Virtual reality anti-addiction system and method

Abstract

The invention discloses a virtual reality anti-addiction system and method, and the method comprises the steps: loading VR safety parameters corresponding to the age group of a target child, and building a personal electroencephalogram baseline of the target child; electroencephalogram data, behavior data and cognitive task data of a target child are synchronously collected, and a multi-dimensional addiction risk assessment model is utilized to perform one-time multi-dimensional addiction risk assessment every first duration; executing hierarchical intervention measures according to the multi-dimensional addiction risk assessment result; and generating a cognitive development report every second duration, and iterating the personal electroencephalogram baseline and the multi-dimensional addiction risk assessment model based on the cognitive development report. The system has the remarkable effects that technologies such as nerve monitoring, cognitive development rules and VR are fused, and accurate recognition, personalized intervention and cognitive promotion are realized through a four-layer closed-loop architecture of data acquisition, data analysis, dynamic intervention and safety monitoring.

Description

Technical Field

[0001] This invention relates to the field of digital media intervention technology for children, specifically to a virtual reality anti-addiction system and method. Background Technology

[0002] Online education has led to a diversification of teaching methods, significantly increasing children's screen time. With the widespread use of mobile devices such as tablets and smartphones, more and more children are starting to use electronic screens from a very young age.

[0003] Excessive use of electronic screen devices can indeed lead to dependency in children and have a profound impact on their cognitive development. Prolonged screen time can affect children's attention span, memory, language skills, social skills, and other cognitive functions. Furthermore, screen dependence can cause a range of health problems in children, including vision issues, sleep disturbances, and difficulties in mood regulation. Therefore, in the context of digital education, how to rationally utilize electronic screen devices to promote children's cognitive development and prevent the negative impacts of screen dependence has become a crucial issue that families, schools, and society urgently need to address.

[0004] Therefore, there is an urgent need for a closed-loop anti-addiction system and method that integrates neural monitoring, cognitive development patterns, and VR technology. Summary of the Invention

[0005] To address the shortcomings of existing technologies, the present invention aims to provide a virtual reality anti-addiction system and method that integrates neural monitoring, cognitive development patterns, and VR technology. Through a four-layer closed-loop architecture of data collection, data analysis, dynamic intervention, and security monitoring, it can achieve accurate identification, personalized intervention, and cognitive promotion.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows: Firstly, this invention proposes a method for preventing virtual reality addiction, the key of which includes the following steps: Step 1: Load VR safety parameters corresponding to the target child's age group and establish the target child's personal EEG baseline; Step 2: Simultaneously collect EEG data, behavioral data, and cognitive task data of the target children, and conduct a multi-dimensional addiction risk assessment using a multi-dimensional addiction risk assessment model at the first interval of each time period. Step 3: Implement tiered intervention measures based on the results of the multi-dimensional addiction risk assessment; Step 4: Generate a cognitive development report every second time interval, and iterate the personal EEG baseline and multi-dimensional addiction risk assessment model based on the cognitive development report.

[0007] Furthermore, the process of establishing the individual's EEG baseline includes: Step 1.1: Obtain the age and cognitive developmental foundation of the target child; Step 1.2: Load the normal range of EEG indicators, cognitive task library, and VR safety parameters for the target child's corresponding age group; Step 1.3: Guide the child to complete the basic EEG calibration procedure for the third duration; Step 1.4: Establish the individual EEG baseline for the target child based on the EEG data obtained after the calibration operation.

[0008] Furthermore, the EEG data mentioned in step 2 includes event-related potential P300 and N400 components and α / θ wave spectral power ratio; the behavioral data includes head rotation frequency, frequency of interactive operations, content type and proportion of educational / entertainment content; and the cognitive task data includes the performance data of the target child when completing non-interference random embedded tasks in VR content corresponding to the age group.

[0009] Furthermore, the electroencephalogram (EEG) data is collected by an EEG headband, and the behavioral data is collected by a VR device.

[0010] Furthermore, step 2, which involves conducting a multi-dimensional addiction risk assessment using a multi-dimensional addiction risk assessment model, specifically includes: If the calculated value output by the multi-dimensional addiction risk assessment model is less than the first threshold, it is judged as low risk; If the calculated value output by the multi-dimensional addiction risk assessment model is greater than the first threshold and less than the second threshold, it is judged as medium risk. If the calculated value output by the multi-dimensional addiction risk assessment model is greater than the second threshold, it is judged as high risk.

[0011] Furthermore, the tiered intervention measures implemented in step 3 based on the multi-dimensional addiction risk assessment results include: When the multi-dimensional addiction risk assessment result is low risk, a natural scene reminder will be pushed every fourth hour. When the multi-dimensional addiction risk assessment result is medium risk, the system will forcibly switch to a lightweight VR cognitive training task that matches the cognitive development goals. After five hours of training and meeting the target, the system will return to the original VR content. If the multi-dimensional addiction risk assessment result is high risk, VR content will be immediately suspended and parent-child interactive tasks will be pushed. Parents must confirm the completion before the VR content can be unlocked or educational VR content can be pushed.

[0012] Secondly, this invention proposes a virtual reality anti-addiction system, comprising: The data acquisition module is used to acquire the target child's EEG data, behavioral data, and cognitive task data in real time. The data analysis module is used to construct an individual EEG baseline based on the target child's age group and to conduct a multi-dimensional addiction risk assessment using a multi-dimensional addiction risk assessment model. The dynamic intervention module is used to implement tiered intervention measures based on the results of a multi-dimensional addiction risk assessment. The iterative update module is used to generate a cognitive development report every second time interval, and iterate the individual EEG baseline and multi-dimensional addiction risk assessment model based on the cognitive development report.

[0013] Furthermore, the data acquisition module includes: The EEG monitoring unit is used to collect EEG data from target children when they use VR devices via an EEG headband; The behavior monitoring unit is used to collect behavioral data of the target child when using the VR device through the built-in sensors of the VR device. Cognitive task units are used to collect cognitive task data from target children as they complete non-intrusive, randomly embedded tasks from a built-in age-group cognitive task library.

[0014] Furthermore, the data analysis module includes: Age-group adaptation unit, used to load preset parameters according to the age of the target child; The addiction risk assessment unit is used to build a multi-dimensional addiction risk assessment model; The cognitive state analysis unit is used to correlate the normal range of EEG indicators, behavioral data, and cognitive task data of the target child for the corresponding age group to analyze the current cognitive state of the target child.

[0015] Furthermore, the dynamic intervention module includes: The scene switching unit is used to trigger natural scene reminders, lightweight cognitive training, or parent-child interactive tasks based on the risk level output by the multi-dimensional addiction risk assessment model. The cognitive training unit is used to match VR cognitive training content with cognitive development goals; The parent collaboration unit is used to receive real-time reports on children's usage, customize intervention strategies, and complete parent-child interaction tasks.

[0016] The significant effects of this invention are: 1. Precision: By integrating EEG physiological indicators, behavior, and cognitive performance data, it can accurately distinguish between the two states of "focused learning" and "passive addiction" and make dynamic interventions, filling the research gap of "neural mechanism-anti-addiction-cognitive development" and realizing the innovative application of VR technology in anti-addiction. 2. Dual Objectives: By deeply integrating VR cognitive training with anti-addiction measures, anti-addiction interventions can avoid the negative impacts of electronic screen dependence while promoting children's cognitive abilities such as attention and memory. 3. Personalized: Deeply considering the differences in children's age and cognitive development stage, the thresholds and tasks are adjusted according to the child's age and individual baseline during intervention; 4. Safety: By collecting children's physiological indicators in real time and dynamically adjusting the safety parameters of the VR device, dual protection of physiological and VR parameters is achieved; 5. Family Collaboration: Provides visualized reports on children's usage and actionable collaborative intervention plans, addressing the pain point of "concern about excessive screen time but lack of effective intervention methods," and effectively improving parental involvement in intervention through parent-child interactive tasks. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the system described in this invention; Figure 2 This is a flowchart of the method described in this invention; Figure 3 This is a diagram illustrating the process of establishing the individual's EEG baseline. Detailed Implementation

[0018] The specific embodiments and working principles of the present invention will be further described in detail below with reference to the accompanying drawings.

[0019] Example 1: like Figure 1 As shown, this embodiment of the invention provides a virtual reality anti-addiction system, which includes: The data acquisition module is used to acquire the target child's EEG data, behavioral data, and cognitive task data in real time. The data analysis module is connected in communication with the data acquisition module. It is used to construct an individual EEG baseline based on the age group of the target child and to conduct a multi-dimensional addiction risk assessment using a multi-dimensional addiction risk assessment model. The dynamic intervention module is communicatively connected to the data analysis module and is used to implement graded intervention measures based on the results of multi-dimensional addiction risk assessment. The iterative update module, which is connected to the dynamic intervention module, is used to generate a cognitive development report every second time interval, and iterate the individual EEG baseline and multi-dimensional addiction risk assessment model based on the cognitive development report.

[0020] In some alternative implementations, the data acquisition module includes: The EEG monitoring unit is used to collect EEG data of the target child when using the VR device via an EEG headband; it should be noted that the EEG data may include, for example, the P300 and N400 components of the event-related potential (ERP) and the alpha / theta wave spectral power ratio. The behavior monitoring unit is used to collect behavioral data of the target child when using the VR device through the built-in sensors of the VR device. It should be noted that the behavior data includes head turning frequency, frequency of interactive operations, usage time, content type, and the proportion of educational / entertainment content. Cognitive task units are used to collect cognitive task data from target children as they complete non-intrusive, randomly embedded tasks from a built-in age-group cognitive task library.

[0021] Specifically, the cognitive task unit has a built-in age-group cognitive task library, which stores non-interference, randomly embedded tasks, such as image matching tasks for 3-6 year olds and number memory tasks for 7-12 year olds. These non-interference, randomly embedded tasks are used in VR device usage to collect performance data of the target child when completing the cognitive tasks. In other words, the cognitive task data is the performance data of the target child when completing non-interference, randomly embedded tasks within VR content corresponding to their age group.

[0022] In some alternative implementations, the data analysis module includes: The age-adaptive unit is used to load preset parameters based on the age of the target child, such as: the threshold for the difficulty of cognitive tasks for children aged 3-6, and the normal range of EEG indicators. The normal range of EEG indicators can be that the alpha wave power ratio is ≥30% as normal attention. The addiction risk assessment unit is used to build a multi-dimensional addiction risk assessment model; The cognitive state analysis unit is used to correlate the normal range of EEG indicators, behavioral data, and cognitive task data of the target child for the corresponding age group to analyze the target child's current cognitive state. For example, inattention + cognitive fatigue may be a precursor to addiction, while inattention + stable cognitive performance is a normal state.

[0023] In the specific implementation process, the process of constructing a multi-dimensional addiction risk assessment model by the addiction risk assessment unit is as follows: Obtain historical or statistical data on children's EEG, behavioral data, cognitive task data, and continuous usage time. Determine the weights of the EEG data, behavioral data, cognitive task data, and continuous usage duration data; An initial multi-dimensional addiction risk assessment model was constructed and trained based on a weighted algorithm; After training, the multi-dimensional addiction risk assessment model is obtained.

[0024] The mathematical expression for the multi-dimensional addiction risk assessment model is: Where M represents the fatigue level based on EEG data, V represents the proportion of entertainment content based on behavioral data, X represents the character's performance based on cognitive task data, and T represents the percentage of continuous usage exceeding the allotted time. , , , These are the weighting coefficients, and ; In the specific process described, the fatigue level based on EEG data can be determined according to the growth rate of the theta wave power in the EEG relative to the individual's EEG baseline. For example, when the theta wave power increases by 0% compared to the individual's EEG baseline, M is 0; when the theta wave power increases by 10% compared to the individual's EEG baseline, M is 1; when the theta wave power increases by 20% compared to the individual's EEG baseline, M is 2; when the theta wave power increases by 30% compared to the individual's EEG baseline, M is 3; when the theta wave power increases by 40% compared to the individual's EEG baseline, M is 4; and when the theta wave power increases by 50% compared to the individual's EEG baseline, M is 5.

[0025] The percentage of entertainment content based on behavioral data can be determined by the proportion of entertainment content in VR content. When the proportion of entertainment content is 0%, V is 0; when the proportion of entertainment content is 20%, V is 1; when the proportion of entertainment content is 40%, V is 2; when the proportion of entertainment content is 60%, V is 3; when the proportion of entertainment content is 80%, V is 4; and when the proportion of entertainment content is 100%, V is 5.

[0026] The performance score based on cognitive task data can be determined according to the percentage decrease in the cognitive task accuracy of the target child when completing the random embedded task. When the cognitive task accuracy drops to 0%, the value of X is 0; when the cognitive task accuracy drops to 20%, the value of X is 1; when the cognitive task accuracy drops to 40%, the value of X is 2; when the cognitive task accuracy drops to 60%, the value of X is 3; when the cognitive task accuracy drops to 80%, the value of X is 4; and when the cognitive task accuracy drops to 100%, the value of X is 5.

[0027] The percentage of continuous usage time exceeding the timeout can be obtained by calculating the percentage by which the continuous usage time of the current target child exceeds the preset usage time threshold corresponding to their age. For example, when the continuous usage time exceeds the preset usage time threshold by 0%, T is 0; when the continuous usage time exceeds the preset usage time threshold by 10%, T is 1; when the continuous usage time exceeds the preset usage time threshold by 20%, T is 2; when the continuous usage time exceeds the preset usage time threshold by 30%, T is 3; when the continuous usage time exceeds the preset usage time threshold by 40%, T is 4; and when the continuous usage time exceeds the preset usage time threshold by 50%, T is 5.

[0028] By determining the four indicators in the aforementioned multi-dimensional addiction risk assessment model and assigning their respective weights, a risk assessment value can be calculated. Based on this value, the level of addiction risk can be determined, thus outputting the multi-dimensional addiction risk assessment result. Furthermore, tiered intervention measures can be implemented based on this result, for example: When the calculated risk assessment value is 0-6, it is judged as low risk, and a natural scene reminder will be pushed every four hours, such as 5 minutes. When the calculated risk assessment value is 6-12, it is determined to be medium risk. At this time, it is forcibly switched to a lightweight VR cognitive training task that matches the cognitive development goal. After training for five hours, such as 10 minutes, and meeting the target, it returns to the original VR content. When the calculated risk assessment value is 12-20, it is considered high risk. At this time, VR content will be immediately suspended and parent-child interactive tasks will be pushed. Parents need to confirm the completion before the VR content can be unlocked or educational VR content can be pushed.

[0029] Of course, in the specific implementation process, the risk level can also be classified by direct comparison of indicators, for example: If the theta wave power in the EEG indicators is normal, the accuracy of cognitive tasks is stable, the proportion of educational content is ≥50%, and the continuous usage time does not exceed the preset usage time threshold, then it is judged as low risk. If the theta wave power in the EEG indicators increases by more than 20% compared to the individual's baseline, the accuracy of cognitive tasks decreases by more than 15%, the proportion of entertainment content exceeds 40%, and the continuous usage time does not exceed the preset usage time threshold, it is judged as medium risk. If the theta wave power in the EEG indicators increases by more than 30%, the accuracy rate of cognitive tasks is less than 50%, the proportion of entertainment content exceeds 60%, and the continuous usage time exceeds the preset usage time threshold, it is judged as high risk.

[0030] In some alternative implementations, the dynamic intervention module includes: The scene switching unit is used to trigger natural scene reminders, lightweight cognitive training, or parent-child interactive tasks based on the risk level output by the multi-dimensional addiction risk assessment model. The cognitive training unit is used to match VR cognitive training content with cognitive development goals. Specifically, it can include: Design VR attention tracking tasks for children with attention deficit disorder, such as tracking a fluttering butterfly; For children with weak memory, VR scene memory tasks are designed, such as remembering the location, type or name of items in a VR room; The parent collaboration unit is used to receive real-time child usage reports, customize intervention strategies, and complete parent-child interaction tasks. The child usage reports may include risk level, cognitive performance, intervention records, etc. During implementation, the parent collaboration unit can also be used by parents to customize thresholds for the proportion of educational content, entertainment content, or the ratio of educational to entertainment content; for example, setting the educational content proportion threshold to be greater than or equal to 70%. In practice, the strategies for triggering natural scene reminders, lightweight cognitive training, or parent-child interactive tasks are as follows: During periods of low risk, a natural scene reminder is pushed out every 10 minutes. This natural scene reminder includes elements such as forests or grasslands inserted into the VR experience, combined with the sound of flowing water or soothing music, to promote attention recovery based on the pro-life hypothesis. When needed, children can choose to rest immediately to watch the natural scene and listen to soothing music or the sound of flowing water, or they can choose to rest a few minutes later, thus abruptly cutting off the VR educational content and affecting the educational effect. After resting, they can return to the original VR educational content. In cases of medium risk, a lightweight VR cognitive training task matching the cognitive development goals will be forcibly switched to. After 5-10 minutes of training and meeting the target, the original VR content will be returned. It should be noted that the training duration should be adapted to the child's actual age. A satisfactory cognitive performance after training can be defined as an accuracy rate of ≥80%. If the training is not satisfactory, the parent reminder function will be triggered to remind parents to intervene in a timely manner. In high-risk situations, VR content will be paused and parent-child interactive tasks will be pushed. Parents must confirm completion and upload proof of completion (e.g., photos) before the system resets the continuous usage time and unlocks the VR content. Alternatively, educational or science-related VR content can be pushed to replace the original entertainment content. These parent-child activities can include children and parents looking at dozens of objects outside a window together, or completing a jigsaw puzzle together. The tasks can be customized by both parents and children.

[0031] In practical implementation, this system also includes: a safety monitoring module, which is communicatively connected to the dynamic intervention module, for real-time collection of children's physiological indicators and dynamic adjustment of VR device safety parameters. The safety monitoring module specifically includes: The physiological indicator unit is used to collect children's physiological data and trigger corresponding reminder signals. The children's physiological data may include heart rate, blink frequency, etc., for example: The VR controller uses a built-in sensor to measure heart rate. If the heart rate is greater than 120 beats per minute (the upper limit of the normal range for children), a rest reminder will be triggered. Eye tracking is used to determine blinking frequency; if it is less than 10 times / minute, a visual fatigue warning is issued. The VR adaptation unit is used to adapt VR parameters to children's age. VR parameters can include field of view, screen brightness, and continuous usage time per session, etc. Specifically: For example, the VR field of view for children aged 3-6 should be limited to 80° to avoid dizziness, the screen brightness should be ≤300cd / ㎡ to protect eyesight, the maximum continuous use time per session should be 15 minutes (25 minutes for children aged 7-12), and the mandatory interval rest time should be ≥10 minutes.

[0032] Example 2: like Figure 2 As shown, this embodiment of the invention provides a virtual reality anti-addiction method based on the system described in Embodiment 1. The method includes the following steps: Step 1: Load VR safety parameters corresponding to the target child's age group and establish the target child's personal EEG baseline; Step 2: Synchronously collect EEG data, behavioral data, and cognitive task data of the target children, and conduct a multi-dimensional addiction risk assessment using the multi-dimensional addiction risk assessment model described in Example 1 at the first time interval. Step 3: Implement tiered intervention measures based on the results of the multi-dimensional addiction risk assessment; Step 4: Generate a cognitive development report every second time interval, and iterate the individual EEG baseline and multi-dimensional addiction risk assessment model based on the cognitive development report. The cognitive development report includes: usage time distribution (education / entertainment), number of addiction risk triggers, and changes in cognitive task performance (e.g., a 5% increase in accuracy on attention tasks). In addition, update the cognitive task library and VR intervention scenarios every 3 months (e.g., adding "VR math geometry training" for children aged 7-12, in conjunction with school curriculum progress).

[0033] In some alternative implementations, the process of establishing the individual EEG baseline includes: Step 1.1: Obtain the age and cognitive developmental foundation of the target child; Step 1.2: Load the normal range of EEG indicators, cognitive task library, and VR safety parameters for the target child's age group. The VR safety parameters include preset thresholds for single use time corresponding to the child's age, such as a single use limit of 15 minutes for children aged 3-6 and a single use limit of 25 minutes for children aged 7-12; and may also include preset thresholds for continuous use time corresponding to the child's age, such as a continuous use limit of 45 minutes for children aged 3-6 and a continuous use limit of 90 minutes for children aged 7-12. Step 1.3: Guide the child to complete the basic EEG calibration procedure for the third duration; Step 1.4: Establish the individual EEG baseline for the target child based on the EEG data obtained after the calibration operation.

[0034] In this example, the first duration is 5 minutes, the second duration is one week, and the third duration is 10 minutes.

[0035] In specific implementation, the EEG data in step 2 includes event-related potentials (P300 and N400 components) and the alpha / theta wave spectral power ratio; the behavioral data includes head rotation frequency, frequency of interactive operations, content type, and the proportion of educational / entertainment content; and the cognitive task data includes the performance data of the target child when completing a non-intrusive, randomly embedded task within VR content corresponding to their age group. The EEG data is collected using an EEG headband, and the behavioral data is collected using a VR device.

[0036] Step 2, which describes the process of conducting a multi-dimensional addiction risk assessment using a multi-dimensional addiction risk assessment model, can be summarized as follows: If the calculated value output by the multi-dimensional addiction risk assessment model is less than the first threshold, it is judged as low risk; If the calculated value output by the multi-dimensional addiction risk assessment model is greater than the first threshold and less than the second threshold, it is judged as medium risk. If the calculated value output by the multi-dimensional addiction risk assessment model is greater than the second threshold, it is judged as high risk.

[0037] Specific methods for assessing addiction risk: When the calculated output value is 0-6, it is judged as low risk. At this time, a natural scene reminder will be pushed every four hours, such as 5 minutes. When the output calculated value is 6-12, it is judged as medium risk. At this time, it is forcibly switched to a lightweight VR cognitive training task that matches the cognitive development goal. After training for five hours, such as 10 minutes, and the goal is achieved, it returns to the original VR content. When the output calculated value is 12-20, it is judged as high risk. At this time, VR content is immediately paused and parent-child interactive tasks are pushed. Parents need to confirm the completion before the VR content can be unlocked or educational VR content can be pushed.

[0038] In the specific implementation process, step 3, which involves implementing tiered intervention measures based on the results of a multi-dimensional addiction risk assessment, includes: When the multi-dimensional addiction risk assessment result is low risk, a natural scene reminder will be pushed every fourth hour. When the multi-dimensional addiction risk assessment result is medium risk, the system will forcibly switch to a lightweight VR cognitive training task that matches the cognitive development goals. After five hours of training and meeting the target, the system will return to the original VR content. If the multi-dimensional addiction risk assessment result is high risk, VR content will be immediately suspended and parent-child interactive tasks will be pushed. Parents must confirm the completion before the VR content can be unlocked or educational VR content can be pushed.

[0039] The method described in this embodiment will be applied to a 7-year-old child, Xiaoming, to learn mathematical geometry using VR educational software, in order to help him understand the specific process of the method: Initial setup: Parents input Xiaoming's age as 7 years old, and the VR safety parameters for "7-12 years old" are loaded: maximum single use time of 25 minutes, cognitive task is "geometric shape memory", and the EEG baseline is theta wave power ≥30%; Real-time monitoring: When Xiaoming used VR for 15 minutes, he was given a "geometric shape memory task". The VR displayed 3 shapes and asked him to choose one after 10 seconds. His accuracy rate in the cognitive task data was 80%. However, the EEG headband showed that the theta wave power increased to 45% in the EEG data. Behavioral data showed that his head rotation frequency decreased by 30%, which may indicate that he has attention deficit. Risk Assessment: Based on the EEG data, behavioral data, and cognitive task data of the target children collected above, a multi-dimensional addiction risk assessment was conducted using a multi-dimensional addiction risk assessment model, which determined the risk to be medium (cognitive fatigue + inattention, normal cognitive performance). Dynamic intervention: Automatically switch to "VR geometric puzzle training scenario" (cognitive training). Xiaoming completes the puzzle in 5 minutes with an accuracy rate of 90%. When the EEG shows that the theta wave power drops to 35%, cognitive fatigue is relieved. Feedback on effectiveness: After the training is completed, return to math and geometry learning, and synchronize the intervention record to the parent's APP. After the parent views it, set "the proportion of follow-up education content ≥ 70%"; Safety monitoring: Xiaoming's heart rate was monitored throughout the process (stable at 90 beats / minute, which is normal), and the VR brightness was maintained at 250 cd / ㎡ (suitable for the visual needs of a 7-year-old child) to avoid safety risks.

[0040] In summary, this invention integrates EEG physiological indicators, behavioral data, and cognitive performance data to accurately distinguish between "focused learning" and "passive addiction" and provide dynamic intervention. This fills a research gap in the "neural mechanism-anti-addiction-cognitive development" framework and realizes an innovative application of VR technology in anti-addiction efforts. Through deep integration of VR cognitive training and anti-addiction measures, the intervention avoids the negative impacts of screen addiction while promoting children's attention, memory, and other cognitive abilities. It deeply considers the differences in children's age and cognitive development stages, adjusting thresholds and tasks according to the child's age and individual baseline during intervention, resulting in higher personalization. By collecting children's physiological indicators in real time and dynamically adjusting VR device safety parameters, it achieves dual protection of physiological and VR parameters, ensuring high safety. It provides visualized children's usage reports and operable collaborative intervention plans, addressing the pain point of "concern about excessive screen time but lack of effective intervention methods," and effectively increases parental involvement through parent-child interactive tasks.

[0041] The technical solution provided by this invention has been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this invention. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this invention. It should be noted that those skilled in the art can make several improvements and modifications to this invention without departing from the principles of this invention, and these improvements and modifications also fall within the protection scope of the claims of this invention.

Claims

1. A method for preventing virtual reality addiction, characterized in that, Includes the following steps: Step 1: Load VR safety parameters corresponding to the target child's age group and establish the target child's personal EEG baseline; Step 2: Simultaneously collect EEG data, behavioral data, and cognitive task data of the target children, and conduct a multi-dimensional addiction risk assessment using a multi-dimensional addiction risk assessment model at the first interval of each time period. Step 3: Implement tiered intervention measures based on the results of the multi-dimensional addiction risk assessment; Step 4: Generate a cognitive development report every second time interval, and iterate the personal EEG baseline and multi-dimensional addiction risk assessment model based on the cognitive development report.

2. The virtual reality anti-addiction method according to claim 1, characterized in that: The process of establishing the individual's EEG baseline includes: Step 1.1: Obtain the age and cognitive developmental foundation of the target child; Step 1.2: Load the normal range of EEG indicators, cognitive task library, and VR safety parameters for the target child's corresponding age group; Step 1.3: Guide the child to complete the basic EEG calibration procedure for the third duration; Step 1.4: Establish the individual EEG baseline for the target child based on the EEG data obtained after the calibration operation.

3. The virtual reality anti-addiction method according to claim 1, characterized in that: The EEG data mentioned in step 2 includes event-related potentials (P300, N400 components) and the alpha / theta wave spectral power ratio; the behavioral data includes head rotation frequency, frequency of interactive operations, content type, and the proportion of educational / entertainment content; and the cognitive task data includes the performance data of the target child when completing non-interference random embedded tasks in VR content corresponding to the age group.

4. The virtual reality anti-addiction method according to claim 3, characterized in that: The electroencephalogram (EEG) data was collected using an EEG headband, and the behavioral data was collected using a VR device.

5. The virtual reality anti-addiction method according to claim 1, characterized in that: Step 2, which describes conducting a multi-dimensional addiction risk assessment using a multi-dimensional addiction risk assessment model, specifically includes: If the calculated value output by the multi-dimensional addiction risk assessment model is less than the first threshold, it is judged as low risk; If the calculated value output by the multi-dimensional addiction risk assessment model is greater than the first threshold and less than the second threshold, it is judged as medium risk. If the calculated value output by the multi-dimensional addiction risk assessment model is greater than the second threshold, it is judged as high risk.

6. The virtual reality anti-addiction method according to claim 1, characterized in that: Step 3, which describes implementing tiered intervention measures based on the results of a multi-dimensional addiction risk assessment, includes: When the multi-dimensional addiction risk assessment result is low risk, a natural scene reminder will be pushed every fourth hour. When the multi-dimensional addiction risk assessment result is medium risk, the system will forcibly switch to a lightweight VR cognitive training task that matches the cognitive development goals. After five hours of training and meeting the target, the system will return to the original VR content. If the multi-dimensional addiction risk assessment result is high risk, VR content will be immediately suspended and parent-child interactive tasks will be pushed. Parents must confirm the completion before the VR content can be unlocked or educational VR content can be pushed.

7. A virtual reality anti-addiction system capable of implementing the method according to any one of claims 1-6, characterized in that, include: The data acquisition module is used to acquire the target child's EEG data, behavioral data, and cognitive task data in real time. The data analysis module is used to construct an individual EEG baseline based on the target child's age group and to conduct a multi-dimensional addiction risk assessment using a multi-dimensional addiction risk assessment model. The dynamic intervention module is used to implement tiered intervention measures based on the results of a multi-dimensional addiction risk assessment. The iterative update module is used to generate a cognitive development report every second time interval, and iterate the individual EEG baseline and multi-dimensional addiction risk assessment model based on the cognitive development report.

8. The virtual reality anti-addiction system according to claim 7, characterized in that, The data acquisition module includes: The EEG monitoring unit is used to collect EEG data from target children when they use VR devices via an EEG headband; The behavior monitoring unit is used to collect behavioral data of the target child when using the VR device through the built-in sensors of the VR device. Cognitive task units are used to collect cognitive task data from target children as they complete non-intrusive, randomly embedded tasks from a built-in age-group cognitive task library.

9. The virtual reality anti-addiction system according to claim 7, characterized in that, The data analysis module includes: Age-group adaptation unit, used to load preset parameters according to the age of the target child; The addiction risk assessment unit is used to build a multi-dimensional addiction risk assessment model; The cognitive state analysis unit is used to correlate the normal range of EEG indicators, behavioral data, and cognitive task data of the target child for the corresponding age group to analyze the current cognitive state of the target child.

10. The virtual reality anti-addiction system according to claim 7, characterized in that, The dynamic intervention module includes: The scene switching unit is used to trigger natural scene reminders, lightweight cognitive training, or parent-child interactive tasks based on the risk level output by the multi-dimensional addiction risk assessment model. The cognitive training unit is used to match VR cognitive training content with cognitive development goals; The parent collaboration unit is used to receive real-time reports on children's usage, customize intervention strategies, and complete parent-child interaction tasks.

Images