Safety monitoring method and system for VR flight device

Abstract

The embodiment of the application provides a kind of VR flight device safety monitoring method and system, first, the real-time running data set of VR flight device is acquired, this real-time running data set covers environmental perception data and equipment state data;Then the real-time running data set is analyzed and handled, and the safety state evaluation result is generated, and then the dynamic safety strategy matching processing is executed based on the safety state evaluation result, and the safety control instruction is obtained, finally, the VR flight device operating parameter is adjusted according to the safety control instruction, and the early warning feedback operation is triggered, so as to comprehensively and dynamically monitor the operation safety of VR flight device, discover potential risk in time and carry out effective regulation, ensure stable operation of equipment and user safety experience.

Description

Technical Field

[0001] This application relates to the field of virtual reality technology, and more specifically, to a safety monitoring method and system for VR flight devices. Background Technology

[0002] With the continuous development of virtual reality (VR) technology, VR flight devices, as a type of equipment that can provide users with an immersive flight experience, have been widely used in various fields such as entertainment, education, and training. However, there are currently many shortcomings in the safety monitoring of VR flight devices.

[0003] Existing safety monitoring methods for VR flight devices are often static, relying on pre-set fixed standards to determine device safety. This approach cannot dynamically adjust based on the real-time operation of the VR flight device, resulting in an inability to make effective safety assessments in the face of emergencies or subtle changes in the device's operating status.

[0004] Furthermore, existing security control measures are limited and lack specificity when potential security issues are detected. They typically only issue alarms or stop device operation without developing personalized control strategies based on the specific security situation. This not only affects the user experience but also fails to maximize the security of both the device and the user. Summary of the Invention

[0005] In view of this, the purpose of this application is to provide a safety monitoring method and system for VR flight devices.

[0006] According to a first aspect of this application, a safety monitoring method for a VR flight device is provided, applied to a VR service system, the method comprising:

[0007] Acquire a set of real-time operational data for the VR flight device, the set of real-time operational data including environmental perception data and device status data;

[0008] The real-time operational data set is subjected to security analysis and processing to generate a security status assessment result;

[0009] Based on the security status assessment results, dynamic security policy matching processing is performed to obtain security control instructions;

[0010] Adjust the operating parameters of the VR flight device according to the safety control instructions, and trigger the early warning feedback operation.

[0011] According to a second aspect of this application, a VR service system is provided, the VR service system including a processor and a readable storage medium storing a program that, when executed by the processor, implements the aforementioned safety monitoring method for VR flight devices.

[0012] According to a third aspect of this application, a computer-readable storage medium is provided, wherein computer-executable instructions are stored in the computer-readable storage medium, and when the execution of the computer-executable instructions is detected, the aforementioned safety monitoring method for VR flight devices is implemented.

[0013] Based on any of the above aspects, embodiments of this application acquire a real-time operational data set including environmental perception data and device status data, perform security analysis and processing on the real-time operational data set, and generate a security status assessment result. This enables in-depth mining of potential security risks behind the data, achieving accurate assessment of the operational safety of the VR flight device. Based on this security status assessment result, dynamic security strategy matching processing is executed to obtain security control instructions. The most suitable response strategy can be flexibly matched according to different security states, making security management more targeted and dynamically adaptable. The operating parameters of the VR flight device are adjusted according to the security control instructions, and early warning feedback operations are triggered. This enables timely response to potential dangers, effectively reducing safety hazards during the operation of the VR flight device, ensuring stable operation of the device, and enhancing the user's safety experience. Attached Figure Description

[0014] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 A flowchart illustrating the safety monitoring method for VR flight devices provided in an embodiment of this application is shown.

[0016] Figure 2 A schematic diagram of the component structure of a VR service system for implementing the above-described safety monitoring method for VR flight devices, provided in an embodiment of this application, is shown. Detailed Implementation

[0017] 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 of the present application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present application.

[0018] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0019] Figure 1 The diagram illustrates a flowchart of a safety monitoring method for VR flight devices provided in an embodiment of this application. It should be understood that in other embodiments, the order of some steps in the safety monitoring method for VR flight devices can be interchanged according to actual needs, or some steps can be omitted or deleted. The detailed steps of this safety monitoring method for VR flight devices are described below.

[0020] Example Implementation Section:

[0021] Step S110: Obtain the real-time operation data set of the VR flight device, which includes environmental perception data and device status data.

[0022] In this embodiment, to ensure safe monitoring during flight, the VR flight device needs to collect comprehensive and accurate operational data in real time. For acquiring environmental perception data, the VR flight device is equipped with various types of environmental sensors. When the lidar sensor is working, it emits laser beams into the surrounding environment. Based on the time and angle information of the reflected laser beams, it accurately calculates the distance and orientation of surrounding objects to the flight device. Its high scanning frequency allows it to scan the surrounding environment multiple times in a short period to capture dynamic changes. For example, in a relatively complex flight scenario, the lidar sensor continuously emits laser beams, potentially performing dozens or even hundreds of scans per second, forming a series of point cloud data. This point cloud data reflects the spatial distribution of surrounding objects.

[0023] The camera sensor acquires visual information by capturing images of the flight scene. It has different resolution and frame rate settings to adapt to different flight environments and monitoring needs. In well-lit environments, high-resolution cameras can capture clear images, facilitating subsequent object identification and analysis. Simultaneously, the camera can employ multi-angle shooting to expand the field of view and reduce blind spots. For example, multiple cameras can be installed at different locations on the flight device to capture images of the surrounding environment from different angles; these images can then be stitched and merged to obtain a more comprehensive environmental image.

[0024] Meteorological sensors are used to measure environmental meteorological parameters, including temperature, humidity, wind speed, and air pressure. These meteorological parameters are crucial for the flight safety of VR flight devices. Temperature sensors measure temperature by sensing the thermal effect of the surrounding air, while humidity sensors measure humidity by utilizing the adsorption and desorption properties of specific materials for water vapor. Wind speed sensors can use different working principles, such as mechanical or ultrasonic, to measure wind speed and direction, while air pressure sensors obtain air pressure information by measuring changes in atmospheric pressure. These meteorological sensors transmit the measured data to the flight device's control system in real time.

[0025] Various monitoring systems within the flight vehicle play a crucial role in acquiring equipment status data. Accelerometers, utilizing Newton's second law, determine the flight vehicle's acceleration changes by measuring the force generated by a mass under acceleration. They can accurately measure the acceleration components of the flight vehicle along three coordinate axes and possess high sensitivity and response speed. During flight, the accelerometers continuously collect acceleration data, which reflects the flight vehicle's acceleration, deceleration, and turning motion.

[0026] Gyroscopes, based on the principle of conservation of angular momentum, determine the attitude changes of a flight device by measuring its angular velocity. They can monitor the pitch, roll, and yaw attitude information of the flight device in real time with high accuracy and stability. During flight, the gyroscope continuously outputs attitude data, which is crucial for the attitude control and navigation of the flight device.

[0027] The energy management system monitors the flight device's energy consumption, including battery level and power output. It calculates remaining battery power and power output in real time by measuring parameters such as battery voltage and current. Furthermore, the energy management system optimizes energy allocation and usage to improve energy efficiency. For example, when the flight device is in different flight modes, the energy management system adjusts the energy allocation ratio according to actual needs, ensuring that the flight device utilizes energy to the maximum extent possible while maintaining safety.

[0028] By integrating the aforementioned environmental perception data and equipment status data, a real-time operational data set for the VR flight device is formed.

[0029] Step S120: Perform security analysis and processing on the real-time running data set to generate a security status assessment result.

[0030] In this embodiment, in order to perform effective safety analysis and processing on the real-time operation data set of the VR flight device, it is necessary to further mine the key information in the data, extract representative features, and combine them with a pre-trained model for comprehensive evaluation.

[0031] Step S121: Extract environmental dynamic features from the environmental perception data and extract equipment operation features from the equipment status data.

[0032] In this embodiment, environmental dynamics reflect the real-time changes in the flight environment, while equipment operational characteristics reflect the operational status of the flight device itself. Accurate extraction of these two types of characteristics is a crucial step in safety analysis.

[0033] Step S1211: Perform dynamic scene segmentation processing on the environmental perception data to generate multiple scene regions.

[0034] In this embodiment, dynamic scene segmentation of environmental perception data is performed to divide the complex flight environment into relatively independent regions with different characteristics, enabling more detailed analysis of the environmental situation. Scene segmentation can be based on spatial information and object distribution.

[0035] For point cloud data acquired by LiDAR, density-based clustering algorithms can be used for scene segmentation. This algorithm first defines a neighborhood radius and a minimum point count threshold. Then, starting from a single point, it searches for points within its neighborhood. If the number of points in the neighborhood exceeds the minimum point count threshold, these points are grouped into a cluster. This process continues, searching and clustering unprocessed points until all points have been processed. In this way, point cloud data can be divided into multiple clusters, each corresponding to a scene region.

[0036] For image data captured by a camera, image segmentation algorithms can be used for scene segmentation. For example, deep learning-based semantic segmentation algorithms classify each pixel in the image, dividing it into different semantic regions. These semantic regions can represent different scene elements, such as the ground, buildings, and obstacles. In practical applications, appropriate semantic categories can be selected according to specific needs, and then the image can be segmented into multiple scene regions.

[0037] When performing scene segmentation, it is also necessary to consider dynamic changes in the environment. For example, during flight, surrounding objects may move or change, so the scene segmentation results need to be updated in real time. A time window approach can be used, where scene segmentation is performed on the environmental perception data within each time window, and then the segmentation results of adjacent time windows are compared, with the changed areas being re-segmented and updated.

[0038] Step S1212: Perform obstacle recognition processing for each scene area to determine the obstacle distribution characteristics.

[0039] In this embodiment, after generating multiple scene regions, it is necessary to accurately identify obstacles within each scene region to determine their distribution characteristics. For obstacle identification in LiDAR point cloud data, a feature extraction and classification-based method can be employed. First, geometric features, such as curvature and normal vectors, are extracted from the point cloud data. Then, feature vectors are constructed using these features, and machine learning classification algorithms, such as support vector machines and random forests, are used to classify the points in the point cloud data into obstacle points and non-obstacle points. Next, the points classified as obstacle points are clustered to obtain a point cloud set for each obstacle.

[0040] For obstacle recognition in camera image data, object detection algorithms can be used. Object detection algorithms can locate and identify different types of obstacles in an image and provide their bounding box information. Common object detection algorithms include deep learning-based algorithms such as Faster R-CNN and YOLO. These algorithms learn the features and patterns of different types of obstacles by training on large amounts of image data, thus enabling them to accurately detect obstacles in new images.

[0041] When determining the distribution characteristics of obstacles, information such as their location, size, and shape needs to be considered. The location of an obstacle can be represented by its center coordinates. In LiDAR point cloud data, the centroid coordinates of the obstacle point cloud set can be calculated as the obstacle's center coordinates; in camera image data, the center coordinates can be calculated based on the obstacle's bounding box information. The size of an obstacle can be represented by the length and width of its circumscribed rectangle. In LiDAR point cloud data, the length and width of its circumscribed rectangle can be obtained by calculating the maximum and minimum coordinate values ​​of the obstacle point cloud set along different coordinate axes; in camera image data, the length and width of its circumscribed rectangle can be directly obtained from the obstacle's bounding box information. The shape of an obstacle can be described using its contour information. In LiDAR point cloud data, its contour information can be obtained by extracting the boundaries of the obstacle point cloud set; in camera image data, its contour information can be obtained by edge detection within the obstacle's bounding box.

[0042] By identifying and analyzing obstacles within each scene area, the distribution characteristics of obstacles in the entire flight environment can be obtained.

[0043] Step S1213: Perform feature calculations based on the obstacle distribution characteristics to generate the environmental dynamic features; wherein, the environmental dynamic features include obstacle density features, dynamic change rate features, and spatial distribution uniformity features; the obstacle density features are determined by statistically analyzing the ratio of the number of obstacles to the area of ​​each scene region; the dynamic change rate features are determined by calculating the change amplitude of obstacle distribution within adjacent time windows; the spatial distribution uniformity features are determined by calculating the positional dispersion of obstacles in each scene region, and the dispersion is analyzed using statistical variance methods.

[0044] In this embodiment, after obtaining the obstacle distribution characteristics, it is necessary to further calculate the dynamic characteristics of the environment in order to more comprehensively describe the dynamic changes of the flight environment.

[0045] To calculate obstacle density features, the first step is to count the number of obstacles within each scene region. In LiDAR point cloud data, this can be done by counting the obstacle point cloud set; similarly, in camera image data, it can be done by counting the detected obstacles. Next, the area of ​​each scene region is calculated. For scene regions segmented from LiDAR point cloud data, their area can be calculated based on their spatial coordinates; for scene regions segmented from camera image data, their actual area can be calculated based on the number of pixels in the image and the image resolution. Finally, the obstacle density feature of each scene region is obtained by dividing the number of obstacles by its area.

[0046] Calculating the dynamic rate of change characteristic requires comparing obstacle distribution within adjacent time windows. First, determine the size of the time window, for example, set to 1 second or 2 seconds. Then, calculate the obstacle distribution characteristics within each time window, such as obstacle location and quantity. Next, compare the changes in obstacle distribution characteristics within adjacent time windows and calculate the magnitude of these changes. For example, the average distance obstacle locations move, the rate of change in obstacle quantity, etc., can be calculated within adjacent time windows. These magnitudes of change are then incorporated into the dynamic rate of change characteristic.

[0047] To calculate the spatial distribution uniformity feature, it is necessary to calculate the positional dispersion of obstacles in each scene region. First, the center coordinates of obstacles in each scene region are used as sample points. Then, the mean coordinates of these sample points are calculated. Next, the squared distance between each sample point and the mean coordinates is calculated, and the squared distances of all sample points are summed. Finally, the summation is divided by the number of sample points to obtain the variance of the obstacle positions, i.e., the spatial distribution uniformity feature.

[0048] Through the above calculations, we can obtain the dynamic characteristics of the environment, including obstacle density characteristics, dynamic change rate characteristics, and spatial distribution uniformity characteristics. These characteristics can be represented in vector form, with each characteristic component corresponding to a specific characteristic value.

[0049] Step S1214: Perform time-series segmentation processing on the device status data to generate multiple device operation segments.

[0050] In this embodiment, to better analyze the equipment status data, it is necessary to perform time-series segmentation, dividing the continuous equipment status data into multiple equipment operation segments with different characteristics. Time-series segmentation can be performed based on the changing trends and characteristics of the equipment status data.

[0051] For acceleration data acquired by accelerometers, a threshold-based segmentation method can be used. First, an acceleration change threshold is set. Then, starting from the beginning of the acceleration data, the acceleration change values ​​between adjacent data points are compared. If the acceleration change value exceeds the threshold, that point is considered a segmentation point, and the data is divided into two segments. Next, subsequent data are processed until all data has been segmented.

[0052] For attitude data acquired by gyroscopes, a clustering-based segmentation method can be used. The attitude data is viewed as points in a high-dimensional space, and a clustering algorithm is used to divide these points into different clusters. Each cluster corresponds to a segment of device operation. For example, the K-Means clustering algorithm can be used to divide the attitude data into K clusters, where the value of K can be adjusted according to the actual situation.

[0053] When performing time-series segmentation, the actual operating conditions of the equipment must also be considered. For example, when a flight device undergoes different flight phases such as takeoff, cruise, and landing, the equipment status data will change significantly. Therefore, the results of time-series segmentation can be further adjusted and optimized by incorporating information from each flight phase.

[0054] Step S1215: Perform operation mode recognition processing for each device operation segment to determine the device operation mode characteristics.

[0055] In this embodiment, after generating multiple device operation segments, each segment needs to undergo operation mode recognition processing to determine the device's operation mode characteristics. These operation mode characteristics can reflect the operational status of the flight device at different stages.

[0056] For acceleration data, the operating mode can be identified by analyzing the shape and characteristics of the acceleration curve. For example, a large positive value in the acceleration curve may indicate that the flight device is accelerating; a large negative value may indicate that the flight device is decelerating; and a value close to zero may indicate that the flight device is flying at a constant speed. Rules for identifying the operating mode can be constructed based on the slope, peak value, and other characteristics of the acceleration curve.

[0057] For attitude data, operating modes can be identified by analyzing changes in attitude angles. For example, a large change in pitch angle may indicate that the aircraft is climbing or descending; a large change in roll angle may indicate that the aircraft is turning. Rules for operating mode recognition can be constructed based on characteristics such as the rate and range of change of attitude angles.

[0058] Furthermore, energy consumption data can be combined to further confirm the operating mode. For example, when the flight device accelerates, the energy consumption rate usually increases; when the flight device flies at a constant speed, the energy consumption rate is relatively stable. By comprehensively analyzing acceleration data, attitude data, and energy consumption data, the operating mode of the equipment can be identified more accurately, and the corresponding operating mode characteristics can be determined.

[0059] Step S1216: Calculate the equipment load fluctuation index and equipment energy consumption trend index based on the equipment operation mode characteristics.

[0060] In this embodiment, after determining the characteristics of the equipment's operating mode, it is necessary to further calculate the equipment load fluctuation index and the equipment energy consumption trend index in order to evaluate the equipment's operating status and energy utilization.

[0061] The calculation of equipment load fluctuation index can be based on acceleration and attitude data to reflect the equipment's load status. First, the standard deviations of acceleration and attitude angles are calculated for each equipment operation segment. The standard deviation of acceleration reflects the magnitude of acceleration change during movement, while the standard deviation of attitude angles reflects the magnitude of attitude change during adjustment. Then, the standard deviations of acceleration and attitude angles are weighted and summed to obtain the equipment load fluctuation index. The weights can be adjusted according to actual conditions; for example, they can be determined based on the degree of influence of acceleration and attitude on the equipment load.

[0062] The calculation of equipment energy consumption trend indicators can be based on energy consumption data analysis. First, calculate the average energy consumption rate within each equipment operating segment. Then, analyze the changes in the average energy consumption rate between adjacent equipment operating segments. If the average energy consumption rate shows an upward trend, it indicates that the equipment's energy consumption is increasing; if the average energy consumption rate shows a downward trend, it indicates that the equipment's energy consumption is decreasing. The equipment energy consumption trend indicator can be obtained by calculating the difference in average energy consumption rates between adjacent equipment operating segments.

[0063] Step S1217: Aggregate the equipment load fluctuation index and the equipment energy consumption trend index to generate the equipment operating characteristics.

[0064] In this embodiment, after calculating the equipment load fluctuation index and the equipment energy consumption trend index, these two indexes need to be aggregated to generate equipment operating characteristics. A weighted concatenation method can be used for aggregation.

[0065] First, determine the weights of the equipment load fluctuation index and the equipment energy consumption trend index. The weights can be adjusted based on actual conditions; for example, they can be determined based on the degree of impact of equipment load fluctuation and energy consumption trend on equipment operating status. Then, multiply the equipment load fluctuation index and the equipment energy consumption trend index by their respective weights to obtain weighted indices. Finally, concatenate the weighted equipment load fluctuation index and the equipment energy consumption trend index to obtain the equipment operating characteristics. These characteristics can be represented as a vector, with one component corresponding to the equipment load fluctuation index and the other to the equipment energy consumption trend index.

[0066] Step S122: Input the environmental dynamic characteristics and the equipment operation characteristics into the pre-trained safety assessment model to generate a comprehensive risk assessment index.

[0067] In this embodiment, after obtaining the environmental dynamics and equipment operating characteristics, they need to be input into a pre-trained safety assessment model to generate a comprehensive risk assessment index. The comprehensive risk assessment index can fully reflect the degree of safety risk of the VR flight device under the current environment and operating condition.

[0068] Step S1221: Perform a first standardization process on the environmental dynamic characteristics to obtain standardized environmental characteristics.

[0069] In this embodiment, in order to better adapt the environmental dynamic characteristics to the safety assessment model, a first standardization process is required. Standardization eliminates dimensional differences between different characteristics, making them comparable.

[0070] Z-score standardization can be used to process the dynamic features of the environment. First, calculate the mean and standard deviation of each feature component in the dynamic environmental feature vector. Then, for each feature component, subtract the mean and divide by the standard deviation to obtain the standardized feature component. By standardizing all feature components in the dynamic environmental feature vector, a standardized environmental feature vector can be obtained.

[0071] Step S1222: Perform a second standardization process on the equipment operating characteristics to obtain standardized equipment characteristics.

[0072] In this embodiment, similarly, in order to better input the device operating characteristics into the safety assessment model, a second standardization process is required.

[0073] The same Z-score standardization method as the first standardization process is used. The mean and standard deviation of each feature component in the equipment operation feature vector are calculated. Then, the mean is subtracted from each feature component, and the result is divided by the standard deviation to obtain the standardized feature component. After standardizing all feature components in the equipment operation feature vector, the standardized equipment feature vector is obtained.

[0074] Step S1223: Input the standardized environmental features and the standardized equipment features into the feature interaction layer of the pre-trained security assessment model to generate an interaction feature vector.

[0075] In this embodiment, the feature interaction layer in the pre-trained security assessment model is used to fuse standardized environmental features and standardized device features to generate an interactive feature vector. The feature interaction layer employs a cross-attention mechanism to achieve feature fusion.

[0076] The cross-attention mechanism first calculates the attention score between standardized environment features and standardized device features. For each feature component in the standardized environment feature vector, its similarity to each feature component in the standardized device feature vector is calculated. Similarity can be calculated using methods such as dot product or cosine similarity. These similarity scores are then normalized to obtain attention weights. Next, the standardized device feature vectors are weighted and summed according to the attention weights to obtain the interaction features corresponding to each feature component in the standardized environment feature vector. Finally, all interaction features are combined to form the interaction feature vector.

[0077] Step S1224: The risk assessment layer in the safety assessment model is invoked to perform nonlinear mapping processing on the interactive feature vector to generate the comprehensive risk assessment index; wherein, the feature interaction layer fuses the standardized environmental features and the standardized equipment features through a cross-attention mechanism; the risk assessment layer performs weighted calculation on the interactive feature vector through a multilayer perceptron to output the comprehensive risk assessment index; the comprehensive risk assessment index includes a weighted sum of environmental risk contribution and equipment risk contribution.

[0078] In this embodiment, the risk assessment layer in the security assessment model uses a multilayer perceptron to perform nonlinear mapping processing on the interaction feature vectors in order to generate a comprehensive risk assessment index.

[0079] A multilayer perceptron (MLP) consists of an input layer, hidden layers, and an output layer. The interaction feature vector serves as the input to the input layer, undergoes nonlinear transformation and weighted calculation in the hidden layers, and finally outputs a comprehensive risk assessment index at the output layer. Neurons in the hidden layers perform nonlinear transformations on the input using activation functions, such as the ReLU function, to enhance the model's expressive power. During the training process of the MLP, the connection weights between neurons are continuously adjusted using the backpropagation algorithm, enabling the model to learn the mapping relationship between the interaction feature vector and the comprehensive risk assessment index.

[0080] The comprehensive risk assessment index comprises a weighted sum of environmental risk contribution and equipment risk contribution. The environmental risk contribution is calculated based on the output of standardized environmental features in the multilayer sensing network (MLN), while the equipment risk contribution is calculated based on the output of standardized equipment features in the same network. First, the MSN processes the corresponding interaction features of the standardized environmental and equipment features, respectively, to obtain intermediate outputs related to the environment and equipment. Then, these intermediate outputs are weighted and summed to obtain the environmental and equipment risk contributions. Specifically, for the calculation of the environmental risk contribution, a weight is assigned to each component of the environment-related intermediate output in the MSN; these weights are learned during model training. Each component is multiplied by its corresponding weight and then summed to obtain the environmental risk contribution. Similarly, for the equipment risk contribution, a weight is assigned to each component of the equipment-related intermediate output in the MSN, and then the weighted sum is obtained. Finally, the environmental risk contribution and equipment risk contribution are multiplied by their respective total weights, and the two results are summed to obtain the comprehensive risk assessment index. The total weights here are also adjusted and determined during model training based on the degree of impact of environmental and equipment factors on the overall safety risk.

[0081] Step S123: Perform dynamic comparison processing based on the comprehensive risk assessment index and the preset safety threshold to determine the safety status assessment result.

[0082] In this embodiment, to accurately assess the safety status of the VR flight device, it is necessary to dynamically compare the comprehensive risk assessment indicators with preset safety thresholds. Since the flight environment and equipment operating status are constantly changing, the preset safety thresholds also need to be adjusted in real time according to the actual situation.

[0083] Step S1231: Obtain the dynamic safety threshold adjustment coefficient under the current environmental scenario.

[0084] In this embodiment, obtaining the dynamic safety threshold adjustment coefficient requires comprehensive consideration of environmental complexity and equipment stability. Environmental complexity parameters are calculated based on obstacle density and dynamic change rate indices from environmental perception data. First, the obstacle density index is obtained by statistically analyzing the ratio of the number of obstacles to the area of ​​each scene region. The obstacle density indices of each scene region are then summarized and analyzed to obtain a comprehensive obstacle density index. The dynamic change rate index is determined by calculating the magnitude of change in obstacle distribution within adjacent time windows. Similarly, the dynamic change rate indices of each scene region are summarized and analyzed to obtain a comprehensive dynamic change rate index. Then, weights are assigned to the obstacle density index and the dynamic change rate index, respectively, based on their respective impacts on environmental complexity. Multiplying the obstacle density index by its corresponding weight and the dynamic change rate index by its corresponding weight, and then adding these two results, yields the environmental complexity parameters.

[0085] Equipment stability parameters are calculated based on load fluctuation and energy consumption trend indices from equipment status data. The load fluctuation index is obtained by weighted summation of the standard deviations of acceleration and attitude angles within a given equipment operating segment. The energy consumption trend index is obtained by analyzing the changes in the average energy consumption rate between adjacent equipment operating segments. Similarly, weights are assigned to the load fluctuation and energy consumption trend indices respectively. The load fluctuation index is multiplied by its corresponding weight, and the energy consumption trend index is multiplied by its corresponding weight. The two results are then added together to obtain the equipment stability parameters.

[0086] Finally, the environmental complexity parameter and the equipment stability parameter are weighted and summed to obtain the dynamic safety threshold adjustment coefficient. The weights assigned to the environmental complexity parameter and the equipment stability parameter are determined based on the degree of influence of environmental factors and equipment factors on the safety threshold adjustment.

[0087] Step S1232: The preset security threshold is corrected in real time according to the dynamic security threshold adjustment coefficient to generate a dynamic security threshold.

[0088] In this embodiment, after obtaining the dynamic safety threshold adjustment coefficient, the preset safety threshold needs to be corrected in real time. The preset safety threshold is a fixed value determined during model training or system initialization, representing the safety risk limit of the VR flight device under normal circumstances. Multiplying the preset safety threshold by the dynamic safety threshold adjustment coefficient yields the dynamic safety threshold. In this way, the dynamic safety threshold can be adjusted in real time according to the current environmental complexity and equipment stability, more accurately reflecting the safety requirements under the current flight state.

[0089] Step S1233: Compare the comprehensive risk assessment index with the dynamic safety threshold.

[0090] In this embodiment, the comprehensive risk assessment index calculated above is directly compared with the dynamic safety threshold. This comparison is based on numerical magnitude and aims to determine whether the safety risk of the current VR flight device exceeds the permissible range under the current environmental and equipment conditions.

[0091] Step S1234: When the comprehensive risk assessment index is greater than the dynamic safety threshold, a first risk assessment result is generated.

[0092] In this embodiment, if the comprehensive risk assessment index exceeds the dynamic safety threshold, it indicates that the current VR flight device faces a high safety risk and a dangerous situation may occur. At this time, a first risk assessment result is generated, which represents a high-risk state.

[0093] Step S1235: When the comprehensive risk assessment index is less than or equal to the dynamic safety threshold, a second risk assessment result is generated.

[0094] In this embodiment, if the comprehensive risk assessment index is less than or equal to the dynamic safety threshold, it indicates that the safety risk of the current VR flight device is within an acceptable range, and the flight status is relatively safe. At this time, a second risk assessment result is generated, which represents a low-risk state.

[0095] Step S1236: Determine the safety status assessment result based on the first risk assessment result or the second risk assessment result.

[0096] In this embodiment, the first risk assessment result and the second risk assessment result are used as the basis for judgment to finally determine the safety status assessment result of the VR flight device. If the first risk assessment result is obtained, the safety status assessment result is a high-risk state; if the second risk assessment result is obtained, the safety status assessment result is a low-risk state.

[0097] Step S130: Perform dynamic security policy matching processing based on the security status assessment results to obtain security control instructions.

[0098] In this embodiment, based on the previously determined safety status assessment results, dynamic safety strategy matching processing needs to be performed to obtain corresponding safety control instructions, thereby adjusting the operation of the VR flight device to ensure flight safety.

[0099] Step S131: When the safety status assessment result is the first risk assessment result, the pre-stored emergency control strategy library is invoked to match the first safety control instruction corresponding to the current environmental risk level and equipment operation risk level.

[0100] In this embodiment, if the safety status assessment result is the first risk assessment result, i.e., a high-risk state, it is necessary to call the pre-stored emergency control strategy library. The emergency control strategy library contains a variety of control strategies for high-risk situations, such as equipment emergency speed reduction strategies, environmental obstacle avoidance path adjustment strategies, and energy supply enhancement strategies.

[0101] First, determine the current environmental risk level and the equipment operational risk level. The environmental risk level can be determined based on environmental complexity parameters; the higher the environmental complexity parameter, the higher the environmental risk level. The equipment operational risk level can be determined based on equipment stability parameters; the lower the equipment stability parameter, the higher the equipment operational risk level. Then, search the emergency control strategy library for a strategy combination that matches the current environmental risk level and the equipment operational risk level. For example, if both the environmental risk level and the equipment operational risk level are high, an emergency equipment deceleration strategy, an environmental obstacle avoidance path adjustment strategy, and an energy supply enhancement strategy might be executed simultaneously. Combining these matching strategies yields the first safety control instruction. The first safety control instruction contains the specific parameters required to execute these strategies, such as the priority parameter for the emergency equipment deceleration strategy, the path offset parameter for the environmental obstacle avoidance path adjustment strategy, and the energy allocation ratio parameter for the energy supply enhancement strategy.

[0102] Step S132: When the safety status assessment result is the second risk assessment result, call the pre-stored conventional control strategy library to match the second safety control instruction corresponding to the current environmental risk level and equipment operation risk level.

[0103] In this embodiment, if the safety status assessment result is the second risk assessment result, i.e., a low-risk state, it is necessary to call the pre-stored conventional control strategy library. The conventional control strategy library contains a variety of control strategies for low-risk situations, such as equipment operating parameter optimization strategies, environmental monitoring frequency adjustment strategies, and energy consumption balancing allocation strategies.

[0104] Similarly, first determine the current environmental risk level and equipment operation risk level. Then, search the conventional control strategy library for strategy combinations that match the current environmental risk level and equipment operation risk level. For example, if both the environmental risk level and the equipment operation risk level are low, the equipment operation parameter optimization strategy and the energy consumption balancing allocation strategy might be selected. Combining these matching strategies yields the second safety control instruction. The second safety control instruction also includes the specific parameters required to execute these strategies, such as the parameter adjustment values ​​for the equipment operation parameter optimization strategy and the monitoring time interval for the environmental monitoring frequency adjustment strategy.

[0105] Step S133: Generate the security control instruction according to the first security control instruction or the second security control instruction.

[0106] In this embodiment, a final safety control command is generated based on the previously obtained first or second safety control command. If the safety status assessment result is the first risk assessment result, then the safety control command is the first safety control command; if the safety status assessment result is the second risk assessment result, then the safety control command is the second safety control command. The safety control command includes a series of parameters, which will be used for subsequent adjustments to the operating parameters of the VR flight device.

[0107] Step S140: Adjust the operating parameters of the VR flight device according to the safety control command, and trigger the early warning feedback operation.

[0108] In this embodiment, after receiving safety control instructions, it is necessary to adjust the operating parameters of the VR flight device according to these instructions, and at the same time trigger the corresponding early warning feedback operation to ensure flight safety.

[0109] Step S141: Analyze the priority parameters in the safety control instructions to determine the execution order of the equipment control instructions.

[0110] In this embodiment, the safety control instructions include priority parameters, which are used to determine the execution order of the device control instructions. These priority parameters are assigned during the strategy matching process based on the importance and urgency of different strategies. First, the priority parameters in the safety control instructions are parsed, and the various device control instructions are sorted from highest to lowest priority. For example, if the safety control instructions include an emergency deceleration strategy, an environmental obstacle avoidance path adjustment strategy, and an energy supply enhancement strategy, and the emergency deceleration strategy has the highest priority, then when executing the device control instructions, the emergency deceleration strategy will be executed first, followed by the other strategies.

[0111] Step S142: Adjust the navigation path planning of the VR flight device according to the path offset parameter to generate an updated navigation path.

[0112] In this embodiment, the safety control command includes path offset parameters for the environmental obstacle avoidance path adjustment strategy. The navigation path planning of the VR flight device is adjusted based on these parameters. The navigation path planning is originally determined based on initial environmental information and the flight target; when obstacles are detected in the environment or changes occur, the navigation path needs to be corrected according to the path offset parameters.

[0113] The path offset parameters include information such as the direction and distance for obstacle avoidance. First, the avoidance direction is determined based on the obstacle's position and the path offset parameters. Then, the navigation path is offset by a specified distance. For example, if an obstacle is detected ahead, the path offset parameters indicate a certain distance to the right, and the navigation path is offset accordingly to the right. During the offset process, the flight performance of the flight device and other environmental constraints must be considered to ensure the feasibility of the offset path. By adjusting the navigation path, an updated navigation path is generated, and the flight device will fly according to the updated path.

[0114] Step S143: Redistribute the energy supply mode of the equipment according to the energy distribution ratio parameters.

[0115] In this embodiment, the safety control command includes energy allocation ratio parameters for the energy supply enhancement strategy. The energy supply mode of the equipment is reallocated based on these parameters. The energy supply mode includes switching ratio control between the primary and backup energy modules and smooth transition processing of energy output power.

[0116] First, the switching ratio between the primary and backup energy modules is determined based on the energy allocation ratio parameters. If the parameters indicate an increase in the use of the backup energy module, the energy supply system is adjusted accordingly to draw more energy from it. During the switching process, a smooth transition in energy output power is necessary to avoid sudden changes in energy output affecting the flight system. For example, gradually increasing or decreasing energy output power can make the changes in energy supply more stable. By reallocating the energy supply mode, sufficient energy support is ensured for the flight system under different operating conditions.

[0117] Step S144: Synchronize the execution sequence, the updated navigation path, and the reassigned energy supply mode to the control system of the VR flight device to complete the adjustment of operating parameters.

[0118] In this embodiment, the previously determined execution sequence of device control commands, the updated navigation path, and the reallocated energy supply mode are synchronized to the VR flight device's control system. The control system then uses this information to control and adjust the various components of the flight device, thereby adjusting the operating parameters.

[0119] During synchronization, it is crucial to ensure accurate information transmission and timely processing. The execution sequence, updated navigation path, and reassigned energy supply mode can be sent to the control system via a data communication interface. Upon receiving this information, the control system executes the corresponding control commands sequentially according to the execution sequence, controls the flight direction and speed of the flight device according to the updated navigation path, and adjusts the energy output based on the reassigned energy supply mode. This synchronization process enables the flight device to operate in accordance with the requirements of safety control commands.

[0120] Step S145: Generate a warning level identifier based on the security status assessment results.

[0121] In this embodiment, a warning level identifier is generated based on the previously determined safety status assessment results. If the safety status assessment result is a first risk assessment result, i.e., a high-risk state, a high-risk warning level identifier is generated; if the safety status assessment result is a second risk assessment result, i.e., a low-risk state, a low-risk warning level identifier is generated. The warning level identifier is used to distinguish different levels of safety risk so that corresponding warning feedback operations can be performed subsequently.

[0122] Step S146: When the warning level is identified as a high-risk warning, a multi-level warning notification process is initiated. The multi-level warning notification process includes sending an emergency warning signal to the user terminal, displaying dynamic obstacle avoidance prompts on the VR interface, and activating the device's automatic braking mechanism.

[0123] In this embodiment, if the warning level is marked as a high-risk warning, it indicates that the VR flight device faces a high safety risk and requires the activation of multi-level warning notification processing.

[0124] An emergency warning signal is sent to the user terminal. The emergency warning signal includes a combination of audible warning, vibration feedback, and visual flashing alert. A sharp sound is emitted through the user terminal's speaker to remind the user to pay attention to flight safety; vibration is generated through the user terminal's vibration module to provide the user with a tactile warning; and simultaneously, a flashing warning icon or text is displayed on the user terminal's screen to provide the user with a visual warning.

[0125] Dynamic obstacle avoidance prompts are displayed on the VR interface. These prompts use augmented reality technology to mark obstacle locations and recommend avoidance directions within the VR interface. Utilizing obstacle information from environmental perception data, the positions of obstacles are marked on the VR interface, and based on updated navigation paths and path offset parameters, recommended avoidance directions are displayed to help users better navigate obstacles.

[0126] Activate the equipment's automatic braking mechanism. This mechanism calculates braking distance parameters based on the equipment's current operating speed, distance to environmental obstacles, and a preset braking response time. It then gradually reduces the equipment's speed to within a safe threshold through segmented deceleration control. First, the distance the flight device will travel within the braking response time is calculated based on the current operating speed and the preset braking response time. Then, considering the distance to environmental obstacles, the required deceleration distance and magnitude are determined. Segmented deceleration control divides the deceleration process into multiple stages. Each stage dynamically adjusts the braking gradient based on obstacle distance, ensuring speed adjustment is completed within the braking distance parameter range. For example, a smaller braking gradient is used when the distance to an obstacle is greater; a larger braking gradient is used when the distance to an obstacle is less, until the equipment's operating speed is reduced to within the safe threshold.

[0127] Step S147: When the warning level is identified as a low-risk warning, initiate regular warning notification processing, including sending status reminder information to the user terminal, displaying parameter optimization suggestions on the VR interface, and recording device operation logs.

[0128] In this embodiment, if the warning level is marked as low risk, it means that the safety risk of the VR flight device is within an acceptable range, but some routine warning notification processing is still required.

[0129] Send status alerts to the user terminal. The status alerts inform the user of the current operating status of the flight device in the form of text or voice, such as flight speed and remaining energy, so that the user has a clear understanding of the status of the flight device.

[0130] The VR interface displays parameter optimization suggestions. Based on equipment operating characteristics and safety assessment results, it analyzes whether there is room for optimization in the current flight device's operating parameters. For example, if the equipment load fluctuation index is high, it may suggest adjusting the flight speed or attitude; if the equipment energy consumption trend index shows increased energy consumption, it may suggest optimizing the energy distribution mode. These parameter optimization suggestions are displayed on the VR interface to help users adjust the flight device's operating parameters.

[0131] Record equipment operation logs. These logs document various status information of the flight device during operation, such as acceleration, attitude, and energy consumption. By recording these logs, subsequent analysis and evaluation of the flight device's operation can be conducted to identify potential problems and implement improvements.

[0132] Step S150: After completing the warning feedback operation, continuously monitor the subsequent operation data set of the VR flight device.

[0133] In this embodiment, after completing the early warning feedback operation, it is necessary to continuously monitor the subsequent operational data set of the VR flight device. This is to understand the changes in the flight device's status after adjusting the operating parameters in a timely manner and to determine whether the safety status has improved.

[0134] Using the same method as acquiring real-time operational data sets, various sensors and monitoring systems continuously collect environmental perception data and equipment status data. LiDAR sensors continue to scan the surrounding environment, acquiring the location and distribution changes of obstacles; camera sensors continue to capture images of the flight scene for analyzing dynamic environmental changes; meteorological sensors continuously measure environmental meteorological parameters; accelerometers, gyroscopes, and the energy management system monitor the flight device's acceleration, attitude, and energy consumption, respectively. This collected data is then integrated to form the subsequent operational data set.

[0135] Step S151: Perform security status verification processing on the subsequent running data set to generate verification results.

[0136] In this embodiment, the subsequent operational data set is subjected to safety status verification processing to determine whether the safety status of the flight device has returned to normal.

[0137] Step S1511: Compare the adjusted operating parameters with the safety baseline parameters updated based on the dynamic safety threshold adjustment coefficient.

[0138] In this embodiment, the safety baseline parameters are first updated based on a dynamic safety threshold adjustment coefficient. The safety baseline parameters are reference ranges for the operating parameters of the flight device under normal and safe conditions. These reference ranges are adjusted according to the dynamic safety threshold adjustment coefficient to better match the current environment and equipment status. Then, the adjusted operating parameters are compared with the updated safety baseline parameters. For example, the current flight speed of the flight device is compared with the updated safe speed range, and the energy consumption rate is compared with the updated safe energy consumption rate range. If the adjusted operating parameter is within the range of the updated safety baseline parameters, it indicates that the parameter's operating status is normal; if it exceeds the range, it indicates that the parameter's operating status is at risk.

[0139] Step S1512: Analyze whether the trend of obstacle distribution changes in the environmental perception data meets the preset dynamic obstacle avoidance requirements.

[0140] In this embodiment, the distribution trend of obstacles in environmental perception data is analyzed. By comparing the position, quantity, and size of obstacles within adjacent time windows, it is determined whether the distribution of obstacles has changed and the trend of change. Preset dynamic obstacle avoidance requirements are set based on the flight performance and safety requirements of the flight device. For example, it requires the flight device to maintain a certain safe distance from obstacles and to avoid them in a timely manner when encountered. If the trend of obstacle distribution changes indicates that the flight device can meet these dynamic obstacle avoidance requirements—for example, obstacles gradually moving away from the flight device or the flight device avoiding obstacles according to the planned path—then the environmental safety status is good. Conversely, if the trend of obstacle distribution changes shows that the flight device may collide with obstacles or cannot avoid them in time, then there is a safety risk in the environment.

[0141] Step S1513: Verify whether the load fluctuation stability index in the device status data has recovered to the safe threshold range.

[0142] In this embodiment, the load fluctuation stability index in the equipment status data is verified. The load fluctuation stability index is obtained by weighted summation of the standard deviations of acceleration and attitude angles within a specific equipment operating segment. After the warning feedback operation, the index is recalculated and compared with a safety threshold range. The safety threshold range is determined based on the normal operating state and safety requirements of the equipment. If the load fluctuation stability index returns to the safety threshold range, it indicates that the equipment's operating state is stabilizing and the load fluctuation is within an acceptable range; if the index exceeds the safety threshold range, it indicates that the equipment still experiences significant load fluctuations, which may affect the normal operation and safety of the flight device.

[0143] The verification results are generated by comparing the adjusted operating parameters with the updated safety baseline parameters, analyzing the trend of obstacle distribution changes in environmental perception data, and verifying the load fluctuation stability index in equipment status data. The verification results are divided into two categories: safety status restored to normal and safety status not restored to normal.

[0144] Step S152: When the verification result indicates that the security status has not returned to normal, iteratively execute the dynamic security policy matching process and update the security control instruction.

[0145] In this embodiment, if the verification result indicates that the security status has not returned to normal, it means that the current security control measures have not achieved the expected effect, and dynamic security policy matching processing needs to be executed iteratively.

[0146] The current environmental risk level and equipment operation risk level are reassessed. Based on the latest set of subsequent operational data, the environmental risk level and equipment operation risk level are determined using the previously established methods, namely, based on environmental complexity parameters and equipment stability parameters. The environmental complexity parameters are calculated using obstacle density and dynamic change rate indices from environmental sensing data, while the equipment stability parameters are calculated using load fluctuation and energy consumption trend indices from equipment status data.

[0147] Based on the redefined environmental risk level and equipment operation risk level, the pre-stored emergency control strategy library or regular control strategy library is invoked again. If the safety risk remains high, the emergency control strategy library is invoked; if the safety risk has decreased but has not yet returned to normal, the regular control strategy library is invoked. The appropriate strategy combination corresponding to the current environmental risk level and equipment operation risk level is matched in the corresponding strategy library to generate a new safety control instruction. The new safety control instruction may adjust the previous strategy, such as increasing the magnitude of emergency equipment deceleration, further optimizing environmental obstacle avoidance paths, or adjusting energy allocation ratios.

[0148] Step S153: When the verification result indicates that the safety status has returned to normal, terminate the warning feedback operation and restore the default operating parameters.

[0149] In this embodiment, if the verification result indicates that the safety status has returned to normal, it means that through the previous safety control measures and early warning feedback operations, the operating status of the VR flight device has returned to a safe range. At this time, the early warning feedback operation is terminated, emergency warning signals or status reminders are stopped from being sent to the user terminal, dynamic obstacle avoidance prompts or parameter optimization suggestions are no longer displayed on the VR interface, and the device's automatic braking mechanism is turned off.

[0150] Restore default operating parameters. Default operating parameters are the settings used when the flight device is operating normally and without safety risks, including flight speed, attitude control parameters, and energy distribution mode. Adjusting the flight device's operating parameters back to their default values ​​allows the flight device to continue operating in normal mode. This operation ensures that the flight device can operate efficiently and stably under safe conditions.

[0151] In summary, this VR flight device uses a safety monitoring method to acquire real-time operational data sets, perform safety analysis and processing to generate safety status assessment results, execute dynamic safety strategy matching processing based on the assessment results to obtain safety control instructions, adjust operational parameters according to the instructions and trigger early warning feedback operations, and finally verify and iterate the safety status, forming a complete safety monitoring closed loop that can effectively ensure the flight safety of the VR flight device.

[0152] Furthermore, Figure 2A schematic diagram of the hardware structure of a VR service system 100 for implementing the methods provided in the embodiments of this application is shown. Figure 2 As shown, the VR service system 100 may include at least one processor 102 (the processor 102 may be, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, a transmission device 106 for communication functions, and a controller 108. Those skilled in the art will understand that... Figure 2 The structure shown is for illustrative purposes only and does not limit the structure of the VR service system 100. For example, the VR service system 100 may also include more than Figure 2 The more or fewer components shown, or having the same Figure 2 The different configurations shown.

[0153] The memory 104 can be used to store software programs and modules of application software, such as the program instructions corresponding to the method embodiments described above in this application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the above-described safety monitoring method for a VR flight device. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the VR service system 100 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0154] The transmission device 106 is used to acquire or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the VR service system 100. In one example, the transmission device 106 includes a network adapter that can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a radio frequency module used for wireless communication with the Internet.

[0155] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the exceptions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are also possible or advantageous.

[0156] The embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on its differences from other embodiments. In particular, since the above different embodiments are basically similar to the method embodiments, the descriptions are relatively simple, and relevant parts can be referred to the descriptions of the method embodiments.

[0157] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

Claims

1. A safety monitoring method for a VR flight device, characterized in that, The method includes: Acquire a set of real-time operational data for the VR flight device, the set of real-time operational data including environmental perception data and device status data; The real-time operational data set is subjected to security analysis and processing to generate a security status assessment result; Based on the security status assessment results, dynamic security policy matching processing is performed to obtain security control instructions; Adjust the operating parameters of the VR flight device according to the safety control instructions, and trigger the early warning feedback operation; By inputting environmental dynamics and equipment operational characteristics into a pre-trained safety assessment model, a comprehensive risk assessment index is generated, including: The environmental dynamic characteristics are subjected to a first standardization process to obtain standardized environmental characteristics; The operating characteristics of the equipment are subjected to a second standardization process to obtain standardized equipment characteristics; The standardized environmental features and the standardized equipment features are input into the feature interaction layer of the pre-trained security assessment model to generate an interaction feature vector. The risk assessment layer in the security assessment model is invoked to perform nonlinear mapping processing on the interaction feature vector to generate the comprehensive risk assessment index. The feature interaction layer fuses the standardized environmental features and the standardized equipment features through a cross-attention mechanism; the risk assessment layer performs weighted calculations on the interaction feature vectors through a multi-layer perceptron and outputs the comprehensive risk assessment index; the comprehensive risk assessment index includes a weighted sum of environmental risk contribution and equipment risk contribution. The step of dynamically comparing the comprehensive risk assessment index with a preset safety threshold to determine the safety status assessment result includes: Obtain the dynamic security threshold adjustment coefficient under the current environmental scenario; The preset security threshold is corrected in real time according to the dynamic security threshold adjustment coefficient to generate a dynamic security threshold. Compare the comprehensive risk assessment index with the dynamic safety threshold; When the comprehensive risk assessment index is greater than the dynamic security threshold, a first risk assessment result is generated; When the comprehensive risk assessment index is less than or equal to the dynamic safety threshold, a second risk assessment result is generated; The safety status assessment result is determined based on the first risk assessment result or the second risk assessment result; The dynamic security threshold adjustment coefficient is determined in the following way: Environmental complexity parameters are calculated based on obstacle density and dynamic change rate indices from environmental perception data. Calculate equipment stability parameters based on load fluctuation indicators and energy consumption trend indicators in equipment status data; The weighted sum of the environmental complexity parameter and the equipment stability parameter is used as the dynamic safety threshold adjustment coefficient; The step of performing dynamic security policy matching processing based on the security status assessment results to obtain security control instructions includes: When the safety status assessment result is the first risk assessment result, the pre-stored emergency control strategy library is invoked to match the first safety control instruction corresponding to the current environmental risk level and equipment operation risk level; When the safety status assessment result is the second risk assessment result, the pre-stored conventional control strategy library is invoked to match the second safety control instruction corresponding to the current environmental risk level and equipment operation risk level; The security control instruction is generated according to the first security control instruction or the second security control instruction; The emergency control strategy library includes equipment emergency deceleration strategy, environmental obstacle avoidance path adjustment strategy, and energy supply enhancement strategy. The conventional control strategy library includes equipment operating parameter optimization strategies, environmental monitoring frequency adjustment strategies, and energy consumption balance allocation strategies. The safety control instructions include priority parameters for executing the equipment emergency deceleration strategy, path offset parameters for the environmental obstacle avoidance path adjustment strategy, and energy allocation ratio parameters for the energy supply enhancement strategy. The step of adjusting the operating parameters of the VR flight device according to the safety control command includes: The priority parameters in the safety control instructions are analyzed to determine the execution order of the equipment control instructions; The navigation path planning of the VR flight device is adjusted according to the path offset parameters to generate an updated navigation path; The energy supply mode of the equipment is reallocated according to the energy allocation ratio parameters; The execution sequence, the updated navigation path, and the reallocated energy supply mode are synchronized to the control system of the VR flight device to complete the adjustment of operating parameters; The navigation path planning adjustment includes dynamic correction of obstacle avoidance paths and gradient change control of flight speed; The energy supply mode adjustment includes the switching ratio control between the main energy module and the backup energy module and the smooth transition processing of energy output power. The triggering of the early warning feedback operation includes: A warning level identifier is generated based on the security status assessment results; When the warning level is identified as a high-risk warning, a multi-level warning notification process is initiated, which includes sending an emergency warning signal to the user terminal, displaying dynamic obstacle avoidance prompts on the VR interface, and activating the device's automatic braking mechanism. When the warning level is identified as a low-risk warning, routine warning notification processing is initiated, including sending status reminder information to the user terminal, displaying parameter optimization suggestions on the VR interface, and recording device operation logs. The emergency warning signal includes a combination of audible warning, vibration feedback, and visual flashing alert; The dynamic obstacle avoidance prompts use augmented reality technology to mark the location of obstacles and recommend avoidance directions in the VR interface; The automatic braking mechanism calculates the braking distance parameters based on the current operating speed of the equipment, the distance to environmental obstacles, and the preset braking response time, and gradually reduces the operating speed of the equipment to within the safe threshold through segmented deceleration control; The segmented deceleration control includes dynamically adjusting the braking gradient based on the distance to the obstacle to ensure that speed adjustment is completed within the braking distance parameter range; The method further includes: After completing the aforementioned early warning feedback operation, the subsequent operational data set of the VR flight device is continuously monitored; The subsequent running data set is subjected to security status verification processing to generate verification results; When the verification result indicates that the security status has not returned to normal, the dynamic security policy matching process is executed iteratively to update the security control instruction. When the verification result indicates that the safety status has returned to normal, the warning feedback operation is terminated and the default operating parameters are restored. The security status verification process includes: Compare the adjusted operating parameters with the safety baseline parameters updated based on the dynamic safety threshold adjustment coefficient; Analyze whether the trend of obstacle distribution changes in environmental perception data meets the preset dynamic obstacle avoidance requirements; Verify whether the load fluctuation stability index in the equipment status data has recovered to the safe threshold range.

2. The safety monitoring method for VR flight devices according to claim 1, characterized in that, The step of performing security analysis and processing on the real-time operational data set to generate a security status assessment result includes: Extract dynamic environmental features from the environmental perception data, and extract equipment operation features from the equipment status data; The environmental dynamics and equipment operation characteristics are input into a pre-trained safety assessment model to generate a comprehensive risk assessment index. The safety status assessment result is determined by dynamically comparing the comprehensive risk assessment index with the preset safety threshold.

3. The safety monitoring method for VR flight devices according to claim 2, characterized in that, Extracting dynamic environmental features from the environmental perception data includes: The environmental perception data is dynamically segmented to generate multiple scene regions; For each scene area, obstacle identification processing is performed to determine the obstacle distribution characteristics; The environmental dynamic features are generated by performing feature calculations based on the obstacle distribution characteristics. These environmental dynamic features include obstacle density characteristics, dynamic change rate characteristics, and spatial distribution uniformity characteristics. The obstacle density characteristics are determined by statistically analyzing the ratio of the number of obstacles to the area of ​​each scene region. The dynamic change rate characteristics are determined by calculating the magnitude of change in obstacle distribution within adjacent time windows. The spatial distribution uniformity characteristics are determined by calculating the positional dispersion of obstacles in each scene region, and this dispersion is analyzed using statistical variance methods.

4. The safety monitoring method for VR flight devices according to claim 2, characterized in that, Extracting equipment operating features from the equipment status data includes: The device status data is processed by time-series segmentation to generate multiple device operation segments; For each equipment operation segment, an operation mode identification process is performed to determine the characteristics of the equipment operation mode; Calculate the equipment load fluctuation index and equipment energy consumption trend index based on the characteristics of the equipment operation mode; The equipment load fluctuation index and the equipment energy consumption trend index are aggregated to generate the equipment operating characteristics; The equipment operation mode characteristics include acceleration change characteristics, attitude adjustment frequency characteristics, and energy consumption rate characteristics; The acceleration variation characteristics are determined by analyzing the slope of the acceleration curve during the equipment operation segment; The attitude adjustment frequency characteristic is determined by statistically analyzing the number of times attitude adjustment commands are executed during a segment of equipment operation. The energy consumption rate characteristic is determined by calculating the rate of change of energy consumption per unit time.

5. A VR service system, characterized in that, The VR service system includes a processor and a readable storage medium, the readable storage medium storing a program that, when executed by the processor, implements the safety monitoring method for VR flight devices as described in any one of claims 1-4.

Images