Brain-machine interface and mindfulness meditation-based intervention methods for motion sickness

Abstract

A method for intervening in motion sickness based on a brain-machine interface and mindfulness meditation includes: acquiring the current user's multi-channel / single-channel electroencephalogram (EEG) signals in real time (S1); determining a motion sickness grade, including first and second grades, from the multi-channel / single-channel EEG signals (S2); performing a suspend standby operation if the motion sickness grade is first grade (S3); and selecting a meditation induction feedback scene to guide the current user into meditation and alleviate the symptoms of motion sickness if the motion sickness grade is second grade (S4).

Description

Technical Field

[0004] , , , , ,

[0005] , , , , ,

[0001] This application claims the priority of a Chinese patent application with the application number 202410143539.6 filed with the Chinese Patent Office on February 1, 2024, and all the contents of the application are incorporated herein by reference.

[0002] This application belongs to the technical field of brain-machine interfaces, and relates to, for example, an intervention method for motion sickness based on brain-machine interfaces and mindfulness meditation.

Background Art

[0003] <00OOOO12>When on a vehicle / ship / airplane, some passengers develop symptoms of motion sickness such as fainting, nausea, and loss of appetite, which cause great pain to the passengers. For the solution or prevention of motion sickness, the usual method is drug therapy. However, since drug therapy has side effects on passengers, many passengers are reluctant to receive it, and the effects vary from person to person. Passengers may also relieve or prevent motion sickness by wearing special anti-motion-sickness glasses, etc., but the effects are not obvious for many passengers. That is, there is still no method that can effectively relieve / prevent motion sickness and has no side effects.

Summary of the Invention

[0004] The purpose of this application is to provide an intervention method for motion sickness based on brain-machine interfaces and mindfulness meditation to prevent or substantially relieve the symptoms of motion sickness when the user is on a vehicle.

[0005] To achieve the above purpose, this application collects the current user's multi-channel / single-channel brain wave signals in real time, determines the motion sickness grade including the first grade and the second grade from the multi-channel / single-channel brain wave signals, when the motion sickness grade is the first grade, executes a suspension waiting operation, If the motion sickness grade is Grade 2, the following is included: selecting a meditation induction feedback scene to guide the current user into meditation and alleviate the symptoms of motion sickness. This paper proposes a technical method for intervening in motion sickness based on brain-machine interfaces and mindfulness meditation.

[0006] One preferred technical application of this invention is to acquire the current user's multi-channel / single-channel electroencephalogram (EEG) signals in real time, as described above. Collect multi-channel / single-channel electroencephalogram (EEG) signals from past users, including non-motion disorder users and users with motion disorder, as training data. This involves constructing a training set that includes data pairs of training data and user-reported symptoms of motion sickness, This further includes constructing a motion assessment model based on the aforementioned data pairs.

[0007] One preferred technical application of the present invention is to determine the motion disorder grade from the multi-channel / single-channel electroencephalogram signals. The current user's multi-channel / single-channel electroencephalogram signal is input to the motion evaluation model, Outputting the current user's motion sickness score, If the motion sickness score is within the first preset interval, the motion sickness grade is determined to be Grade 1, indicating that the current user does not develop motion sickness or only experiences mild symptoms of motion sickness. If the motion sickness score is within the second preset interval, the motion sickness grade is determined to be Grade 2, indicating that the current user has already developed severe symptoms of motion sickness. This includes outputting the current user's motion sickness grade.

[0008] One preferred technical application of this invention is to output the current user's motion sickness score as described above. This involves obtaining multiple pre-set motion sickness score intervals corresponding to different severity levels of motion sickness, This includes determining a target score range corresponding to the motion sickness score based on the plurality of motion sickness score ranges.

[0009] One preferred technical application of the present invention is to input the current user's multi-channel / single-channel electroencephalogram signal into the motion evaluation model. The current user's multi-channel / single-channel electroencephalogram (EEG) signal is subjected to preprocessing, including filtering, to obtain an EEG signal segment awaiting measurement. The feature extraction process involves extracting at least one type of feature from time-domain features, frequency-domain features, and time-frequency features from the aforementioned electroencephalogram signal segment awaiting measurement. This includes inputting the results of the feature extraction into the motion evaluation model.

[0010] As one preferred technical application of the present invention, if the motion disorder grade is Grade 1, performing a suspend standby operation is: The aforementioned motion sickness grade is determined to be Grade 1, This involves collecting road condition information, including whether the road is uneven and congested, and whether the road is flat and smooth. If the road conditions are flat and smooth, the current user's motion sickness grade is reassessed according to a predetermined time interval. If the road conditions are not flat and are congested, the system includes selecting a meditation guidance feedback scene to guide the current user into meditation. If the aforementioned road conditions are not flat and are congested, selecting a meditation guidance feedback scene to guide the current user to meditate is, To collect gyro signals, This includes receiving traffic information, including congestion status.

[0011] One preferred technical application of the present invention is to prevent or alleviate motion sickness by selecting a meditation induction feedback scene and inducing the current user to meditate when the gyro signal matches a preset shaking condition and the traffic condition information matches a preset condition.

[0012] As one preferred technical application of the present invention, if the motion sickness grade is Grade 2, the symptoms of motion sickness are alleviated by selecting a meditation induction feedback scene and inducing the current user to meditate. The aforementioned motion sickness grade is determined to be Grade 2, The current user is verbally alerted to begin meditation, Selecting meditation guidance feedback scenes, Based on the current user's multi-channel / single-channel electroencephalogram (EEG) signals, the meditation effect score is calculated, This includes updating the meditation guidance feedback scene based on the aforementioned meditation effectiveness score, The aforementioned meditation induction feedback scene includes at least one of visual feedback, auditory feedback, audiovisual feedback, olfactory feedback, tactile feedback, and electrical stimulation feedback. Before calculating the meditation effect score, This involves collecting multi-channel / single-channel electroencephalogram (EEG) signals from past users in both relaxed and meditative states as training data, This further includes constructing a meditation level assessment model based on the aforementioned training data.

[0013] One preferred technical application of this invention is to calculate the meditation effect score based on the current user's multi-channel / single-channel electroencephalogram (EEG) signals. The current user's multi-channel / single-channel electroencephalogram signals are input into the meditation level evaluation model, This includes outputting the current user's meditation effectiveness score.

[0014] As one preferred technical solution of the present application, updating the meditation induction feedback scene based on the meditation effect score includes: when the meditation effect score decreases, reducing the expressiveness of the meditation induction feedback scene; when the meditation effect score increases, enhancing the expressiveness of the meditation induction feedback scene.

[0015] As one preferred technical solution of the present application, the current user rides on a vehicle that induces motion sickness, and the vehicle that induces motion sickness includes at least one of a car, a ship, and an airplane.

Brief Description of the Drawings

[0016] [Figure 1] It is a flowchart of a method for intervening in motion sickness according to the present application.

Embodiments for Carrying out the Invention

[0017] Hereinafter, the technical solutions in the embodiments of the present application will be described in conjunction with the drawings in the embodiments of the present application.

[0018] Referring to FIG. 1, a method for intervening in motion sickness based on a brain machine interface and mindfulness meditation according to the present application includes: S1: Collecting the multi-channel / single-channel brain wave signals of the current user in real time; S2: Determining a motion sickness grade including a first grade and a second grade from the multi-channel / single-channel brain wave signals; S3: Performing a suspension waiting operation when the motion sickness grade is the first grade; S4: Selecting a meditation induction feedback scene to induce the current user to meditate and relieve the symptoms of motion sickness when the motion sickness grade is the second grade.

[0019] Motion sickness can be divided into two grades: Grade 1, where there are no symptoms of motion sickness, or where mild symptoms of motion sickness occur but the patient is able to tolerate them; and Grade 2, where severe (unbearable) symptoms of motion sickness occur.

[0020] The suspend standby operation is the process of continuously determining the motion disorder grade from multi-channel / single-channel electroencephalogram (EEG) signals.

[0021] Selecting a meditation guidance feedback scene means choosing from pre-configured meditation guidance feedback scenes. When a user uses the service for the first time, they can select an initial default meditation scene from the available options. Of course, users can customize the meditation guidance feedback scenes according to their own usage habits.

[0022] This invention proposes a motion sickness warning method based on multi-channel / single-channel electroencephalogram (EEG) signals and real-time road condition information. It detects when a user exhibits significant motion sickness symptoms or when the current road conditions are not smooth and are congested, and prompts the user to begin mindfulness meditation via voice alert, thereby mitigating or preventing motion sickness in a timely manner. It has a wide range of applicability, is not dependent on specific vehicles, and can be used in situations prone to motion sickness, such as in cars, steamships, and airplanes. While the user is in a vehicle, motion sickness can be effectively prevented and mitigated by performing mindfulness meditation based on a brain-machine interface, adjusting their attention target in real time based on feedback from multiple sensory organs, and determining and continuously detecting the motion sickness grade or inducing meditation to relax the mind and body. Compared to related visual compensation and drug interventions, this invention has advantages such as no side effects and significant intervention effects.

[0023] In this embodiment, preferably, before acquiring the current user's multi-channel / single-channel electroencephalogram (EEG) signals in real time, Collect multi-channel / single-channel electroencephalogram (EEG) signals from past users, including non-motion disorder users and users with motion disorder, as training data. This involves constructing a training set that includes data pairs of training data and user-reported symptoms of motion sickness, This further includes constructing a motion assessment model based on data pairs.

[0024] The steps for constructing the motion assessment model are as follows:

[0025] 1) Collect signals, and among them, collect multi-channel / single-channel electroencephalogram (EEG) signals from multiple non-motion-sick users and motion-sick users (e.g., 100 non-motion-sick users and 100 motion-sick users) while they are in a vehicle. The collection devices include Neuroscan (EEG meter / EEG collection system), South China Brain Control's multi-channel / single-channel headband, etc.

[0026] 2) Process the signal. 2.1 The collected electroencephalogram (EEG) signals are preprocessed and then divided into EEG signal segments of uniform duration (e.g., 5 seconds), with each EEG signal segment forming a single sample. 2.2 Bandpass filtering is performed on each sample, and filters such as Chebyshev filters and Butterworth bandpass filters can be used. 2.3 Feature extraction is performed on the preprocessed sample, and the resulting features include at least one of the following: time-domain features, frequency-domain features, and time-frequency features.

[0027] 3) Annotate the data, and for each electroencephalogram (EEG) signal segment, label it as either "no significant symptoms of motion disorder" or "motion disorder" according to the motion disorder symptoms reported by the user.

[0028] 4) Train a model, constructing a machine learning model such as a support vector machine model or a random forest model, or a deep network model such as a convolutional neural network or a recurrent neural network, and use the feature extraction results and the corresponding motion disorder labels to train the model and output a motion assessment model with constant parameters, which can be used to assess motion disorder within a subject, between subjects, and over time.

[0029] In this embodiment, it is preferable to determine the motion disorder grade from multi-channel / single-channel electroencephalogram signals. The current user's multi-channel / single-channel EEG signals are input into the motion assessment model, Output the current user's motion sickness score, If the motion sickness score is within the first preset interval, the motion sickness grade is determined to be Grade 1, indicating that the current user does not experience motion sickness or only experiences mild symptoms of motion sickness. If the motion sickness score is within the second preset interval, the motion sickness grade is determined to be Grade 2, indicating that the current user has already developed significant symptoms of motion sickness. This includes outputting the current user's motion sickness grade.

[0030] The motion sickness score can be easily divided into two categories: Grade 1 and Grade 2. For example, if the motion sickness score is between 0 and 10, the first preset interval can be set to [0,3), meaning the first preset interval includes 0 but does not include 3, and the second preset interval can be set to [3,10], meaning the second preset interval includes both 3 and 10. The current user's motion sickness grade is determined based on the current user's motion sickness score.

[0031] The embodiments of this invention utilize a user-to-user motion sickness symptom and meditation level evaluation model, and a time-spanning motion sickness symptom and meditation state evaluation model, which eliminate the need to pre-collect current user EEG training data when using the motion evaluation model. The user can directly use the model to evaluate their current state and output a motion sickness score and a meditation effect score. The invention also allows for the pre-collection of the current user's multi-channel / single-channel EEG signals and their use for training or fine-tuning the motion evaluation model and the meditation level evaluation model.

[0032] In this embodiment, preferably, the current user's motion sickness score is output. This involves obtaining multiple pre-set motion sickness score intervals corresponding to different severity levels of motion sickness, This includes determining a target score range corresponding to a motion sickness score based on multiple motion sickness score ranges.

[0033] Besides simply dividing the motion sickness score into two categories, Grade 1 and Grade 2, the motion sickness score interval may be divided into multiple intervals depending on actual needs. Similarly, taking the motion sickness score as 0 to 10 points as an example, one preset interval can be set to [0,3)], meaning the preset interval includes 0 points but does not include 3 points, indicating that the current user is not experiencing motion sickness. Another preset interval can be set to [3,6)], meaning the preset interval includes 3 points but does not include 6 points, indicating that the current user is experiencing only mild symptoms of motion sickness. A third preset interval can be set to [6,10], meaning the preset interval includes both 6 points and 10 points, indicating that the current user is already experiencing significant symptoms of motion sickness.

[0034] In this embodiment, preferably, the current user's multi-channel / single-channel electroencephalogram signal is input to the motion assessment model. The current user's multi-channel / single-channel EEG signal is preprocessed, including filtering, to obtain an EEG signal segment awaiting measurement. The process involves extracting features from an electroencephalogram (EEG) signal segment awaiting measurement, including at least one of the following: time-domain features, frequency-domain features, and time-frequency features. This includes inputting the results of feature extraction into a motion evaluation model.

[0035] In this embodiment, preferably, if the motion sickness grade is Grade 1, the suspend standby operation is performed. The determination that the motion sickness grade is Grade 1, This involves collecting road condition information, including whether the road is uneven and congested, and whether the road is flat and smooth. If the road conditions are flat and smooth, the current user's motion sickness grade will be reassessed according to a predetermined time interval, This includes selecting a meditation guidance feedback scene when the road conditions are not flat and are congested, and guiding the current user to meditate. If the road conditions are not flat and there is congestion, selecting a meditation guidance feedback scene to guide the current user into meditation is a good approach. To collect gyro signals, Receiving traffic information, including congestion status, This includes preventing or alleviating motion sickness by selecting a meditation induction feedback scene and guiding the current user to meditate when the gyro signal matches pre-set shaking conditions and the traffic condition information also matches pre-set conditions.

[0036] If the motion sickness grade is Grade 1, road condition information is collected. Generally, gyro signals and traffic condition information from invoked third-party software can be used as road condition information. Road condition information includes whether the road is uneven and congested, and whether the road is flat and smooth. Uneven and congested road conditions indicate that situations such as congestion, road repairs, traffic accidents, and continuous curves have occurred, while flat and smooth road conditions indicate that no traffic abnormalities have occurred and the vehicle can travel stably. If the road conditions are flat and smooth, the current user's motion sickness grade is reassessed according to a preset time interval. If the road conditions are uneven and congested, a meditation induction feedback scene is selected to guide the current user into meditation. This helps to alleviate or prevent motion sickness in a timely manner.

[0037] In this embodiment, preferably, when the motion sickness grade is Grade 2, a meditation induction feedback scene is selected to guide the current user into meditation, thereby alleviating the symptoms of motion sickness. The determination that the motion sickness grade is Grade 2, The system will use voice prompts to encourage the current user to begin meditating, Selecting meditation guidance feedback scenes, Based on the current user's multi-channel / single-channel electroencephalogram (EEG) signals, the meditation effect score will be calculated, and This includes updating the meditation guidance feedback scene based on the meditation effectiveness score, Meditation induction feedback scenes include one or more of the following: visual feedback, auditory feedback, audiovisual feedback, olfactory feedback, tactile feedback, and electrical stimulation feedback. Before calculating the meditation effect score, This involves collecting multi-channel / single-channel electroencephalogram (EEG) signals from past users in both relaxed and meditative states as training data, This further includes constructing a meditation level assessment model based on training data.

[0038] The steps for constructing the meditation level assessment model are as follows:

[0039] 1) Collect signals, and from these, collect multi-channel / single-channel electroencephalogram (EEG) signals from multiple users (e.g., 100 cases) in both relaxed (or resting) and meditative states, with collection devices including Neuroscan and South China Brain Control's multi-channel / single-channel headbands.

[0040] 2) Process the signal. 2.1 The collected electroencephalogram (EEG) signals are preprocessed and then divided into EEG signal segments of uniform duration (e.g., 10 seconds), with each EEG signal segment forming a single sample. 2.2 Bandpass filtering is performed on each sample, and filters such as Chebyshev filters and Butterworth bandpass filters can be used. 2.3 Feature extraction is performed on the preprocessed sample, and the resulting features include at least one of the following: time-domain features, frequency-domain features, and time-frequency features.

[0041] 3) Design a model and build a machine learning model such as a support vector machine model or a random forest model, or a deep network model such as a convolutional neural network or a recurrent neural network, and this model can be used to evaluate the degree of meditation within a subject, the degree of meditation between subjects, and the degree of meditation over time.

[0042] 4) Output the model, and use the feature extraction results and the corresponding labels for relaxed or meditative states to train the model constructed in step 3). After completing the training, output a meditation degree evaluation model with constant parameters.

[0043] In this embodiment, preferably, the meditation effect score is calculated based on the current user's multi-channel / single-channel electroencephalogram (EEG) signal. The current user's multi-channel / single-channel electroencephalogram (EEG) signals are input into the meditation level assessment model, This includes outputting the current user's meditation effectiveness score.

[0044] In this embodiment, preferably, updating the meditation induction feedback scene based on the meditation effect score is If the meditation effectiveness score decreases, it is due to a decrease in the expressiveness of the meditation guidance feedback scene, If the meditation effectiveness score increases, this includes improving the expressiveness of the meditation guidance feedback scene.

[0045] A meditation guidance feedback scene is a scene in which the user is guided to meditate and self-adjusts according to the user's feedback (expressed as a meditation effectiveness score), and includes, but is not limited to, visual, auditory, tactile, and olfactory scenes. In visual scenes, expressiveness generally refers to the clarity of the picture; in auditory scenes, expressiveness generally refers to the clarity of the sound, the loudness and intensity of the noise; in tactile scenes, expressiveness generally refers to the vibration amplitude or electrical stimulation intensity of the wearable device; and in olfactory scenes, expressiveness generally refers to the concentration and pleasantness of the smell.

[0046] For varying degrees of motion sickness, users may be encouraged to select and use different types of meditation scenes, including visual, auditory, audiovisual, olfactory, tactile, and electrical stimulation feedback. Alternatively, users may be supported in independently selecting meditation guidance feedback scenes. This can effectively enhance the user's meditation effect and lower the barrier to entering a meditative state.

[0047] In this embodiment, preferably, the current user is on board a vehicle that induces motion sickness, and the vehicle that induces motion sickness includes one of the following: a car, a ship, and an airplane.

[0048] In one feasible implementation scenario, Brain-machine interface and mindfulness meditation-based interventions for motion sickness include the following:

[0049] 1) The user first attaches an electroencephalogram (EEG) signal acquisition device, and then transmits the EEG signals in real time to a computing device such as an in-car computer, laptop, tablet, or mobile phone via Bluetooth or wired communication.

[0050] 2) The computing device performs signal processing on the electroencephalogram signal, including segmentation, baseline removal, filtering, and feature extraction.

[0051] 3) Input the processed electroencephalogram signal into the motion assessment model described above and output the motion disorder assessment score.

[0052] 4) Based on the interval in which the motion disorder score is located, the current state of motion disorder of the user is determined, using a score of 1 to 100 as an example. 4.1 If the motion disorder score is in the range [1, a], it indicates that the user does not have significant motion disorder symptoms and corresponds to Grade 1 of motion disorder; for example, a may be set to 20. If the motion disorder score is in the range [a, 100], it indicates that the user is in a motion state and has developed significant motion disorder symptoms; for example, a may be set to 20. 4.2 Furthermore, evaluation results can be output by further subdividing the motion sickness score to different degrees. For example, a score of 1-20 indicates no significant motion sickness symptoms, a score of 21-70 indicates mild motion sickness, and a score of 71-100 indicates severe motion sickness.

[0053] 5) If the user is in Grade 2 of motion sickness, the system will verbally remind the user to begin mindfulness meditation. At this time, the mindfulness meditation system will automatically turn on and recommend a feedback scene to the user, which the user can then use to perform mindfulness meditation. Alternatively, the user may select an appropriate scene according to their preference and perform mindfulness meditation, thereby alleviating the symptoms of motion sickness. 5.1 The meditation guidance feedback scene is displayed on the in-car computer / laptop / tablet / mobile phone display and audio, electrical stimulation, and other devices. 5.2 After entering the meditation induction feedback scene, the computing device inputs the pre-processed electroencephalogram (EEG) signal into the meditation level evaluation model described above and outputs a meditation effect score. 5.3 The expressiveness of the meditation guidance feedback scene is controlled based on the meditation effect score. This includes changes in the clarity and field of view of the visual scene, changes in auditory volume, tone, and type of sound, changes in tactile intensity, and changes in electrical stimulation intensity, all of which can be summarized as changes in expressiveness. In one specific implementation method, the user's meditation state is evaluated once at regular intervals (e.g., every 2 seconds). If the meditation effect score at that time is higher than the previous time, i.e., the meditation effect score increases, it indicates that the user's meditation is deeper or more effective. In this case, the three-dimensional (3D) / two-dimensional (2D) visual scene becomes clearer and more beautiful, and the sound becomes louder. If the meditation effect score at this time is lower than the previous time, i.e., the meditation effect score decreases, it indicates that the user's meditation is shallower or less effective / distracting. In this case, the 3D / 2D visual scene becomes blurred and less beautiful, and the sound becomes quieter. 5.4 Visual feedback scenes may include animations of the sky, clouds, bonfires, waves, and forests; auditory feedback scenes may include pink noise, the sound of raindrops, the sound of running water, the sound of flames, and music; audiovisual feedback scenes may include both visual and auditory feedback simultaneously; olfactory feedback may include aromatherapy; tactile feedback may include vibrations from a mobile device or massage from a seat; and electrical stimulation feedback may include direct current electrical stimulation. All of the above sensory feedback scenes are equipped with meditative guidance words to guide the user's training.

[0054] 6) If the user does not exhibit significant symptoms of motion sickness, gyro data is collected, traffic condition information is received (by calling third-party map software), and transmitted to the current computing device via Bluetooth or wireless internet. 6.1 If road conditions are not flat and traffic is congested, for example, if the gyro's angular velocity changes too much, or if the map software provides feedback that traffic ahead is congested, the system will verbally alert the user to meditate. In this case, the mindfulness meditation system will automatically turn on and recommend a meditation guidance feedback scene, or the user will select an appropriate scene to perform mindfulness meditation, thereby reducing or preventing symptoms of motion sickness. 6.2 When road conditions are flat and smooth, do not prompt the user to practice mindfulness meditation.

[0055] The embodiments of this application have already been shown and described, and details can be found in the above detailed description, but it should be understood that these embodiments can be modified, altered, substituted, and transformed in various ways without departing from the principles and spirit of this application, and the scope of this application is limited by the appended claims and equivalents.

Claims

1. To acquire the current user's multi-channel / single-channel electroencephalogram (EEG) signals in real time, Determining motion disorder grades, including first and second grades, from the multi-channel / single-channel electroencephalogram signals, If the motion sickness grade is Grade 1, the suspend standby operation is performed. If the motion sickness grade is Grade 2, the following is included: selecting a meditation induction feedback scene to guide the current user into meditation and alleviate the symptoms of motion sickness. Intervention methods for motion sickness based on brain-machine interfaces and mindfulness meditation.

2. Prior to acquiring the current user's multi-channel / single-channel electroencephalogram (EEG) signals in real time, as described above, Collect multi-channel / single-channel electroencephalogram (EEG) signals from past users, including non-motion disorder users and users with motion disorder, as training data. This involves constructing a training set that includes data pairs of training data and user-reported symptoms of motion sickness, This further includes constructing a motion assessment model based on the aforementioned data pairs, The method according to claim 1.

3. Determining the motion sickness grade from the aforementioned multi-channel / single-channel electroencephalogram signals is, The current user's multi-channel / single-channel electroencephalogram signal is input to the motion evaluation model, Outputting the current user's motion sickness score, If the motion sickness score is within the first preset range, it is determined that the motion sickness grade is grade 1, indicating that the current user does not develop motion sickness or only develops mild symptoms of motion sickness. If the motion sickness score is within the second preset interval, the motion sickness grade is determined to be Grade 2, indicating that the current user has already developed severe symptoms of motion sickness. This includes outputting the current user's motion sickness grade, The method according to claim 2.

4. Outputting the current user's motion sickness score, as described above, This involves obtaining multiple pre-set motion sickness score intervals corresponding to different severity levels of motion sickness, This includes determining a target score range corresponding to the motion sickness score based on the plurality of motion sickness score ranges, The method according to claim 3.

5. Inputting the current user's multi-channel / single-channel electroencephalogram signal into the motion evaluation model is, The current user's multi-channel / single-channel electroencephalogram (EEG) signal is subjected to preprocessing, including filtering, to obtain an EEG signal segment awaiting measurement. The feature extraction process involves extracting at least one type of feature from time-domain features, frequency-domain features, and time-frequency features from the aforementioned electroencephalogram signal segment awaiting measurement. This includes inputting the results of the feature extraction into the motion evaluation model, The method according to claim 3.

6. If the motion sickness grade is Grade 1, performing a suspend standby operation is: The aforementioned motion sickness grade is determined to be Grade 1, This involves collecting road condition information, including whether the road is uneven and congested, and whether the road is flat and smooth. If the road conditions are flat and smooth, the current user's motion sickness grade is reassessed according to a predetermined time interval. If the road conditions are not flat and are congested, the system includes selecting a meditation guidance feedback scene to guide the current user into meditation. If the aforementioned road conditions are not flat and are congested, selecting a meditation guidance feedback scene to guide the current user to meditate is, To collect gyro signals, Receiving traffic information, including congestion status, The system includes, when the gyro signal matches a preset shaking condition and the traffic condition information matches a preset condition, selecting a meditation induction feedback scene and inducing the current user to meditate, thereby preventing or alleviating motion sickness. The method according to claim 1.

7. If the motion sickness grade is Grade 2, mitigating the symptoms of motion sickness by selecting a meditation induction feedback scene and guiding the current user to meditate is possible. The aforementioned motion sickness grade is determined to be grade 2, The current user is verbally alerted to begin meditation, Selecting meditation guidance feedback scenes, Based on the current user's multi-channel / single-channel electroencephalogram (EEG) signals, the meditation effect score is calculated, This includes updating the meditation guidance feedback scene based on the aforementioned meditation effectiveness score, The aforementioned meditation induction feedback scene includes at least one of visual feedback, auditory feedback, audiovisual feedback, olfactory feedback, tactile feedback, and electrical stimulation feedback. Before calculating the meditation effect score, This involves collecting multi-channel / single-channel electroencephalogram (EEG) signals from past users in both relaxed and meditative states as training data, This further includes constructing a meditation level assessment model based on the aforementioned training data, The method according to claim 1.

8. Calculating the meditation effect score based on the current user's multi-channel / single-channel EEG signals is possible. The current user's multi-channel / single-channel electroencephalogram signals are input into the meditation level evaluation model, This includes outputting the current user's meditation effectiveness score, The method according to claim 7.

9. Updating the meditation guidance feedback scene based on the aforementioned meditation effectiveness score is: If the aforementioned meditation effectiveness score decreases, the expressiveness of the meditation guidance feedback scene will be reduced, If the aforementioned meditation effect score increases, this includes enhancing the expressiveness of the meditation guidance feedback scene, The method according to claim 7.

10. The aforementioned current user is riding in a vehicle that induces kinesiology, and the vehicle that induces kinesiology includes at least one of a car, a ship, and an airplane. The method according to claim 1.

Images