can also determine the temporal characteristics of the first deep brain electrophysiological signal based on the second branch network.

[0078] Specifically, the computer device can input a deep brain electrophysiological signal into the second branch network to obtain the temporal characteristics of the first deep brain electrophysiological signal output by the first branch network.

[0079] Step 203: Determine the artifact type information of the first deep brain electrophysiological signal based on the time-frequency domain characteristics and time-domain characteristics.

[0080] In some exemplary embodiments, after determining the time-frequency domain features and the time-domain features, the computer device can determine the artifact type information of the first deep brain electrophysiological signal based on the time-frequency domain features and the time-domain features.

[0081] Specifically, such as Figure 11 As shown, the artifact type recognition model, in addition to the first and second branch networks, can also include fully connected layers, Dropout layers, and classification layers. Computer devices can utilize fully connected layers, Dropout layers, and classification layers to determine the artifact type information of the first deep brain electrophysiological signal based on time-frequency domain features and time-domain features.

[0082] In one exemplary embodiment, such as Figure 3 As shown, determining the artifact type information of the first deep brain electrophysiological signal based on time-frequency domain features and time-domain features includes the following steps:

[0083] Step 301: Perform feature fusion processing on the time-frequency domain features and the time-domain features to obtain the initial artifact type information of the first deep brain electrophysiological signal.

[0084] In some exemplary embodiments, after determining the time-frequency domain features and the time-domain features, the computer device can perform feature fusion processing on the time-frequency domain features and the time-domain features to obtain initial artifact type information of the first deep brain electrophysiological signal.

[0085] Specifically, the computer equipment can first perform feature fusion processing on the time-frequency domain features and the time-domain features, and then use fully connected layers, Dropout, and classification layers to determine the initial artifact type information of the first deep brain electrophysiological signal based on the fused features obtained from the feature fusion processing.

[0086] Step 302: Correct the initial artifact type information based on the multi-window voting correction algorithm to obtain the artifact type information of the first deep brain electrophysiological signal.

[0087] In some exemplary embodiments, after acquiring the initial artifact type information of the first deep brain electrophysiological signal, the computer device can perform correction processing on the initial artifact type information based on a multi-window voting correction algorithm to obtain the artifact type information of the first deep brain electrophysiological signal.

[0088] Specifically, considering the continuous nature of artifacts, the computer device can set a time window and collect the initial artifact type information within the time window. The initial artifact type information of the continuous window is weighted and voted. If the votes for a certain type of artifact exceed a preset threshold, the initial artifact type information is corrected to obtain the artifact type information of the first deep brain electrophysiological signal.

[0089] In one exemplary embodiment, such as Figure 4 As shown, the first artifact processing strategy is determined based on the artifact type information, including the following steps:

[0090] Step 401: If the artifact type information includes the electrical pulse artifact type, determine the artifact processing strategy corresponding to the electrical pulse artifact type from multiple artifact processing strategies as the first artifact processing strategy.

[0091] The first artifact processing strategy is used to instruct the first deep brain electrophysiological signal to be processed using an adaptive filtering algorithm.

[0092] In some exemplary embodiments, after determining the artifact type information, if the computer device determines that the artifact type information is an electrical pulse artifact type, it can determine the artifact processing strategy corresponding to the electrical pulse artifact type as the first artifact processing strategy from multiple artifact processing strategies.

[0093] Furthermore, the computer device can perform first artifact processing on the first deep brain electrophysiological signal using a determined first artifact processing strategy.

[0094] Specifically, the computer equipment can perform first artifact processing on the first deep brain electrophysiological signal based on an adaptive filtering algorithm.

[0095] For example, computer equipment can use adaptive filtering algorithms to dynamically adjust parameters, combined with notch filtering and template matching techniques for processing.

[0096] Step 402: If the artifact type information includes ECG artifact type, determine the artifact processing strategy corresponding to the ECG artifact type from multiple artifact processing strategies as the first artifact processing strategy.

[0097] The first artifact processing strategy is used to instruct the first deep brain electrophysiological signal to be processed based on the correlation analysis algorithm.

[0098] In some exemplary embodiments, after determining the artifact type information, if the computer device determines that the artifact type information is an ECG artifact type, it can determine the artifact processing strategy corresponding to the ECG artifact type as the first artifact processing strategy from multiple artifact processing strategies.

[0099] Furthermore, the computer device can perform first artifact processing on the first deep brain electrophysiological signal using a determined first artifact processing strategy.

[0100] Specifically, computer equipment can perform first artifact processing on the first deep brain electrophysiological signal based on correlation analysis algorithms.

[0101] For example, computer devices can construct ECG artifact templates and remove them through correlation analysis.

[0102] Step 403: If the artifact type information includes the motion artifact type, determine the artifact processing strategy corresponding to the motion artifact type from multiple artifact processing strategies as the first artifact processing strategy.

[0103] The first artifact processing strategy is used to instruct the first deep brain electrophysiological signal to be processed based on the annotation elimination method.

[0104] In some exemplary embodiments, after determining the artifact type information, if the computer device determines that the artifact type information is a motion artifact type, it can determine the artifact processing strategy corresponding to the motion artifact type as the first artifact processing strategy from multiple artifact processing strategies.

[0105] Furthermore, the computer device can perform first artifact processing on the first deep brain electrophysiological signal using a determined first artifact processing strategy.

[0106] Specifically, computer equipment can perform first artifact processing on the first deep brain electrophysiological signal based on the labeling and removal method.

[0107] For example, computer equipment can directly label and remove the corresponding time period from subsequent processing.

[0108] In one exemplary embodiment, such as Figure 5 As shown, a first artifact processing strategy is determined based on artifact type information, and the first deep brain electrophysiological signal is processed based on the first artifact processing strategy to obtain a second deep brain electrophysiological signal after artifact processing. The process includes the following steps:

[0109] Step 501: When the artifact type information includes multiple artifact types, determine the artifact processing strategy corresponding to the multiple artifact types from the multiple artifact processing strategies as the first artifact processing strategy.

[0110] In some exemplary embodiments, after determining the spoofing type information, if the computer device determines that the spoofing type information includes multiple spoofing types, it can first determine the spoofing processing strategy corresponding to each of the multiple spoofing types as the first spoofing processing strategy from the multiple spoofing processing strategies.

[0111] Step 502: Determine the processing priority information for multiple artifact types, and perform first artifact processing on the first deep brain electrophysiological signal based on the first artifact processing strategy and processing priority information to obtain the second deep brain electrophysiological signal.

[0112] Optionally, the processing priority information is used to indicate the execution order of the artifact processing strategies corresponding to multiple artifact types.

[0113] In some exemplary embodiments, after determining a first spoofing processing strategy corresponding to multiple spoofing types, the computer device can determine processing priority information for multiple spoofing types.

[0114] Specifically, computer devices can determine processing priority information based on multiple artifact types, according to pre-processing priority rules.

[0115] Furthermore, after determining the processing priority information, the computer device can perform first artifact processing on the first deep brain electrophysiological signal based on the first artifact processing strategy and the processing priority information to obtain the second deep brain electrophysiological signal.

[0116] Specifically, the computer equipment can first determine the processing order of the first artifact processing based on the processing priority information, and then, based on the processing order, use the first artifact processing strategy to perform the first artifact processing on the first deep brain electrophysiological signal to obtain the second deep brain electrophysiological signal.

[0117] For example, if the processing priority information indicates that the processing priority of a certain artifact type is the highest priority, then the execution order of the first artifact processing strategy corresponding to that artifact type can be determined as first. In the process of performing first artifact processing on the first deep brain electrophysiological signal using the first artifact processing strategy, the first artifact processing on the first deep brain electrophysiological signal is performed first based on the first artifact processing strategy, and then the first artifact processing on the first deep brain electrophysiological signal is performed based on other first artifact processing strategies.

[0118] In one exemplary embodiment, such as Figure 6 As shown, determining the processing priority information for multiple artifact types includes the following steps:

[0119] Step 601: Determine whether the multiple artifact types include the motion artifact type. If so, determine the processing priority information of the motion artifact type as high processing priority.

[0120] In some exemplary embodiments, when a computer device determines that multiple artifact types exist, it can first determine whether the multiple artifact types include motion artifact types. If they do, the processing priority information of the motion artifact type is determined to be high processing priority.

[0121] Step 602: If not included, determine whether the multiple artifact types include the electrical pulse artifact type. If included, determine the processing priority information of the electrical pulse artifact type as high processing priority.

[0122] In some exemplary embodiments, if the computer device determines that multiple artifact types do not include motion artifact types, it determines whether the multiple artifact types include electrical pulse artifact types. If they do, it determines that the processing priority information of the electrical pulse artifact type is high processing priority.

[0123] That is, if multiple artifact types include body motion artifact type, electrical impulse artifact type and electrocardiogram artifact type, then the first deep brain electrophysiological signal is first processed based on the first artifact processing strategy corresponding to the body motion artifact type, then the first deep brain electrophysiological signal is processed based on the first artifact processing strategy corresponding to the electrical impulse artifact type, and finally, the first deep brain electrophysiological signal is processed based on the first artifact processing strategy corresponding to the electrocardiogram artifact type.

[0124] In an optional embodiment of this application, after obtaining the target deep brain electrophysiological signal, the computer device can also perform a quality assessment on the target deep brain electrophysiological signal to determine whether the target deep brain electrophysiological signal meets the requirements for subsequent analysis.

[0125] In an optional embodiment of this application, a real-time processing mechanism for the first deep brain electrophysiological signal is also provided. Specifically, the window length can be 500 sampling points (500ms); the overlap is 50%; the historical data cache is 200 sampling points for filling the front of the window; the flip data compensation is 200 sampling points for reducing the edge effect at the back of the window; the overall data processing can combine the current delay-free data in the sliding window with historical data for real-time artifact recognition and removal.

[0126] In one exemplary embodiment, such as Figure 7 As shown, a method for processing deep brain electrophysiological signals is provided, which includes the following steps:

[0127] Step 701: Obtain the first deep brain electrophysiological signal to be processed; determine the time-frequency domain features of the first deep brain electrophysiological signal based on the first branch network in the pre-trained artifact type recognition model; determine the time domain features of the first deep brain electrophysiological signal based on the second branch network in the pre-trained artifact type recognition model.

[0128] Step 702: Perform feature fusion processing on the time-frequency domain features and time-domain features to obtain the initial artifact type information of the first deep brain electrophysiological signal; perform correction processing on the initial artifact type information based on the multi-window voting correction algorithm to obtain the artifact type information of the first deep brain electrophysiological signal; the artifact type recognition model is a multi-branch deep network model.

[0129] Step 703: When the artifact type information includes the electrical pulse artifact type, determine the artifact processing strategy corresponding to the electrical pulse artifact type from multiple artifact processing strategies as the first artifact processing strategy. The first artifact processing strategy is used to instruct the first deep brain electrophysiological signal to be processed based on the adaptive filtering algorithm.

[0130] Step 704: When the artifact type information includes ECG artifact type, determine the artifact processing strategy corresponding to the ECG artifact type from multiple artifact processing strategies as the first artifact processing strategy. The first artifact processing strategy is used to instruct the first deep brain electrophysiological signal to be processed based on the correlation analysis algorithm.

[0131] Step 705: If the artifact type information includes body motion artifact types, determine the artifact processing strategy corresponding to the body motion artifact type from multiple artifact processing strategies as the first artifact processing strategy. The first artifact processing strategy is used to instruct the first deep brain electrophysiological signal to be processed based on the annotation elimination method. If the artifact type information includes multiple artifact types, determine the artifact processing strategy corresponding to the multiple artifact types from multiple artifact processing strategies as the first artifact processing strategy.

[0132] Step 706: Determine whether the multiple artifact types include the body motion artifact type. If so, determine the processing priority information of the body motion artifact type as high processing priority. If not, determine whether the multiple artifact types include the electrical pulse artifact type. If so, determine the processing priority information of the electrical pulse artifact type as high processing priority. Then, perform first artifact processing on the first deep brain electrophysiological signal based on the first artifact processing strategy and processing priority information to obtain the second deep brain electrophysiological signal after artifact processing.

[0133] Step 707: Perform artifact detection on the second deep brain electrophysiological signal according to the pre-trained artifact detection model, and if the detection result indicates that there are artifacts in the second deep brain electrophysiological signal, use the second artifact processing strategy to perform second artifact processing on the second deep brain electrophysiological signal to obtain the target deep brain electrophysiological signal.

[0134] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0135] Based on the same inventive concept, this application also provides a deep brain electrophysiological signal processing device for implementing the aforementioned method for processing deep brain electrophysiological signals. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the deep brain electrophysiological signal processing device provided below can be found in the limitations of the deep brain electrophysiological signal processing method described above, and will not be repeated here.

[0136] In one exemplary embodiment, such as Figure 8 As shown, a deep brain electrophysiological signal processing device 800 is provided, comprising: an acquisition module 801, a determination module 802, and an execution module 803, wherein:

[0137] The acquisition module 801 is used to acquire the first deep brain electrophysiological signal to be processed, and to determine the artifact type information of the first deep brain electrophysiological signal based on a pre-trained artifact type recognition model. The artifact type recognition model is a multi-branch deep network model.

[0138] The determination module 802 is used to determine a first artifact processing strategy based on artifact type information, and to perform first artifact processing on the first deep brain electrophysiological signal based on the first artifact processing strategy to obtain a second deep brain electrophysiological signal after artifact processing.

[0139] The execution module 803 is used to perform artifact detection on the second deep brain electrophysiological signal according to the pre-trained artifact detection model, and when the detection result indicates that there are artifacts in the second deep brain electrophysiological signal, it uses a second artifact processing strategy to perform second artifact processing on the second deep brain electrophysiological signal to obtain the target deep brain electrophysiological signal.

[0140] In one embodiment, the artifact type identification model includes a first branch network and a second branch network. The acquisition module 801 is specifically used to determine the time-frequency domain features of the first deep brain electrophysiological signal based on the first branch network; determine the time domain features of the first deep brain electrophysiological signal based on the second branch network; and determine the artifact type information of the first deep brain electrophysiological signal based on the time-frequency domain features and the time domain features.

[0141] In one embodiment, the acquisition module 801 is specifically used to perform feature fusion processing on time-frequency domain features and time-domain features to obtain initial artifact type information of the first deep brain electrophysiological signal; and to perform correction processing on the initial artifact type information based on a multi-window voting correction algorithm to obtain artifact type information of the first deep brain electrophysiological signal.

[0142] In one embodiment, the determining module 802 is specifically configured to: when the artifact type information includes an electrical pulse artifact type, determine from multiple artifact processing strategies the artifact processing strategy corresponding to the electrical pulse artifact type as a first artifact processing strategy, the first artifact processing strategy being used to instruct the first deep brain electrophysiological signal to undergo first artifact processing based on an adaptive filtering algorithm; when the artifact type information includes an electrocardiogram artifact type, determine from multiple artifact processing strategies the artifact processing strategy corresponding to the electrocardiogram artifact type as a first artifact processing strategy, the first artifact processing strategy being used to instruct the first deep brain electrophysiological signal to undergo first artifact processing based on a correlation analysis algorithm; when the artifact type information includes a body motion artifact type, determine from multiple artifact processing strategies the artifact processing strategy corresponding to the body motion artifact type as a first artifact processing strategy, the first artifact processing strategy being used to instruct the first deep brain electrophysiological signal to undergo first artifact processing based on a labeling and elimination method.

[0143] In one embodiment, the determining module 802 is specifically configured to, when the artifact type information includes multiple artifact types, determine the artifact processing strategy corresponding to the multiple artifact types as the first artifact processing strategy from the multiple artifact processing strategies; determine the processing priority information of the multiple artifact types; and perform first artifact processing on the first deep brain electrophysiological signal based on the first artifact processing strategy and the processing priority information to obtain the second deep brain electrophysiological signal.

[0144] In one embodiment, the determining module 802 is specifically used to determine whether the multiple artifact types include the body motion artifact type. If it does, the processing priority information of the body motion artifact type is determined to be high processing priority; if it does not, the multiple artifact types are determined whether the multiple artifact types include the electrical pulse artifact type. If it does, the processing priority information of the electrical pulse artifact type is determined to be high processing priority.

[0145] Each module in the aforementioned deep brain electrophysiological signal processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0146] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network. When executed by the processor, the computer program implements a method for processing deep brain electrophysiological signals.

[0147] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 10As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When executed by the processor, the computer program implements a method for processing deep brain electrophysiological signals. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0148] Those skilled in the art will understand that Figure 9 and Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0149] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0150] The first deep brain electrophysiological signal to be processed is acquired, and the artifact type information of the first deep brain electrophysiological signal is determined based on a pre-trained artifact type recognition model, which is a multi-branch deep network model.

[0151] The first artifact processing strategy is determined based on the artifact type information, and the first deep brain electrophysiological signal is processed based on the first artifact processing strategy to obtain the second deep brain electrophysiological signal after artifact processing.

[0152] The second deep brain electrophysiological signal is subjected to artifact detection based on a pre-trained artifact detection model. If the detection results indicate the presence of artifacts in the second deep brain electrophysiological signal, a second artifact processing strategy is adopted to process the second deep brain electrophysiological signal to obtain the target deep brain electrophysiological signal.

[0153] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the time-frequency domain characteristics of the first deep brain electrophysiological signal based on the first branch network; determining the time-domain characteristics of the first deep brain electrophysiological signal based on the second branch network; and determining the artifact type information of the first deep brain electrophysiological signal based on the time-frequency domain characteristics and the time-domain characteristics.

[0154] In one embodiment, when the processor executes the computer program, it further performs the following steps: performing feature fusion processing on time-frequency domain features and time-domain features to obtain initial artifact type information of the first deep brain electrophysiological signal; and performing correction processing on the initial artifact type information based on a multi-window voting correction algorithm to obtain artifact type information of the first deep brain electrophysiological signal.

[0155] In one embodiment, when the processor executes the computer program, it further implements the following steps: If the artifact type information includes an electrical impulse artifact type, determine from multiple artifact processing strategies the artifact processing strategy corresponding to the electrical impulse artifact type as a first artifact processing strategy, the first artifact processing strategy being used to instruct the first deep brain electrophysiological signal to undergo first artifact processing based on an adaptive filtering algorithm; if the artifact type information includes an electrocardiogram (ECG) artifact type, determine from multiple artifact processing strategies the artifact processing strategy corresponding to the ECG artifact type as a first artifact processing strategy, the first artifact processing strategy being used to instruct the first deep brain electrophysiological signal to undergo first artifact processing based on a correlation analysis algorithm; if the artifact type information includes a body motion artifact type, determine from multiple artifact processing strategies the artifact processing strategy corresponding to the body motion artifact type as a first artifact processing strategy, the first artifact processing strategy being used to instruct the first deep brain electrophysiological signal to undergo first artifact processing based on a label removal method.

[0156] In one embodiment, when the processor executes the computer program, it further performs the following steps: when the artifact type information includes multiple artifact types, it determines the artifact processing strategy corresponding to the multiple artifact types as the first artifact processing strategy from the multiple artifact processing strategies; it determines the processing priority information of the multiple artifact types, and performs first artifact processing on the first deep brain electrophysiological signal based on the first artifact processing strategy and the processing priority information to obtain the second deep brain electrophysiological signal.

[0157] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining whether the multiple artifact types include a body motion artifact type; if so, determining the processing priority information of the body motion artifact type as a high processing priority; if not, determining whether the multiple artifact types include an electrical pulse artifact type; if so, determining the processing priority information of the electrical pulse artifact type as a high processing priority.

[0158] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method of any of the above embodiments.

[0159] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method of any of the above embodiments.

[0160] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0161] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0162] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0163] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method of processing deep brain electrophysiological signals, characterized in that, The method comprises: acquiring a first brain deep electrophysiological signal to be processed, and determining artifact type information of the first brain deep electrophysiological signal based on a pre-trained artifact type recognition model, the artifact type recognition model being a multi-branch deep network model; determining a first artifact processing strategy according to the artifact type information, and performing first artifact processing on the first brain deep electrophysiological signal based on the first artifact processing strategy to obtain a second brain deep electrophysiological signal after artifact processing; performing artifact detection on the second brain deep electrophysiological signal according to a pre-trained artifact detection model, and performing second artifact processing on the second brain deep electrophysiological signal using a second artifact processing strategy in the case where the detection result indicates that the second brain deep electrophysiological signal has artifacts, to obtain a target brain deep electrophysiological signal.

2. The method of claim 1, wherein, The artifact type recognition model comprises a first branch network and a second branch network, and the determination of the artifact type information of the first brain deep electrophysiological signal based on the pre-trained artifact type recognition model comprises: determining time-frequency domain features of the first brain deep electrophysiological signal based on the first branch network; determining time domain features of the first brain deep electrophysiological signal based on the second branch network; determining the artifact type information of the first brain deep electrophysiological signal according to the time-frequency domain features and the time domain features.

3. The method of claim 2, wherein, The determination of the artifact type information of the first brain deep electrophysiological signal according to the time-frequency domain features and the time domain features comprises: performing feature fusion processing on the time-frequency domain features and the time domain features to obtain initial artifact type information of the first brain deep electrophysiological signal; performing correction processing on the initial artifact type information based on a multi-window voting correction algorithm to obtain the artifact type information of the first brain deep electrophysiological signal.

4. The method according to any one of claims 1 to 3, characterized in that, The determination of the first artifact processing strategy according to the artifact type information comprises: in the case where the artifact type information comprises an electrical pulse artifact type, determining, from a plurality of artifact processing strategies, an artifact processing strategy corresponding to the electrical pulse artifact type as the first artifact processing strategy, the first artifact processing strategy being used to instruct the first artifact processing on the first brain deep electrophysiological signal based on an adaptive filtering algorithm; in the case where the artifact type information comprises an electrocardio artifact type, determining, from the plurality of artifact processing strategies, an artifact processing strategy corresponding to the electrocardio artifact type as the first artifact processing strategy, the first artifact processing strategy being used to instruct the first artifact processing on the first brain deep electrophysiological signal based on a correlation analysis algorithm; in the case where the artifact type information comprises a body movement artifact type, determining, from the plurality of artifact processing strategies, an artifact processing strategy corresponding to the body movement artifact type as the first artifact processing strategy, the first artifact processing strategy being used to instruct the first artifact processing on the first brain deep electrophysiological signal based on a labeling rejection method.

5. The method of claim 4, wherein, The first artifact processing strategy is determined according to the artifact type information, and first artifact processing is performed on the first deep brain electrophysiological signal based on the first artifact processing strategy to obtain a second deep brain electrophysiological signal after artifact processing. In a case where the artifact type information includes a plurality of artifact types, artifact processing strategies corresponding to the plurality of artifact types are determined as the first artifact processing strategy from the plurality of artifact processing strategies. Processing priority information of the plurality of artifact types is determined, and the first artifact processing is performed on the first deep brain electrophysiological signal based on the first artifact processing strategy and the processing priority information to obtain the second deep brain electrophysiological signal.

6. The method of claim 5, wherein, The processing priority information of the plurality of artifact types is determined, including: It is determined whether the body movement artifact type is included in the plurality of artifact types, and if so, the processing priority information of the body movement artifact type is determined as a high processing priority. If not, it is determined whether the electrical pulse artifact type is included in the plurality of artifact types, and if so, the processing priority information of the electrical pulse artifact type is determined as the high processing priority.

7. A brain deep electrophysiological signal processing apparatus, characterized by, The apparatus includes: An acquisition module configured to acquire a first deep brain electrophysiological signal to be processed, and determine artifact type information of the first deep brain electrophysiological signal based on a pre-trained artifact type identification model, the artifact type identification model being a multi-branch deep network model; A determination module configured to determine a first artifact processing strategy according to the artifact type information, and perform first artifact processing on the first deep brain electrophysiological signal based on the first artifact processing strategy to obtain a second deep brain electrophysiological signal after artifact processing; An execution module configured to perform artifact detection on the second deep brain electrophysiological signal according to a pre-trained artifact detection model, and perform second artifact processing on the second deep brain electrophysiological signal using a second artifact processing strategy to obtain a target deep brain electrophysiological signal in a case where a detection result indicates that the second deep brain electrophysiological signal has artifacts.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the steps of the method of any one of claims 1 to 6.

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

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6. The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

Images