Respiratory rehabilitation training system combined with virtual reality technology

Abstract

The invention discloses a respiratory rehabilitation training system combined with a virtual reality technology, and the system comprises a patient information collection module which is used for collecting the basic information and medical history of a patient; the basic disease confirmation module and the respiratory training method selection module are used for systematically collecting basic information and medical history of a patient, so that accurate data support is provided for formulating a personalized training scheme; proper training steps are automatically selected, so that the safety and pertinence of a training scheme are ensured; the respiratory training method selection module intelligently recommends the most appropriate respiratory training method according to the specific condition of the patient, and dynamically adjusts the training intensity through the training intensity calculation unit, so that the training is more scientific and reasonable; the virtual reality training module utilizes an immersive environment and interactive training to improve the participation degree and the training effect of a patient, and meanwhile, the training effect evaluation unit unifies the judgment standard through a datamation evaluation method, does not depend on experience purely and effectively reduces the misjudgment rate.

Description

Technical Field

[0001] This invention relates to the field of medical rehabilitation technology, and in particular to a respiratory rehabilitation training system that incorporates virtual reality technology. Background Technology

[0002] In the field of medical rehabilitation, especially in respiratory rehabilitation training, the demand for respiratory rehabilitation training is growing with the aging of the global population and the increase in chronic respiratory diseases. Respiratory rehabilitation is of great significance for improving patients' respiratory function, improving their quality of life, and reducing the consumption of medical resources. The development of this field has received widespread attention, especially among patients with respiratory diseases such as chronic obstructive pulmonary disease (COPD), asthma, and pulmonary fibrosis, where respiratory rehabilitation training has become an important part of the treatment plan.

[0003] Existing respiratory rehabilitation training systems typically lack an immersive training environment, which may reduce patient engagement and motivation. Traditional training methods often have limitations. These methods may lack personalization and fail to adequately adapt to the specific needs of different patients, leading to poor training results. Furthermore, the monitoring and feedback mechanisms during training are inadequate, often relying on the subjective judgment of medical staff and lacking objective data support. This may result in untimely and inaccurate adjustments to the training plan, thus affecting the patient's rehabilitation progress. In addition, adjustments to the training plan usually require the intervention of professionals, which not only increases medical costs but also limits the possibility of patients conducting self-rehabilitation at home or in the community. Summary of the Invention

[0004] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0005] In view of the problems existing in the above-mentioned respiratory rehabilitation training systems that combine virtual reality technology, the present invention is proposed.

[0006] Therefore, the purpose of this invention is to provide a respiratory rehabilitation training system that incorporates virtual reality technology.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a respiratory rehabilitation training system combining virtual reality technology, comprising,

[0008] The patient information collection module is used to collect patients' basic information and medical history;

[0009] The underlying disease confirmation module is used to confirm whether a patient has an underlying disease and select different training steps based on the results;

[0010] The breathing training method selection module is used to select a suitable breathing training method based on the patient's specific condition.

[0011] The virtual reality training module is used to provide an immersive training environment and simulate different training scenarios through virtual reality technology;

[0012] A real-time monitoring module is used to monitor and track the patient's physiological parameters during training.

[0013] The feedback adjustment module is used to adjust the training plan in real time based on the monitoring results.

[0014] As a preferred embodiment of the respiratory rehabilitation training system combining virtual reality technology described in this invention, the patient information collection module includes:

[0015] The identity information input unit is used to input the patient's basic information;

[0016] The medical history input unit is used to input the patient's medical history.

[0017] As a preferred embodiment of the respiratory rehabilitation training system combining virtual reality technology described in this invention, the underlying disease confirmation module includes:

[0018] The underlying disease detection unit is used to detect whether a patient has any underlying diseases.

[0019] The training step selection unit is used to select different training steps based on the test results of the underlying disease. If the test results indicate that there is an underlying disease, the breathing training steps that include adjustments are selected; if the test results indicate that there is no underlying disease, the standard breathing training steps are selected.

[0020] As a preferred embodiment of the respiratory rehabilitation training system combining virtual reality technology described in this invention, the respiratory training method selection module includes:

[0021] Abdominal breathing selection unit, used to select abdominal breathing training methods;

[0022] The pursed-lip breathing selection unit is used to select pursed-lip breathing training methods;

[0023] The respiratory muscle resistance training selection unit is used to select respiratory muscle resistance training methods; and

[0024] Training intensity calculation unit, the calculation formula is as follows

[0025]

[0026] Where I represents training intensity, P represents the patient's lung function parameters, V represents the patient's respiratory volume, T represents training time, and E represents the patient's endurance level. The weighting coefficients are set to 0.4, 0.3, 0.2, and 0.1 respectively.

[0027] As a preferred embodiment of the respiratory rehabilitation training system combining virtual reality technology described in this invention, the virtual reality training module includes:

[0028] Virtual reality environment generation unit, used to generate immersive training environments;

[0029] Training scenario simulation unit, used to simulate different training scenarios;

[0030] Interactive training units are designed to provide an interactive training experience.

[0031] Training effectiveness evaluation unit, evaluation formula is:

[0032]

[0033] Among them, E f Indicates the training effect, e i Let w represent the i-th training performance metric. i Let be the weight of the i-th training result.

[0034] As a preferred embodiment of the respiratory rehabilitation training system combining virtual reality technology described in this invention, the virtual reality training module includes:

[0035] Virtual reality environment generation unit, used to generate immersive training environments;

[0036] Training scenario simulation unit, used to simulate different training scenarios;

[0037] Interactive training units are designed to provide an interactive training experience.

[0038] Training effectiveness evaluation unit, evaluation formula is:

[0039]

[0040] Among them, E f Indicates the training effect, e i Let w represent the i-th training performance metric. i Let be the weight of the i-th training result.

[0041] As a preferred embodiment of the respiratory rehabilitation training system combining virtual reality technology described in this invention, the real-time monitoring module includes:

[0042] Physiological parameter monitoring unit, used to monitor the patient's physiological parameters;

[0043] The data monitoring unit is used to process the monitoring results into data.

[0044] The non-standard application detection unit is used to detect non-standard applications during the training process;

[0045] The parameter anomaly handling unit is used to handle parameter anomalies according to the processing formula.

[0046] As a preferred embodiment of the respiratory rehabilitation training system combining virtual reality technology described in this invention, the processing formula is:

[0047]

[0048] Where A represents the abnormal handling result, M represents the monitored physiological parameter, N represents the preset normal value, and S represents the patient's subjective feeling; This represents the dynamic adjustment coefficient, which is dynamically adjusted based on the training phase and patient feedback.

[0049] As a preferred embodiment of the respiratory rehabilitation training system combining virtual reality technology described in this invention, the feedback adjustment module includes:

[0050] The monitoring results analysis unit is used to analyze monitoring results.

[0051] The training program adjustment unit is used to adjust the training program in real time based on the analysis results.

[0052] A security assessment unit is used to assess the security of training.

[0053] The dynamic adjustment coefficient calculation unit is used to make dynamic adjustments according to the adjustment formula.

[0054] As a preferred embodiment of the respiratory rehabilitation training system combining virtual reality technology described in this invention, the adjustment formula is:

[0055]

[0056] Where T represents training time, P represents the patient's physiological stress level, and e is a constant, usually taken as 2.71828.

[0057] The beneficial effects of this invention are as follows: By systematically collecting patients' basic information and medical history, accurate data support is provided for the development of personalized training programs; the underlying disease confirmation module accurately detects whether patients have underlying diseases and automatically selects appropriate training steps accordingly, ensuring the safety and relevance of the training program; the breathing training method selection module intelligently recommends the most suitable breathing training method based on the patient's specific condition and dynamically adjusts the training intensity through the training intensity calculation unit, making the training more scientific and reasonable; the virtual reality training module utilizes an immersive environment and interactive training to improve patient participation and training effectiveness, while the training effect evaluation unit uses data-driven evaluation methods to unify judgment criteria, no longer relying solely on experience, effectively reducing the misjudgment rate; the real-time monitoring module accurately monitors patients' physiological parameters and performs data processing, providing a basis for real-time adjustment of the training program; the parameter anomaly handling unit can promptly detect and handle abnormal situations during training, reducing training risks; the feedback adjustment module dynamically adjusts the training program based on monitoring results and patient feedback, making the training more adaptable to individual patient differences and rehabilitation stages, improving rehabilitation efficiency. Attached Figure Description

[0058] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0059] Figure 1 The present invention relates to a computer device for a respiratory rehabilitation training system that incorporates virtual reality technology. Detailed Implementation

[0060] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0061] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0062] 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 phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0063] Secondly, the present invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of the present invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not according to the usual scale. Furthermore, the schematic diagrams are merely examples and should not limit the scope of protection of the present invention. In addition, actual fabrication should include three-dimensional spatial dimensions of length, width, and depth.

[0064] Traditional technical solutions suffer from the following problems: existing respiratory rehabilitation training systems lack an immersive training environment, resulting in insufficient patient participation and motivation; training programs lack personalization and cannot adapt to the needs of different patients; the monitoring and feedback mechanism during training is imperfect, relying on the subjective judgment of medical staff, lacking objective data support, and the program adjustment is not timely and accurate, requiring professional intervention, increasing medical costs, and limiting the possibility of self-rehabilitation.

[0065] Based on this, this embodiment provides a respiratory rehabilitation training system combining virtual reality technology, including a patient information collection module for collecting the patient's basic information and medical history; an underlying disease confirmation module for confirming whether the patient has an underlying disease and selecting different training steps based on the results; a respiratory training method selection module for selecting a suitable respiratory training method based on the patient's specific condition; a virtual reality training module for providing an immersive training environment and simulating different training scenarios through virtual reality technology; a real-time monitoring module for monitoring the patient's physiological parameters during training; and a feedback adjustment module for adjusting the training plan in real time based on the monitoring results.

[0066] This solution utilizes a multi-module collaborative approach to address multiple shortcomings of existing technologies and construct a personalized, intelligent respiratory rehabilitation training system. The information collection module serves as the data foundation, collecting basic information such as patient name, age, gender, height, and weight through the identity information input unit. This information is stored in the system database in structured data form, providing fundamental dimensional data for the personalized adaptation of subsequent training programs. The medical history input unit focuses on the patient's history of respiratory diseases such as chronic obstructive pulmonary disease, asthma, and pulmonary fibrosis, treatment history including medication and surgery, and previous rehabilitation training experiences. A standardized input interface guides patients or medical staff to accurately enter this information, ensuring the completeness and accuracy of medical history data, providing crucial evidence for basic disease confirmation and the selection of respiratory training methods. The underlying disease confirmation module receives data from the patient information collection module. The underlying disease detection unit accurately determines whether a patient has an underlying disease by automatically retrieving and analyzing medical history data and combining it with preset underlying disease determination rules. The training step selection unit triggers different training processes based on the test results. If an underlying disease is determined, the system automatically calls customized training steps that include adjustments to training intensity gradients, adaptation of breathing rhythm, and optimization of rest intervals. For example, for patients with chronic obstructive pulmonary disease, the initial training steps will reduce the breathing depth requirement and prolong the expiratory rest time. If no underlying disease is determined, standard breathing training steps are used, covering routine breathing pattern training and intensity increment processes to ensure the relevance and safety of the training. The breathing training method selection module provides corresponding training methods based on the patient's lung function parameters, respiratory volume, endurance level, etc., through the abdominal breathing selection unit, pursed-lip breathing selection unit, and respiratory muscle resistance training selection unit. Abdominal breathing training focuses on strengthening diaphragmatic movement, guiding the patient to complete breathing through abdominal rise and fall; pursed-lip breathing training improves gas exchange efficiency by controlling expiratory airflow rate; and respiratory muscle resistance training enhances respiratory muscle strength by setting resistance thresholds. The system will automatically match the most suitable single or combined training methods based on the patient's information. The virtual reality training module serves as the core interactive unit. Through the virtual reality environment generation unit, it utilizes the Unity3D engine to construct immersive scenes such as forest walks and underwater explorations, combined with VR headsets like the Oculus Quest 2 to provide patients with an immersive training experience. The training scene simulation unit dynamically generates adaptive interactive scenes based on the selected breathing training method; for example, in an abdominal breathing training scene, the growth rate of virtual plants is linked to the patient's breathing depth. The interactive training unit uses a handheld controller to capture the patient's breathing movements and corresponding physical feedback, such as simulating abdominal rise and fall, enabling real-time interaction between the patient and the virtual scene and enhancing the training's enjoyment. The training effect evaluation unit quantifies training effectiveness through multi-dimensional indicators.The real-time monitoring module intervenes throughout the training process. The physiological parameter monitoring unit collects physiological parameters such as heart rate (beats / min), blood oxygen saturation (percentage), respiratory rate (breaths / min), and respiratory depth (ml) in real time through wearable sensors such as heart rate bracelets, pulse oximeters, and respiratory sensors. The sampling frequency is set to 10Hz to ensure real-time parameter capture. The data monitoring unit converts the collected analog signals into digital signals and generates analyzable monitoring data through data standardization processing, such as outlier removal. The non-standard application detection unit identifies non-standard training behaviors in real time by comparing the patient's respiratory movement data with standard training movement templates, such as whether the abdominal rise and fall amplitude during diaphragmatic breathing meets the standard and whether the lip closure degree meets the requirements during pursed-lip breathing. The parameter anomaly handling unit initiates anomaly handling procedures for physiological parameters that exceed the preset normal range, such as blood oxygen saturation below 90% and heart rate above 120 beats / min, to ensure training safety. The feedback adjustment module is based on the data output of the real-time monitoring module. The monitoring result analysis unit comprehensively analyzes physiological parameter data, records of non-standard behaviors, and training progress data to determine the suitability of the training plan, such as analyzing the correlation between heart rate changes and training intensity, and assessing the applicability of the breathing training method to the patient. The training plan adjustment unit dynamically optimizes training parameters based on the analysis results. For example, when the patient's respiratory rate is detected to be persistently high, the training intensity is automatically reduced or the rest interval is increased. The safety assessment unit assesses the safety of the training process through quantitative indicators such as the incidence of abnormal physiological parameters and the frequency of non-standard behaviors. If the risk value exceeds the threshold, a training pause command is immediately triggered. The dynamic adjustment coefficient calculation unit optimizes and adjusts parameters in real time based on the early, middle, and late stages of the training phase and patient feedback to ensure the dynamic suitability of the training plan.

[0067] The technical effects achieved by the above embodiments include: enabling personalized customization of respiratory rehabilitation training to suit patients with different underlying disease states and physical conditions; enhancing patient participation through an immersive training environment; ensuring safe and effective training through real-time monitoring and dynamic adjustment, reducing reliance on professional personnel, and assisting in self-rehabilitation.

[0068] Traditional technical solutions suffer from the following problems: existing patient information collection modules have vague classifications of patient information, lack clear distinctions between basic information and medical history collection, and data entry is chaotic, which makes it impossible for subsequent modules to accurately obtain effective data and affects the accuracy of training program development.

[0069] Based on this, the patient information collection module includes an identity information input unit for inputting the patient's basic information and a medical history input unit for inputting the patient's medical history.

[0070] This solution ensures the standardization and completeness of information collection by breaking down information collection units and clearly classifying data. The identity information input unit serves as the basic information collection entry point. A visual input interface allows for the setting of required and optional fields. Required fields include patient name, gender, age (in years), height (in centimeters), weight (in kilograms), and contact information. Optional fields include occupation and lifestyle habits such as smoking history and exercise frequency. The input interface supports text entry and dropdown selection. For example, age is limited to a numeric input box ranging from 0 to 120 years, and gender is selected via dropdown options for male / female and others, ensuring the accuracy and standardization of basic information. Entered data is stored in real-time in the system's backend database, and encryption algorithms are used to ensure information security. The medical history input unit focuses on patients' medical information, guiding the entry through a structured form. Core fields include disease diagnosis (multiple selections allowed, such as chronic obstructive pulmonary disease, asthma, pulmonary fibrosis, no related diseases), diagnosis time in years / months, treatment method (drug therapy, surgical therapy, conservative treatment), drug name (if applicable), surgery time (if applicable), previous respiratory rehabilitation training experience (if present, training duration and method required), and allergy history (e.g., medication, environmental factors). Each field is equipped with input prompts; for example, the disease diagnosis field provides a list of common respiratory diseases for selection, avoiding vague descriptions. This allows medical staff to assist patients in completing the entry, ensuring the completeness and accuracy of medical history data. The entered data is stored in association with the patient's unique identifier, such as their ID number, providing direct data support for subsequent modules such as basic disease confirmation and respiratory training method selection. For instance, the disease diagnosis results in the medical history directly serve as the core basis for basic disease detection, while treatment history and rehabilitation experience help optimize respiratory training methods and intensity settings.

[0071] The technical effects achieved by the above embodiments include: standardizing the patient information collection process, clarifying the classification of basic information and medical history, ensuring data accuracy and completeness, providing reliable data input for subsequent modules, and improving the accuracy of training program formulation.

[0072] Traditional technical solutions have the following technical problems: existing respiratory rehabilitation training systems do not design differentiated training steps based on whether patients have underlying diseases. The uniform training process cannot be adapted to the physical tolerance of patients with underlying diseases, which can easily lead to training risks, such as discomfort caused by excessive training intensity in patients with underlying diseases, while reducing the rehabilitation efficiency of patients without underlying diseases.

[0073] Based on this, the underlying disease confirmation module includes an underlying disease detection unit for detecting whether the patient has an underlying disease; and a training step selection unit for selecting different training steps based on the underlying disease detection results. Specifically, if the detection result indicates the presence of an underlying disease, a breathing training step with adjustments is selected; if the detection result indicates the absence of an underlying disease, a standard breathing training step is selected.

[0074] This solution employs differentiated training steps to adapt to the health conditions of different patients, enhancing the safety and effectiveness of training. The underlying disease detection unit receives data from the medical history input unit in the patient information collection module. It analyzes the medical history data using a pre-set underlying disease determination algorithm. The algorithm incorporates diagnostic criteria for common respiratory underlying diseases. The system automatically retrieves the disease diagnosis fields entered by the patient. If a record matching the criteria is found, the patient is determined to have an underlying disease; otherwise, if no relevant diagnostic record is found or only a history of acute respiratory illness is present, the patient is determined to have no underlying disease. The detection results are fed back to the training step selection unit in real time. The training step selection unit calls the corresponding training step template based on the detection results. The standard breathing training steps are suitable for patients without underlying diseases. The process includes a 5-minute warm-up phase using shallow, rapid breathing at a rate of 15-20 breaths / minute; a 15-minute basic training phase alternating between diaphragmatic and pursed-lip breathing, gradually increasing the breathing depth to 60% of the patient's maximum respiratory capacity; and a 5-minute relaxation phase using slow, deep breathing at a rate of 10-12 breaths / minute. The training intensity increases at a fixed gradient, increasing by 10% every 5 minutes, without any additional adjustment mechanism. The adjusted breathing training steps are designed for patients with underlying medical conditions. Based on the standard steps, they are optimized in multiple dimensions. First, the initial training intensity is reduced to 50% of the standard steps; for example, the initial breathing depth in the basic training phase is 30% of the patient's maximum respiratory capacity, and the escalation gradient is slowed to 5% every 10 minutes. Second, the breathing rhythm is adjusted to suit specific rhythms for different types of underlying conditions; for example, patients with chronic obstructive pulmonary disease (COPD) use a 2-second inhale-4-second exhale rhythm, while asthma patients use a 3-second inhale-3-second exhale rhythm. Rest intervals are also added, with a 1-minute rest period every 5 minutes of training, during which patients are guided to perform slow, relaxing breathing. Furthermore, a real-time risk monitoring node is incorporated into the steps, assessing patient tolerance every 3 minutes using physiological parameter data. If any abnormality in discomfort-related parameters occurs, training is automatically paused and the steps adjusted. Both training step templates are stored in the system's step library, and the training step selection unit achieves rapid switching via interface calls, ensuring a smooth transition in the training process.

[0075] The technical effects achieved by the above embodiments include: accurately matching the training needs of patients with different underlying disease states, ensuring the rehabilitation efficiency of patients without underlying diseases through standardized procedures, reducing the training risks for patients with underlying diseases through adjusted procedures, and improving the adaptability and safety of training.

[0076] Traditional technical solutions have the following technical problems: the training intensity settings of existing respiratory rehabilitation training systems are subjective and arbitrary, and do not take into account the patient's lung function, respiratory volume, training time, endurance level and other key parameters for quantitative calculation. This results in the training intensity being too high, which may cause discomfort to the patient, and too low, which will affect the rehabilitation effect, and cannot achieve personalized and precise adaptation.

[0077] Based on this, the breathing training method selection module includes an diaphragmatic breathing selection unit for selecting an diaphragmatic breathing training method; a pursed-lip breathing selection unit for selecting a pursed-lip breathing training method; a respiratory muscle resistance training selection unit for selecting a respiratory muscle resistance training method; and a training intensity calculation unit, the calculation formula of which is:

[0078] ;

[0079] in, The training intensity is dimensionless, ranging from 0 to 10, corresponding to three levels: low, medium, and high. The patient's lung function parameter is selected as the forced expiratory volume in one second (FEV1), expressed in liters, with a range of 0.5 to 4.0 liters. The respiratory volume of a patient is expressed as tidal volume, measured in milliliters, with a range of 300 to 800 milliliters. The training time is expressed in minutes, ranging from 5 to 30 minutes. The patient's endurance level is represented by a score corresponding to a 6-minute walking distance. This score is dimensionless, ranging from 1 to 5 points, corresponding to walking distances of less than 300 meters to greater than or equal to 500 meters. Weighting coefficients are 0.4, 0.3, 0.2, and 0.1, respectively. This scheme calculates training intensity using a quantitative formula and combines it with multi-dimensional patient parameters to achieve personalized and precise setting of training intensity, overcoming the drawbacks of subjective settings.

[0080] The abdominal breathing selection unit, pursed-lip breathing selection unit, and respiratory muscle resistance training selection unit correspond to the invocation and configuration of three core breathing training methods. After the abdominal breathing selection unit is activated, the system guides the patient to use nasal inhalation and oral exhalation through voice guidance and virtual scene animations, such as a virtual human body model showing abdominal rise and fall, focusing on the contraction and relaxation of the diaphragm. During training, the system captures the patient's abdominal movement amplitude in real time and provides feedback on whether the standard movement requirements have been met. The pursed-lip breathing selection unit guides the patient to exhale slowly with pursed lips after inhalation. The exhalation speed is visualized through airflow simulation in a virtual scene, such as a slowly flowing beam of light, helping the patient control the exhalation rhythm and improve gas exchange efficiency. The respiratory muscle resistance training selection unit strengthens the patient's inspiratory and expiratory muscles by setting respiratory resistance thresholds, such as simulating different resistance levels using a breathing trainer. The system can set a resistance increment gradient based on the patient's initial state. The training intensity calculation unit is the core of this module. Its calculation formula is designed based on the physiological mechanisms and clinical experience of respiratory rehabilitation training. Weighting coefficients reflect the influence of each parameter on the training intensity, including lung function parameters. As a core indicator reflecting a patient's respiratory function, respiratory volume directly determines the patient's upper limit of tolerance to training intensity, therefore it is assigned the highest weight of 0.4; The gas exchange capacity of a patient in a single breath is an important basis for setting training intensity, and is assigned a weight of 0.3; training time The cumulative fatigue level of patients is affected and needs to be appropriately adjusted to avoid overtraining; a weight of 0.2 is assigned to this level. This reflects the patient's overall physical condition and directly affects the sustainability of training intensity. A weight of 0.1 is assigned, and each weight coefficient has been validated through clinical trials to ensure the scientific validity of the training intensity calculation. The dimensions of each parameter in the formula are clearly defined. FEV1 is obtained through actual measurement using a pulmonary function testing device, and the unit is liters. For example, a patient's FEV1 value is 2.5 liters. Tidal volume is monitored in real time by a respiratory sensor, with the unit being milliliters, such as a monitored value of 500 milliliters; The training time is set according to the patient's initial rehabilitation stage: 10 minutes in the initial stage, 15 minutes in the middle stage, and 20 minutes in the later stage. The endurance level is calculated based on the distance covered by a 6-minute walking test. A distance of less than 300 meters is worth 1 point, 300-400 meters is worth 2 points, 400-500 meters is worth 3 points, 500-600 meters is worth 4 points, and more than 600 meters is worth 5 points. For example, a patient walking 450 meters... In calculating training intensity, each parameter is first standardized, converting the actual measured values ​​into dimensionless values ​​from 0 to 10, such as... Increase to the corresponding standardized value of 5. Milliliters correspond to a standardized value of 5. The standardized value for minutes is 3. The corresponding standardized value is 3, which is then substituted into the formula for calculation, for example: Calculation results Corresponding to moderate training intensity, the system configures corresponding breathing training parameters, such as the depth requirement for diaphragmatic breathing and the resistance level for resistance training. The training intensity calculation unit works in real time with the patient information acquisition module and the real-time monitoring module. When the patient's lung function parameters, respiratory volume, and other data change, such as FEV1 increasing to 2.8 liters after rehabilitation training, the system automatically recalculates the training intensity and dynamically adjusts the training plan to ensure that the training intensity is always suitable for the patient's rehabilitation status.

[0081] The technical effects achieved by the above embodiments include: realizing personalized and precise setting of training intensity through quantitative formulas, avoiding subjective setting deviations, adapting to the patient's physical condition, improving the effectiveness and safety of training, and promoting the rehabilitation process.

[0082] Traditional technical solutions suffer from the following technical problems: existing virtual reality training modules lack a systematic training effect evaluation mechanism, the determination of training effect depends on subjective feelings, there is no unified quantitative standard, it cannot accurately reflect the patient's rehabilitation progress, and it is difficult to optimize the training program accordingly.

[0083] Based on this, the virtual reality training module includes a virtual reality environment generation unit for generating an immersive training environment; a training scenario simulation unit for simulating different training scenarios; an interactive training unit for providing an interactive training experience; and a training effect evaluation unit, with the evaluation formula being:

[0084] ;

[0085] in, The score represents the dimensionless training effect, ranging from 0 to 100, with higher scores indicating better results. Indicates the first The training effectiveness indicators include: respiratory depth attainment rate (dimensionless, range 0 to 100%); respiratory rhythm stability (dimensionless, range 0 to 100%); training completion rate (dimensionless, range 0 to 100%); and physiological parameter fit rate (dimensionless, range 0 to 100%). For the first The weights for each training effect are: breathing depth attainment rate (0.3), breathing rhythm stability (0.25), training completion rate (0.25), and physiological parameter fit (0.2). This scheme uses a quantitative evaluation formula combined with multi-dimensional indicators to accurately determine training effectiveness, providing data support for optimizing training programs.

[0086] The virtual reality environment generation unit uses the Unity3D engine combined with a VR development toolkit to construct a highly immersive virtual environment. Environment types are set according to training needs, including natural scenes such as forests and beaches, and fun scenes such as cartoon parks. The lighting and sound effects in the environment are linked to the patient's breathing movements; for example, when the patient takes a deep breath, flowers in the virtual scene bloom, enhancing the fun and immersion of the training. This unit presents the virtual environment to the patient in real time through VR headsets such as HTC VivePro, ensuring an immersive visual and auditory experience and reducing the monotony of training. The training scenario simulation unit dynamically generates adaptive interactive scenarios based on the selected breathing training method. For example, in the abdominal breathing training scenario, the inflation speed of the virtual balloon is related to the patient's breathing depth; the deeper the breathing, the faster the balloon inflates. In the pursed-lip breathing training scenario, the flow rate of the virtual stream matches the patient's exhalation speed, guiding the patient to control their exhalation rhythm. In the respiratory muscle resistance training scenario, the slope of the virtual mountain corresponds to the training resistance; the greater the resistance, the steeper the slope. The scenario simulation unit receives instructions from the breathing training method selection module in real time to achieve rapid switching and adaptation of scenarios. The interactive training unit utilizes a VR controller and wearable sensors. The controller captures the patient's limb movements, such as hand gestures simulating abdominal movements, while the sensors collect the patient's respiratory parameters. This data is synchronized to the virtual scene, enabling real-time interaction between the patient and virtual elements. For example, when the patient completes a standard abdominal breath, the virtual character moves forward a short distance, and the system provides voice feedback, such as "breathing is normal," to maintain positive guidance and enhance patient engagement. This unit also supports pause and adjustment commands during training, allowing patients to adjust their training status at any time via controller buttons. The training effectiveness evaluation unit is the core of this module, quantifying training effectiveness through multi-dimensional indicators and evaluation formulas. Based on the weighted allocation of factors influencing training effectiveness, the respiratory depth attainment rate directly reflects the achievement of the core goals of respiratory training, with a maximum weight of 0.3. It is calculated as the ratio of the number of times the preset respiratory depth standard is reached to the total number of breaths during training. Respiratory rhythm stability reflects the patient's ability to control respiratory rate and inspiratory-to-expiratory ratio, with a weight of 0.25. It is calculated by the inverse deviation rate between the actual respiratory rhythm and the standard rhythm; the lower the deviation rate, the higher the stability. Training completion reflects the patient's adherence to training, with a weight of 0.25, i.e., the ratio of the actual completed training time to the preset training time. Physiological parameter fit reflects the patient's physiological state during training, with a weight of 0.2, calculated by the percentage of normal range for parameters such as heart rate and blood oxygen saturation during training. (Each indicator...) The values ​​range from 0 to 100%. For example, if a patient's respiratory depth achievement rate is 80%, respiratory rhythm stability is 75%, training completion rate is 90%, and physiological parameter fit is 85% during training, the values ​​can be substituted into the formula for calculation: A score corresponds to a good training effect. The training effect evaluation unit feeds the calculation results back to the feedback adjustment module, providing a direct basis for the dynamic adjustment of the training plan. If the score is below 60, the system will analyze the specific low-scoring items, such as the low rate of achieving the breathing depth target, and adjust the training parameters accordingly, such as lowering the breathing depth requirement.

[0087] The technical effects achieved by the above embodiments include: accurately evaluating training effects through quantitative formulas, avoiding subjective judgment bias, clearly reflecting the patient's rehabilitation progress, providing data support for optimizing training programs, and improving the pertinence and effectiveness of rehabilitation training.

[0088] Traditional technical solutions have the following technical problems: existing real-time monitoring modules can only monitor a single physiological parameter, and the monitoring results are not systematically processed. They cannot detect non-standard operations and parameter anomalies during training in a timely manner, resulting in the inability to provide timely warnings of training risks and affecting training safety.

[0089] Based on this, the real-time monitoring module includes a physiological parameter monitoring unit for monitoring the patient's physiological parameters; a data-driven monitoring unit for processing the monitoring results; a non-standard application detection unit for detecting non-standard applications during the training process; and a parameter anomaly handling unit for handling parameter anomalies according to a processing formula.

[0090] This solution achieves comprehensive monitoring of physiological parameters, data processing, non-standard detection, and anomaly handling through multi-unit collaboration, thereby improving the comprehensiveness and security of training monitoring.

[0091] The physiological parameter monitoring unit collects the patient's core physiological parameters in real time through wearable sensing devices, such as a smart vest integrating heart rate, blood oxygen, and respiration sensors. These parameters include heart rate (beats / min, normal range 60-100 beats / min), blood oxygen saturation (percentage, normal range 95%-100%), respiratory rate (breaths / min, normal range 12-20 breaths / min), and respiratory depth (milliliters, based on tidal volume conversion). The sensing devices communicate with the system host in real time via Bluetooth 5.0 protocol, with a sampling frequency set to 10Hz to ensure the continuity and real-time nature of parameter acquisition, providing raw data support for subsequent processing. The data monitoring unit receives the raw data from the physiological parameter monitoring unit and first performs data preprocessing, including outlier removal such as instantaneous extreme values ​​caused by sensor jitter, and data smoothing using a moving average algorithm with a window size of 5 sampling points to ensure data accuracy. Then, the preprocessed analog signals are converted into digital signals and stored in a database in a structured format of timestamp-parameter type-parameter value-unit, for example, 2024-05-2010:00:01-heart rate-75-beats / min. Simultaneously, real-time data curves are generated to visually present the changing trends of the patient's physiological parameters, providing a visual reference for medical staff and patients. The data-processed information is also synchronously pushed to the non-standard application detection unit and the parameter anomaly handling unit. The non-standard application detection unit is based on preset breathing training standards. It detects non-standard behaviors during training by comparing the patient's breathing parameters (breathing frequency, depth, inspiratory-to-expiratory ratio) with the standard parameter range. For example, in diaphragmatic breathing training, if the patient's breathing depth is consistently below 60% of the standard value, it is judged as shallow breathing; in pursed-lip breathing training, if the ratio of exhalation time to inhalation time is less than 1.5, it is judged as short exhalation. At the same time, combined with the interactive data of the virtual reality training module, if the patient's limb operation and breathing action are not synchronized, such as the patient not responding in time after the breathing action command is issued in the virtual scene, it is also judged as non-standard application. The detection results are marked in real time and fed back to the system interface, and a voice prompt is triggered, such as "Please deepen your breathing". The parameter anomaly handling unit sets abnormal thresholds for physiological parameters processed by the data monitoring unit, such as heart rate greater than 120 beats / min or less than 50 beats / min, blood oxygen saturation less than 90%, and respiratory rate greater than 25 breaths / min or less than 10 breaths / min. When a parameter exceeds the threshold, the unit automatically calls the anomaly handling formula to calculate the processing result. Based on the result, corresponding processing measures are triggered, such as reducing training intensity, pausing training, and issuing alarms, to ensure timely handling of safety risks during training. The parameter anomaly handling unit and the feedback adjustment module work together in real time to synchronize the anomaly handling results to the training plan adjustment unit, providing a basis for optimizing the training plan.

[0092] The technical effects achieved by the above embodiments include: realizing comprehensive monitoring and systematic processing of physiological parameters, timely detection of non-standard operations and parameter abnormalities, rapid triggering of response measures, reducing training risks, and ensuring the safety and standardization of the training process.

[0093] Traditional technical solutions have the following technical problems: existing parameter abnormality handling is based on simple judgment based on fixed thresholds, without taking into account the patient's subjective feelings and the dynamic adjustment of the treatment strategy during the training stage. This results in insufficient targeting of treatment measures, which may lead to over-intervention or untimely intervention, affecting the safety and continuity of training.

[0094] Based on this, the processing formula of the parameter anomaly handling unit is:

[0095] ;

[0096] in, This indicates that the anomaly handling result is dimensionless, ranging from -10 to 10. Negative values ​​correspond to reducing training intensity, 0 corresponds to maintaining the status quo, and positive values ​​correspond to pausing training. This indicates the monitored physiological parameters, such as heart rate, measured in beats per minute; and blood oxygen saturation, measured as a percentage. This indicates that the preset normal heart rate range is 60 to 100 beats per minute, with the median value of 80 beats per minute taken; the normal blood oxygen saturation range is 95% to 100%, with 98% taken. The subjective feelings of patients are dimensionless, ranging from -5 to 5, where -5 corresponds to severe discomfort, 0 corresponds to no discomfort, and 5 corresponds to comfort. This indicates that the dynamic adjustment coefficient is dimensionless, ranging from 0.2 to 1.0, and its value is determined based on the initial stage of the training phase. Mid-term Later The system dynamically adjusts based on patient feedback. By combining objective parameters with subjective feelings through dynamic formulas, this approach achieves precise adaptation to abnormal situations, improving the targetedness and rationality of treatment measures.

[0097] Processing formula The design is based on the core logic of objective parameter deviation + subjective feedback + dynamic stage adaptation, aiming to break through the limitations of traditional fixed threshold processing and achieve personalized anomaly handling. The dimensions and meanings of each parameter in the formula are clearly defined. For the specific values ​​of the physiological parameters to be monitored in real time, it is necessary to compare them with... The parameter types are consistent, such as when monitoring heart rate. The measured heart rate is expressed in beats per minute. When monitoring blood oxygen saturation, The measured blood oxygen saturation value is expressed as a percentage. To ensure the reasonableness of deviation calculations, the median value of the parameter's normal range is selected to correspond to the preset normal values ​​of physiological parameters. For example, the normal heart rate is 60 to 100 beats per minute. Blood oxygen saturation is 95% to 100% per minute. ; The system scores patients' subjective feelings based on button feedback or voice input via VR controllers. During training, the system pops up feedback prompts every 3 minutes. Patients select the corresponding score based on their own feelings, such as chest tightness, shortness of breath, dizziness, etc. -5 points correspond to severe discomfort, such as inability to continue breathing; -3 points correspond to obvious discomfort, such as obvious chest tightness; -1 point corresponds to mild discomfort, such as mild shortness of breath; 0 points correspond to no discomfort; 1 point corresponds to mild comfort; 3 points correspond to obvious comfort; 5 points correspond to very comfortable. This ensures the quantification and accuracy of subjective feeling data. This is a dynamically adjusted coefficient, and its value is strongly correlated with the training phase. In the early stages of training, the patient's body has not yet adapted to the training intensity, and the tolerance for abnormal parameters is low. A value of 0.2 was used to reduce the impact of objective parameter bias on the treatment results and avoid over-intervention; by the middle of the training period, the patient had adapted to the basic training rhythm. A value of 0.5 was used to balance the influence of objective parameters and subjective feelings; in the later stages of training, the patient's rehabilitation effect became apparent, and tolerance improved. Setting it to 1.0 strengthens the influence of objective parameter bias, ensuring a balance between training effectiveness and safety. Adjustments can be made based on the patient's historical feedback. For example, if the patient reports discomfort multiple times but the parameter deviation is small, the parameter can be appropriately increased. This enhances the sensitivity of parameter monitoring. The application of the formula needs to be combined with the specific type of physiological parameter. Taking heart rate monitoring as an example, a patient in the early stages of training... Actual heart rate Frequency / minute, preset normal value Frequency / minute, patient's subjective feeling For mild discomfort, substitute the formula for calculation: , A positive value corresponds to suspending training; if the patient is in the middle of training... With other parameters remaining unchanged, the calculation yields If the value exceeds the upper limit of 10, it will be treated as 10, still triggering a training pause; if the patient is in the early stages of training, times / minute Calculated The system maintains the current status quo while closely monitoring parameter changes. Regarding the blood oxygen saturation parameter, a patient in the later stages of training... Actual blood oxygen saturation Default normal value Subjective feelings Clearly uncomfortable, substitute into the formula: If the value exceeds the lower limit of -10, it will be treated as -10, corresponding to a significant reduction in training intensity. (Anomaly handling results) The range of values ​​is divided into different intervals, each with a specific processing strategy: When the value is less than -5, significantly reduce the training intensity by 50% of the current intensity; -5≤ When the value is less than 0, slightly reduce the training intensity by 20% of the current intensity; At this time, maintain the current training intensity and continue monitoring; 0 < If the value is ≤5, pause training for 1 minute and provide breathing adjustment guidance; If an anomaly occurs, training is immediately paused, and a voice alarm is issued to alert medical personnel for intervention. The parameter anomaly handling unit calculates the processing result in real time using this formula, dynamically triggering corresponding measures. Simultaneously, the processing result and parameter data are synchronized to the feedback adjustment module, providing a basis for subsequent optimization of the training plan. This ensures the accuracy and flexibility of anomaly handling, maximizing the continuity of training while guaranteeing training safety.

[0098] The technical effects achieved by the above embodiments include: dynamically adjusting the abnormal handling strategy by combining objective physiological parameters and subjective feelings, improving the pertinence and rationality of the handling measures, ensuring training safety, and maintaining training continuity.

[0099] Traditional technical solutions suffer from the following problems: the analysis of monitoring results by existing feedback adjustment modules is superficial, the adjustment of training programs lacks data support, safety assessments are not conducted, and the dynamic adjustment coefficients are set subjectively, resulting in inaccurate optimization of training programs and an inability to adapt to the real-time rehabilitation status of patients.

[0100] Based on this, the feedback adjustment module includes a monitoring result analysis unit for analyzing monitoring results; a training scheme adjustment unit for adjusting the training scheme in real time based on the analysis results; a security assessment unit for assessing the security of training; and a dynamic adjustment coefficient calculation unit for making dynamic adjustments based on the adjustment formula.

[0101] This solution achieves precise optimization of the training program through multi-unit collaborative analysis and adjustment, ensuring the safety and adaptability of the training.

[0102] The monitoring results analysis unit receives data output from the real-time monitoring module, including physiological parameters such as heart rate and blood oxygen saturation, results of non-standard application of detection, and results of parameter anomaly handling. It analyzes the correlations between data points using data mining algorithms such as association rule algorithms, for example, analyzing the correlation between training intensity and increased heart rate, and the correlation between non-standard breathing movements and decreased blood oxygen saturation. Simultaneously, it combines the training effect evaluation results from the virtual reality training module. Values, addressing the adaptation issues of the training scheme, such as Low values ​​and poor respiratory depth attainment rates indicate that the training intensity is set too high or the breathing method guidance is insufficient. During the analysis, a detailed data analysis report is generated, including parameter change trend charts, anomaly statistics, and performance indicator breakdowns, providing data support for training program adjustments and safety assessments. Analysis results are pushed to other units in real time. The training program adjustment unit dynamically adjusts training program parameters based on the monitoring results analysis unit's report, targeting different problem types. If the analysis determines that the training intensity is too high, such as a persistently high heart rate or subjective discomfort, the intensity value of the training intensity calculation unit is reduced. If the value is lowered by 1 to 2 levels, or the rest interval is extended (e.g., from 5 minutes to 7 minutes), adjust accordingly. If the problem is poor adaptability of the breathing method (e.g., low rhythm stability during pursed-lip breathing training), adjust the guidance method of the training scenario (e.g., increase the frequency of voice rhythm prompts) and optimize breathing rhythm parameters (e.g., adjust the inhalation-exhalation ratio). If the problem is poor training effect, etc. If the score is below 60, the breathing training method selection module will switch to a more suitable training method, such as switching from pursed-lip breathing to diaphragmatic breathing. The adjusted training plan is synchronized to the virtual reality training module in real time through the system interface to ensure real-time adaptation of the training. An adjustment log is also recorded for subsequent tracking and optimization. The safety assessment unit evaluates the safety of the training process using quantitative indicators. Core assessment indicators include the incidence rate of abnormal physiological parameters, the ratio of the number of abnormal parameters to the total number of monitoring sessions, the frequency of non-standard applications, the number of non-standard operations per unit time, and the patient discomfort feedback rate (frequency of discomfort scores). Safety thresholds are set: abnormal incidence rate <5%, non-standard frequency <2 times / minute, and discomfort feedback rate <10%. If the assessment indicators do not exceed the thresholds, the training is considered safe, and the adjusted training plan can continue. If the thresholds are exceeded, it is considered high-risk, and a training pause command is immediately triggered, generating a safety risk report to prompt medical staff to investigate the cause, such as changes in the patient's physical condition or equipment malfunction. The safety assessment unit completes a comprehensive assessment every 5 minutes, providing real-time feedback on the assessment results to ensure the safety of the training plan's execution. The dynamic adjustment coefficient calculation unit calculates the dynamic adjustment coefficients used to optimize the training scheme using an adjustment formula, as shown in the formula. This unit receives data analysis reports from the monitoring results analysis unit and assessment results from the safety assessment unit, and combines them with the patient's rehabilitation stage and historical training data. It then precisely calculates coefficient values ​​using adjusted formulas, such as dynamically adjusting them based on training stage and patient feedback. The value is used to ensure that the coefficient value is adapted to the patient's real-time status; the calculated dynamic adjustment coefficient is synchronized to the parameter anomaly handling unit and the training intensity calculation unit, providing a dynamic basis for anomaly handling and training intensity setting, and realizing closed-loop optimization of the entire training system.

[0103] The technical effects achieved by the above embodiments include: accurately adjusting the training program by analyzing monitoring results from multiple dimensions, ensuring training safety by combining safety assessments, dynamically adjusting coefficients to improve program adaptability, and promoting efficient patient recovery.

[0104] Traditional technical solutions have the following technical problems: existing training time adjustments are based on fixed duration settings and do not dynamically optimize in combination with the patient's physiological stress level. This results in training time that is too long causing patient fatigue and discomfort, while training time that is too short cannot achieve the desired rehabilitation effect, and cannot achieve precise matching between training time and the patient's physical condition.

[0105] Based on this, the adjustment formula of the dynamic adjustment coefficient calculation unit is as follows: ,in, The training time is expressed in minutes, ranging from 5 to 30 minutes. The patient's physiological stress level is dimensionless, ranging from 0 to 2, where 0 corresponds to no stress and 2 corresponds to extremely high stress. It is calculated using deviations in heart rate and blood oxygen saturation.

[0106] ;

[0107] It is a constant, typically taking the value 2.71828. The baseline time factor is in minutes and is set according to the patient's underlying disease status. (No underlying disease is considered.) Having underlying medical conditions This program uses a dynamic formula combined with physiological stress levels to achieve personalized and precise setting of training time, adapting to the patient's real-time physical condition.

[0108] Adjusting the formula The design is based on the human physiological stress response mechanism. The higher the level of physiological stress, the lower the patient's tolerance to training, and the shorter the required training time should be accordingly. This is achieved through an exponential function. Achieving a dynamic relationship where training time decreases as physiological stress levels rise ensures that adjustments to training time align with human physiological patterns.

[0109] The dimensions and meanings of each parameter in the formula are clearly defined. The adjusted actual training time is in minutes, with a range of 5 to 30 minutes to avoid training time being too short or too long, ensuring the effectiveness and safety of the training. The patient's physiological stress level is dimensionless and is calculated by converting the deviation between heart rate and blood oxygen saturation. The conversion formula is... middle, The measured heart rate is in beats per minute. The normal heart rate is 80 beats per minute. The measured blood oxygen saturation is expressed as a percentage. For example, a patient's measured heart rate is 98%, which is considered normal for blood oxygen saturation. Breaths / min, measured blood oxygen saturation Substituting into the conversion formula, we get That is, physiological stress level ; This is a natural constant, fixed at 2.71828, to ensure consistency in formula calculations; This is the baseline time factor, expressed in minutes, set according to the patient's underlying medical condition. Patients without underlying conditions tend to have higher tolerance. Minutes, patients with underlying medical conditions have lower tolerance. Minutes are allocated to ensure initial adaptation to the baseline time. The formula is derived based on clinical respiratory rehabilitation training data. By analyzing patients' tolerance time under different physiological stress levels, an exponential relationship model between physiological stress level and training time is established. Extensive clinical trials have validated this model, which accurately reflects the patient's physiological stress state and its demand for training time. For example, when... Without physiological stress, That is, the training time is the baseline time, which meets the training needs when the patient is in good physical condition; when During moderate physiological stress, Training time was reduced to 60.65% of the baseline time, suitable for patients with mild fatigue; when Under high physiological stress, Training time is further shortened to avoid excessive patient fatigue. The application of the formula needs to be combined with the patient's underlying medical condition and real-time physiological parameters. Taking a patient without underlying medical conditions as an example... Minutes, if the patient's measured heart rate pulses / minute, blood oxygen saturation ,but Substituting into the formula, we get Minutes, rounded to 26 minutes, are used by the system to set the training time; if the patient's heart rate rises to [a certain value] during training... bpm, blood oxygen saturation dropped to ,but Calculated The training time is adjusted automatically, rounded down to 15 minutes, to prevent discomfort caused by increased physiological stress. For patients with underlying medical conditions... Minutes, if the patient times / minute ,but Calculated Minutes, rounded to 13 minutes, are adjusted to suit the tolerance of patients with underlying diseases; if the patient's physiological stress level drops to... ,but The time is rounded down to 16 minutes, and the training time can be appropriately extended to improve rehabilitation effects. The training time calculated by the adjustment formula should be limited to the range of 5 to 30 minutes. If the calculated result is less than 5 minutes, set it to 5 minutes to ensure the basic training duration; if it is greater than 30 minutes, set it to 30 minutes to avoid overtraining. The dynamic adjustment coefficient calculation unit will calculate the... Synchronize with the training program adjustment unit and virtual reality training module to update training duration settings in real time, while recording training time adjustment logs and combining them with patient training effect evaluation results. Value Continuous Optimization If the training effect is good, the value can be appropriately increased. This value enables closed-loop dynamic optimization of training time, ensuring that the training time is always adapted to the patient's physiological stress level and rehabilitation status.

[0110] The technical effects achieved by the above embodiments include: accurately setting training time by combining dynamic formulas with physiological stress levels, avoiding the drawbacks of fixed duration, adapting to the patient's real-time physical condition, improving the effectiveness and safety of training, and reducing fatigue and discomfort.

[0111] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A respiratory rehabilitation training system incorporating virtual reality technology, characterized in that: include, The patient information collection module is used to collect patients' basic information and medical history; The underlying disease confirmation module is used to confirm whether a patient has an underlying disease and select different training steps based on the results; The breathing training method selection module is used to select a suitable breathing training method based on the patient's specific condition. The virtual reality training module is used to provide an immersive training environment and simulate different training scenarios through virtual reality technology; A real-time monitoring module is used to monitor and track the patient's physiological parameters during training. The feedback adjustment module is used to adjust the training plan in real time based on the monitoring results.

2. The respiratory rehabilitation training system combining virtual reality technology as described in claim 1, characterized in that: The patient information collection module includes, The identity information input unit is used to input the patient's basic information; The medical history input unit is used to input the patient's medical history.

3. The respiratory rehabilitation training system combining virtual reality technology as described in claim 1 or 2, characterized in that: The underlying disease confirmation module includes, The underlying disease detection unit is used to detect whether a patient has any underlying diseases. The training step selection unit is used to select different training steps based on the test results of the underlying disease. If the test results indicate that there is an underlying disease, the breathing training steps that include adjustments are selected; if the test results indicate that there is no underlying disease, the standard breathing training steps are selected.

4. The respiratory rehabilitation training system combining virtual reality technology as described in claim 1, characterized in that: The breathing training method selection module includes, Abdominal breathing selection unit, used to select abdominal breathing training methods; The pursed-lip breathing selection unit is used to select pursed-lip breathing training methods; The respiratory muscle resistance training selection unit is used to select respiratory muscle resistance training methods. as well as Training intensity calculation unit, the calculation formula is as follows Where I represents training intensity, P represents the patient's lung function parameters, V represents the patient's respiratory volume, T represents training time, E represents the patient's endurance level, and the weighting coefficients are 0.4, 0.3, 0.2, and 0.1, respectively.

5. The respiratory rehabilitation training system combining virtual reality technology as described in claim 1, characterized in that: The virtual reality training module includes, Virtual reality environment generation unit, used to generate immersive training environments; Training scenario simulation unit, used to simulate different training scenarios; Interactive training units are designed to provide an interactive training experience. Training effectiveness evaluation unit, evaluation formula is: Among them, E f Indicates the training effect, e i Let w represent the i-th training performance metric. i Let be the weight of the i-th training result.

6. The respiratory rehabilitation training system combining virtual reality technology as described in claim 1 or 5, characterized in that: The real-time monitoring module includes, Physiological parameter monitoring unit, used to monitor the patient's physiological parameters; The data monitoring unit is used to process the monitoring results into data. The non-standard application detection unit is used to detect non-standard applications during the training process; The parameter anomaly handling unit is used to handle parameter anomalies according to the processing formula.

7. The respiratory rehabilitation training system combining virtual reality technology as described in claim 6, characterized in that: The processing formula is as follows: Where A represents the abnormal handling result, M represents the monitored physiological parameter, N represents the preset normal value, S represents the patient's subjective feeling, and represents the dynamic adjustment coefficient, which is dynamically adjusted according to the training stage and patient feedback.

8. The respiratory rehabilitation training system combining virtual reality technology as described in claim 7, characterized in that: The feedback adjustment module includes, The monitoring results analysis unit is used to analyze monitoring results. The training program adjustment unit is used to adjust the training program in real time based on the analysis results. A security assessment unit is used to assess the security of training. The dynamic adjustment coefficient calculation unit is used to make dynamic adjustments according to the adjustment formula.

9. The respiratory rehabilitation training system combining virtual reality technology as described in claim 8, characterized in that: The adjustment formula is: Where T represents training time, P represents the patient's physiological stress level, and e is a constant, usually taken as 2.71828.

Images