Brain-computer interface-based attention training methods, systems, devices, and storage media

Abstract

This application discloses a brain-computer interface (BCI)-based attention training method, system, device, and storage medium, belonging to the field of BCI technology. The attention method is based on real-time EEG signal data of the trainee measured by the BCI. It provides a training role, controlling the role's movement based on attention values, and further offers various training modes such as attention intensity training tasks, execution training tasks, inhibition training tasks, and working memory training tasks. The method, system, device, and medium of this invention offer strong BCI training interactivity and adopt a multi-task training paradigm, overcoming the shortcomings of existing technologies that are singular and monotonous. This improves trainee compliance, increases training frequency, and achieves better training results. ADHD patients can train not only in hospitals but also at home, making it more convenient, economical, and efficient. Especially for school-aged children and adolescents, it greatly improves patient training compliance and reduces the dropout rate during training.

Description

Technical Field

[0001] This application relates to the field of brain-computer interface technology, and in particular to attention training methods, systems, devices and storage media based on brain-computer interfaces. Background Technology

[0002] Attention deficit hyperactivity disorder (ADHD) is a common neurodevelopmental disorder characterized by inattention, hyperactivity, and / or impulsivity. It is mainly divided into three types: attention deficit, hyperactivity-impulsivity, and mixed manifestations.

[0003] Currently, the mainstream treatments for ADHD include pharmacological and non-pharmacological therapies. EEG biofeedback is a non-invasive brain-computer interface (BCI) technology that improves neural function by monitoring and modulating brain electrical activity in real time. It is a clinically accepted non-pharmacological treatment with low risk and side effects. Its core principle is based on biofeedback mechanisms and the theory of neuroplasticity, training patients to voluntarily adjust the frequency and intensity of specific brain waves, thereby improving attention.

[0004] However, current EEG biofeedback methods all use audiovisual feedback (such as animation and sound). This type of feedback training is monotonous and boring, resulting in low patient compliance, which in turn affects the training frequency and the final training effect. Summary of the Invention

[0005] This application provides a brain-computer interface-based attention training method, system, device, and storage medium to at least solve the above-mentioned technical problems existing in the prior art.

[0006] The first aspect of this application provides an attention training method based on a brain-computer interface, comprising the following steps:

[0007] The brainwave signal data of the trainee, measured in real time via a brain-computer interface, is obtained, filtered at 1Hz to 35Hz, and then converted into attention values.

[0008] A training character and an observable scene are provided. The training character is located at a certain position in the observable scene. The movement speed of the training character is set according to the attention value. The training character moves relative to the observable scene along the movement path at the movement speed.

[0009] P obstacles, P ≥ 1, are set along the movement path of the training character. When the distance between the training character and any one of the obstacles is a first preset distance threshold, continuous detection of the presence of a first command begins until the first command is detected or the training time ends.

[0010] If the first instruction is detected, the training character continues to move at the specified speed, unaffected by the obstacle. If the first instruction is not detected until the distance between the training character and the obstacle reaches a second preset distance threshold, the training character's movement speed is set to 0. Once the first instruction is detected, the training character's movement speed is reset using the current attention value, so that the training character is no longer affected by the obstacle and continues to move.

[0011] In some embodiments of this application, throughout the training time, the presence of a second instruction is continuously detected, and M target objects are displayed at intervals in the observable scene, where M≥1. During the movement of the training character, each of the target objects first approaches the training character and then moves away from it.

[0012] If the second instruction is detected once or more while the target object is not displayed, a multi-action error is recorded for each detection.

[0013] If the second instruction is detected once or multiple times during the period when the target object is displayed but the distance between the target object and the training character is greater than a third preset distance threshold, then a reaction error is recorded for each detection.

[0014] If the second instruction is detected once or multiple times during the period when the target object is displayed and the distance between the target object and the training character is not greater than the third preset distance threshold, only one correct response is recorded, and each additional detection is recorded as an over-action error.

[0015] In some possible embodiments of this application, N non-target objects, N≥1, are also displayed at intervals in the observable scene. During the movement of the training character, each of the non-target objects moves closer to the training character and then moves further away from it.

[0016] If the second instruction is detected once or more during the period when the target object and the non-target object are not displayed, a multi-action error is recorded for each detection.

[0017] If the second instruction is detected once or more during the display of the non-target object, a suppression error is recorded for each detection;

[0018] If the second instruction is not detected during the display of the non-target object, then a successful suppression is recorded.

[0019] In some possible implementations of this application, M ≥ 2, and the M target objects are all different. In the observable scene, the M target objects are first displayed in sequence for a period of time, the period of time being 2~5 seconds, and then each target object is randomly displayed once or multiple times. Target objects displayed in sequence are called ordered objects, and target objects not displayed in sequence are called unordered objects.

[0020] If the second instruction is detected once or more while the target object is not displayed, a multi-action error is recorded for each detection.

[0021] If the second instruction is detected once or multiple times when the ordered object is displayed but the distance between the ordered object and the training character is greater than the third preset distance threshold, then a reaction error is recorded for each detection.

[0022] If the second instruction is detected once or multiple times when the ordered objects are displayed and the distance between the ordered objects and the training character is not greater than the third preset distance threshold, only one correct response is recorded, and each additional detection is recorded as an over-action error.

[0023] If the second instruction is detected once or more during the display of the non-ordered object, a suppression error is recorded for each detection;

[0024] If the second instruction is not detected during the display of the non-ordered object, a successful suppression is recorded.

[0025] In some possible implementations of this application, in step S2, the EEG signal data is subjected to spectral analysis by Fourier transform, and the power spectral density of different frequency bands is calculated. The attention value is then obtained based on the power spectral density.

[0026] A second aspect of this application provides an attention training system based on a brain-computer interface, comprising the following modules:

[0027] The EEG signal data receiving and processing module is used to receive EEG signal data of the trainee measured in real time based on the brain-computer interface, perform filtering processing from 1Hz to 35Hz, and convert the EEG signal data into attention values.

[0028] A visualization module is used to provide a training character and an observable scene, wherein the training character is located at a certain position in the observable scene.

[0029] A training character control module, connected to the EEG signal data receiving and processing module and the visualization module, is used to set the movement speed of the training character according to the attention value, and the training character moves relative to the observable scene at the movement speed along the movement path;

[0030] The training function control module is used to set P obstacles in front of the direction of movement of the training character, where P ≥ 1.

[0031] The distance detection module is used to detect the distance between the training character and any one of the obstacles.

[0032] The instruction recognition module is used to recognize the first instruction;

[0033] The judgment module, connected to the distance detection module, the instruction detection module, and the training character control module respectively, is used to continuously detect the existence of a first instruction when the distance between the training character and any of the obstacles is a first preset distance threshold, until the first instruction is detected or the training time ends, and is also used to:

[0034] If the first instruction is detected, the training character is controlled to continue moving at the specified speed, unaffected by the obstacle. If the first instruction is not detected until the distance between the training character and the obstacle reaches a second preset distance threshold, the movement speed of the training character is set to 0 until the first instruction is detected. Then, the movement speed of the training character is reset using the current attention value, so that the training character is no longer affected by the obstacle and continues to move.

[0035] In some possible implementations of this application, the instruction detection module is further configured to identify a second instruction; the training function control module is further configured to display M target objects at intervals in the observable scene, where M≥1, and during the movement of the training character, each target object first approaches the training character and then moves away from it.

[0036] The distance detection module is also used to detect the distance between the training character and any of the target objects.

[0037] The judgment module is also used to continuously detect the existence of a second instruction throughout the entire training time and perform the following recording operations:

[0038] If the second instruction is detected once or more while the target object is not displayed, a multi-action error is recorded for each detection.

[0039] If the second instruction is detected once or multiple times during the period when the target object is displayed but the distance between the target object and the training character is greater than a third preset distance threshold, then a reaction error is recorded for each detection.

[0040] If the second instruction is detected once or multiple times during the period when the target object is displayed and the distance between the target object and the training character is not greater than the third preset distance threshold, only one correct response is recorded, and each additional detection is recorded as an over-action error.

[0041] In some possible embodiments of this application, the training function control module is further configured to display N non-target objects at intervals in the observable scene, where N≥1, and during the movement of the training character, each of the non-target objects moves closer to and then moves further away from the training character.

[0042] The judgment module is also used to complete the following records:

[0043] If the second instruction is detected once or more during the period when the target object and the non-target object are not displayed, a multi-action error is recorded for each detection.

[0044] If the second instruction is detected once or more during the display of the non-target object, a suppression error is recorded for each detection;

[0045] If the second instruction is not detected during the display of the non-target object, then a successful suppression is recorded.

[0046] In some embodiments of this application, M ≥ 2, and the M target objects are all different. The training function control module is used to first display the M target objects in sequence for a period of time (2-5 seconds) in the observable scene, and then randomly display each target object once or multiple times. Target objects displayed in sequence are called ordered objects, and target objects not displayed in sequence are called unordered objects.

[0047] The judgment module is used to complete the following recording:

[0048] If the second instruction is detected once or more while the target object is not displayed, a multi-action error is recorded for each detection.

[0049] If the second instruction is detected once or multiple times when the ordered object is displayed but the distance between the ordered object and the training character is greater than the third preset distance threshold, then a reaction error is recorded for each detection.

[0050] If the second instruction is detected once or multiple times during the period when the sequential objects are displayed and the distance between the sequential objects and the training character is not greater than the third preset distance threshold, only one correct response is recorded, and each additional detection is recorded as an over-action error.

[0051] If the second instruction is detected once or more during the display of the non-ordered object, a suppression error is recorded for each detection;

[0052] If the second instruction is not detected during the display of the non-ordered object, a successful suppression is recorded.

[0053] A third aspect of this application provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform any of the attention training methods described in the first aspect of this application.

[0054] A fourth aspect of this application provides a non-transitory computer-readable storage medium storing computer instructions, characterized in that the computer instructions are used to cause the computer to execute the attention training method according to any of the first aspects of this application.

[0055] Compared with the prior art, this application has the following advantages:

[0056] The methods, systems, devices, and media in this application target the three core competencies that ADHD patients need to improve, providing targeted neurofeedback training in attention intensity, executive inhibition, and working memory. This comprehensively improves the symptoms and enhances the cognitive level of ADHD patients.

[0057] The methods, systems, devices, and media of this invention provide highly interactive brain-computer interface training and adopt a multi-task training paradigm, which overcomes the shortcomings of existing technologies in terms of their singularity and monotony. This allows trainees to improve their compliance, increase the frequency of training, and thus achieve better training results.

[0058] Using the methods, systems, devices, or media of this application, ADHD patients can undergo training not only in hospitals but also at home, making it more convenient, economical, and efficient. This is particularly beneficial for school-aged children and adolescents, significantly improving patient adherence to training and reducing dropout rates.

[0059] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0060] The above and other objects, features, and advantages of exemplary embodiments of this application will become readily apparent upon reading the following detailed description with reference to the accompanying drawings. Several embodiments of this application are illustrated in the drawings by way of example and not limitation, in which:

[0061] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts.

[0062] Figure 1 This illustration shows a training character encountering an obstacle according to an embodiment of this application;

[0063] Figure 2 This illustration shows a training character encountering a target object according to an embodiment of this application.

[0064] Figure 3 This illustration shows a training character encountering a target / non-target object in a blind box, according to an embodiment of this application.

[0065] Figure 4 A schematic diagram illustrating the implementation flow of one embodiment of this application is shown;

[0066] Figure 5 A schematic diagram of the composition structure of an electronic device according to an embodiment of this application is shown. Detailed Implementation

[0067] To make the objectives, features, and advantages of this application more apparent and understandable, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0068] This application employs closed-loop brain-computer interface technology for attention training.

[0069] First, by wearing a wearable EEG acquisition device, real-time electroencephalogram (EEG) signals are collected from the prefrontal cortex of the trainee's brain. After the EEG data processing module decodes the neural signals, real-time attention values ​​are obtained. The specific EEG data processing steps include the following:

[0070] 1. Data preprocessing: Perform filtering from 1Hz to 35Hz.

[0071] 2. Feature extraction: Fourier transform was used to perform spectral analysis of EEG data and the power spectral density of different frequency bands such as delta waves (0.5-4Hz), theta waves (4-8Hz), alpha waves (8-13Hz), and beta waves (13-35Hz) was calculated.

[0072] 3. Calculate Attention Values: Select attention-related EEG data features (such as the power spectral density of beta and alpha waves) for calculation (e.g., beta wave power spectral density / alpha wave power spectral density) to obtain the specific value Yi(t) for trainee i at time point t. Based on the existing EEG dataset of N trainees in the database (e.g., 1000 datasets), normalize Yi(t) to a value in the range [0,1], then amplify it by 100 times to convert it into an attention value Ai(t) in the range [0,100].

[0073] The attention score reflects the state of brain activity closely related to attentional cognitive activities. Trainees can adjust their attentional state to increase or decrease the energy proportion of different frequency segments in the brain, thereby increasing or decreasing the attention score.

[0074] In this embodiment, an observable scene is provided, and a training character (cartoon character or cartoon animal) is provided at a location in the observable scene. The observable scene can be a scene that can be observed by the naked eye, such as a graphical interface, or a scene that can be observed through tools such as VR glasses.

[0075] Furthermore, the movement speed of the training character is set based on the obtained attention values. Furthermore, the state (including actions and expressions) of the training character is set based on the obtained attention data. Even further, the background music is set based on the obtained attention data, as shown in Table 1.

[0076] Table 1. Relationship between attention values ​​and training character parameters

[0077]

[0078] In one embodiment, only attention intensity training (referred to as the beginner course) is included. In the beginner course, the movement of the training character is controlled using parameters from Table 1, based on the trainee's real-time attention scores. The trainee can adjust their brain activity to change their attention scores, thereby altering the speed at which the training character moves within the provided scene. In the beginner course, the greater the distance moved within a specified time (e.g., 3 minutes), the higher the score. This motivates the trainee to strive to improve their attention scores, thus achieving the training objective.

[0079] Furthermore, P obstacles will appear at intervals ahead of the training character's movement path, such as... Figure 1As shown, when the training character moves to a distance of no more than L1 (i.e., the first preset distance threshold) from the obstacle (in this embodiment, the distance is the distance between the vertical center line of the training character and the vertical center line of the obstacle), it detects whether the trainer has sent an instruction (the first instruction). This first instruction can be a body movement (such as nodding, shaking the head, raising a hand, waving, clapping, clicking, pressing a button, etc.), a specified sound, or an expression. The first instruction is collected by a corresponding signal collector. After the first instruction is detected, the training character is controlled to perform a first action, such as jumping, hitting, striking, knocking, pushing, pulling, kicking, etc., to cross or remove the obstacle. Alternatively, the obstacle can be directly moved or disappeared. If no first instruction is detected, the training character stops when it moves to a distance of L2 (i.e., the second preset distance threshold) from the obstacle, until the first instruction issued by the trainer is detected. The trainer needs to maintain attention and issue the first instruction at the appropriate time to avoid the obstacle and allow the character to continue moving. Similarly, since the goal is to obtain a higher score by running a longer distance within a specified time, the trainer will concentrate more and issue the first instruction correctly at the appropriate time, thereby completing the attention intensity training.

[0080] In this embodiment, the frequency of obstacle appearance is increased or decreased based on the trainee's average attention span. For example, the average attention span over 10 seconds is calculated, and the frequency of obstacle appearance is increased or decreased accordingly.

[0081] In this embodiment, the following training metrics are obtained based on the attention data during the training process:

[0082] (1) The average attention span of trainees during the training period;

[0083] (2) The trainee's average attention during the training period, as well as the highest attention, lowest attention and / or the ratio of those attention;

[0084] (3) The percentage of time a trainee spends focused during training;

[0085] (4) The trainee’s maximum reaction time, minimum reaction time and / or average reaction time to obstacles to be avoided during the training period.

[0086] Among them, the focus time ratio refers to the ratio of focus time to training time, and focus means that the attention value is not less than the preset attention threshold (60 in this embodiment); reaction time refers to the time interval from when the distance between the training character and the obstacle is the first preset threshold until the first instruction is detected.

[0087] Attention can also be represented by the movement speed of the training character.

[0088] In this embodiment, the trainee's previous training scores are first obtained to determine the appropriate number of obstacles. In this case, each time training begins, identifiable information about the trainee (including but not limited to registration ID, national ID card, student ID, mobile phone number, etc.) needs to be obtained, and after training, the training results are stored under the trainee's name to form a training database.

[0089] In another embodiment, in addition to the attention intensity training task, the training task is also included. Specifically, M (M≥1, for example, M=3) target objects (fruits in this embodiment) are displayed at intervals in the observable scene. During the movement of the training character, the target objects move relative to the trainee from an undefined direction, first approaching and then moving away.

[0090] In this embodiment, the system continuously detects whether the trainee has issued a second instruction. This second instruction can also be a body movement (such as nodding, shaking the head, raising the hand, waving the hand, clapping, clicking, pressing a button, etc.), a specified sound, or an expression. The second instruction is collected by a corresponding signal collector.

[0091] Upon detecting the second instruction, the training character is controlled to perform a second action, such as jumping, hitting, striking, knocking, pushing, pulling, kicking, capturing, touching, waving, punching, etc., to contact the target object.

[0092] If a second instruction is detected once or more during the period when the target object is not displayed (i.e., the target object does not yet exist in the observable scene), each detection is recorded as a redundant error, indicating that the trainer has performed redundant operations.

[0093] If one or more second instructions are detected during the period when the target object is displayed but the distance between the target object and the training character is greater than the third preset distance threshold, then each detection will be recorded as a reaction error.

[0094] In this embodiment, as Figure 2 As shown, a circle is drawn with the center point of the training character as the center and the third preset distance threshold (L3) as the radius. If the entire target object is outside this circle (indicating it has not yet approached or has already moved away), it means the distance between the target object and the training character is greater than the third preset distance threshold. If a second command is detected at this time, it indicates that the trainee reacted too early or too late. The direction and path of the target object approaching the training character are not limited; for example, it could be... Figure 2 The movement path shown by the solid line can also be shown by the dashed line, as long as it enters and leaves the circle (in an extreme case, the movement path is tangent to the circle, but in this case, the training subject has very limited time to react in time). In this embodiment, the time from the target object entering the circle to leaving the circle is 2 to 5 seconds, and the trainee must concentrate fully and issue the second command in time.

[0095] If the second instruction is detected once or multiple times during the period when the target object is displayed and the distance between it and the training character is not greater than the third preset distance threshold (i.e. when the target object is within the circle), only one correct response is recorded, and each additional detection is recorded as an over-action error.

[0096] In this embodiment, after recording a correct reaction, the target object is controlled to disappear or be placed in a certain area of ​​the observable scene.

[0097] For the target object, if the reaction is recorded as correct, the reaction time is also recorded. This reaction time refers to the time from when the target object comes into contact with the circle until the second command is detected for the first time.

[0098] In this embodiment, the second instruction may be the same as or different from the first instruction. When the second instruction is the same as the first instruction, the presence of an instruction (collectively referred to as an instruction since the first and second instructions are both) is continuously detected throughout the training process. If an obstacle exists in the observable scene, an over-action error is recorded only when an instruction is detected while the distance between the training character and the obstacle is greater than L1.

[0099] In this embodiment, the trainee needs to concentrate on observing the position of the training character and the target object, and issue a second command at the appropriate time to try to get a correct response, while trying to avoid response errors and hyperactivity errors, thereby achieving the training effect of improving attention.

[0100] At the end of the training, the number of correct responses, the number of incorrect responses, and the number of hyperactivity errors were counted, and the correct response rate was calculated as follows: Correct response rate = (Number of correct responses / (Number of correct responses + Number of incorrect responses)) × 100%.

[0101] In another embodiment, in addition to the attention intensity training task and the execution training task, an inhibition training task (or intermediate course) is also included. In this embodiment, the three tasks are performed simultaneously. The attention intensity training task and the execution training task are as described above, and the inhibition training task is as follows:

[0102] In the observable scene, N (N≥1, e.g. N=3) non-target objects (in this embodiment, any object other than fruit, such as a folder) are also displayed at intervals. The non-target objects also move relative to the trainee from an undefined direction, first approaching and then moving away.

[0103] If the second instruction is detected once or more during the period when neither the target object nor the non-target object is displayed (at which time neither the first target object nor the non-target object exists in the observable scene), then each detection will be recorded as a multi-action error.

[0104] The instruction log during the display of the target object is as described above; for non-target objects:

[0105] If the second instruction is detected once or more during the display of a non-target object, a suppression error is recorded for each detection;

[0106] If the second instruction is not detected during the display of a non-target object, then a successful suppression is recorded.

[0107] At the end of the training, the number of times the correct suppression was performed and the number of times the incorrect suppression was performed were also counted, and the correct suppression rate was calculated as follows: Correct suppression rate = Number of times the correct suppression was performed / (Number of times the correct suppression was performed + Number of times the incorrect suppression was performed) × 100%.

[0108] In this embodiment, as Figure 3 As shown, regardless of whether it's a target object or a non-target object, when its distance from the circle on its movement path exceeds a fourth preset distance threshold (L4), it enters the observable scene as a blind box. It is only displayed as a target object or non-target object when its distance from the circle on its movement path becomes less than L4. The fourth preset distance is calculated in real-time based on the relative speed and path of the training character and / or (non-)target object. When a target object or non-target object moves along its movement path, the distance from its real-time calculated relative speed to the circle within 1.5 seconds is set as L4. In other words, the target object or non-target object is only displayed when it is 1.5 seconds away from the circle. In this case, the trainee needs to react quickly within a limited time, thus requiring focused attention, which can further improve the training effect.

[0109] In this embodiment, the correct reaction rate and / or correct inhibition rate of the trainee in previous training are first obtained. During the current training process, the number of target objects (e.g., M+1) and / or the number of non-target objects (e.g., N+1) are increased to increase the training difficulty. This process is repeated to continuously improve the training effect.

[0110] In yet another embodiment, the training task may or may not be suppressed, but may include an upgraded training task.

[0111] In the upgraded execution training task, there are M (M≥2) different target objects (e.g., 3 different fruits, in the order of apple, banana and pineapple). First, the 3 fruits in the order are displayed in the observable scene (the presentation time is limited, e.g. 3 seconds). Then, each target object is randomly displayed once or multiple times. The target objects displayed in the order are called ordered objects, and the target objects displayed out of order are called unordered objects.

[0112] In this scenario, there are no target objects (whether ordered or unordered) or non-target objects in the observable scene (if the suppression training task is also included), so each time the second instruction is detected, a multi-action error is recorded.

[0113] The instruction records during the display of ordered objects are the same as those for the target object, and the instruction records during the display of unordered objects are the same as those for the non-target object.

[0114] If a second instruction is detected once or multiple times when the distance between the ordered object and the training character is greater than the third preset distance threshold, a reaction error is recorded for each detection.

[0115] If one or more second instructions are detected during the period when the distance between the ordered object and the training character is not greater than the third preset distance threshold, only one correct response is recorded, and each additional detection is recorded as an over-action error.

[0116] If the second instruction is detected once or more during the display of non-ordered objects, a suppression error is recorded for each detection;

[0117] If the second instruction is not detected during the display of non-ordered objects, then a successful suppression is recorded.

[0118] In this scenario, the trainee needs to rely on working memory to remember the target objects and their order. For ordered objects, the trainee needs to send a second instruction at an appropriate time; for unordered objects and non-target objects, the trainee needs to control themselves from sending a second instruction, thereby further improving the trainee's attention.

[0119] In this embodiment, similarly, regardless of whether the target objects appear in sequence or not, when their distance from the circle on the movement path is greater than the fourth preset distance threshold (L4), they enter the observable scene as blind boxes. Only when the target object's distance from the circle on the movement path begins to fall below L4 is it displayed in its true form. In this case, the trainee needs to react quickly within a limited time.

[0120] At the end of the training, the number of correct responses and the number of incorrect responses were counted, and the correct response rate was calculated as follows: Correct response rate = (Number of correct responses / (Number of correct responses + Number of incorrect responses)) × 100%.

[0121] If the suppression training task is included, the number of times the suppression was correct and the number of times the suppression was incorrect are also counted, and the correct suppression rate is calculated as follows: Correct suppression rate = Number of times the suppression was correct / (Number of times the suppression was correct + Number of times the suppression was incorrect) × 100%.

[0122] In one embodiment, a task that includes an attention training task, an upgraded executive training task, and an inhibition training task is called a working memory training task (or advanced course).

[0123] In this embodiment, the correct response rate and correct inhibition rate of the trainee in previous training are first obtained. During the current training process, the number of target objects (e.g., M+1) and / or the number of non-target objects (e.g., N+1) are increased to increase the training difficulty. This process is repeated to continuously improve the training effect.

[0124] In one embodiment of this application, only one object (blind box, target object, or non-target object) is displayed in the observable scene at a time. The next object will only be displayed in the observable scene after the previous object has disappeared. Furthermore, if the first instruction and the second instruction are the same, obstacles are not displayed simultaneously as blind boxes, target objects, or non-target objects.

[0125] In some embodiments of this application, using, for example Figure 4 The process is trained, specifically:

[0126] S1, Real-time EEG Data Acquisition

[0127] Using a C / S system architecture that combines a wearable EEG data acquisition device based on brain-computer interface, a mobile terminal (tablet or smartphone), and a server, trainers' EEG signal data can be collected in real time.

[0128] S2, EEG data processing

[0129] S21, Data preprocessing: Perform filtering from 1Hz to 35Hz;

[0130] S22, Feature Extraction: Spectral analysis of EEG data is performed using Fourier transform, and the power spectral density of different frequency bands of alpha waves (8-13Hz) and beta waves (13-35Hz) is calculated.

[0131] S23, Attention Value Calculation: Select attention-related EEG data features (such as the power spectral density of beta waves and alpha waves) to calculate (beta wave power spectral density / alpha wave power spectral density) to obtain the specific value Y(t) for the trainee at time point t. Based on the existing EEG dataset of N trainees in the database (e.g., 1000 datasets), normalize Y(t) to a value in the range [0,1], then amplify it by 100 times to convert it into an attention value A(t) in the range [0,100].

[0132] S3, EEG biofeedback therapy, includes three courses: beginner, intermediate, and advanced. Regardless of the course type, all courses include attention intensity training tasks.

[0133] The beginner course only includes attention intensity training tasks;

[0134] In addition to attention intensity training tasks, intermediate courses also include execution training tasks, and further include inhibition training tasks. Execution training tasks and inhibition training tasks are collectively referred to as execution and inhibition training tasks.

[0135] In addition to attention intensity training tasks, advanced courses also include upgraded executive training tasks, further upgraded executive training tasks, and even further upgraded inhibition training tasks. The upgraded executive training tasks and inhibition training tasks are collectively referred to as working memory training tasks.

[0136] One embodiment of this application also provides an electronic device and a readable storage medium.

[0137] Figure 5 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of this application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the application described and / or claimed herein.

[0138] like Figure 5 As shown, device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 802 or a computer program loaded from storage unit 808 into random access memory (RAM) 803. RAM 803 may also store various programs and data required for the operation of device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via bus 804. Input / output (I / O) interface 805 is also connected to bus 804.

[0139] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of monitors, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0140] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the attention training method described above. For example, in some embodiments, the attention training method can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed on device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the attention training method described above can be performed. Alternatively, in other embodiments, the computing unit 801 can be configured to perform the attention training method by any other suitable means (e.g., by means of firmware).

[0141] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0142] The program code used to implement the methods of this application may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0143] In the context of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0144] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0145] The systems and technologies described herein can be implemented in computing systems that include back-end components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0146] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0147] The system, device, or medium of this application is based on real-time acquired EEG data and can be used in conjunction with a wearable EEG data acquisition device.

[0148] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this application can be achieved, and this is not limited herein.

[0149] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An attention training system based on a brain-computer interface, characterized in that, Includes the following modules: The EEG signal data receiving and processing module is used to receive EEG signal data of the trainee measured in real time based on the brain-computer interface, perform filtering processing from 1Hz to 35Hz, and convert the EEG signal data into attention values. A visualization module is used to provide a training character and an observable scene, wherein the training character is located at a certain position in the observable scene. A training character control module, connected to the EEG signal data receiving and processing module and the visualization module, is used to set the movement speed of the training character according to the attention value, and the training character moves relative to the observable scene at the movement speed along the movement path; The training function control module is used to set P obstacles in front of the direction of movement of the training character, where P ≥ 1. The distance detection module is used to detect the distance between the training character and any one of the obstacles. The instruction recognition module is used to recognize the first instruction; The judgment module, connected to the distance detection module, the training function control module, the instruction recognition module, and the training role control module respectively, is used to continuously detect the existence of a first instruction when the distance between the training role and any of the obstacles is a first preset distance threshold, until the first instruction is detected or the training time ends, and is also used to: If the first instruction is detected, the training character continues to move at the specified speed, unaffected by the obstacle. If the first instruction is not detected until the distance between the training character and the obstacle reaches a second preset distance threshold, the training character's movement speed is set to 0 until the first instruction is detected. Then, the current attention value is used to reset the training character's movement speed, allowing the training character to continue moving without being affected by the obstacle. The instruction recognition module is also used to recognize a second instruction; the training function control module is also used to display M target objects at intervals in the observable scene, where M≥1, and during the movement of the training character, each of the target objects first moves relatively closer to the training character and then moves relatively further away from it. The distance detection module is also used to detect the distance between the training character and any of the target objects. The judgment module is also used to continuously detect the existence of a second instruction throughout the entire training time and perform the following recording operations: If the second instruction is detected once or more while the target object is not displayed, a multi-action error is recorded for each detection. If the second instruction is detected once or multiple times during the period when the target object is displayed but the distance between the target object and the training character is greater than a third preset distance threshold, then a reaction error is recorded for each detection. If the second instruction is detected once or multiple times during the period when the target object is displayed and the distance between the target object and the training character is not greater than the third preset distance threshold, only one correct response is recorded, and each additional detection is recorded as an over-action error.

2. The attention training system according to claim 1, characterized in that, The training function control module is also used to display N non-target objects at intervals in the observable scene, where N≥1. During the movement of the training character, each of the non-target objects moves closer to the training character and then moves further away from it. The judgment module is also used to complete the following records: If the second instruction is detected once or more during the period when the target object and the non-target object are not displayed, a multi-action error is recorded for each detection. If the second instruction is detected once or more during the display of the non-target object, a suppression error is recorded for each detection; If the second instruction is not detected during the display of the non-target object, then a successful suppression is recorded.

3. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to perform an attention training method including the following steps: The brainwave signal data of the trainee, measured in real time via a brain-computer interface, is obtained, filtered at 1Hz to 35Hz, and then converted into attention values. A training character and an observable scene are provided. The training character is located at a certain position in the observable scene. The movement speed of the training character is set according to the attention value. The training character moves relative to the observable scene along the movement path at the movement speed. P obstacles, P ≥ 1, are set along the movement path of the training character. When the distance between the training character and any one of the obstacles is a first preset distance threshold, continuous detection of the presence of a first command begins until the first command is detected or the training time ends. If the first instruction is detected, the training character continues to move at the specified speed, unaffected by the obstacle. If the first instruction is not detected until the distance between the training character and the obstacle reaches a second preset distance threshold, the training character's movement speed is set to 0 until the first instruction is detected. Then, the current attention value is used to reset the training character's movement speed, ensuring the training character is no longer affected by the obstacle and continues moving. Throughout the training time, the presence of a second instruction is continuously detected. M target objects are displayed at intervals in the observable scene, where M≥1. During the movement of the training character, each target object first approaches the training character and then moves away from it. If the second instruction is detected once or more while the target object is not displayed, a multi-action error is recorded for each detection. If the second instruction is detected once or multiple times during the period when the target object is displayed but the distance between the target object and the training character is greater than a third preset distance threshold, then a reaction error is recorded for each detection. If the second instruction is detected once or multiple times during the period when the target object is displayed and the distance between the target object and the training character is not greater than the third preset distance threshold, only one correct response is recorded, and each additional detection is recorded as an over-action error.

4. The electronic device according to claim 3, characterized in that, In the observable scene, N non-target objects are also displayed at intervals, where N≥1. During the movement of the training character, each of the non-target objects moves closer to the training character and then moves further away from it. If the second instruction is detected once or more during the period when the target object and the non-target object are not displayed, a multi-action error is recorded for each detection. If the second instruction is detected once or more during the display of the non-target object, a suppression error is recorded for each detection; If the second instruction is not detected during the display of the non-target object, then a successful suppression is recorded.

5. The electronic device according to claim 3 or 4, characterized in that, M ≥ 2, where the M target objects are all different. In the observable scene, the M target objects are first displayed in sequence for a period of time, which is 2~5 seconds. Then, each target object is randomly displayed once or multiple times. Target objects displayed in sequence are called ordered objects, and target objects displayed out of sequence are called unordered objects. If the second instruction is detected once or more while the target object is not displayed, a multi-action error is recorded for each detection. If the second instruction is detected once or multiple times when the ordered object is displayed but the distance between the ordered object and the training character is greater than the third preset distance threshold, then a reaction error is recorded for each detection. If the second instruction is detected once or multiple times during the period when the sequential objects are displayed and the distance between the sequential objects and the training character is not greater than the third preset distance threshold, only one correct response is recorded, and each additional detection is recorded as an over-action error. If the second instruction is detected once or more during the display of the non-ordered object, a suppression error is recorded for each detection; If the second instruction is not detected during the display of the non-ordered object, a successful suppression is recorded.

6. The electronic device according to claim 3 or 4, characterized in that, The EEG signal data is subjected to spectral analysis by Fourier transform, and the power spectral density of different frequency bands is calculated. The attention value is then obtained based on the power spectral density.

7. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform an attention training method including the following steps: The brainwave signal data of the trainee, measured in real time via a brain-computer interface, is obtained, filtered at 1Hz to 35Hz, and then converted into attention values. A training character and an observable scene are provided. The training character is located at a certain position in the observable scene. The movement speed of the training character is set according to the attention value. The training character moves relative to the observable scene along the movement path at the movement speed. P obstacles, P ≥ 1, are set along the movement path of the training character. When the distance between the training character and any one of the obstacles is a first preset distance threshold, continuous detection of the presence of a first command begins until the first command is detected or the training time ends. If the first instruction is detected, the training character continues to move at the stated speed, unaffected by the obstacle. If the first instruction is not detected until the distance between the training character and the obstacle reaches a second preset distance threshold, the movement speed of the training character is set to 0. Once the first instruction is detected, the movement speed of the training character is reset using the current attention value, so that the training character is no longer affected by the obstacle and continues to move. Throughout the training time, the presence of a second instruction is continuously detected. M target objects are displayed at intervals in the observable scene, where M≥1. During the movement of the training character, each target object first approaches the training character and then moves away from it. If the second instruction is detected once or more while the target object is not displayed, a multi-action error is recorded for each detection. If the second instruction is detected once or multiple times during the period when the target object is displayed but the distance between the target object and the training character is greater than a third preset distance threshold, then a reaction error is recorded for each detection. If the second instruction is detected once or multiple times during the period when the target object is displayed and the distance between the target object and the training character is not greater than the third preset distance threshold, only one correct response is recorded, and each additional detection is recorded as an over-action error.

8. The non-transitory computer-readable storage medium according to claim 7, characterized in that, In the observable scene, N non-target objects are also displayed at intervals, where N≥1. During the movement of the training character, each of the non-target objects moves closer to the training character and then moves further away from it. If the second instruction is detected once or more during the period when the target object and the non-target object are not displayed, a multi-action error is recorded for each detection. If the second instruction is detected once or more during the display of the non-target object, a suppression error is recorded for each detection; If the second instruction is not detected during the display of the non-target object, then a successful suppression is recorded.

9. The non-transitory computer-readable storage medium according to claim 7 or 8, characterized in that, M ≥ 2, where the M target objects are all different. In the observable scene, the M target objects are first displayed in sequence for a period of time, which is 2~5 seconds. Then, each target object is randomly displayed once or multiple times. Target objects displayed in sequence are called ordered objects, and target objects displayed out of sequence are called unordered objects. If the second instruction is detected once or more while the target object is not displayed, a multi-action error is recorded for each detection. If the second instruction is detected once or multiple times when the ordered object is displayed but the distance between the ordered object and the training character is greater than the third preset distance threshold, then a reaction error is recorded for each detection. If the second instruction is detected once or multiple times during the period when the sequential objects are displayed and the distance between the sequential objects and the training character is not greater than the third preset distance threshold, only one correct response is recorded, and each additional detection is recorded as an over-action error. If the second instruction is detected once or more during the display of the non-ordered object, a suppression error is recorded for each detection; If the second instruction is not detected during the display of the non-ordered object, a successful suppression is recorded.

10. The non-transitory computer-readable storage medium according to claim 7 or 8, characterized in that, The EEG signal data is subjected to spectral analysis by Fourier transform, and the power spectral density of different frequency bands is calculated. The attention value is then obtained based on the power spectral density.

Images