ADHD neural feedback training system and method based on EEG multi-person cooperation

Abstract

The invention belongs to the technical field of mixed reality. According to the ADHD neural feedback training system and method based on EEG multi-person cooperation, intelligent car cross-country adventure serves as the background, a rich personalized MR scene is constructed, an intelligent car is controlled to run along an autonomously-planned walking route through attention so as to conduct neural feedback training, a user can choose different control modes to play together by one or more persons, and the user experience is improved. The low-cost EEG equipment is used for obtaining the electroencephalogram signals of the users, the attention level of each user is calculated to control the speed of the intelligent trolley, corresponding feedback is provided by using the MR effect according to the attention level of each user, and the neural feedback training process is more effective.

Description

Technical Field

[0001] The present invention relates to the field of mixed reality technology, and in particular to an ADHD neurofeedback training system and method based on EEG multi-person collaboration. Background Art

[0002] The statements in this section merely provide background art related to the present invention and do not necessarily constitute prior art.

[0003] Mixed Reality (MR) is a technology that combines virtual information with the real world, and is widely used, especially on mobile device clients. Through the camera, sensor and screen of a smartphone or tablet, MR technology can overlay virtual elements on the user's real field of view, enhancing the perception and interactive experience of the surrounding environment. Users can see real-time virtual images merged with real scenes on mobile device clients, thus gaining a more intuitive and rich experience. This technology is widely used in games, navigation, shopping, education and other fields, not only providing users with innovative ways of interaction, but also greatly enhancing the immersion and emotional communication of the user experience.

[0004] EEG is a method of recording brain activity using electrophysiological indicators. When the brain is active, the postsynaptic potentials of a large number of neurons occur synchronously and are summed up. EEG records the changes in electric waves during brain activity and is a general reflection of the electrophysiological activity of brain nerve cells in the cerebral cortex or scalp surface. EEG equipment is a biological amplifier that measures EEG signals. It collects physiological signals from the human head through EEG sensors, processes and analyzes and records the signals after amplification and filtering, and displays, records and transmits them based on the analysis results. In recent years, with the continuous advancement of microelectronics technology, medical signal processing technology, electrophysiological technology, etc., the stability, reliability and portability of EEG equipment have been greatly improved.

[0005] Neurofeedback training is a non-invasive therapy often used to help people with attention deficit hyperactivity disorder (ADHD) improve their symptoms. Through real-time monitoring and feedback of the brain's electrical activity, patients can learn how to self-regulate specific brainwave patterns to enhance focus and self-control. During training, patients often receive immediate feedback through on-screen games or tasks, which helps them understand when they have achieved their ideal brainwave state. Over time, this increased ability to self-regulate can significantly improve attention, impulse control, and behavior management in people with ADHD. Neurofeedback training offers a drug-free intervention, providing an additional option for patients and families seeking alternative treatment options.

[0006] The inventors have found that there are currently some technical solutions based on EEG neurofeedback training that help ADHD children with rehabilitation training through various interactive methods. However, the problems existing in the current ADHD rehabilitation training system are mainly manifested in:

[0007] (1) The training method in the existing neurofeedback training system is very boring. It simply gives pictures or prompts to let users concentrate and give feedback; (2) The existing neurofeedback training system equipment connection is complicated, and generally requires users to sit in front of the computer for a long time. Users will have many inconveniences when using the system, and it cannot be ported to the mobile device client, making it difficult to conduct rehabilitation training at home; (3) The existing neurofeedback training system can only be used by one person, and parents cannot participate in the training of their children. Summary of the invention

[0008] In order to address the deficiencies of the prior art, the present invention provides an ADHD neurofeedback training system and method based on EEG multi-person collaboration, which takes the off-road adventure of a smart car as the background, constructs a rich personalized MR scene, and conducts neurofeedback training by controlling the smart car to travel along an autonomously planned walking route through attention. Users can choose different control modes to play together alone or in groups, and use low-cost EEG equipment to obtain the user's EEG signals, calculate the attention level of each user to control the speed of the smart car, and use MR effects to provide corresponding feedback according to the attention level of each user, making the neurofeedback training process more effective.

[0009] In order to achieve the above object, the present invention adopts the following technical solution:

[0010] In a first aspect, the present invention provides an EEG-based multi-person collaborative ADHD neurofeedback training system.

[0011] An ADHD neurofeedback training system based on EEG multi-person collaboration, comprising: a mobile terminal, a server, a first EEG signal acquisition device, a second EEG signal acquisition device and an intelligent car, wherein the first EEG signal acquisition device and the second EEG signal acquisition device are both connected to the server, the server is respectively connected to the mobile terminal and the intelligent car for communication, and the mobile terminal is connected to the intelligent car for communication;

[0012] The server is used to generate a relevant walking route after processing the scene image uploaded by the mobile terminal, and feed it back to the mobile terminal, so that the mobile terminal can model according to the walking route, and the modeled virtual vehicle model is bound to the real position of the smart car collected in real time by the mobile terminal;

[0013] The server is used to calculate attention according to the EEG signals of the first EEG signal acquisition device and the second EEG signal acquisition device, and to control the speed of the smart car in combination with the task mode selected by the user.

[0014] As a further limitation of the first aspect of the present invention, the mobile terminal includes: a theme selection and model generation module, a scene arrangement module, an EEG data interactive feedback module and a communication module;

[0015] Theme selection and model generation module includes: the user selects the theme scene, the user takes a photo of the pasted route and uploads it, and the user modifies the generated model;

[0016] The scene layout module generates the corresponding scene model according to the scene theme selected by the user, and supports the user to place the theme-related model by aligning the coordinates and clicking a button;

[0017] The EEG data interactive feedback module provides feedback on the attention of the two training participants in a visual form;

[0018] The communication module is used to establish communication between the mobile terminal and the server.

[0019] As a further limitation of the first aspect of the present invention, the task mode includes: a joint force mode and a division of labor mode;

[0020] In the joint force mode, the speed of the smart car is: (average value of each user's attention / 100)*V, where V is the limit speed of the smart car in cm / s;

[0021] In the division of labor mode, the attention of the first user is used to control the start and stop of the smart car. If the attention of the first user is less than the set threshold, the smart car will not start regardless of the attention of the second user. If the attention of the first user is greater than or equal to the set threshold, the smart car will start, and the speed of the smart car is controlled by the attention of the second user, specifically: (the attention value of the second user / 100)*V.

[0022] As a further limitation of the first aspect of the present invention, the basic image for generating the walking route is derived from hand-drawing or tape arrangement, including a scene route map of a desired construction drawn by a user on paper, or a scene route map pasted with tape in an actual venue;

[0023] The mobile terminal uploads the actual route map captured by the camera to the server. The server supports manual or automatic image distortion correction, corrects the distortion of the actual route map, processes the corrected image, extracts the walking route, and encodes it and transmits it back to the mobile terminal.

[0024] As a further limitation of the first aspect of the present invention, the mobile terminal supports users to select corresponding scene themes, and the mobile terminal models MR scene models in virtual space according to the returned codes. The mobile terminal supports users to place MR scene models at specific locations. After the MR scene model is built, it supports the selection of spatial coordinates through the mobile device client, and places a small model related to the selected scene theme at the specified location.

[0025] As a further limitation of the first aspect of the present invention, the mobile terminal calls the camera to identify the position of the smart car. After successful identification, the virtual vehicle model in the corresponding MR scene model is bound to the identified smart car. The virtual vehicle model supports replacement according to preference.

[0026] As a further limitation of the first aspect of the present invention, providing feedback on the attention of two training participants in a visual form includes: UI feedback and MR feedback;

[0027] UI feedback is achieved through an energy bar. In the training scenario, when the user's attention is low, the corresponding energy bar changes to a set color to prompt the user that the attention is low.

[0028] MR feedback is displayed through different special effects of the speed ring. When the user's attention value is greater than or equal to threshold A and less than or equal to threshold B, the transmission speed is 0, and the smart car decelerates, and the speed ring displays the first setting effect; when the user's attention is greater than threshold B and less than or equal to threshold C, a medium speed is transmitted, and when the smart car runs at a medium speed, the speed ring displays the second setting effect; when the user's attention is greater than threshold C, a higher speed is transmitted, and the smart car runs at a high speed, and the speed ring will display the third setting effect.

[0029] As a further limitation of the first aspect of the present invention, during the training process, each user is supported to adjust his or her own attention and conduct team communication and coordination according to the feedback results of the energy bar and the smart car; after the training, the user is supported to view the results of this training, which include the average attention value, the time distribution of the attention level, the total mileage of the smart car and the number of placed objects.

[0030] In a second aspect, the present invention provides an EEG-based multi-person collaborative ADHD neurofeedback training method.

[0031] An ADHD neurofeedback training method based on EEG multi-person collaboration, using the ADHD neurofeedback training system based on EEG multi-person collaboration described in the first aspect of the present invention, includes the following process:

[0032] The user selects the role and scene theme;

[0033] The user can freely design the walking route of the smart car within a given space according to his own ideas. After the walking route design is completed, the mobile terminal takes a photo of the walking route and uploads it to the server for analysis and processing. The server analyzes the image, extracts the walking route from it, and returns it to the mobile terminal. After receiving the data, the mobile terminal generates a corresponding MR scene model according to the previously selected scene theme, and the user puts it into the real world and puts the smart car in the real walking route. At this time, the mobile terminal automatically captures the position of the smart car and generates a virtual vehicle model in the virtual space to cover the real smart car. The virtual vehicle model is freely selected by the user;

[0034] There is a halo under the virtual vehicle model. During the training process, the halo's special effects are adjusted in real time according to the speed of the smart car. Users can freely place small models related to the theme in the virtual space to improve the vividness of the training scene.

[0035] Two users wear the first EEG signal acquisition device and the second EEG signal acquisition device respectively, turn on the server to start formal training, and after the "Start Training" button is clicked, the countdown starts automatically, and the training officially begins;

[0036] During the training process, the raw EEG data is transmitted to the computer server. After receiving the raw EEG data, the server calculates the real-time attention value of each user and controls the speed of the smart car according to the task mode selected by the user.

[0037] As a further limitation of the second aspect of the present invention, the smart car uses a front camera to achieve a line-following function, and adjusts the wheel speed in real time according to the received speed, thereby using attention to control the speed of the smart car.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] 1. The present invention innovatively proposes an ADHD neurofeedback training method based on EEG multi-person collaboration. Users do not have to wear heavy and expensive head-mounted display devices, but only need a portable terminal device (such as a mobile phone, tablet, etc.) to participate in the training process. It adopts a multi-person collaborative mixed reality interaction method, with the background of inviting participants to plan and participate in competitions. The game has shared collective task goals and measures the collective game status for real-time game adjustment, which helps to stimulate the motivation and behavior of multi-person collaboration and enhance the cohesion of the team and the empathy of individuals.

[0040] 2. The present invention improves the existing neurofeedback training and is no longer limited to simple image content on the computer screen. It organically combines the virtual world and the real world through the camera of the mobile terminal device, which not only makes the entire training process more personalized, but also helps to enhance the sustainability of user training.

[0041] 3. During the task process, each team member of the present invention should not only consider his own attention and relaxation, but also observe the attention and relaxation of other team members. During the game, the team members who are in poor condition can be reminded to improve the collective attention of the team, and the cooperation efficiency of team members can be improved through mutual communication and cooperation among members.

[0042] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0044] Figure 1 A diagram of the hardware structure provided by an embodiment of the present invention;

[0045] Figure 2 A schematic diagram of the mobile platform APP workflow provided by an embodiment of the present invention;

[0046] Figure 3 A schematic diagram of the BrainLink Pro EEG intelligent hardware device worn by a user provided in an embodiment of the present invention;

[0047] Figure 4 An example diagram for users to paste paths with help;

[0048] Figure 5 An example diagram of a user using an application to collect a paste path image;

[0049] Figure 6 Generate and launch example diagrams of the track master model for users with help;

[0050] Figure 7 An example diagram of a user using a mobile device client to run an application to experience a scenario;

[0051] FIG8( a ) is a diagram showing an example of scene theme selection in a specific embodiment provided by an embodiment of the present invention;

[0052] FIG8( b ) is an example diagram of photographing an actual track according to a specific embodiment of the present invention;

[0053] FIG8( c ) is an example diagram of a scene generation effect applied to a specific embodiment provided by an embodiment of the present invention;

[0054] FIG8( d) is a diagram showing an example of the placement of a scene theme model applied to a specific embodiment provided by an embodiment of the present invention;

[0055] FIG8( e ) is an example diagram of an MR vehicle model applied to a specific embodiment provided by an embodiment of the present invention;

[0056] FIG8( f) is an example diagram of an attention level feedback UI applied to an execution practice scenario of a specific embodiment provided by an embodiment of the present invention;

[0057] FIG8( g ) is a diagram showing corresponding special effects examples of an MR car model applied to a training scenario in a specific embodiment provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0058] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0059] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0060] In this implementation, an ADHD neurofeedback training system based on EEG equipment is proposed to construct a training environment that combines virtuality and reality. This system not only uses the smart car to provide users with a rich physical interaction experience, but also uses mixed reality technology to provide users with a virtual space where they can create freely, which greatly optimizes the user's training experience and helps to improve the sustainability of user training. In the process of arranging the virtual space, users can communicate and negotiate with each other to create a common environment, which is conducive to improving users' comprehensive abilities such as social skills, rather than just focusing on improving attention ability. During the training process, each user not only needs to examine his or her own attention level, but also the attention level of his or her partners. The system will adjust the speed of the smart car according to the previously set mode, so each user needs to work together to better complete the task.

[0061] The system includes: a computer server (i.e., a server), a mobile device client (i.e., a mobile terminal), a TurboPi AI smart car, and two EEG signal acquisition devices (BrainLink, i.e., a first EEG signal acquisition device and a second EEG signal acquisition device). The computer server is respectively communicated with the smart car, the EEG signal acquisition device, and the mobile device client, and the mobile device client is communicated with the smart car.

[0062] In this implementation, all devices are in the same local area network. The local area network is opened by the smart car to provide a data transmission channel. Two sets of BrainLink EEG smart hardware devices are connected to the computer server via Bluetooth and exchange data.

[0063] Specifically, the mobile device client includes a theme selection and model generation module, a scene arrangement module, an EEG data interactive feedback module and a communication module.

[0064] The theme selection and model generation module includes: a user selecting a theme scene, a user taking a photo of the pasted route and uploading it, and a user correcting the generated model. In these three scenes, the users participating in the training complete the virtual modeling of the path pasted in the actual scene with the help of relevant personnel.

[0065] The scene arrangement module is configured to: generate a corresponding scene model in the APP of the mobile device client based on the Vuforia architecture according to the scene theme selected by the test user, and allow the user to place the theme-related model by aligning the coordinates and clicking a button.

[0066] The EEG data interactive feedback module is configured to provide feedback on the attention of the two training participants in a visual form. The feedback is divided into UI feedback and MR feedback. The UI feedback is implemented through the "energy bar" as shown in Figure 8(f). In the training scenario, if the attention of user 1 is low, the corresponding "energy bar" will turn red, indicating that the user's attention is low.

[0067] MR feedback is displayed through different special effects of the "speed ring" in Figure 8(g). When the user's attention value is greater than or equal to threshold A and less than or equal to threshold B, the transmission speed is 0, and the smart car slows down, and the speed ring shows an "icing" effect; when the user's attention is greater than threshold B and less than or equal to threshold C, a medium speed is transmitted, and when the smart car runs at a medium speed, the speed ring shows a "flash" effect; when the user's attention is greater than threshold C, a higher speed is transmitted, the smart car runs at a high speed, and the speed ring will show a "star halo" effect.

[0068] The communication module is used to connect the communication between the APP and the server, including establishing a connection, sending data, parsing data, etc. The server has data processing and forwarding functions to achieve direct communication and message transmission with the APP and the smart car. Users of this system do not have to worry about the distance between team users. Using the communication module, they can control the smart car in the local area network.

[0069] In this implementation, the APP is installed on any mobile device client, and the device's camera and WIFI functions need to be called. When the user plays and experiences this training system, the user needs to wear an EEG signal acquisition device to collect and transmit the user's EEG information to the server for attention assessment.

[0070] The EEG signal detection device uses two EEG devices that communicate with the server. The EEG devices are used to provide the user's brain wave data. When the human brain functions normally, brain neurons will release neurotransmitters to transmit information. The process of neurons releasing and transmitting neurotransmitters is an electrochemical reaction process, which will produce weak brain currents called brain waves. The user's THETA distraction wave, SMR attention wave and Hi-beta tension wave are obtained through the EEG device, and then the built-in eSense algorithm is used to analyze the length of the band to analyze the user's attention and relaxation.

[0071] The EEG device first amplifies the original brain wave signal and filters out the interference caused by environmental noise and muscle tissue movement. The eSense algorithm is applied to the processed signal to calculate the quantized eSense parameter value. The eSense algorithm represents the results of the analysis and processing in a quantized numerical form. The working principle of the eSense algorithm is to perform fast Fourier transform on the collected EEG data, and then filter the frequency according to the needs to obtain alpha waves and beta waves, and finally perform power spectrum analysis, select the basic reference value, and complete normalization.

[0072] Before the formal training begins, users can design training scenarios on their own. Users can paste smart walking routes according to their own ideas within a given space. After the walking routes are pasted, the system generates a corresponding virtual vehicle model based on the actual walking routes. The virtual vehicle model supports a high degree of customization. Users can independently select the model theme and the virtual vehicle model of the smart car, and can also freely place small models related to the theme on the virtual vehicle model.

[0073] After the training scene is arranged, formal training begins. Each user can start training after wearing the EEG device. At this time, the system will convert the attention value of each user into the speed of the smart car in real time according to the previously set task mode after certain processing. This process is completely transparent to the user. During the training process, the user's attention will be fed back to the user in real time in the form of an energy bar so that the user can make corresponding adjustments. Throughout the training, the user's only task is to do his best to improve his and his team's attention and make the smart car run farther within the given 3 minutes.

[0074] After the training is completed, the system will automatically record various data during the training process, including the time distribution of each user's attention, the mileage of the smart car, etc., so that users and researchers can conduct further analysis.

[0075] Specifically, Figure 2 As shown, the following steps are included:

[0076] (1) System introduction and theme selection: In this step, the user will first have an overall understanding of the background and functions of the system. The user can select the role and scene theme in this system, as shown in Figure 8(a).

[0077] (2) Training scenario design: First, users can freely design intelligent walking routes within a given space according to their own ideas. These routes can be in the shape of a quadrilateral, a five-pointed star, or a heart (e.g. Figure 4 After the walking route design is completed, the user uses the mobile device client to take a photo of the walking route, as shown in Figure 8(b), and uploads it to the computer server for analysis (as shown in Figure 8(b)). Figure 5 The computer server uses perspective transformation, threshold recognition and other technologies to analyze the image, extract model data from it, as shown in Figure 8(c), and returns it to the mobile device client. After receiving the data, the mobile device client generates a corresponding MR scene model based on the previously selected scene theme, and the user puts it into the real world (such as Figure 6 8(e)); then, place the smart car in the real walking route. At this point, the system will automatically capture the position of the smart car and generate a virtual vehicle model in the virtual space to cover the real smart car, as shown in Figure 8(e). The virtual vehicle model can be freely selected by the user and can be a pickup truck, police car, excavator, etc. There is a halo under the virtual vehicle model. During the training process, the system will adjust the special effects of the halo in real time according to the speed state of the smart car, as shown in Figure 8(g), which corresponds to low speed, medium speed and high speed from left to right; after that, the user can freely place small models related to the theme in the virtual space, as shown in Figure 8(d), making the training scene more vivid and interesting.

[0078] (3) Preparation before formal training: The user correctly wears the EEG signal acquisition device, such as Figure 3 As shown, start the server of the smart car, perform connection test and function test, and after the test is correct, enter the formal training.

[0079] (4) Formal training: Click the "Start Training" button, and the system will automatically start a three-minute countdown, and the training will officially begin. During the training, the BrainLink device collects the user's original EEG data and transmits it to the computer server. After receiving the original EEG data, the server calculates the real-time attention value of each user, and converts the attention value into the corresponding smart car speed according to the pre-set conversion formula, and sends it to the smart car;

[0080] The corresponding relationship between the speed of the smart car and the user's attention value is:

[0081] If it is the combined force mode, the speed of the smart car is equal to: (average value of each user's attention / 100)*V, where V is the limit speed of the smart car in cm / s;

[0082] If it is a division of labor mode, the attention of user 1 (i.e. the first user) is used to control the start and stop of the smart car. If the attention of user 1 is less than the set threshold, the smart car will not start regardless of the attention of user 2 (i.e. the second user). If the attention of user 1 is greater than or equal to the set threshold, the smart car will start and the speed will be controlled by the attention of user 2, specifically: (user 2's attention value / 100)*V.

[0083] The smart car uses the front camera to realize the line-following function and adjusts the wheel speed of the smart car in real time according to the received speed, thereby realizing the function of controlling the speed of the smart car with attention. During the entire training process, the interface on the mobile device client will give users rich feedback in real time, including using the length and color of the energy bar to prompt the user's attention level (as shown in Figure 8(f)) and using halo effects to prompt the status of the smart car.

[0084] (5) End of training: After the system countdown ends for three minutes, the training stops and the system automatically records the user data during the training process, including raw EEG data, real-time attention value, and the total mileage of the smart car.

[0085] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An ADHD neurofeedback training system based on EEG multi-person collaboration, It is characterized in that It includes: a mobile terminal, a server, a first EEG signal acquisition device, a second EEG signal acquisition device and an intelligent car, wherein the first EEG signal acquisition device and the second EEG signal acquisition device are both connected to the server, the server is respectively connected to the mobile terminal and the intelligent car for communication, and the mobile terminal is connected to the intelligent car for communication; The server is used to generate a relevant walking route after processing the scene image uploaded by the mobile terminal, and feed it back to the mobile terminal, so that the mobile terminal can model according to the walking route, and the modeled virtual vehicle model is bound to the real position of the smart car collected in real time by the mobile terminal; The server is used to calculate attention according to the EEG signals of the first EEG signal acquisition device and the second EEG signal acquisition device, and to control the speed of the smart car in combination with the task mode selected by the user.

2. The EEG multi-person collaborative ADHD neurofeedback training system according to claim 1, characterized in that: The mobile terminal includes: a theme selection and model generation module, a scene arrangement module, an EEG data interactive feedback module and a communication module; Theme selection and model generation module includes: scenarios where the user selects a theme, where the user takes a photo of the pasted route and uploads it, and where the user modifies the generated model; The scene layout module generates the corresponding scene model according to the scene theme selected by the user, and supports the user to place the theme-related model by aligning the coordinates and clicking a button; The EEG data interactive feedback module provides feedback on the attention of the two training participants in a visual form; The communication module is used to establish communication between the mobile terminal and the server.

3. The EEG multi-person collaborative ADHD neurofeedback training system according to claim 1, characterized in that: The task mode includes: a joint force mode and a division of labor mode; In the joint force mode, the speed of the smart car is: (average value of each user's attention / 100)*V, where V is the limit speed of the smart car in cm / s; In the division of labor mode, the attention of the first user is used to control the start and stop of the smart car. If the attention of the first user is less than the set threshold, the smart car will not start regardless of the attention of the second user. If the attention of the first user is greater than or equal to the set threshold, the smart car will start, and the speed of the smart car is controlled by the attention of the second user, specifically: (the attention value of the second user / 100)*V.

4. The EEG multi-person collaborative ADHD neurofeedback training system according to claim 1, characterized in that: The basic image for generating the walking route comes from hand-drawing or tape layout, including the scene route map that the user draws on paper or the scene route map that is pasted with tape in the actual venue; The mobile terminal uploads the actual route map captured by the camera to the server. The server supports manual or automatic image distortion correction, corrects the distortion of the actual route map, processes the corrected image, extracts the walking route, and encodes it and transmits it back to the mobile terminal.

5. The EEG multi-person collaborative ADHD neurofeedback training system according to claim 1, characterized in that: The mobile terminal supports users to select corresponding scene themes. The mobile terminal models the MR scene model in the virtual space according to the transmitted codes. The mobile terminal supports users to place the MR scene model in a specific location. After the MR scene model is built, it supports the selection of spatial coordinates through the mobile device client, and places a small model related to the selected scene theme at the specified location.

6. The EEG multi-person collaborative ADHD neurofeedback training system according to claim 1, characterized in that: The mobile terminal uses the camera to identify the position of the smart car. After successful identification, the virtual vehicle model in the corresponding MR scene model is bound to the identified smart car. The virtual vehicle model can be replaced according to preference.

7. The EEG-based multi-person collaborative ADHD neurofeedback training system according to claim 1, characterized in that: Provide feedback on the attention of two training participants through visual forms, including: UI feedback and MR feedback; UI feedback is achieved through an energy bar. In the training scenario, when the user's attention is low, the corresponding energy bar changes to a set color to prompt the user that the attention is low. MR feedback is displayed through different special effects of the speed ring. When the user's attention value is greater than or equal to threshold A and less than or equal to threshold B, the transmission speed is 0, and the smart car decelerates, and the speed ring displays the first setting effect; when the user's attention is greater than threshold B and less than or equal to threshold C, a medium speed is transmitted, and when the smart car runs at a medium speed, the speed ring displays the second setting effect; when the user's attention is greater than threshold C, a higher speed is transmitted, and the smart car runs at a high speed, and the speed ring will display the third setting effect.

8. The EEG multi-person collaborative ADHD neurofeedback training system according to claim 7, characterized in that: During the training process, each user is supported to adjust their attention and conduct team communication and coordination based on the feedback from the energy bar and the smart car; After the training is completed, users are supported to view the results of this training, which include the average attention value, the time distribution of the attention level, the total mileage of the smart car and the number of placed objects.

9. An EEG-based multi-person collaborative ADHD neurofeedback training method, characterized in that: The ADHD neurofeedback training system based on EEG multi-person collaboration according to any one of claims 1 to 8 comprises the following process: The user selects the role and scene theme; The user can freely design an intelligent walking route within a given space according to his own ideas. After the intelligent walking route is designed, the mobile terminal takes a photo of the walking route and uploads it to the server for analysis and processing. The server analyzes the image, extracts the intelligent walking route from it, and returns it to the mobile terminal. After receiving the data, the mobile terminal generates a corresponding MR scene model according to the previously selected scene theme, and the user puts it into the real world and puts the smart car in the real walking route. At this time, the mobile terminal automatically captures the position of the smart car and generates a virtual vehicle model in the virtual space to cover the real smart car. The virtual vehicle model is freely selected by the user; There is a halo under the virtual vehicle model. During the training process, the halo's special effects are adjusted in real time according to the speed of the smart car. Users can freely place small models related to the theme in the virtual space to improve the vividness of the training scene. Two users wear the first EEG signal acquisition device and the second EEG signal acquisition device respectively, turn on the server to start formal training, and after the "Start Training" button is clicked, the countdown starts automatically, and the training officially begins; During the training process, the raw EEG data is transmitted to the computer server. After receiving the raw EEG data, the server calculates the real-time attention value of each user and controls the speed of the smart car according to the task mode selected by the user.

10. The EEG-based multi-person collaborative ADHD neurofeedback training method according to claim 9, characterized in that: The smart car uses the front camera to achieve the line-following function, and adjusts the wheel speed in real time according to the received speed, thereby using attention to control the speed of the smart car.

Images