VR-based neurofeedback training system

Abstract

The application discloses a VR-based neural feedback training system, which comprises a host computer module, an electroencephalogram acquisition module, an electroencephalogram amplification module and a VR device, wherein the VR device comprises a VR visualization module and a VR helmet; the host computer module is used for determining a target training scheme; the electroencephalogram acquisition module is used for acquiring first electroencephalogram data and second electroencephalogram data of a target subject; the VR visualization module is used for determining first control instructions and second control instructions; the VR helmet is used for generating a target VR scene and target guide voice; the electroencephalogram amplification module is used for amplifying the first and second electroencephalogram data to obtain third and fourth electroencephalogram data; and the host computer module is further used for determining a target training effect according to the third and fourth electroencephalogram data and feeding back and adjusting the target VR scene according to the target training effect. The neural feedback treatment effect is improved by adopting the embodiment.

Description

Technical Field

[0001] This application relates to the field of medical technology, and in particular to a VR-based neurofeedback training system. Background Technology

[0002] Neurofeedback detects and extracts brain activity signals in real time and selectively provides visual or auditory feedback to the individual, allowing them to learn to autonomously regulate brain activity and change their cognition and behavior. Neurofeedback training is a safe, non-invasive brain-boosting method that has been widely used in the intervention of ADHD in children.

[0003] Currently, the unimodal feedback training used in the field of neurofeedback mainly uses two-dimensional image feedback, which has weak sensory stimulation, is easy to distract attention, lacks interactivity and fun, and results in poor patient immersion, thus leading to poor feedback therapy effects.

[0004] Therefore, how to improve the effectiveness of neurofeedback therapy has become an urgent problem to be solved. Summary of the Invention

[0005] This application provides a VR-based neurofeedback training system that improves the effectiveness of neurofeedback therapy.

[0006] In a first aspect, embodiments of this application provide a VR-based neurofeedback training system, the system comprising: a host computer module, an EEG acquisition module, an EEG amplification module, and a VR device, the VR device comprising: a VR visualization module and a VR headset, the host computer module communicating with the VR device, and the VR headset being worn on the head of a target subject, wherein:

[0007] The host computer module is used to acquire the target basic data and neurofeedback training objectives of the target subject; and to determine the target training scheme based on the target basic data and the neurofeedback training objectives; the target training scheme includes: a target VR scene and a target training task;

[0008] The EEG acquisition module is used to acquire the first EEG data of the target subject;

[0009] The VR visualization module is used to determine the first control command corresponding to the target VR scene and the second control command corresponding to the target training task.

[0010] The VR headset is used to generate the target VR scene according to the first control command; and to generate target guidance voice according to the second control command; the target guidance voice is used to guide the target subject to perform the target training task in the target VR scene.

[0011] The EEG acquisition module is also used to acquire the second EEG data of the target subject during the target training task.

[0012] The EEG amplification module is used to amplify the first EEG data and the second EEG data respectively to obtain the third EEG data and the fourth EEG data.

[0013] The host computer module is also used to determine the target training effect based on the third EEG data and the fourth EEG data; and to adjust the target VR scene based on the target training effect.

[0014] Secondly, embodiments of this application provide a VR-based neurofeedback training device, including the VR-based neurofeedback training system described in the first aspect.

[0015] Implementing this application will have the following beneficial effects:

[0016] As can be seen, the VR-based neurofeedback training system described in this application, on the one hand, effectively avoids the inefficiency of general solutions by combining the basic data and training objectives of the target subjects to customize exclusive VR scenes and training tasks; on the other hand, the system provides intuitive dynamic feedback through VR scenes, which makes it easier for subjects to perceive changes in their own neural activity compared to traditional two-dimensional images. Combined with guided voice to enhance operational understanding, it improves the subjects' focus on actively adjusting their neural state, thereby improving the effect of neurofeedback therapy. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the background art, the accompanying drawings used in the embodiments of this application or the background art will be described below.

[0018] Figure 1 This is an application scenario diagram of a VR-based neurofeedback training system provided in an embodiment of this application;

[0019] Figure 2 This is a schematic diagram of the structure of a VR-based neurofeedback training system provided in an embodiment of this application;

[0020] Figure 3 This is a schematic diagram of the structure of a VR device provided in an embodiment of this application;

[0021] Figure 4 This is a schematic diagram of a preset VR scene set provided in an embodiment of this application;

[0022] Figure 5 This is a flowchart illustrating a method for determining a target VR scene according to an embodiment of this application;

[0023] Figure 6 This is a flowchart of a method for determining the training effect of a target provided in an embodiment of this application;

[0024] Figure 7 This is a flowchart of a VR-based neurofeedback training system provided in an embodiment of this application;

[0025] Figure 8 This is a schematic diagram of the structure of a VR-based neurofeedback training device provided in an embodiment of this application. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0027] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0028] It should be understood that the term "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document indicates that the preceding and following related objects are in an "or" relationship. In the embodiments of this application, "multiple" refers to two or more.

[0029] In the embodiments of this application, "at least one item" or its similar expression refers to any combination of these items, including any combination of a single item or a plurality of items. "One or more" means one or more, while "multiple" means two or more. For example, "at least one item" of a, b, or c can represent the following seven cases: a, b, c; a and b; a and c; b and c; a, b, and c. Each of a, b, and c can be an element or a set containing one or more elements.

[0030] In this application, the term "connection" refers to various connection methods, such as direct connection or indirect connection, to achieve communication between devices. This application does not impose any limitations on this.

[0031] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0032] The following describes the relevant content, concepts, meanings, technical issues, technical solutions, and beneficial effects involved in the embodiments of this application.

[0033] First, let me explain some of the technical terms or phrases used in this application:

[0034] Neurofeedback training: a non-invasive closed-loop neuromodulation technology that collects and decodes the user's EEG signals in real time, and provides the user with core EEG indicators (e.g., heart rate variability, EEG power spectrum, etc.) in a visual form, guiding the user to actively regulate their own neural activity, thereby achieving the goal of treating mental illnesses (e.g., anxiety disorder, attention deficit disorder) or enhancing cognitive abilities (e.g., attention, working memory improvement).

[0035] VR (Virtual Reality): An immersive virtual environment built using computer technology. Through multi-source information fusion, interactive three-dimensional dynamic visuals, and physical behavior simulation, it allows users to have a "being there" sensory experience. Its core features are immersion, interactivity, and imagination.

[0036] VR headsets: The core hardware devices for realizing immersive VR experiences. They are typically equipped with high-definition displays, sensors (such as posture sensors and position tracking sensors), and audio components. When worn, they can isolate visual interference from the real environment and guide the user's vision and hearing into the virtual scene. They are the key interactive terminal connecting the user and the VR system.

[0037] Heart rate variability (HRV) refers to the minute variations in the time interval between consecutive heartbeats, reflecting the regulatory function of the autonomic nervous system (sympathetic and parasympathetic nervous systems) on the heart. HRV is a key indicator for assessing autonomic nervous system balance, which is responsible for regulating unconscious physiological functions such as heartbeat and respiration. Clinically, a higher HRV generally indicates stronger autonomic nervous system regulation and a more stable mental and physical state (e.g., relaxation and emotional stability); a lower HRV may be associated with anxiety disorders, excessive stress, cardiovascular disease, etc., suggesting excessive activation of the sympathetic nervous system (a state of tension).

[0038] HID (Human Interface Device Protocol) is a general protocol used for communication between computers and "human-computer interaction devices" (such as keyboards, mice, game controllers, EEG amplifiers, etc.), and is a sub-protocol of the USB protocol.

[0039] TCP (Transmission Control Protocol) is a connection-oriented, reliable network transmission protocol that operates at the transport layer of the OSI (Open Systems Interconnection Model).

[0040] DHCP (Dynamic Host Configuration Protocol) is a network protocol used to automatically assign IP addresses within a local area network.

[0041] UDP (User Datagram Protocol) is a connectionless network transport protocol that operates at the transport layer of the OSI model.

[0042] BDF (BioSemi Data Format): A standardized file format specifically designed for storing bioelectrical signals (such as electroencephalograms and electrocardiograms).

[0043] VR all-in-one devices: These typically run on an Android system and do not require an external computer or host. They have their own independent processor, memory, storage, and operating system. They can run VR applications independently and are characterized by high portability and simple deployment. They are suitable for neurofeedback training scenarios with moderate scene complexity requirements.

[0044] PCVR: A VR device that requires a wired or wireless connection to a computer to operate. It does not have independent computing power and relies on the computer's high-performance hardware to handle complex VR scene rendering and data processing. It can support complex virtual scenes with high resolution and high frame rate, and is suitable for training needs that require high immersion and scene complexity.

[0045] Please see Figure 1 , Figure 1 This is an application scenario diagram of a VR-based neurofeedback training system provided in this application embodiment. As can be seen, the host computer module in the VR-based neurofeedback training system (hereinafter referred to as the system) is connected to the VR device for communication, and the VR headset is worn on the head of the target subject. The system sends control commands to the VR device through the host computer module to drive the VR device to generate corresponding VR scenes, so that the target subject can immerse himself in observing the dynamic changes of the VR scene, understand the regulatory effect of his own neural activity, and then actively adjust his neural state. In this way, neurofeedback training of the target subject can be achieved.

[0046] Please see Figure 2 , Figure 2 This is a schematic diagram of a VR-based neurofeedback training system provided in an embodiment of this application; it can be seen that the system includes: a host computer module, an EEG acquisition module, an EEG amplification module, and a VR device; next, please refer to... Figure 3 , Figure 3 This is a schematic diagram of the structure of a VR device provided in an embodiment of this application. As can be seen, the VR device includes: a VR visualization module and a VR headset. The host computer module is communicatively connected to the VR device, and the VR headset is worn on the head of the target subject.

[0047] The host computer module is used to acquire the target basic data and neurofeedback training objectives of the target subject; and to determine the target training scheme based on the target basic data and the neurofeedback training objectives; the target training scheme includes: a target VR scene and a target training task;

[0048] In a specific embodiment, the target subject can be tested using medical testing equipment to obtain basic target data. For example, assuming the basic target data is blood pressure data, the medical testing equipment can be a blood pressure monitor. The blood pressure data of the target subject is measured using the blood pressure monitor. Then, the host computer module can read the basic target data from the medical testing equipment. Next, the target training expectation of the target subject can be obtained. For example, the target training expectation can be "hoping to alleviate anxiety", "hoping to reduce irritability when insomnia", "wanting to improve concentration time when studying", etc., without limitation. Then, the neurofeedback training goal is determined according to the target training expectation. For example, a preset mapping relationship between training expectations and training goals can be stored in advance. The neurofeedback training goal corresponding to the above target training expectation is determined based on the mapping relationship. For example, assuming the target training expectation is "hoping to alleviate anxiety", the neurofeedback training goal can be "enhancing frontal alpha wave power (enhancing relaxation state)". Then, the target training plan can be determined according to the basic target data and the neurofeedback training goal.

[0049] It should be explained that, in some embodiments, the target doctor may also manually input the target basic data and neurofeedback training target into the host computer module, where the target doctor is the doctor who treats the target subject.

[0050] Optionally, the host computer module can read the raw EEG signal output by the EEG amplifier via the HID protocol, convert the raw EEG signal into a voltage signal via digital-to-analog conversion, and record the voltage signal as a BDF format EEG file via a file stream. On the other hand, it can perform neurofeedback training on the target subjects according to the preset experimental settings.

[0051] Optionally, the VR visualization module supports adaptation to different brands of VR devices. For example, for stand-alone VR devices running Android, the VR visualization module can be packaged as an APK application; for PCVR devices that need to be connected to a computer, the VR visualization module can be packaged as an EXE desktop application.

[0052] Optionally, the host computer module and the VR device are connected via TCP protocol. Specifically, the system may include a router that uses DHCP protocol to dynamically assign IP addresses to the devices. Since the IP address may change each time the device is powered on, the host computer module needs to perform device discovery before establishing a TCP connection with the VR visualization module in the VR device. This process is based on UDP protocol, and the specific steps are as follows:

[0053] VR visualization module initialization: When enabled, two services are automatically started: a UDP address server (for receiving device discovery requests) and a TCP worker server (for subsequent neural feedback data transmission).

[0054] The host computer module initiates device discovery: After clicking the refresh button, the host computer module sends a UDP broadcast through the router within the local area network. The broadcast content includes its own IP address and port number.

[0055] VR visualization module response and information feedback: After the VR visualization module listens for a UDP broadcast, it sends a UDP unicast message to the host computer IP address contained in the broadcast, which contains its own IP address and TCP port number.

[0056] Connection establishment and state switching: After the host computer module obtains the IP address and TCP port of the VR visualization module, it can establish a TCP connection and start the neural feedback process; during the operation of the TCP server, the UDP address server is automatically closed to avoid repeated connection establishment.

[0057] Optionally, the target basic data may include: target age, target physiological parameters, and target disease; in determining the target training scheme based on the target basic data and the neurofeedback training target, the host computer module is specifically used to perform the following steps:

[0058] A1. Determine the reference training task set corresponding to the target disease; the reference training task set includes a training tasks; a is an integer greater than 1;

[0059] A2. Determine the reference attention duration corresponding to the target age;

[0060] A3. Determine the attention-influencing factors corresponding to the target disease;

[0061] A4. Adjust the reference attention duration according to the attention influencing factor to obtain the target attention duration;

[0062] A5. Determine the target physical strength value corresponding to the target physiological parameter;

[0063] A6. Determine the target training task based on the target physical strength value, the target attention duration, the a training tasks, and the neurofeedback training target;

[0064] A7. Determine the target training type corresponding to the target training task;

[0065] A8. Determine the target VR scene based on the target training type, the neurofeedback training objective, and the preset VR scene set.

[0066] In this embodiment, the preset VR scene set can be preset in advance or defaulted to. The preset VR scene set can include at least two of the following: Earth rotation scene, floating wooden box scene, forest fire scene, orbiting ball scene, bilateral lighthouse scene, etc., without limitation; the target disease can include at least one of the following: ADHD, autism, learning disability, anxiety disorder, etc., without limitation; the target physiological parameter can include at least one of the following: height, weight, maximum oxygen uptake, blood pressure, blood oxygen saturation, etc., without limitation; the target training type can include one of the following: enhancement type, inhibition type, balance type, etc., without limitation.

[0067] Optional, please refer to Figure 4 , Figure 4 This is a schematic diagram of a preset VR scene set provided in an embodiment of this application. As can be seen, the preset VR scene set may include: Earth rotation scene, wooden box floating scene, and forest fire scene.

[0068] In a specific embodiment, a reference training task set corresponding to the target disease can be determined. Specifically, relevant medical literature, hospital databases, medical websites, etc., can be consulted to obtain research data on the target disease. The reference training task set is determined based on this research data. For example, assuming the target disease is anxiety disorder, a search on a medical website reveals that "for anxiety disorder, HRV neurofeedback combined with slow breathing training can significantly improve the parasympathetic nerve activity of patients." Based on this, the reference training task is determined to be "slow breathing training" (slowly changing the VR scene by maintaining the breathing rhythm, corresponding to the enhancement of HRV indicators), and this reference training task is added to the reference training task set.

[0069] Next, the reference attention duration corresponding to the target age can be determined. Specifically, a pre-stored mapping relationship between age and attention duration can be used to determine the reference attention duration corresponding to the target age. Then, the attention influencing factor corresponding to the target disease can be determined. Similarly, a pre-stored mapping relationship between disease and influencing factor can be used to determine the attention influencing factor corresponding to the target disease. The value range of the attention influencing factor can be -0.3 to 0.3. Furthermore, the reference attention duration can be adjusted according to the attention influencing factor, as follows:

[0070] Target attention duration = Reference attention duration × (1 + Attention influencing factor);

[0071] Based on the above formula, the target attention duration can be obtained; then, the target physical strength value corresponding to the target physiological parameter can be determined. Specifically, a pre-stored mapping relationship between the physiological parameter and the physical strength value can be used to determine the target physical strength value corresponding to the target physiological parameter; then, the target training task can be determined based on the target physical strength value, the target attention duration, a training tasks, and the neurofeedback training target.

[0072] Then, the target training type corresponding to the target training task can be determined. Specifically, the control direction of the target training task can be determined to obtain the target control direction. Based on the target control direction, the target training type can be determined. For example, assuming the target training task is a "ball obstacle avoidance task", performing this target training task can improve a person's concentration. Then, its corresponding target control direction is the enhancement direction, that is, the target training type is enhancement type. Finally, the target VR scene can be determined based on the target training type, the neurofeedback training target, and the preset VR scene set.

[0073] In this way, by using the target disease, age, and physiological parameters as quantitative criteria, the training task is not "one-size-fits-all" and a training task suitable for the target subjects is obtained. In addition, by linking multiple parameters (physical strength, attention, etc.) in decision-making, the training effect and execution feasibility are balanced, ineffective training is reduced, and the closed-loop regulation efficiency of neurofeedback is enhanced.

[0074] Optionally, each training task includes: training actions, the number of rounds per training session, the duration of each round, and the rest time between rounds; regarding the determination of the target training task based on the target physical strength value, the target attention duration, the a training tasks, and the neurofeedback training target, the host computer module is specifically used to perform the following steps:

[0075] B1. Determine the training task corresponding to the neural feedback training objective among the a training tasks to obtain b training tasks; b is a positive integer less than or equal to a.

[0076] B2. Determine the duration of each round corresponding to each of the b training tasks to obtain b durations;

[0077] B3. Determine the minimum duration among the b durations;

[0078] B4. When the minimum duration is greater than the target attention duration, determine the training task corresponding to the minimum duration in the b training tasks to obtain the first training task; the first training task includes: the first training action, the number of the first rounds in each training session, the first duration of each round, and the first rest duration between rounds.

[0079] B5. Adjust the first training task according to the target physical strength value, the target attention duration, and the minimum duration to obtain the target training task.

[0080] In this embodiment, training tasks corresponding to the neurofeedback training objective can be determined from a number of training tasks to obtain b training tasks. Specifically, the control direction of the neurofeedback training objective can be determined first to obtain a first control direction. Then, training tasks with the same first control direction can be selected from the a training tasks to obtain b training tasks. For example, assuming the first control direction is an enhancement direction, a training types corresponding to the a training tasks can be obtained. Among the a training types, enhancement-type training types can be determined to obtain b training types. Then, training tasks corresponding to these b training types can be determined from the a training tasks to obtain b training tasks.

[0081] Next, the duration of each round corresponding to each of the b training tasks can be determined, resulting in b durations. Specifically, since each training task contains the duration of each round, the corresponding durations can be directly extracted from the b training tasks, resulting in b durations. Then, the minimum value among these b durations, i.e., the minimum duration, can be found. When the minimum duration is greater than the target attention duration, the training task corresponding to the minimum duration among the b training tasks can be found, resulting in the first training task. Finally, the first training task can be adjusted based on the target stamina value, the target attention duration, and the minimum duration to obtain the target training task.

[0082] In this way, by first screening b tasks that are directly related to the training goal and excluding irrelevant tasks, we can ensure that subsequent adjustments always revolve around the training goal and avoid deviating from the core objective. Then, by extracting the minimum duration of the b tasks, we can find the "attention tolerance limit" that the subjects may face. The minimum duration is the duration that is easiest to complete in the task set. If it still exceeds the target attention duration, it means that the task needs to be adjusted first to avoid the subjects becoming fatigued and giving up due to exceeding the time limit, which would affect the training effect.

[0083] Optionally, in the process of adjusting the first training task based on the target physical strength value, the target attention duration, and the minimum duration to obtain the target training task, the host computer module is specifically used to perform the following steps:

[0084] C1. Determine the first average physical strength value based on the first training action and the first duration;

[0085] C2. Determine the ratio between the target physical strength value and the first average physical strength value to obtain the first ratio;

[0086] C3. Adjust the first round number according to the first ratio to obtain the target round number;

[0087] C4. Determine the difference between the minimum duration and the target attention duration to obtain a first difference;

[0088] C5. Determine the first optimization factor and the second optimization factor corresponding to the first difference;

[0089] C6. Adjust the first duration according to the first optimization factor to obtain the target duration;

[0090] C7. Adjust the first rest duration according to the second optimization factor to obtain the target rest duration;

[0091] C8. Determine the target training task based on the first training action, the target number of rounds, the target duration, and the target rest duration.

[0092] In this embodiment of the application, a first average physical strength value can be determined based on a first training action and a first duration. Specifically, the basic physical strength value per unit time of the first training action can be determined based on the physical exertion standards of sports medicine or rehabilitation medicine (e.g., metabolic equivalent). Alternatively, a preset mapping relationship between training actions and physical strength values ​​can be stored in advance, and the basic physical strength value per unit time corresponding to the first training action can be determined based on the mapping relationship. Then, the first average physical strength value can be obtained by multiplying the basic physical strength value per unit time by the first duration.

[0093] Next, the ratio between the target stamina value and the first average stamina value can be determined, as follows:

[0094] First ratio = Target physical strength value / First average physical strength value;

[0095] Based on the above formula, the first ratio can be obtained. Then, the number of rounds in the first round can be adjusted according to the first ratio to obtain the target number of rounds. Specifically, the size of the first ratio and the number of rounds in the first round can be compared. If the number of rounds in the first round is less than or equal to the first ratio, the number of rounds in the first round can be directly used as the target number of rounds. If the number of rounds in the first round is greater than the first ratio, the first ratio can be used as the target number of rounds. Next, the difference between the minimum duration and the target attention duration can be determined to obtain the first difference. Specifically, the first difference can be obtained by subtracting the target attention duration from the minimum duration.

[0096] Furthermore, a first optimization factor and a second optimization factor corresponding to the first difference can be determined. For example, a preset mapping relationship between differences and optimization factors can be stored in advance, and the first optimization factor and the second optimization factor corresponding to the first difference can be determined based on this mapping relationship. The value range of the first optimization factor and the second optimization factor can both be -0.5 to 0.5. Then, the first duration can be adjusted according to the first optimization factor, as follows:

[0097] Target duration = first duration × (1 + first optimization factor);

[0098] Based on the above formula, the target duration can be obtained; then, the first rest duration can be adjusted according to the second optimization factor, as follows:

[0099] Target rest duration = first rest duration × (1 + second optimization factor);

[0100] Based on the above formula, the target rest duration can be obtained; finally, the target training task can be composed of the first training action, the target number of rounds, the target duration, and the target rest duration.

[0101] Thus, adjusting the number of rounds by the ratio of the target physical strength value to the first average physical strength value is essentially a dynamic adjustment of the total training volume based on the subject's physical endurance. If the first average physical strength value is higher than the target physical strength value (ratio < 1), the number of rounds is reduced to decrease the total consumption; if it is lower than the target physical strength value (ratio > 1), the number of rounds is increased to increase the training intensity, ensuring that the physical consumption per round and the total physical consumption always fit within the subject's tolerance range, avoiding fatigue interruption due to excessive physical strength, or affecting the training effect due to insufficient physical strength.

[0102] In addition, addressing the core issue of the minimum duration exceeding the target attention duration, the single-round duration and rest duration are adjusted by an optimization factor corresponding to the first difference. The target duration is shortened to match the attention limit, and the target rest duration is extended to alleviate attention fatigue. This reduces the attention load from both the "single-round duration" and "rest buffer" aspects, allowing the subjects to complete each round of training, avoiding distraction and inadequate task execution due to attention overload, and ensuring the continuity of neural feedback.

[0103] Optionally, the host computer module is specifically used to perform the following steps:

[0104] D1. When the minimum duration is less than or equal to the target attention duration, determine the durations among the b durations that are less than or equal to the target attention duration, and obtain c durations; c is a positive integer less than or equal to b.

[0105] D2. Determine the c training tasks corresponding to the c durations in the b training tasks;

[0106] D3. Determine the stamina consumption value corresponding to each of the c training tasks to obtain c stamina consumption values.

[0107] D4. Determine the stamina consumption values ​​among the c stamina consumption values ​​that are less than or equal to the target stamina value, to obtain d stamina consumption values; d is a natural number less than or equal to c;

[0108] D5. Determine the minimum stamina consumption value among the d stamina consumption values;

[0109] D6. Determine the training task corresponding to the minimum physical exertion value among the c training tasks to obtain the target training task.

[0110] In this embodiment of the application, when the minimum duration is less than or equal to the target attention duration, the durations that are less than or equal to the target attention duration among the b durations are determined to obtain c durations. Specifically, each duration among the b durations can be compared with the target attention duration to find all durations that are less than or equal to the target attention duration, thus obtaining c durations.

[0111] Next, we can identify the corresponding training tasks for each of the c durations out of the b training tasks, with each duration corresponding to one training task. Then, we can determine the stamina consumption value for each of the c training tasks, resulting in c stamina consumption values. Further, we can identify the stamina consumption values ​​among the c stamina consumption values ​​that are less than or equal to the target stamina value, resulting in d stamina consumption values. Specifically, we can compare each of the c stamina consumption values ​​with the target stamina value to find all stamina consumption values ​​that are less than or equal to the target stamina value, resulting in d stamina consumption values.

[0112] It should be explained that if all c stamina expenditure values ​​exceed the target stamina value, it indicates that the target participant's target stamina value is too low and they are not suitable for training. The system can issue a voice prompt: "The stamina expenditure values ​​of all current tasks exceed the target stamina value. We suggest you appropriately increase the target stamina value and re-select. If you need to lower the stamina threshold, you can try the simplified training tasks provided by the system." The simplified training tasks refer to adaptive tasks that retain the core training objectives of the original tasks (e.g., improving focus, emotion regulation) by reducing difficulty, decreasing stamina expenditure, or simplifying operational logic. These tasks are specifically designed for participants with weaker stamina or insufficient abilities.

[0113] Next, we can find the minimum value among the d stamina consumption values, which is the minimum stamina consumption value; finally, we can take the training task corresponding to the minimum stamina consumption value among the c training tasks as the target training task.

[0114] In this way, by prioritizing the selection of c training tasks whose duration is less than or equal to the target attention duration, tasks that cause the subject to be distracted and unable to complete due to exceeding the time limit are directly excluded. This ensures that the training matches the subject's attention tolerance from the root, and avoids training interruption or reduced effectiveness caused by attention overdraft.

[0115] In addition, by selecting d tasks that consume less than or equal to the target physical strength value, options that exceed the physical strength requirement are eliminated to avoid fatigue and discomfort caused by excessive physical exertion. This method is especially suitable for subjects with weaker physical strength, such as patients with diseases and the elderly, ensuring a safe and stress-free training process.

[0116] Optionally, in determining the stamina consumption value corresponding to each of the c training tasks to obtain c stamina consumption values, the host computer module is specifically used to perform the following steps:

[0117] E1. Obtain the second training task; the second training task includes: a second training action, the number of second rounds in each training session, the second duration of each round, and the second rest duration between rounds; the second training task is any one of the c training tasks.

[0118] E2. Determine the second average physical strength value based on the second training action and the second duration;

[0119] E3. Determine the reference stamina value based on the second average stamina value and the second number of rounds;

[0120] E4. Determine the physical exertion parameters corresponding to the target disease;

[0121] E5. Adjust the reference physical exertion value according to the physical exertion parameter to obtain the physical exertion value corresponding to the second training task.

[0122] In this embodiment, a second training task can be obtained first. Then, a second average physical strength value can be calculated based on the second training action and the second duration. Specifically, the calculation method of the second average physical strength value is the same as the calculation method of the first average physical strength value. Then, a reference physical strength value can be determined based on the second average physical strength value and the number of rounds. For example, the reference physical strength value can be obtained by multiplying the second average physical strength value by the number of rounds.

[0123] Furthermore, the physical exertion parameters corresponding to the target disease can be determined. Specifically, a pre-stored mapping relationship between diseases and influence parameters can be used to determine the physical exertion parameters corresponding to the target disease. The value range of the physical exertion parameters is -0.25 to 0.25. Then, the reference physical exertion value can be adjusted according to the physical exertion parameters, as follows:

[0124] The stamina consumption value for the second training task = reference stamina consumption value × (1 + stamina influence parameter);

[0125] Based on the above formula, the stamina consumption value corresponding to the second training task can be obtained.

[0126] Since the target disease may alter the physical endurance of the subjects (for example, ADHD patients are prone to irritability and fidgeting due to difficulty concentrating, which leads to lower physical endurance than the general population), by introducing a "physical exertion parameter," the reference physical exertion value can be adjusted in a targeted manner, so that the final physical exertion value is more in line with the actual physical condition of the subjects, and avoids distortion of physical exertion assessment due to ignoring the influence of the disease.

[0127] Optional, please refer to Figure 5 , Figure 5 This is a flowchart of a method for determining a target VR scene according to an embodiment of this application. In determining the target VR scene based on the target training type, the neurofeedback training objective, and a preset VR scene set, the host computer module is specifically used to execute... Figure 5 The steps shown are as follows:

[0128] F1. Determine e VR scenes in the preset VR scene set that correspond to the target training type, resulting in e VR scenes; e is a positive integer.

[0129] F2. Determine the target scenario requirements corresponding to the neurofeedback training objective;

[0130] F3. Determine the scene feature parameters corresponding to each of the e VR scenes to obtain the e scene feature parameters;

[0131] F4. Determine the matching degree between each of the e scene feature parameters and the target scene requirement to obtain e matching degrees;

[0132] F5. Determine the maximum matching degree among the e matching degrees, and determine the VR scene corresponding to the maximum matching degree as the target VR scene.

[0133] In this embodiment of the application, the scene feature parameters may include at least one of the following: scene feedback form (e.g., positive feedback or negative feedback), associated physiological parameters, scene style (e.g., intense scene, soothing scene), etc., which are not limited here.

[0134] In a specific embodiment, VR scenes corresponding to the target training type can be determined from a preset VR scene set, resulting in e VR scenes. Specifically, each VR scene in the preset VR scene set can be labeled first, as follows:

[0135] The core feedback form of the labeled scenario is as follows: Based on the response logic of the scenario to changes in physiological indicators (or EEG indicators), the corresponding feedback labels are assigned. For example, "Forest fire scenario" (the flames become stronger when HRV is within the target range, corresponding to the "positive feedback" label); "Track ball scenario" (the ball decelerates when theta waves exceed the target range, corresponding to the "reverse constraint" label); "Bilateral lighthouse scenario" (the brightness of the left and right lighthouses adjusts asymmetrically with alpha waves, corresponding to the "symmetric feedback" label).

[0136] The control direction for scene adaptation is directly associated with any of the "enhanced / inhibitory / balanced" types. For example, the "forest fire scene" is adapted to the enhanced type, the "orbit ball scene" is adapted to the inhibited type, and the "double-sided lighthouse scene" is adapted to the balanced type.

[0137] In this way, the label corresponding to each VR scene in the preset VR scene set can be determined, resulting in multiple scene labels. For example, the scene label corresponding to the "forest campfire scene" can be "positive feedback-reinforcement". Then, the scene label corresponding to the target training type among the multiple scene labels can be determined, resulting in e scene labels. The e scene labels can then be determined to correspond to e VR scenes in the preset VR scene set.

[0138] Next, the target scenario requirements corresponding to the neurofeedback training objectives can be determined. Specifically, core regulatory parameters can be extracted from the neurofeedback training objectives to clarify which type of parameter needs to be adjusted (e.g., HRV, theta wave, frontal alpha wave asymmetry). Then, the first regulatory direction corresponding to the neurofeedback training objectives can be obtained. Based on the core regulatory parameters and the first regulatory direction, the target scenario requirements can be determined. For example, if the regulatory direction is "enhancement direction" and the core regulatory parameter is HRV, that is, HRV needs to be enhanced, then the target scenario requirements can be: to guide the subject to actively adjust HRV (e.g., guide breathing rhythm and relaxation state through the scenario) and to have positive feedback function. When HRV reaches the preset enhancement threshold, an immediate positive response is given (e.g., brightness increase, scenario unlocking, sound effect enhancement) to strengthen the subject's correct adjustment behavior and help HRV continuously improve.

[0139] Then, the scene feature parameters corresponding to each of the e VR scenes can be determined, resulting in e scene feature parameters. For example, scene feature parameters can include three types of information: scene feedback form, associated physiological parameters, and scene style. For each VR scene, its corresponding scene feedback form, associated physiological parameters, and scene style can be obtained, thus obtaining e scene feature parameters. Furthermore, the matching degree between each of the e scene feature parameters and the target scene requirements can be determined, resulting in e matching degrees. Specifically, the matching degree of the e scene feature parameters can be scored according to the target scene requirements, resulting in e matching scores, or e matching degrees.

[0140] To illustrate, suppose the target scenario requires "guided adjustment of HRV, positive feedback, and soothing low-interference," and a VR scenario is a forest fire scene. The scene feature parameters and their scores for this forest fire scene are as follows:

[0141] Scenario feedback format: When HRV is met, the flame becomes stronger, the positive feedback is clear, and it meets the needs of the target scenario, so it scores 100 points;

[0142] Related physiological parameters: It can guide respiration to regulate HRV, which meets the needs of the target scenario, and scores 90 points;

[0143] Scene style: Forest landscape, soft color tone, soothing and low-interference, meets the needs of the target scene, score 80 points;

[0144] Final match rate: (100+90+80) / 3×100%=90%.

[0145] Finally, we can find the maximum value among the e matching degrees, that is, the maximum matching degree, and determine the VR scene corresponding to the maximum matching degree as the target VR scene.

[0146] In this way, by clearly defining the requirements of the target scenario, a clear standard is provided for scenario matching, avoiding the selection of scenarios based solely on subjective feelings, and ensuring that the final selected scenario can serve the neurofeedback training objective and does not deviate from the core logic.

[0147] The EEG acquisition module is used to acquire the first EEG data of the target subject.

[0148] In this embodiment, the EEG acquisition module may include at least one of the following: EEG sensor, EEG cap, EEG acquisition and analysis instrument, etc., which are not limited here.

[0149] In a specific embodiment, the EEG acquisition module can first be connected to the host computer module via Bluetooth or USB. The module's accompanying software can be opened to perform device self-test and signal calibration to ensure that the module can work normally. Next, the target subject can wash the electrode contact areas such as the forehead and behind the ears (to remove oil and sweat and improve conductivity). Then, conductive paste or saline can be evenly applied to the electrode contacts. Finally, the EEG acquisition module can be placed on the target subject's head, ensuring that the electrodes of the EEG acquisition module are in close contact with the skin (without looseness or gaps). The EEG acquisition module is then activated to start collecting EEG data to obtain the first EEG data.

[0150] The VR visualization module is used to determine the first control command corresponding to the target VR scene and the second control command corresponding to the target training task.

[0151] In a specific embodiment, the VR visualization module can pre-store a mapping relationship between preset VR scenes and control commands, and determine the first control command corresponding to the target VR scene based on the mapping relationship. Similarly, it can also pre-store a mapping relationship between preset training tasks and control commands, and determine the second control command corresponding to the target training task based on the mapping relationship.

[0152] The VR headset is used to generate the target VR scene according to the first control instruction; and to generate target guidance voice according to the second control instruction; the target guidance voice is used to guide the target subject to perform the target training task in the target VR scene.

[0153] In a specific embodiment, the VR headset can receive a first control command and a second control command sent by a host computer, then generate a target VR scene corresponding to the first control command, and can also generate target guidance voice according to the second control command.

[0154] The EEG acquisition module is also used to acquire second EEG data of the target subject during the target training task.

[0155] In a specific embodiment, during the target training task, the target subject can use an EEG acquisition module to collect the target subject's second EEG data. Specifically, the method for acquiring the second EEG data can be the same as the method for acquiring the first EEG data, and will not be described in detail here.

[0156] The EEG amplification module is used to amplify the first EEG data and the second EEG data respectively to obtain the third EEG data and the fourth EEG data.

[0157] In this embodiment of the application, the input end of the EEG amplification module can be connected to the output end of the EEG acquisition module, and the output end of the EEG amplification module can be connected to the host computer module.

[0158] In a specific embodiment, the EEG amplification module can be a differential amplifier. The first EEG data is amplified by a preset factor (e.g., 1000 times) by the differential amplifier to obtain the third EEG data. Similarly, the second EEG data can be amplified by a preset factor to obtain the fourth EEG data.

[0159] The host computer module is also used to determine the target training effect based on the third EEG data and the fourth EEG data; and to adjust the target VR scene based on the target training effect.

[0160] Optional, please refer to Figure 6 , Figure 6 This is a flowchart illustrating a method for determining the target training effect according to an embodiment of this application. In determining the target training effect based on the third EEG data and the fourth EEG data, the host computer module is specifically used to execute... Figure 6 The steps shown are as follows:

[0161] G1. Determine the target indicator type corresponding to the neurofeedback training objective;

[0162] G2. Determine the first indicator value corresponding to the third EEG data and the second indicator value corresponding to the fourth EEG data according to the target indicator type.

[0163] G3. Determine the target training effect based on the first indicator value and the second indicator value.

[0164] In the embodiments of this application, the target index type may include at least one of the following: HRV, EEG power spectrum related indexes (e.g., alpha wave power, theta wave power, gamma wave power, etc.), frontal alpha wave asymmetry, etc., which are not limited here.

[0165] In a specific embodiment, the target indicator type corresponding to the neurofeedback training goal can be determined. Specifically, the core regulatory parameter, i.e. the target indicator type, can be extracted from the neurofeedback training goal. For example, assuming the neurofeedback training goal is "to improve the patient's concentration by enhancing the beta wave", the core regulatory parameter extracted is "beta wave power". This core regulatory parameter is the target indicator type.

[0166] Next, the first indicator value corresponding to the third EEG data and the second indicator value corresponding to the fourth EEG data can be determined based on the target indicator type. For example, assuming the target indicator type is beta-wave power, the beta-wave power of the third EEG data can be calculated, which is the first indicator value. Similarly, the beta-wave power of the fourth EEG data can be calculated, which is the second indicator value. Finally, the target training effect can be determined based on the first and second indicator values. Specifically, the target difference can be obtained by subtracting the first indicator value from the second indicator value. Then, the target training effect is determined based on the target difference and the neurofeedback training objective. For example, if the neurofeedback training objective is an enhancement objective (i.e., increasing the indicator value), the larger the target difference, the better the target training effect. If the neurofeedback training objective is an inhibition objective (i.e., decreasing the indicator value), the smaller the target difference, the better the target training effect. Alternatively, it can be calculated based on the first and second indicator values, as follows:

[0167] Target change rate = (Second indicator value - First indicator value) / First indicator value × 100%;

[0168] Based on the above formula, the target change rate can be calculated. The target training effect is determined based on the target change rate and the neurofeedback training target. Specifically, first, it is determined whether the direction of change of the target change rate is consistent with the training target. Second, it is determined whether the change magnitude reaches the expectation. If the change direction is consistent, the larger the change magnitude, the better the target training effect. Conversely, if the change direction is inconsistent, the larger the change magnitude, the worse the target training effect. In this way, the target training effect can be determined.

[0169] In this way, by quantitatively comparing the first and second indicator values, data replaces subjective judgment, ensuring that the effect evaluation is repeatable and unambiguous.

[0170] Optionally, in terms of providing feedback adjustments to the target VR scene based on the target training effect, the host computer module is specifically configured to perform the following steps:

[0171] H1. Obtain the scene dynamic parameters of the target VR scene at the current moment to obtain the first scene dynamic parameters;

[0172] H2. Determine the first adjustment factor corresponding to the second indicator value;

[0173] H3. Determine the target optimization factor corresponding to the target training effect;

[0174] H4. Optimize the first adjustment factor according to the target optimization factor to obtain the second adjustment factor;

[0175] H5. Adjust the dynamic parameters of the first scene according to the second adjustment factor to obtain the dynamic parameters of the second scene;

[0176] H6. Determine the third control instruction corresponding to the second scene dynamic parameters, and transmit the third control instruction to the VR headset; the third control instruction is used to adjust the scene dynamic parameters of the target VR scene to the second scene dynamic parameters.

[0177] In this embodiment of the application, the dynamic parameters of each scene may include at least one of the following: rate of change, buoyancy, color brightness, intensity, etc., which are not limited here.

[0178] In a specific embodiment, the dynamic parameters of the target VR scene at the current moment are obtained to obtain the first scene dynamic parameters. Specifically, the host computer module communicates with the VR headset, the scene rendering program running in the VR headset records and stores the current scene dynamic parameters in real time, the host computer module sends a parameter reading request to the VR headset through the communication link, the VR headset responds to the request and returns the current parameter data, and after receiving the current parameter data, the host computer module parses it to obtain the first scene dynamic parameters.

[0179] Next, the first adjustment factor corresponding to the second indicator value can be determined. For example, a pre-stored mapping relationship between indicator values ​​and adjustment factors can be used to determine the first adjustment factor corresponding to the second indicator value. The value range of the first adjustment factor can be -0.25 to 0.25. Then, the target optimization factor corresponding to the target training effect can be determined. Similarly, a pre-stored mapping relationship between training effect and optimization factor can be used to determine the target optimization factor corresponding to the target training effect. The value range of the target optimization factor can be -0.5 to 0.5. Furthermore, the first adjustment factor can be optimized based on the target optimization factor, as follows:

[0180] Second adjustment factor = First adjustment factor × (1 + Target optimization factor);

[0181] Based on the above formula, the second adjustment factor can be obtained; then, the dynamic parameters of the first scene can be adjusted according to the second adjustment factor, as follows:

[0182] Second scene dynamic parameters = First scene dynamic parameters × (1 + Second adjustment factor);

[0183] Based on the above formula, the second scene dynamic parameters can be obtained. Finally, corresponding control commands can be generated based on the second scene dynamic parameters to obtain the third control command, and the third control command can be transmitted to the VR headset to control the VR headset to adjust the scene dynamic parameters of the target VR scene to the second scene dynamic parameters.

[0184] In this way, by generating adjustment criteria (first adjustment factor) based on current scene parameters (first dynamic parameters) and real-time indicators (second indicator values), the adjustment is ensured to fit the training state. Then, the adjustment strategy is optimized in combination with training effect (target optimization factor) to avoid blind adjustment, thereby improving training efficiency and adaptability.

[0185] In summary, the VR-based neurofeedback training system described in this application, on the one hand, effectively avoids the inefficiency of general solutions by combining the basic data and training objectives of the target subjects to customize exclusive VR scenes and training tasks; on the other hand, the system provides intuitive dynamic feedback through VR scenes, which makes it easier for subjects to perceive changes in their own neural activity compared to traditional two-dimensional images. Combined with guided voice to enhance operational understanding, it improves the subjects' ability to actively regulate their neural state and thus enhances the effectiveness of neurofeedback therapy.

[0186] Optional, please refer to Figure 7 , Figure 7 This is a flowchart of a VR-based neurofeedback training system provided in an embodiment of this application. As can be seen, the host computer module can be the experimenter's end, and the VR all-in-one device can be the subject's end, which includes a VR visualization module. The specific workflow of the system is as follows:

[0187] First, the raw EEG data of the target subjects is collected through the EEG acquisition module and uploaded to the EEG amplification module;

[0188] Second, the raw EEG data is amplified by the EEG amplification module to obtain analyzable EEG data (amplifying the microvolt-level signal to the volt level for easier subsequent calculations). Then, the analyzable EEG data is uploaded to the host computer module.

[0189] Third, the host computer module analyzes and processes the analyzable EEG data to calculate neural indicators (e.g., first indicator value, second indicator value); then, the host computer module can also generate "TCP action packets" to convert the neural indicators into dynamic parameter adjustment instructions for the VR scene and send them to the VR visualization module on the subject's end.

[0190] Fourth, the host computer module receives feedback information returned by the VR visualization module, such as confirmation of command reception and acquisition of VR scene status;

[0191] Fifth, the host computer module stores the processed EEG data as EEG files in a preset format (e.g., BDF format) for training recording and subsequent analysis.

[0192] Please see Figure 8 , Figure 8This is a schematic diagram of the structure of a VR-based neurofeedback training device provided in an embodiment of this application. The VR-based neurofeedback training device may include any of the VR-based neurofeedback training systems described in the above embodiments.

[0193] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0194] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0195] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0196] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

[0197] The steps of the methods or algorithms described in the embodiments of this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in RAM, flash memory, ROM, EPROM, electrically erasable programmable read-only memory (EEPROM), registers, hard disk, portable hard disk, read-only optical disk (CD-ROM), or any other form of storage medium well known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Furthermore, the ASIC can reside in a terminal device or management device. Alternatively, the processor and storage medium can exist as discrete components in the terminal device or management device.

[0198] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in the embodiments of this application can be implemented, in whole or in part, by software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated.

[0199] The aforementioned computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media.

[0200] The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0201] The modules / units included in the various devices and products described in the above embodiments can be software modules / units, hardware modules / units, or a combination of both. For example, for devices and products applied to or integrated into a chip, all modules / units can be implemented using hardware methods such as circuits, or at least some modules / units can be implemented using software programs that run on a processor integrated within the chip, while the remaining (if any) modules / units can be implemented using hardware methods such as circuits. For devices and products applied to or integrated into a chip module, all modules / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components of the chip module, or at least some modules / units can be implemented using hardware methods such as circuits. The implementation is achieved through a software program that runs on the processor integrated within the chip module. The remaining modules / units (if any) can be implemented using hardware methods such as circuits. For various devices and products applied to or integrated into terminal equipment, each of their modules / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components within the terminal equipment. Alternatively, at least some modules / units can be implemented through a software program that runs on the processor integrated within the terminal equipment, while the remaining modules / units (if any) can be implemented using hardware methods such as circuits.

[0202] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the embodiments of this application. It should be understood that the above descriptions are merely specific embodiments of the embodiments of this application and are not intended to limit the protection scope of the embodiments of this application. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solutions of the embodiments of this application should be included within the protection scope of the embodiments of this application.

Claims

1. A VR-based neurofeedback training system, characterized in that, The system includes: a host computer module, an EEG acquisition module, an EEG amplification module, and a VR device. The VR device includes: a VR visualization module and a VR headset. The host computer module communicates with the VR device, and the VR headset is worn on the head of the target subject. The host computer module is used to acquire the target basic data and neurofeedback training objectives of the target subject; and to determine the target training scheme based on the target basic data and the neurofeedback training objectives; the target training scheme includes: a target VR scene and a target training task; The EEG acquisition module is used to acquire the first EEG data of the target subject; The VR visualization module is used to determine the first control command corresponding to the target VR scene and the second control command corresponding to the target training task. The VR headset is used to generate the target VR scene according to the first control command; and to generate target guidance voice according to the second control command; the target guidance voice is used to guide the target subject to perform the target training task in the target VR scene. The EEG acquisition module is also used to acquire the second EEG data of the target subject during the target training task. The EEG amplification module is used to amplify the first EEG data and the second EEG data respectively to obtain the third EEG data and the fourth EEG data. The host computer module is also used to determine the target training effect based on the third EEG data and the fourth EEG data; and to provide feedback adjustment to the target VR scene based on the target training effect. The target basic data includes: target age, target physiological parameters, and target disease; In determining the target training scheme based on the target basic data and the neural feedback training target, the host computer module is specifically used for: Determine a reference training task set corresponding to the target disease; the reference training task set includes a training tasks; a is an integer greater than 1; Determine the reference attention duration corresponding to the target age; Identify the attention-influencing factors corresponding to the target disease; The target attention duration is obtained by adjusting the reference attention duration based on the attention influencing factor. Determine the target physical strength value corresponding to the target physiological parameter; The target training task is determined based on the target physical strength value, the target attention duration, the a training tasks, and the neurofeedback training target; Determine the target training type corresponding to the target training task; The target VR scene is determined based on the target training type, the neurofeedback training objective, and the preset VR scene set.

2. The system as described in claim 1, characterized in that, In determining the target training effect based on the third and fourth EEG data, the host computer module is specifically used for: Determine the type of target indicator corresponding to the neurofeedback training objective; The first indicator value corresponding to the third EEG data and the second indicator value corresponding to the fourth EEG data are determined according to the target indicator type. The target training effect is determined based on the first indicator value and the second indicator value.

3. The system as described in claim 2, characterized in that, In the aspect of providing feedback adjustment to the target VR scene based on the target training effect, the host computer module is specifically used for: Obtain the scene dynamic parameters of the target VR scene at the current moment to obtain the first scene dynamic parameters; Determine the first adjustment factor corresponding to the second indicator value; Determine the target optimization factor corresponding to the target training effect; The first adjustment factor is optimized based on the target optimization factor to obtain the second adjustment factor; The dynamic parameters of the first scene are adjusted according to the second adjustment factor to obtain the dynamic parameters of the second scene; A third control instruction corresponding to the second scene dynamic parameters is determined, and the third control instruction is transmitted to the VR headset; the third control instruction is used to adjust the scene dynamic parameters of the target VR scene to the second scene dynamic parameters.

4. The system as described in claim 1, characterized in that, Each training task includes: training movements, number of rounds per training session, duration of each round, and rest time between rounds; In determining the target training task based on the target physical strength value, the target attention duration, the a training tasks, and the neurofeedback training target, the host computer module is specifically used for: Determine the training task corresponding to the neural feedback training objective among the a training tasks to obtain b training tasks; b is a positive integer less than or equal to a. Determine the duration of each round corresponding to each of the b training tasks to obtain b durations; Determine the minimum duration among the b durations; When the minimum duration of attention is greater than the target duration of attention, the training task corresponding to the minimum duration of attention in the b training tasks is determined to obtain the first training task; the first training task includes: a first training action, the number of the first rounds in each training session, the first duration of each round, and the first rest duration between rounds. The first training task is adjusted based on the target physical strength value, the target attention duration, and the minimum duration to obtain the target training task.

5. The system as described in claim 4, characterized in that, In the process of adjusting the first training task based on the target physical strength value, the target attention duration, and the minimum duration to obtain the target training task, the host computer module is specifically used for: A first average physical strength value is determined based on the first training action and the first duration. Determine the ratio between the target physical strength value and the first average physical strength value to obtain a first ratio; The first round number is adjusted according to the first ratio to obtain the target round number; Determine the difference between the minimum duration and the target attention duration to obtain a first difference; Determine the first optimization factor and the second optimization factor corresponding to the first difference; The first duration is adjusted according to the first optimization factor to obtain the target duration; The first rest duration is adjusted according to the second optimization factor to obtain the target rest duration; The target training task is determined based on the first training action, the target number of rounds, the target duration, and the target rest duration.

6. The system as described in claim 4, characterized in that, The host computer module is specifically used for: When the minimum duration is less than or equal to the target attention duration, determine the durations of the b durations that are less than or equal to the target attention duration to obtain c durations. c is a positive integer less than or equal to b; Determine the c training tasks corresponding to the c durations in the b training tasks; Determine the stamina consumption value corresponding to each of the c training tasks to obtain c stamina consumption values; Determine the stamina consumption values ​​among the c stamina consumption values ​​that are less than or equal to the target stamina value, and obtain d stamina consumption values; d is a natural number less than or equal to c; Determine the minimum stamina consumption value among the d stamina consumption values; The training task corresponding to the minimum physical exertion value among the c training tasks is determined to obtain the target training task.

7. The system as described in claim 6, characterized in that, In determining the stamina consumption value corresponding to each of the c training tasks and obtaining c stamina consumption values, the host computer module is specifically used for: Obtain a second training task; the second training task includes: a second training action, the number of second rounds in each training session, the second duration of each round, and the second rest duration between rounds; the second training task is any one of the c training tasks. A second average physical strength value is determined based on the second training action and the second duration; The reference stamina value is determined based on the second average stamina value and the second number of rounds; Determine the physical exertion parameters corresponding to the target disease; The reference stamina consumption value is adjusted according to the stamina influence parameters to obtain the stamina consumption value corresponding to the second training task.

8. The system as described in claim 1, characterized in that, In determining the target VR scene based on the target training type, the neurofeedback training objective, and the preset VR scene set, the host computer module is specifically used for: The VR scenes corresponding to the target training type in the preset VR scene set are determined to obtain e VR scenes; e is a positive integer; Determine the target scenario requirements corresponding to the neural feedback training objective; Determine the scene feature parameters corresponding to each of the e VR scenes to obtain e scene feature parameters; Determine the matching degree between each of the e scene feature parameters and the target scene requirement to obtain e matching degrees; Determine the maximum matching degree among the e matching degrees, and determine the VR scene corresponding to the maximum matching degree as the target VR scene.

9. The system according to any one of claims 1-3, characterized in that, The host computer module and the VR device are connected via TCP protocol.

Images