Respiration monitoring simulation analysis method and device based on virtual reality technology

Abstract

The invention discloses a respiration monitoring simulation analysis method and device based on a virtual reality technology, and relates to the technical field of respiration monitoring analysis. Comprising the following steps: constructing a dynamic virtual environment, and determining individual baseline environment bearing capacity and a pressure distribution matrix; dividing task behavior difficulty based on user adaptability and real-time state, perfecting the pressure distribution matrix, and constructing a fusion vector; a dynamic respiratory metabolism interaction model is constructed through a deep learning and time sequence analysis method, and the comprehensive influence of environment pressure and interaction tasks on a user respiratory mode, respiratory efficiency and a metabolic state is analyzed; on the basis of the dynamic respiration metabolism interaction model, the respiration and metabolism adaptive capacity of the user in multiple scenes is predicted, personalized respiration optimization suggestions are provided, and suggestion results are output in a visual mode in virtual reality. According to the method, the comprehensive influence of environment pressure and task behaviors on the breathing mode, the breathing efficiency and the metabolic state of the user can be accurately analyzed, so that personalized breathing optimization suggestions are provided.

Description

Technical Field

[0001] The present invention relates to the technical field of respiratory monitoring and analysis, in particular to a respiratory monitoring simulation and analysis method and device based on virtual reality technology. Background Art

[0002] With the continuous advancement of science and technology, virtual reality (VR) technology has been widely used in many fields, such as medical health, education, entertainment, etc. In recent years, physiological monitoring based on virtual reality technology has gradually become an important research direction in the field of medicine and health management, especially in respiratory and metabolic monitoring. Virtual reality technology can create an immersive environment, collect and analyze the user's physiological data in real time, to assist in disease diagnosis, personalized treatment and health management.

[0003] Traditional respiratory monitoring methods mostly rely on physical equipment, such as portable respiratory monitors, gas exchange analyzers, etc. These methods can usually only provide static data records, and often ignore the combined effects of environmental pressure and behavioral tasks on respiratory patterns. Therefore, how to combine virtual reality with physiological data collection to establish a more accurate respiratory and metabolic monitoring system has become a hot topic in current technical research.

[0004] At present, many studies have combined virtual reality technology with physiological data monitoring, but there are still some technical bottlenecks and shortcomings. For example, most existing systems lack dynamic adjustment of users' individual physiological parameters and cannot accurately reflect the impact of different environmental pressures and task behaviors on individuals; and existing systems generally lack deep interactive modeling of environmental pressure and physiological response, and cannot adjust the virtual environment in real time to adapt to the user's physiological changes. More importantly, although some studies have tried to use machine learning methods to analyze physiological data, there are still problems such as insufficient model accuracy and high computational complexity. Summary of the invention

[0005] In view of the above problems in the prior art, the present invention is proposed.

[0006] Therefore, the problem to be solved by the present invention is how to accurately analyze the comprehensive impact of environmental pressure and task behavior on the user's breathing pattern, breathing efficiency and metabolic state, so as to provide personalized breathing optimization suggestions.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, the present invention provides a respiratory monitoring simulation analysis method based on virtual reality technology, which includes: constructing a dynamic virtual environment, collecting physiological data of users in resting and dynamic states, and determining individual baseline environmental tolerance and pressure distribution matrix; dividing task behavior difficulty based on user adaptability and real-time status, improving the pressure distribution matrix, constructing a fusion vector and optimizing the task scenario and user physiological matching through a dynamic adjustment algorithm; combining the improved pressure distribution matrix and the fusion vector, constructing a dynamic respiratory metabolic interaction model through deep learning and time series analysis methods, and analyzing the comprehensive impact of environmental pressure and interactive tasks on user breathing patterns, respiratory efficiency and metabolic states; based on the dynamic respiratory metabolic interaction model, integrating user history and real-time data, predicting the user's respiratory and metabolic adaptability in multiple scenarios, providing personalized respiratory optimization suggestions, and outputting the suggestion results in a visual manner in virtual reality.

[0008] As a preferred solution of the respiratory monitoring simulation analysis method based on virtual reality technology described in the present invention, wherein: the individual baseline environmental tolerance is obtained by weighted calculation of the physiological parameters of the user in a resting state; the determination of the pressure distribution matrix includes: according to the individual baseline environmental tolerance, combined with the reference standard of the preset environmental pressure factor, using a fuzzy reasoning algorithm to calculate the individualized dynamic pressure range matrix; based on the dynamic pressure range, a hierarchical mapping algorithm is used to generate the pressure distribution matrix of the virtual scene.

[0009] As a preferred solution of the respiratory monitoring simulation analysis method based on virtual reality technology described in the present invention, the method comprises the following steps: dividing the difficulty of task behavior based on user adaptability and real-time status, improving the pressure distribution matrix, and constructing a fusion vector: dividing the difficulty level of task behavior according to user adaptability and task objectives, and mapping the real-time dynamic changes of task behavior to the pressure distribution matrix; using motion capture equipment to collect the user's behavior parameters and muscle activity data in the interactive scene in real time, and fusing and correlating them with the physiological data in the virtual environment to construct a fusion vector; through the task feedback adjustment algorithm, dynamically adjusting the difficulty of task behavior according to the user's real-time fatigue status, and updating the adjusted task parameters to the pressure distribution matrix in real time to ensure the synchronous changes of the virtual environment and the task behavior.

[0010] As a preferred solution of the respiratory monitoring simulation analysis method based on virtual reality technology of the present invention, the expression for dynamically adjusting the difficulty of the task behavior according to the real-time fatigue state of the user is: ; in, is the task parameter adjustment amount, Provide users with real-time fatigue error, and To control the parameters for adjusting sensitivity, To complete the accuracy error for the user's real-time tasks, and is the task adjustment coefficient; when Threshold exceeded When , the task difficulty is reduced through an exponential function; when Threshold exceeded When the task characteristics are adjusted dynamically through the cosine function, the matching degree of user behavior is optimized.

[0011] As a preferred solution of the respiratory monitoring simulation analysis method based on virtual reality technology described in the present invention, the method comprises the following steps: combining the improved pressure distribution matrix and the fusion vector, and constructing a dynamic respiratory metabolism interaction model through deep learning and time series analysis methods: constructing a unified respiratory metabolism physiological data set based on the real-time collected data in the fusion vector combined with the environmental variables of the pressure distribution matrix; based on the respiratory metabolism physiological data set, using an adaptive multidimensional mapping algorithm, correlating and analyzing the environmental pressure variables, task behavior parameters, and the user's respiratory efficiency and metabolic state, generating a task-environmental pressure-respiratory metabolism response matrix, and quantitatively describing the combined impact of environmental pressure and task behavior changes on the user's respiratory and metabolic state; extracting the time series data in the task-environmental pressure-respiratory metabolism response matrix, and dynamically correlating the respiratory rhythm-lactate threshold using a dynamic time warping algorithm; on the basis of the dynamic correlation between the respiratory rhythm and lactate threshold, combining a recurrent neural network deep learning algorithm, integrating the real-time updated task difficulty parameters, the pressure distribution matrix, and the user behavior completion error, to construct a dynamic respiratory metabolism interaction model.

[0012] As a preferred embodiment of the respiratory monitoring simulation analysis method based on virtual reality technology of the present invention, the task-environmental pressure-respiratory metabolism response matrix The generation includes: ; in, is a nonlinear mapping function, implemented using a multilayer perceptron. ~ is the dynamically adjusted weight factor, is the gradient of the environmental pressure variable, reflecting the rate of dynamic environmental change. is the gradient of the task behavior parameter, reflecting the rate of change of the user's real-time behavior. is the covariance between environmental pressure and behavioral parameters, is the dynamic gradient of metabolic state, is the task behavior intensity, It is the user's breathing efficiency indicator. is a regularization term used to control the complexity of the model. is the lactate threshold change rate, is the regularization weight.

[0013] As a preferred solution of the respiratory monitoring simulation analysis method based on virtual reality technology of the present invention, the dynamic association of respiratory rhythm and lactate threshold includes: extracting time series features from the task-environmental pressure-respiratory metabolic response matrix; using the DTW algorithm to measure the time series similarity of respiratory rhythm and lactate threshold changes. : ; ; in, and is the time series of breathing rhythm and lactate threshold, is the number of time steps, is the normalized time step weight, is the time step between the current time point and the previous time point; Dynamic correlation between breathing rhythm and lactate threshold: ; in, It is the lactate threshold dynamic drift indicator. and is the weight parameter, is the rate of change of breathing rhythm.

[0014] As a preferred solution of the respiratory monitoring simulation analysis method based on virtual reality technology of the present invention, the dynamic respiratory metabolism interaction model includes: the construction of multimodal time series features includes , task behavior difficulty data, pressure distribution matrix and user behavior completion error; slice the multimodal time series features into fixed-length input windows to capture dynamic change rules; use recurrent neural networks to build a model architecture: input multimodal time series features into the RNN model; multi-layer RNN units capture long-term dependencies in time series; output task adjustment parameters and respiratory metabolic state evaluation results; and optimize task behavior parameters and respiratory metabolic state by minimizing the loss function, so that the user's physiological state dynamically matches the task environment.

[0015] In a second aspect, the present invention provides a respiratory monitoring simulation and analysis device based on virtual reality technology, which includes: a dynamic virtual environment generation module, which is used to construct a dynamic virtual environment, collect physiological data of users in resting and dynamic states, and determine individual baseline environmental tolerance and pressure distribution matrix; a virtual interactive behavior scenario module, which is used to divide the task behavior difficulty based on the user's adaptability and real-time status, improve the pressure distribution matrix, construct a fusion vector and optimize the task scenario and user physiological matching through a dynamic adjustment algorithm; a data fusion and deep learning analysis module, which is used to combine the improved pressure distribution matrix and the fusion vector, construct a dynamic respiratory metabolism interaction model through deep learning and time series analysis methods, and analyze the comprehensive impact of environmental pressure and interactive tasks on the user's breathing pattern, respiratory efficiency and metabolic state; a multi-scenario respiratory metabolism prediction and optimization module, which is used to predict the user's respiratory and metabolic adaptability in multiple scenarios based on the dynamic respiratory metabolism interaction model, integrate user history and real-time data, provide personalized respiratory optimization suggestions, and output the suggestion results in a visual manner in virtual reality.

[0016] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the respiratory monitoring simulation analysis method based on virtual reality technology as described in the first aspect of the present invention are implemented.

[0017] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of the respiratory monitoring simulation analysis method based on virtual reality technology as described in the first aspect of the present invention are implemented.

[0018] The beneficial effects of the present invention are as follows: by constructing a personalized dynamic virtual environment and pressure distribution matrix, the present invention can collect the user's physiological data in resting and dynamic states in real time, and dynamically adjust it in combination with virtual task behavior data. Through deep learning and time series analysis methods, the present invention can accurately analyze the combined impact of environmental pressure and task behavior on the user's breathing pattern, breathing efficiency and metabolic state, thereby providing personalized breathing optimization suggestions. The present invention can not only overcome the limitations of the prior art, but also achieve dynamic adaptation in multiple scenarios, and through virtual reality visualization output, enhance the user experience and applicability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 This is a flow chart of the respiratory monitoring simulation analysis method based on virtual reality technology.

[0021] Figure 2 Schematic diagram of constructing a dynamic respiratory metabolism interactive model for respiratory monitoring simulation analysis method based on virtual reality technology.

[0022] Figure 3 Schematic diagram of a respiratory monitoring simulation and analysis device based on virtual reality technology. DETAILED DESCRIPTION

[0023] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0024] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0025] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0026] Example 1: Reference Figure 1~Figure 2 , which is the first embodiment of the present invention, and provides a respiratory monitoring simulation analysis method based on virtual reality technology, such as Figure 1 As shown, including: S1: Build a dynamic virtual environment, collect the user's physiological data in resting and dynamic states, and determine the individual baseline and environmental pressure adaptation range.

[0027] S1.1: First, collect the user's resting physiological parameters, including heart rate variability, tidal volume, respiratory rate and blood oxygen saturation, and determine the individual baseline environmental tolerance based on the physiological parameters to provide data support for the initialization of the virtual scene.

[0028] Among them, the individual baseline environmental tolerance is obtained by weighted calculation of physiological parameters.

[0029] S1.2: Based on the individual baseline environmental tolerance and the reference standards of preset environmental stress factors (such as temperature range of 20℃~40℃, humidity range of 30%~90%, etc.), the fuzzy inference algorithm is used to calculate the individualized dynamic pressure range matrix to clarify the upper and lower limits of the user's adaptation range.

[0030] Specifically, the individual baseline environmental tolerance is used as a comprehensive physiological index input in the user's resting state to reflect the user's environmental tolerance in a normal state; each environmental stress factor (such as temperature, humidity, oxygen concentration and air pressure) has a fixed standard dynamic range (such as temperature of 20°C to 40°C, humidity of 30% to 90%). These ranges define the possible value range of the stress factor.

[0031] Map individual baseline environmental carrying capacity values ​​to a fuzzy scale of “low, medium, high”; Based on experience or experimental data, set rules for the relationship between the range of stress factors and the individual baseline environmental tolerance, for example: If the individual's baseline environmental tolerance is "low", the temperature range may be limited to 20°C to 30°C; If the individual baseline environmental tolerance is "high", the temperature variation range can be expanded to 20℃~40℃, etc.

[0032] Fuzzy logic is used to reason based on the input values, combining the user's tolerance and environmental factors to output the upper and lower limits of the pressure factor that the user can adapt to.

[0033] Furthermore, the fuzzy reasoning results are defuzzified by methods such as the centroid method to generate clear upper and lower bounds of the pressure factors, and the upper and lower bounds of all factors are combined into a dynamic pressure range matrix.

[0034] S1.3: Based on the dynamic pressure range, a layered mapping algorithm is used to generate a virtual scene pressure distribution matrix, and the dynamic changes of the pressure factor (such as the humidity gradually increasing to the upper limit) are adaptively associated with the visual elements in the virtual environment (such as different scenes) to form a multi-dimensional dynamic virtual environment scene.

[0035] It should be noted that when generating the stress distribution matrix, a hierarchical division is performed, for example, the first layer: task type; the second layer: environmental stress factors; the third layer: individual physiological responses, etc. Tasks and environmental factors are classified through hierarchical clustering methods (such as K-means or hierarchical clustering), and multivariate regression analysis is combined to determine the weights and relationships of the mapping.

[0036] S1.4: By collecting the user's physiological responses in the virtual scene (such as respiratory exchange ratio, lactate concentration, etc.) in real time, comparing and analyzing the physiological responses with the pressure distribution matrix, and using the feedback control mechanism to adjust the pressure factor parameters, the virtual environment dynamically adapts to the user's current state.

[0037] Preferably, the feedback control mechanism formula is expressed as: ; in, is the pressure factor adjustment, is the deviation between the current user state and the target state, is the adjustment coefficient, and is the nonlinear adjustment parameter, is the weight coefficient for dynamic adjustment of amplitude.

[0038] It can be seen that the present invention uses a nonlinear function (such as and ) for feedback control, which can more sensitively capture subtle changes in user status. Compared with traditional linear control, it can not only respond quickly to large deviations, but also effectively avoid over-adjustment under small deviations.

[0039] In addition, in a virtual environment, the user's physiological parameters (such as lactate concentration, respiratory exchange ratio, etc.) may change dynamically over time, and the deviation The complex characteristics need to be more accurately reflected through nonlinear formulas.

[0040] After dynamic adjustment, the new environmental stress factors are recorded together with the user’s real-time physiological data.

[0041] It can be seen that the introduction of the personalized dynamic pressure range matrix of the present invention realizes the precise matching of the environment and the user status; the dynamic changes of the pressure factor are associated with the virtual scene elements through the hierarchical mapping algorithm, which improves the realism and interactivity of the virtual environment, and further ensures that the virtual environment can dynamically adapt to the real-time status of the user through the feedback control mechanism.

[0042] S2: Based on the user's adaptability and real-time status, the task behavior difficulty is divided, the pressure distribution matrix is ​​improved, the fusion vector is constructed, and the task scenario and the user's physiological matching are optimized through a dynamic adjustment algorithm.

[0043] First, the difficulty level of task behavior is divided according to the user's adaptability and task objectives, and the real-time dynamic changes of task behavior are mapped to the pressure distribution matrix (multi-dimensional dynamic virtual environment scene) to ensure the coordination between the task scene and the environment.

[0044] The task behaviors are divided into multiple difficulty levels according to the individual baseline environmental tolerance of the user. For example, the climbing task is divided into multiple levels according to the climbing angle and speed.

[0045] The task behavior parameters (such as climbing angle and running speed) are associated with the pressure distribution matrix through a mapping algorithm to ensure that the dynamic changes of the task scenario are consistent with the user's physiological adaptation range.

[0046] Furthermore, motion capture equipment is used to collect the user's behavioral parameters (such as movement amplitude, movement frequency, completion accuracy) and muscle activity data (electromyogram (EMG)) in the interactive scene in real time, and then integrated and correlated with the physiological data (such as respiratory exchange ratio) in the virtual environment.

[0047] Specifically, the collected behavioral parameters and muscle activity data are converted into unified time series data to eliminate the differences in collection equipment; Synchronize the user's respiratory response data (such as respiratory exchange ratio and lactate concentration) in the virtual environment as a reference baseline for behavioral parameters; The behavioral parameters, muscle activity data, and physiological data are mapped to the same moment using timestamps to construct a fusion vector.

[0048] Furthermore, through the task feedback adjustment algorithm, the difficulty of the task behavior is dynamically adjusted (such as lowering the climbing angle or slowing down the running speed) according to the user's real-time fatigue status (such as excessive lactate accumulation rate and weakened electromyography signal), and the updated task data is synchronized with the pressure distribution matrix.

[0049] Preferably, when users complete complex tasks (such as climbing and running) in a virtual scene, their physiological state (such as lactate accumulation rate) and behavioral performance (such as movement accuracy) will change dynamically with the intensity of the task, while traditional linear adjustment methods cannot quickly respond to fluctuations in user state.

[0050] The present invention combines the user's fatigue error (such as weakened muscle signal or excessive lactic acid accumulation) and behavior completion error (such as inaccurate action completion) to balance the dynamic adjustment requirements of task difficulty among multiple variables, ensuring that the adjustment at each moment meets the user's real-time ability. The expression is: ; in, is the task parameter adjustment amount, Provide users with real-time fatigue errors (such as lactate accumulation rate exceeding the baseline value), and To control the parameters for adjusting sensitivity, To complete the accuracy error for the user's real-time tasks, and is the task adjustment factor, which weighs the impact of fatigue state and task accuracy.

[0051] when Threshold exceeded When the lactate accumulation rate increases, the task difficulty is rapidly reduced through an exponential function (e.g., lowering the climbing angle, slowing down the running speed); when Threshold exceeded When the task completion accuracy deviation is high, the cosine function is used to dynamically adjust the task characteristics and optimize the user behavior matching.

[0052] Among them, the user's real-time fatigue error can be obtained by weighted calculation of physiological and psychological parameters; The user real-time task completion accuracy error is defined as the difference between the ratio of the number of correctly completed subtasks in the task and the total number of subtasks in the task and 1.

[0053] It can be seen that in high-intensity tasks, when the user is tired or the completion rate is low, the task difficulty will drop rapidly to reduce the physical burden and ensure the health and safety of the user in the virtual scene.

[0054] The adjusted task parameters are updated in real time to the virtual environment pressure distribution matrix to ensure the synchronous changes of the virtual environment and task behavior.

[0055] S3: Combine the improved pressure distribution matrix and fusion vector, build a dynamic respiratory metabolism interaction model through deep learning and time series analysis methods, and analyze the comprehensive impact of environmental pressure and interactive tasks on the user's breathing pattern, respiratory efficiency and metabolic state.

[0056] The method of combining the improved pressure distribution matrix and the fusion vector to construct a dynamic respiratory metabolism interaction model through deep learning and time series analysis methods includes the following steps: S3.1: Based on the data collected in real time by the fusion vector, including behavioral parameters (such as movement amplitude, movement frequency, completion accuracy), muscle activity data (such as electromyography (EMG)), and physiological data in the virtual environment (such as respiratory exchange ratio), combined with the environmental variables of the pressure distribution matrix (such as oxygen concentration, air pressure, temperature and humidity), a unified multimodal respiratory metabolic physiological data set is constructed.

[0057] In addition, respiratory rate, tidal volume and respiratory-related muscle activity data (such as the electrical activity of the diaphragm and intercostal muscles) are further introduced to enhance the ability to characterize the dynamic relationship between the user's breathing pattern and task behavior.

[0058] It should be noted that by synchronizing data streams from different sources through timestamps, building a unified time series data format, and adopting data standardization methods (such as z-score standardization), the dimensional differences between different data dimensions are eliminated.

[0059] Furthermore, the behavioral parameters, muscle activity data and environmental variables were integrated into a multimodal respiratory metabolic physiological dataset using a weighted feature fusion method, and the multimodal dataset was stored as a multidimensional array structure.

[0060] S3.2: Based on the respiratory metabolic physiological data set, an adaptive multidimensional mapping algorithm is used to correlate environmental pressure variables (such as oxygen concentration, air pressure changes, carbon dioxide partial pressure, etc.), task behavior parameters (such as task difficulty, real-time fatigue error, etc.) with the user's respiratory efficiency and metabolic state, and generate a task-environmental pressure-respiratory metabolic response matrix to quantitatively describe the joint impact of environmental pressure and task behavior changes on the user's respiratory and metabolic state.

[0061] The optimal task-environmental stress-respiratory metabolic response matrix The formation includes: ; in, is a nonlinear mapping function, implemented using a multilayer perceptron. ~ is the dynamically adjusted weight factor, is the gradient of the environmental pressure variable, reflecting the rate of dynamic environmental change. is the gradient of the task behavior parameter, reflecting the rate of change of the user's real-time behavior. is the covariance between environmental pressure and behavioral parameters, is the dynamic gradient of metabolic state, is the task behavior intensity, It is the user's breathing efficiency indicator. is a regularization term used to control the complexity of the model. is the lactate threshold change rate, is the regularization weight.

[0062] It can be seen that the above calculation process introduces the dynamic change gradient and covariance of environmental pressure and task behavior parameters into the matrix construction, which can more accurately describe the joint impact of the dynamic environment on the respiratory metabolic state. At the same time, by combining the nonlinear mapping function with the respiratory efficiency change rate, the ability to capture the nonlinear characteristics of complex systems is further improved.

[0063] S3.3: Extracting the Task-Environmental Stress-Respiratory Metabolic Response Matrix The time series data in the dynamic time warping algorithm (DTW) is used to dynamically associate the respiratory rhythm-lactate threshold, as follows: First, time series features were extracted from the task-environmental pressure-respiratory metabolic response matrix, including indicators such as respiratory rhythm stability and lactate threshold drift; Using DTW algorithm to measure the time series similarity between respiratory rhythm and lactate threshold changes : ; ; in, and is the time series of breathing rhythm and lactate threshold, is the number of time steps, is the normalized time step weight, is the time step between the current time point and the previous time point.

[0064] Dynamic correlation between breathing rhythm and lactate threshold: ; in, It is the lactate threshold dynamic drift indicator. and is the weight parameter, is the rate of change of breathing rhythm.

[0065] The dynamic association between breathing rhythm and lactate threshold provides a real-time feedback mechanism for user adaptability assessment by analyzing the dynamic effects of different task behavior intensities and environmental pressure changes on user breathing patterns (such as breathing rhythm stability) and lactate threshold drift.

[0066] S3.4: Based on the dynamic correlation between breathing rhythm and lactate threshold, combined with the recurrent neural network (RNN) deep learning algorithm, the real-time updated task difficulty parameters, pressure distribution matrix and user behavior completion error are integrated to construct a dynamic respiratory metabolism interaction model.

[0067] The dynamic respiratory metabolism interaction model includes: The construction of multimodal time series features includes , task behavior difficulty data, pressure distribution matrix, and user behavior completion error.

[0068] Split multimodal time series features into fixed-length input windows to capture dynamic changes; Building the model architecture using a recurrent neural network (RNN): Input multimodal time series features into the RNN model; Multi-layer RNN units (such as LSTM or GRU) capture long-term dependencies in time series; Output task adjustment parameters and respiratory metabolic status assessment results.

[0069] And by minimizing the loss function, optimizing the task behavior parameters and respiratory metabolic state, the user's physiological state is dynamically matched with the task environment.

[0070] S4: Based on the dynamic respiratory and metabolic interaction model, the user's historical and real-time data are integrated to predict the user's respiratory and metabolic adaptability in multiple scenarios, provide personalized respiratory optimization suggestions, and output the suggestion results in a visual way in virtual reality.

[0071] Preferably, based on the dynamic respiratory metabolism interaction model, the user's physiological data and behavioral data in the current scene are collected in real time, including but not limited to real-time physiological data and real-time task data; Physiological and behavioral characteristic data in relevant scenarios are retrieved from the user's historical data records. These data are used to compare the user's adaptability in the current task with the performance in similar tasks in the past.

[0072] Furthermore, the characteristics of the virtual reality scene in which the user is located are analyzed, including task type, task difficulty, environmental pressure conditions, etc.; at the same time, the key influencing factors of the scene on the user's physiological load are extracted in combination with the user's current respiratory metabolic state and behavioral performance.

[0073] Using a dynamic respiratory metabolic interaction model, real-time data is combined with historical data to calculate the user's respiratory metabolic adaptability in the current task and scenario, including: Respiratory adaptability: measures the deviation of the user's current respiratory efficiency from the normal state, such as whether the minute ventilation volume is sufficient to support the current task intensity; Metabolic adaptability: Evaluate whether the user's metabolic state in the current scenario is within a healthy range through indicators such as lactate emission rate and respiratory exchange ratio.

[0074] Through time-series analysis of historical user data and combined with dynamic changes in scene features, the user’s adaptability in similar future scenes is predicted. For example, if the user currently shows decreased breathing efficiency in a high-stress environment, it is predicted that they may need to reduce task intensity or optimize their breathing rhythm in similar environments.

[0075] Based on the user's adaptability assessment results, the following types of personalized recommendations are generated: Breathing pattern optimization: such as adjusting breathing rhythm, prolonging breathing cycle, and increasing breathing depth; Task behavior adjustment: such as reducing task intensity, increasing rest intervals, and optimizing range of motion; Optimization of environmental conditions: such as adjusting the oxygen concentration in the virtual environment, reducing stress factors such as ambient temperature and humidity.

[0076] The generated personalized metabolic optimization suggestions are presented in a visual way through virtual reality equipment, including dynamic prompts for task suggestions (such as color marking of interactive task difficulty) and breathing optimization animation guidance (such as deep breathing frequency and rhythm animation), allowing users to intuitively understand and implement optimization strategies.

[0077] This embodiment also provides a computer device, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the respiratory monitoring simulation analysis method based on virtual reality technology as proposed in the above embodiment.

[0078] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0079] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the respiratory monitoring simulation analysis method based on virtual reality technology proposed in the above embodiment is implemented.

[0080] In summary, the present invention can collect the user's physiological data in resting and dynamic states in real time by constructing a personalized dynamic virtual environment and pressure distribution matrix, and dynamically adjust it in combination with virtual task behavior data. Through deep learning and timing analysis methods, the present invention can accurately analyze the comprehensive impact of environmental pressure and task behavior on the user's breathing pattern, breathing efficiency and metabolic state, thereby providing personalized breathing optimization suggestions. The present invention can not only overcome the limitations of the prior art, but also achieve dynamic adaptation in multiple scenarios, and through virtual reality visualization output, enhance the user experience and the applicability of the system.

[0081] Example 2: Reference Figure 3 , a respiratory monitoring simulation and analysis device based on virtual reality technology is provided for this embodiment, including: Dynamic virtual environment generation module, used to build a dynamic virtual environment, collect the user's physiological data in resting and dynamic states, and determine the individual baseline environmental tolerance and pressure distribution matrix; A virtual interactive behavior scenario module, which is used to divide the task behavior difficulty based on the user's adaptability and real-time status, improve the pressure distribution matrix, construct a fusion vector, and optimize the task scenario and the user's physiological matching through a dynamic adjustment algorithm; The data fusion and deep learning analysis module is used to combine the improved pressure distribution matrix and the fusion vector, build a dynamic respiratory metabolism interaction model through deep learning and time series analysis methods, and analyze the comprehensive impact of environmental pressure and interactive tasks on the user's breathing pattern, respiratory efficiency and metabolic state; The multi-scenario respiratory metabolism prediction and optimization module is used to predict the user's respiratory and metabolic adaptability in multiple scenarios based on a dynamic respiratory metabolism interaction model and integrate user historical and real-time data, provide personalized respiratory optimization suggestions, and output the suggestion results in a visual way in virtual reality.

[0082] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A respiratory monitoring simulation analysis method based on virtual reality technology, characterized in that: include: Build a dynamic virtual environment, collect users' physiological data in resting and dynamic states, and determine individual baseline environmental tolerance and pressure distribution matrix; Based on the user's adaptability and real-time status, the task behavior difficulty is divided, the pressure distribution matrix is ​​improved, the fusion vector is constructed, and the task scenario and the user's physiological matching are optimized through a dynamic adjustment algorithm; The improved pressure distribution matrix and fusion vector are combined to build a dynamic respiratory metabolism interaction model through deep learning and time series analysis methods to analyze the comprehensive impact of environmental pressure and interactive tasks on the user's breathing pattern, respiratory efficiency and metabolic state; Based on a dynamic respiratory and metabolic interactive model, the system integrates user historical and real-time data to predict the user's respiratory and metabolic adaptability in multiple scenarios, provide personalized respiratory optimization suggestions, and output the recommended results in a visual way in virtual reality.

2. The respiratory monitoring simulation analysis method based on virtual reality technology as claimed in claim 1, characterized in that: The individual baseline environmental tolerance is obtained by weighted calculation of the user's physiological parameters in a resting state; The determination of the pressure distribution matrix includes: According to the individual baseline environmental tolerance, combined with the reference standard of the preset environmental stress factor, the individualized dynamic pressure range matrix is ​​calculated using a fuzzy inference algorithm; Based on the dynamic pressure range, a layered mapping algorithm is used to generate a pressure distribution matrix of the virtual scene.

3. The respiratory monitoring simulation analysis method based on virtual reality technology as claimed in claim 1, characterized in that: The method of dividing the task behavior difficulty based on the user's adaptability and real-time status, improving the pressure distribution matrix, and constructing the fusion vector includes the following steps: According to the user's adaptability and task objectives, the difficulty level of the task behavior is divided, and the real-time dynamic changes of the task behavior are mapped into the pressure distribution matrix; Use motion capture equipment to collect user behavior parameters and muscle activity data in real time in interactive scenes, and fuse and associate them with physiological data in the virtual environment to construct a fusion vector; Through the task feedback adjustment algorithm, the difficulty of the task behavior is dynamically adjusted according to the user's real-time fatigue status. The adjusted task parameters are updated to the pressure distribution matrix in real time to ensure the synchronous changes of the virtual environment and task behavior.

4. The respiratory monitoring simulation analysis method based on virtual reality technology as claimed in claim 3, characterized in that: The expression for dynamically adjusting the difficulty of the task behavior according to the real-time fatigue state of the user is: ； in, is the task parameter adjustment amount, Provide users with real-time fatigue error, and To control the parameters for adjusting sensitivity, To complete the accuracy error for the user's real-time tasks, and is the task adjustment coefficient; when Threshold exceeded When , the task difficulty is reduced through an exponential function; when Threshold exceeded When the task characteristics are adjusted dynamically through the cosine function, the matching degree of user behavior is optimized.

5. The respiratory monitoring simulation analysis method based on virtual reality technology as claimed in claim 4, characterized in that: The method of combining the improved pressure distribution matrix and the fusion vector to construct a dynamic respiratory metabolism interaction model through deep learning and time series analysis methods includes the following steps: A unified respiratory metabolic physiological data set is constructed based on the real-time collected data in the fusion vector combined with the environmental variables of the pressure distribution matrix; Based on the respiratory metabolic physiological data set, an adaptive multidimensional mapping algorithm is used to correlate environmental pressure variables, task behavior parameters, and user respiratory efficiency and metabolic state, generate a task-environmental pressure-respiratory metabolic response matrix, and quantitatively describe the combined effects of environmental pressure and task behavior changes on the user's respiratory and metabolic state; Extracting time series data from the task-environmental pressure-respiratory metabolic response matrix, and dynamically correlating respiratory rhythm-lactate threshold using a dynamic time warping algorithm; Based on the dynamic association between breathing rhythm and lactate threshold, combined with the recurrent neural network deep learning algorithm, the real-time updated task difficulty parameters, pressure distribution matrix and user behavior completion error are integrated to construct a dynamic respiratory metabolism interaction model.

6. The respiratory monitoring simulation analysis method based on virtual reality technology as claimed in claim 5, characterized in that: The task-environmental stress-respiratory metabolic response matrix The generation includes: ； in, is a nonlinear mapping function, implemented using a multilayer perceptron. ~ is the dynamically adjusted weight factor, is the gradient of the environmental pressure variable, reflecting the rate of dynamic environmental change. is the gradient of the task behavior parameter, reflecting the rate of change of the user's real-time behavior. is the covariance between environmental pressure and behavioral parameters, is the dynamic gradient of metabolic state, is the task behavior intensity, It is the user's breathing efficiency indicator. is a regularization term used to control the complexity of the model. is the lactate threshold change rate, is the regularization weight.

7. The respiratory monitoring simulation analysis method based on virtual reality technology as claimed in claim 6, characterized in that: The dynamic association between breathing rhythm and lactate threshold includes: extracting time series features from the task-environmental stress-respiratory metabolic response matrix; Using DTW algorithm to measure the time series similarity between respiratory rhythm and lactate threshold changes : ； ； in, and is the time series of breathing rhythm and lactate threshold, is the number of time steps, is the normalized time step weight, is the time step between the current time point and the previous time point; Dynamic correlation between breathing rhythm and lactate threshold: ； in, It is the lactate threshold dynamic drift indicator. and is the weight parameter, is the rate of change of breathing rhythm.

8. The respiratory monitoring simulation analysis method based on virtual reality technology as claimed in claim 7, characterized in that: The dynamic respiratory metabolism interaction model includes: The construction of multimodal time series features includes , task behavior difficulty data, pressure distribution matrix, and user behavior completion error; Slice the multimodal time series features into fixed-length input windows to capture dynamic change patterns; Building the model architecture using a recurrent neural network: Input multimodal time series features into the RNN model; Multi-layer RNN units capture long-term dependencies in time series; Output task adjustment parameters and respiratory metabolic status assessment results; And by minimizing the loss function, optimizing the task behavior parameters and respiratory metabolic state, the user's physiological state is dynamically matched with the task environment.

9. A respiratory monitoring simulation analysis device based on virtual reality technology, based on the respiratory monitoring simulation analysis method based on virtual reality technology according to any one of claims 1 to 7, characterized in that: The respiratory monitoring simulation analysis device comprises: Dynamic virtual environment generation module, used to build a dynamic virtual environment, collect the user's physiological data in resting and dynamic states, and determine the individual baseline environmental tolerance and pressure distribution matrix; A virtual interactive behavior scenario module, which is used to divide the task behavior difficulty based on the user's adaptability and real-time status, improve the pressure distribution matrix, construct a fusion vector, and optimize the task scenario and the user's physiological matching through a dynamic adjustment algorithm; The data fusion and deep learning analysis module is used to combine the improved pressure distribution matrix and the fusion vector, build a dynamic respiratory metabolism interaction model through deep learning and time series analysis methods, and analyze the comprehensive impact of environmental pressure and interactive tasks on the user's breathing pattern, respiratory efficiency and metabolic state; The multi-scenario respiratory metabolism prediction and optimization module is used to predict the user's respiratory and metabolic adaptability in multiple scenarios based on a dynamic respiratory metabolism interaction model and integrate user historical and real-time data, provide personalized respiratory optimization suggestions, and output the suggestion results in a visual way in virtual reality.

Images