Personalized intelligent rehabilitation training system for critical respiratory disease patient in rehabilitation period

Abstract

The invention relates to the technical field of personal health risk assessment, and provides a respiratory critically ill patient rehabilitation period personalized intelligent rehabilitation training system, which comprises a training stability acquisition module, an abnormal degree acquisition module, a training effect acquisition module and a screening module, based on the actual training intensity of each training item in each rehabilitation training process in the historical time period, the training stability of each training item is obtained, and the abnormal degree of each rehabilitation training process is obtained according to the difference between the standard training item sequence and the actual training item sequence of each rehabilitation training process. The actual training effect of each rehabilitation training process is obtained by combining the comprehensive training stability of each rehabilitation training process, so that the optimal rehabilitation training process is determined from each rehabilitation training process, and the arrangement of each training item in the optimal rehabilitation training process is most reasonable; next rehabilitation training is carried out according to the optimal rehabilitation training process, and the rehabilitation effect of the patient can be remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of personal health risk assessment technology, specifically to a personalized intelligent rehabilitation training system for critically ill respiratory patients during their recovery period. Background Technology

[0002] Patients with respiratory critical illness are those whose respiratory function is severely impaired due to various reasons, leading to respiratory failure and other life-threatening conditions. During their illness, these patients often experience disuse atrophy of their respiratory muscles due to prolonged bed rest and mechanical ventilation. Rehabilitation training can specifically strengthen respiratory muscles, improve respiratory efficiency, and enhance lung ventilation, enabling patients to exchange gases more effectively and reducing symptoms of dyspnea.

[0003] Traditional rehabilitation training systems typically involve multiple training sessions, each with the same training items, such as training item A, B, C, and D. However, these systems often follow a fixed sequence, neglecting the patient's real-time physical changes. As patients recover and become more proficient with the training items, the actual intensity of the training changes. Continuing with a fixed order ignores the patient's actual recovery level, leading to inappropriate training intensity and negatively impacting rehabilitation outcomes. Summary of the Invention

[0004] To address the technical problem of poor rehabilitation outcomes in existing rehabilitation training systems, the present invention aims to provide a personalized intelligent rehabilitation training system for critically ill respiratory patients during their recovery period. The specific technical solution adopted is as follows: This invention provides a personalized intelligent rehabilitation training system for critically ill respiratory patients during their recovery period, comprising: The training stability acquisition module is used to obtain the training stability of each training item based on the actual training intensity of each training item in each rehabilitation training process during the historical time period of the respiratory critically ill patient. The abnormality level acquisition module is used to obtain the abnormality level of each rehabilitation training process based on the difference between the standard training program sequence and the actual training program sequence of each rehabilitation training process; the standard training program sequence is obtained from the actual comprehensive training intensity of each training program, and the actual comprehensive training intensity is obtained from the actual training intensity of the same training program for all rehabilitation training processes. The training effect acquisition module is used to obtain the actual training effect of each rehabilitation training process based on the degree of abnormality and the overall training stability of each rehabilitation training process; the overall training stability is obtained by the training stability of all training items in the same rehabilitation training process. The screening module is used to determine the optimal rehabilitation training process from each rehabilitation training session based on the actual training effect.

[0005] In an exemplary embodiment, before the anomaly degree acquisition module, the system further includes a training stability correction module, which is used to: The importance weight of each reference training item is obtained based on the time interval between each reference training item and the target training item; the importance weight is inversely proportional to the time interval; the target training item is any training item, and each reference training item is a training item that is in the same rehabilitation training process as the target training item and precedes the target training item. Based on the importance weight of each reference training item, the actual training intensity of each reference training item is weighted and summed to obtain the reference training intensity corresponding to the target training item. Based on the reference training intensity, the correction coefficient for the target training item is obtained; The training stability of the target training item is corrected based on the correction coefficient.

[0006] In an exemplary embodiment, obtaining the correction coefficient for the target training item based on the reference training intensity includes: If the target training item is the first training item in the rehabilitation training process, then the correction coefficient of the target training item is set to the value 1; If the target training item is not the first training item in the rehabilitation training process, then the correction coefficient of the target training item is the result of negative correlation normalization with the degree of target interference; the degree of target interference is obtained from the reference training intensity.

[0007] In an exemplary embodiment, the process of obtaining the standard training item order includes: arranging the actual comprehensive training intensity of each training item in ascending order to obtain the standard training item order.

[0008] In an exemplary embodiment, the process of obtaining the degree of abnormality includes: Obtain the number of inversions in the actual training item sequence of each rehabilitation training session relative to the standard training item sequence; The degree of abnormality in each rehabilitation training process is obtained based on the number of inversions in each rehabilitation training process, and the degree of abnormality is proportional to the number of inversions.

[0009] In one exemplary embodiment, the overall training stability is the average of the training stability of all training items in the same rehabilitation training process; The process of obtaining the actual training effect includes: By negatively correlating the degree of abnormality in each rehabilitation training session, the training effect factor of each rehabilitation training session can be obtained. Based on the training effect factors and the overall training stability of each rehabilitation training session, the actual training effect of each rehabilitation training session is obtained.

[0010] In an exemplary embodiment, determining the optimal rehabilitation training process from each rehabilitation training process includes: taking the rehabilitation training process corresponding to the maximum actual training effect among the actual training effects of each rehabilitation training process as the optimal rehabilitation training process.

[0011] In an exemplary embodiment, the process of obtaining the actual training intensity includes: The high-intensity training sustainability factor of the training program is obtained based on the duration of respiratory rate increase within the corresponding duration of the training program and the overall rate of increase of respiratory rate in the training program. Obtain the peak respiratory rate period within the corresponding duration of the training project; the peak respiratory rate period consists of multiple consecutive peak respiratory rate moments; the peak respiratory rate moment is the moment when the respiratory rate is greater than a preset respiratory rate threshold. The continuity of peak periods in the training program is obtained by considering the duration of peak respiratory rate periods and the time interval between adjacent peak respiratory rate periods. Based on the continuity of the peak period and the overall level of the breathing rate of the training program, the maximum training intensity of the training program is obtained. By combining the high-intensity training persistence factor and the maximum training intensity, the actual training intensity of the training item is obtained.

[0012] In an exemplary embodiment, the process of obtaining the overall growth rate of respiratory rate includes: obtaining the slope of change between the first respiratory rate and the maximum respiratory rate within the corresponding duration of the training item, as the overall growth rate of respiratory rate.

[0013] In one exemplary embodiment, the training stability is obtained by fusing the actual training intensity and training recovery capability of the training item; The process of acquiring the training recovery capability includes: Obtain the recovery time for respiratory rate to return to baseline at the end of the training program; The degree of fluctuation between the time intervals between any two adjacent respiratory rate increase moments in the training project is obtained; all the respiratory rate increase moments in the training project constitute the respiratory rate increase duration. The training recovery capability is obtained based on the recovery time and the degree of fluctuation.

[0014] This invention has the following beneficial effects: Since the order of training items in different rehabilitation training sessions for critically ill respiratory patients may vary, the degree of abnormality in each rehabilitation training session can be used to represent the abnormality in the order of training items. Then, by combining the overall training stability of each rehabilitation training session, the actual training effect of each session can be obtained. The actual training effect characterizes the actual recovery level of the critically ill respiratory patient in each rehabilitation training session. The better the actual training effect, the more the order of training items in the corresponding rehabilitation training session meets the requirements of rehabilitation training for critically ill respiratory patients. Therefore, by determining the optimal rehabilitation training process from each session based on the actual training effect, the arrangement of training items in the optimal rehabilitation training process is the most reasonable. Arranging the next rehabilitation training session for critically ill respiratory patients according to the optimal rehabilitation training process can significantly improve the rehabilitation effect of critically ill respiratory patients. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the structure of a personalized intelligent rehabilitation training system for critically ill respiratory patients during their recovery period, provided in one embodiment of the present invention. Figure 2 This is a flowchart of the steps corresponding to each module of a personalized intelligent rehabilitation training system for critically ill respiratory patients during their recovery period, provided in one embodiment of the present invention. Figure 3 This is a flowchart of the process for obtaining actual training intensity according to an embodiment of the present invention; Figure 4 This is a flowchart illustrating the acquisition of training recovery capability according to an embodiment of the present invention; Figure 5 This is a flowchart illustrating the specific implementation of the training stability correction module provided in one embodiment of the present invention; Figure 6 This is a flowchart of the process for obtaining the degree of abnormality provided in one embodiment of the present invention; Figure 7 This is a flowchart illustrating the acquisition of actual training results according to an embodiment of the present invention. Detailed Implementation

[0016] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the specific implementation methods, structures, features, and effects of the present invention are described in detail below with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0017] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. All data and information collected in this application have been obtained with full consent.

[0018] This embodiment provides a personalized intelligent rehabilitation training system for critically ill respiratory patients during their recovery period. The applicable scenario is as follows: the rehabilitation training cycle for critically ill respiratory patients (hereinafter referred to as "patients") may last for a long time, such as 3-6 months, requiring multiple rehabilitation training sessions. The training items are the same in each rehabilitation training session, for example, training item A, training item B, training item C, and training item D in each session. The difference lies in the order of the training items in different sessions. The number and specific items of the training items are set by the doctor according to the patient's actual physical condition, such as deep breathing training, respiratory rhythm training, vital capacity training, respiratory flow training, and physical recovery training. The duration of each training item is also set by the doctor according to the patient's actual physical condition. The order of the training items in each rehabilitation training session is also set by the doctor according to the patient's actual physical condition. Furthermore, there is a certain time interval between each training item; that is, after completing one training item, the patient needs to rest for a certain period of time to recover their strength before proceeding to the next training item. During each rehabilitation training session, the time interval between two adjacent training programs is set by the doctor based on the patient's actual physical condition.

[0019] The frequency of rehabilitation training is set by the doctor based on the patient's actual physical condition. For example, once a day, then one rehabilitation training session is conducted daily. This embodiment pre-defines a historical time period, the length of which is set by the doctor based on the patient's actual physical condition. The length of the historical time period determines the number of rehabilitation training sessions used for data processing; the longer the historical time period, the more rehabilitation training sessions are conducted. In an exemplary embodiment, the historical time period is the most recent week, which includes 7 days, or 7 rehabilitation training sessions. The purpose of this invention is to determine the optimal rehabilitation training process based on the actual training effects of each rehabilitation training session within the patient's historical time period, and to dynamically adjust the order of rehabilitation training items for the patient according to the order of each training item in the optimal rehabilitation training process.

[0020] like Figure 1 As shown, this embodiment provides a personalized intelligent rehabilitation training system for critically ill respiratory patients during their recovery period, comprising: a training stability acquisition module, an abnormality degree acquisition module, a training effect acquisition module, and a screening module. Each module can be a software module, essentially a corresponding method step; or it can be a hardware module, with the executed method steps configured within the hardware module to enable the hardware module to perform the corresponding function. Accordingly, the personalized intelligent rehabilitation training system for critically ill respiratory patients during their recovery period can be a software system, configured in a relevant processor, computer host, and related medical platform; or it can be a hardware system, such as a server or computer host. This embodiment does not limit the specific configuration of each module or the personalized intelligent rehabilitation training system for critically ill respiratory patients during their recovery period.

[0021] like Figure 2 As shown, the method steps corresponding to each module in the personalized intelligent rehabilitation training system for critically ill respiratory patients during the recovery period are as follows: The training stability acquisition module is used to obtain the training stability of each training item based on the actual training intensity of each training item during each rehabilitation training session in the historical time period of critically ill respiratory patients. The abnormality level acquisition module is used to obtain the abnormality level of each rehabilitation training process based on the difference between the order of standard training items and the actual order of training items in each rehabilitation training process. The training effect acquisition module is used to obtain the actual training effect of each rehabilitation training process based on the degree of abnormality and the overall training stability of each rehabilitation training process. The screening module is used to determine the optimal rehabilitation training process from each rehabilitation training session based on the actual training results.

[0022] The specific implementation process of each module is described below with reference to the accompanying drawings.

[0023] The training stability acquisition module is used to obtain the training stability of each training item based on the actual training intensity of each training item during each rehabilitation training session in the historical time period of patients with respiratory critical illness.

[0024] Acquire daily respiratory rate data of the patient within a historical time period. In an exemplary embodiment, a wearable device can be worn by the patient to monitor their respiratory rate. The wearable device can be a chest strap / waist strap respiratory monitor, which works by detecting the expansion and contraction of the chest / abdomen using impedance methods or stretch sensors. The patient should wear the wearable device, ensuring good contact between the device and the patient's body and that the sensors are functioning properly. The respiratory rate detection frequency is set according to actual needs; this embodiment uses a detection frequency of once every 2 seconds as an example.

[0025] Simultaneously, the system records the start and end times of each training session within a historical timeframe, thereby obtaining respiratory rate data for the corresponding duration of each training session. The start and end times of each training session can be manually recorded by the doctor while supervising the patient's execution; alternatively, the patient can manually record the start and end times of each training session; or, in scenarios where different training sessions require different movements or postures, the patient can wear an accelerometer and gyroscope to monitor their movement status in real time. By sensing changes in the patient's movement or posture, the system determines whether the patient is performing a training session. For example, some training sessions may be identified through specific angle changes (such as extension or bending) or movement speed. A timing function is triggered when a change in the patient's movement or posture is detected; the timer ends when the patient stops moving or enters a resting state, thus obtaining the start and end times of each training session. It should be understood that although automatic recording can be achieved through accelerometers and gyroscopes, there are certain drawbacks, and the accuracy of detection is affected by the actual situation of each training project.

[0026] Based on the above method, respiratory rate data for each training item during each rehabilitation training session in the historical time period are obtained. Since the duration of each training item includes multiple sampling moments (hereinafter referred to as moments), the respiratory rate of each training item includes multiple moments, thus forming the respiratory rate time sequence of the training item, thereby obtaining the respiratory rate time sequence of each training item during each rehabilitation training session in the historical time period.

[0027] It should be understood that, for ease of subsequent processing, the respiratory frequencies of each training item in each rehabilitation training session within the historical time period are normalized. This normalization can be achieved by obtaining the maximum and minimum respiratory frequencies among all training items in all rehabilitation training sessions within the historical time period, and then using a maximum-minimum value normalization method to normalize the respiratory frequencies of each training item in each rehabilitation training session within the historical time period. All respiratory frequencies mentioned below are normalized respiratory frequencies, and the respiratory frequency time series are normalized respiratory frequency time series.

[0028] When the human body exercises, especially during aerobic exercise or strength training, the muscles' demand for oxygen increases. The body automatically increases its respiratory rate to meet this demand. Respiratory rate, as a direct reflection of the body's metabolic needs, is usually proportional to training intensity. Higher training intensity typically leads to a faster respiratory rate because the body requires more oxygen to support higher energy expenditure. Correspondingly, a patient's respiratory rate will also change during a training program. Accordingly, the actual training intensity of the training program is obtained based on the patient's respiratory rate during the program. In an exemplary embodiment, such as... Figure 3 As shown, the following is a specific acquisition process: Step 1-1: Based on the duration of respiratory rate increase within the corresponding training period and the overall rate of increase of respiratory rate within the training period, obtain the high-intensity training sustainability factor of the training program.

[0029] For ease of explanation, any training item in any rehabilitation training session is defined as the target training item. The respiratory rate increase duration of the respiratory rate time sequence of the target training item is obtained. Specifically, the difference between the second and first respiratory rates (i.e., the respiratory rates at two adjacent moments) within the respiratory rate increase duration is calculated. Taking the (k+1)th and kth respiratory rates as an example, the difference between the (k+1)th and kth respiratory rates is calculated and denoted as the increase rate of the kth respiratory rate. ,like If the value is greater than 0, then the moment of the k-th breathing frequency is recorded as the breathing frequency increase moment. This allows us to obtain the breathing frequency increase moments in the target training program, as well as the number of these moments. All the breathing frequency increase moments in the target training program constitute the breathing frequency increase duration; therefore, the breathing frequency increase duration is essentially the number of breathing frequency increase moments.

[0030] Obtain the total number of moments within the target training program's corresponding duration, which is taken as the training duration of the target training program. Calculate the ratio of the number of moments with increased respiratory rate within the target training program to the total number of moments, which is taken as the high-intensity training duration parameter for the patient during the target training program. The larger the high-intensity training duration parameter, the longer the duration of increased respiratory rate in the target training program, representing a longer period of high-intensity exercise.

[0031] During rehabilitation training, the patient's respiratory rate should increase slowly. A rapid increase indicates the patient's inability to adapt quickly, potentially leading to unsatisfactory training results. Therefore, the overall respiratory rate increase rate of the target training program is obtained. This overall respiratory rate increase rate characterizes the overall rate of increase in respiratory rate over the duration of the target training program. In an exemplary embodiment, the first respiratory rate and the maximum respiratory rate (if multiple maximum respiratory rates exist, the first maximum respiratory rate is obtained) are obtained from the time-series sequence of the respiratory rates of the target training program. The slope between the first and maximum respiratory rates is obtained, i.e., the difference between the maximum and first respiratory rates, and the time interval between them. The ratio of the respiratory rate difference to the time interval is used as the slope between the first and maximum respiratory rates, and this slope is taken as the overall respiratory rate increase rate. Then, the overall respiratory rate increase rate is normalized for subsequent calculations. The normalization method here can be: ,in, Represents a normalized object. This represents an exponential function with the natural constant e as its base.

[0032] The high-intensity training sustainability factor of the target training project is obtained based on the high-intensity training sustainability parameter of the target training project and the normalized overall growth rate of the respiratory rate of the target training project. In an exemplary embodiment, the product of the high-intensity training sustainability parameter of the target training project and the normalized overall growth rate of the respiratory rate of the target training project is calculated, and the result is the high-intensity training sustainability factor of the target training project.

[0033] At the start of training, the respiratory rate may be low. As the intensity of exercise increases, the respiratory rate will gradually rise and reach a peak. This peak respiratory rate reflects the intensity requirements of the patient's target training program. Generally, a higher respiratory rate indicates a greater exercise intensity. When the respiratory rate reaches its peak, it usually means that the exercise intensity has approached or reached its maximum level. At this point, the body's respiratory system is providing more oxygen to support high-intensity exercise.

[0034] Step 1-2: Obtain the peak respiratory rate period within the corresponding duration of the training program.

[0035] A preset respiratory rate threshold is established. This threshold is used to compare with each respiratory rate in the respiratory rate time series of the target training item to determine whether each respiratory rate is too high. The preset respiratory rate threshold ranges from 0 to 1, and its specific value is set according to the actual judgment needs. In this embodiment, 0.8 is used as an example. The times corresponding to the respiratory rates in the respiratory rate time series of the target training item that are higher than the preset respiratory rate threshold are obtained. The times corresponding to the respiratory rates that are higher than the preset respiratory rate threshold are defined as the respiratory rate peak times, thereby obtaining multiple respiratory rate peak times.

[0036] Then, multiple consecutive respiratory rate peaks are combined into a respiratory rate peak period, thus obtaining several respiratory rate peak periods in the respiratory rate time series of the target training item. It should be understood that isolated respiratory rate peaks, i.e., those without any other adjacent respiratory rate peaks, are considered noise data and are not treated as separate respiratory rate peak periods.

[0037] The true peak respiratory rate period typically refers to a stable phase with a high respiratory rate (i.e., high exercise intensity). Sudden fluctuations in respiratory rate increase may indicate a sudden condition and do not reflect sustained high-intensity exercise. The longer the peak respiratory rate period lasts, the longer the exercise intensity is maintained at a high level, the greater the workload, and the higher the corresponding training intensity for the patient during the target training program.

[0038] Steps 1-3: Based on the duration of the peak respiratory rate period of the training program and the time interval between adjacent peak respiratory rate periods, the continuity of the peak period of the training program is obtained.

[0039] The longer the peak respiratory rate period of the target training program, the shorter the time interval between two adjacent peak respiratory rate periods, and the stronger the continuity of the peak periods of the target training program.

[0040] Obtain the total duration of peak respiratory rate periods in the target training item. If multiple peak respiratory rate periods exist, the sum of their durations is taken as the total duration of the peak respiratory rate periods. Calculate the ratio of the total duration of the peak respiratory rate periods in the target training item to the total duration of the target training item; this ratio is defined as the duration characteristic of the peak respiratory rate periods in the target training item. The larger the duration characteristic, the longer the total duration of the peak respiratory rate periods in the target training item, and the stronger the continuity of the peak respiratory rate periods.

[0041] The time interval characteristics of the peak respiratory rate periods in the target training item are determined. If the target training item has only one peak respiratory rate period, then there are no two adjacent peak respiratory rate periods, and the time interval characteristic of the peak respiratory rate period is set to 0. If the target training item has at least two peak respiratory rate periods, the time interval between each two adjacent peak respiratory rate periods is obtained, and then the average of the time intervals is calculated as the time interval characteristic of the peak respiratory rate periods. The smaller the time interval characteristic, that is, the shorter the time interval between adjacent peak respiratory rate periods in the target training item, the stronger the continuity of the peak periods in the target training item. Therefore, the time interval characteristic is negatively correlated and normalized. Unless otherwise specified, the negative correlation normalization method in this embodiment is as follows: ,in, The objects are those that are negatively correlated and normalized.

[0042] The product of the duration of the peak respiratory rate period in the target training exercise and the negatively correlated normalized time interval is calculated. This product represents the peak period continuity of the target training exercise. The stronger the peak period continuity, the greater the training intensity of the target training exercise.

[0043] Steps 1-4: Based on the continuity of peak periods and the overall level of breathing frequency in the training program, determine the maximum training intensity of the training program.

[0044] To obtain the overall respiratory rate level of the target training item, in one exemplary embodiment, the average respiratory rate in the time series of the target training item's respiratory rate is obtained as the overall respiratory rate level of the target training item. The higher the overall respiratory rate level of the target training item, the greater the training intensity of the target training item.

[0045] Therefore, the continuity of peak periods and the overall respiratory rate level of the target training program are closely related to its maximum training intensity. The maximum training intensity of the target training program is characterized by a combination of these two aspects. As a specific quantification method, the product of the continuity of peak periods and the overall respiratory rate level of the target training program is calculated, and the resulting product is taken as the maximum training intensity of the target training program.

[0046] Steps 1-5: Combine the high-intensity training persistence factor and the maximum training intensity to obtain the actual training intensity of the training program.

[0047] Step 1-1 yields the high-intensity training persistence factor for the target training item, and step 1-4 yields the maximum training intensity of the target training item. The high-intensity training persistence factor is used as the coefficient of the maximum training intensity of the target training item; that is, the product of the high-intensity training persistence factor and the maximum training intensity of the target training item is calculated, and the result is the actual training intensity of the target training item.

[0048] Using the above process, the actual training intensity of each training item in each rehabilitation training session within the historical time period is obtained. To further improve the reliability of subsequent data processing, the actual training intensity of each training item in each rehabilitation training session within the historical time period can be normalized using a maximum-minimum value normalization method. Specifically: obtain the maximum and minimum values ​​of the actual training intensity of each training item in each rehabilitation training session within the historical time period, and then normalize the actual training intensity of each training item in each rehabilitation training session within the historical time period based on the maximum and minimum values. The actual training intensity mentioned later will be the normalized result.

[0049] The above analysis examined the actual training intensity of each training program. For patients, their bodies have a relatively low capacity to handle exercise loads. Even with appropriate training intensity, patients may experience fluctuations in physical strength, respiration, or other physiological aspects during training, indicating poor stability during the program. Lower stability indicates poorer training effectiveness and a greater likelihood of reduced rehabilitation outcomes. Accordingly, the training recovery ability of the target training program is obtained. Training recovery ability represents the patient's ability to recover to a normal state after the training program concludes. In an exemplary embodiment, such as... Figure 4 As shown, the following is a specific process for acquiring training recovery capability: Steps 1-6: Obtain the recovery time for the respiratory rate to return to the baseline level at the end of the training program; Steps 1-7: Obtain the degree of fluctuation in the time interval between each two adjacent moments of respiratory rate increase in the training project; Steps 1-8: Obtain training recovery ability based on recovery time and fluctuation level.

[0050] For the target training program, a baseline respiratory rate is preset. The baseline represents the respiratory rate of a human body in a normal state, i.e., a non-exercise state. The baseline can be set manually; in this embodiment, 0.4 is used as an example. Alternatively, since different people have different physical conditions, such as different physical fitness, their baseline respiratory rate will not be exactly the same. In this case, the respiratory rates of several people in a normal state (also normalized respiratory rates) can be obtained in advance, and then the maximum value can be determined as the baseline.

[0051] The recovery time for a patient's respiratory rate to return to baseline at the end of the training program is recorded. A shorter recovery time indicates stronger recovery ability and better training stability. A longer recovery time may indicate excessive training intensity or that the patient's body has not yet adapted to the current intensity, resulting in poor training stability. Therefore, training recovery ability is inversely proportional to recovery time.

[0052] The process involves acquiring the moments of respiratory rate increase in the target training program, determining the time interval between any two adjacent moments of respiratory rate increase, and finally calculating the degree of fluctuation in the time intervals between all adjacent moments of respiratory rate increase. In this embodiment, variance is used to characterize the degree of fluctuation, i.e., the variance of the time intervals between all adjacent moments of respiratory rate increase is calculated. A larger variance indicates that the rate of increase in the patient's respiratory rate is more unstable during the training process of the target program, meaning greater fluctuations in physical condition, which affects rehabilitation outcomes and reduces training stability. Therefore, training recovery ability is inversely proportional to variance.

[0053] The above analysis shows that the recovery time and variance of the target training item determine its training recovery capability. Therefore, by combining the recovery time and variance of the target training item, the training recovery capability of the target training item is obtained. In an exemplary embodiment, the following is a method for quantifying the training recovery capability of the target training item: ; in, This indicates the patient's recovery ability for the x-th training item during the c-th rehabilitation training session. This indicates the recovery time corresponding to the x-th training item during the c-th rehabilitation training session. This represents the variance corresponding to the x-th training item during the c-th rehabilitation training session.

[0054] Using the above process, the training recovery ability of each training item in each rehabilitation training session within the historical time period is obtained. To further improve the reliability of subsequent data processing, the training recovery ability of each training item in each rehabilitation training session within the historical time period can be normalized using a maximum-minimum value normalization method. Specifically: obtain the maximum and minimum values ​​of the training recovery ability of each training item in each rehabilitation training session within the historical time period, and then normalize the training recovery ability of each training item in each rehabilitation training session within the historical time period based on the maximum and minimum values. The training recovery abilities mentioned later are all the normalized results.

[0055] As analyzed above, the actual training intensity and recovery ability of a target training item comprehensively characterize its training stability from two different perspectives. Therefore, the training stability of a target training item is obtained by integrating these two factors. In an exemplary embodiment, a specific quantification method is given below: a weighted sum of the actual training intensity and the recovery ability of the target training item is performed, with each factor having a weight of 0.5. The result obtained is the training stability of the target training item. Using the above process, the training stability of each training item in each rehabilitation training session within a historical time period is obtained.

[0056] Because each rehabilitation session during the patient's recovery period includes multiple training programs, the patient accumulates fatigue during training. Furthermore, the later a training program appears in the corresponding rehabilitation training process, the more it is affected by the preceding training programs, especially high-intensity programs, leading to more severe accumulated fatigue. Accumulated fatigue affects the training stability of the training programs. Therefore, after the steps corresponding to the training stability acquisition module and before the steps corresponding to the anomaly degree acquisition module, the system also includes a training stability correction module. This module corrects the training stability obtained by the training stability acquisition module to make the training stability more consistent with the actual situation. In an exemplary embodiment, such as... Figure 5 As shown, the training stability correction module is specifically used for: Step 2-1: Obtain the importance weight of each reference training item based on the time interval between each reference training item and the target training item.

[0057] For ease of explanation, we define each training item that is part of the same rehabilitation training process as the target training item and precedes the target training item as a reference training item for the target training item. For example, if the target training item is the fourth training item in the rehabilitation training process, then the first three training items in that rehabilitation training process are reference training items for the target training item.

[0058] Obtain the time interval between each reference training item and the target training item, that is, the time interval between the end time of the reference training item and the start time of the target training item. For any reference training item, the longer the time interval between the reference training item and the target training item, the weaker the influence of the reference training item on the target training item, the weaker the importance of the reference training item, and therefore, the smaller the importance weight of the reference training item. Thus, the importance weight of the reference training item is inversely proportional to the time interval. In an exemplary embodiment, the time interval corresponding to the reference training item is negatively correlated and normalized to obtain the importance weight of the reference training item.

[0059] This allows us to obtain the importance weights of each reference training item for the target training item.

[0060] Furthermore, to ensure the accuracy of subsequent data processing, this embodiment normalizes the importance weights of each reference training item for the target training item as follows: The sum of the importance weights of each reference training item for the target training item is obtained; then, the ratio of the importance weight of each reference training item to this sum is calculated, and this ratio is used as the processed importance weight of each reference training item, thus ensuring that the sum of the importance weights of all reference training items is 1. The importance weights of each reference training item used below are all after this processing. It should be understood that if there is only one reference training item before the target training item, then the importance weight of that reference training item is 1.

[0061] Step 2-2: Based on the importance weight of each reference training item, perform a weighted sum of the actual training intensities of each reference training item to obtain the reference training intensity corresponding to the target training item.

[0062] In one exemplary embodiment, the formula for calculating the reference training intensity is as follows: ; in, This indicates the reference training intensity for the x-th training item during the c-th rehabilitation training session. This represents the actual training intensity of the nth reference training item in the xth training item during the cth rehabilitation training session. This represents the importance weight of the nth reference training item for the xth training item during the cth rehabilitation training session, where N represents the number of reference training items for the xth training item.

[0063] It should be understood that if the target training program is the first training program in the current rehabilitation training process, then steps 2-1 and 2-2 above should not be performed.

[0064] Steps 2-3: Obtain the correction coefficients for the target training items based on the reference training intensity.

[0065] If the target training item is the first training item in the rehabilitation training process, then the target training item will not be affected by other training items in the same rehabilitation training process. Therefore, the correction coefficient of the target training item is set to the value of 1.

[0066] If the target training item is not the first training item in the rehabilitation training process, the target interference level of the target training item is obtained from the reference training intensity of the target training item. In an exemplary embodiment, the reference training intensity of the target training item is used as the target interference level of the target training item. The greater the reference training intensity, the stronger the influence of the reference training item on the target training item, and the higher its target interference level. Then, the target interference level of the target training item is negatively correlated and normalized, and the result is used as the correction coefficient of the target training item.

[0067] Steps 2-4: Correct the training stability of the target training item based on the correction coefficient.

[0068] Multiplying the correction factor of the target training item by the training stability of the target training item yields the corrected training stability of the target training item.

[0069] If the target training item is the first training item in the rehabilitation training process, and the correction coefficient of the target training item is 1, then the training stability after correction is equal to the training stability before correction.

[0070] If the target training item is not the first training item in the current rehabilitation training process, the formula for calculating the modified training stability of the target training item is as follows: ; in, This indicates the stability of the patient's training after the correction of the x-th training item during the c-th rehabilitation training session. This indicates the training stability of the x-th training item during the c-th rehabilitation training session, i.e., the training stability before correction. This represents the correction factor for the x-th training item during the c-th rehabilitation training session.

[0071] Through the above process, the training stability of each training item in each rehabilitation training session during the historical period is corrected to obtain the corrected training stability.

[0072] The abnormality level acquisition module is used to obtain the abnormality level of each rehabilitation training process based on the difference between the order of standard training items and the actual order of training items in each rehabilitation training process.

[0073] The order of training exercises varies throughout a patient's rehabilitation program, and a proper arrangement of these exercises is crucial for effective rehabilitation. For example, if a patient has been bedridden for a long time or has limited breathing, starting with high-intensity training (such as increasing weight or endurance training) may cause fatigue and difficulty breathing. In this case, subsequent training exercises (such as deep breathing or stretching exercises) may be ineffective due to excessive fatigue, thus affecting the overall training outcome.

[0074] For the target training program, since each rehabilitation training session includes the target training program, the actual training intensity of the target training program in each rehabilitation training session is analyzed, and the average actual training intensity of the target training program in each rehabilitation training session is calculated. This average is taken as the actual comprehensive training intensity of the target training program across all rehabilitation training sessions. This yields the actual comprehensive training intensity of each training program across all rehabilitation training sessions, i.e., the actual comprehensive training intensity of each training program.

[0075] To obtain the standard training program order, since ideally, the training intensity of the training programs should increase from low to high during a rehabilitation training process, in an exemplary embodiment, the actual comprehensive training intensity of each training program is arranged in ascending order, and the resulting sorting result is the standard training program order.

[0076] Obtain the actual sequence of training items in each rehabilitation training session, that is, the actual order of each training item in each rehabilitation training session during the actual implementation by the patient.

[0077] For any given rehabilitation training session, the greater the difference between the actual training sequence and the standard training sequence, the further the actual training sequence deviates from the ideal, and the more unreasonable the sequence is. For example, initiating high-intensity training exercises prematurely may cause excessive fatigue or difficulty in completing subsequent exercises, thus affecting the training effect and failing to maximize rehabilitation outcomes. In such cases, the degree of abnormality in the rehabilitation training session is higher. In an exemplary embodiment, such as... Figure 6 As shown, the following is a specific process for obtaining the degree of anomaly: Step 3-1: Obtain the number of inversions in the actual training program sequence for each rehabilitation training session relative to the standard training program sequence; Step 3-2: Based on the number of inversions in each rehabilitation training process, determine the degree of abnormality in each rehabilitation training process.

[0078] Taking the standard training item order as a benchmark, compare it with the actual training item order of each rehabilitation training process to obtain the number of inversions in the actual training items of each rehabilitation training process. The number of inversions refers to the total number of "inversion pairs" in a sequence. Definition of an inversion pair: In a sequence, if there are two elements ai and aj, where i < j, but ai > aj, then this pair of elements (ai, aj) is called an inversion pair. The number of inversions measures the "disorder degree" of the sequence: the larger the number of inversions, the more chaotic the sequence; when the number of inversions is 0, the sequence is completely ordered, that is, in ascending order.

[0079] Then, the larger the number of inversions in the actual training items of the rehabilitation training process, the more unreasonable the setting of the actual training item order of the patient in the rehabilitation training process. The larger the number of inversions, the higher the degree of abnormality, and the degree of abnormality is proportional to the number of inversions. Therefore, according to the number of inversions in each rehabilitation training process, the degree of abnormality of each rehabilitation training process is obtained. In an exemplary embodiment, the number of inversions in each rehabilitation training process is used as the degree of abnormality of each rehabilitation training process.

[0080] The training effect acquisition module is used to obtain the actual training effect of each rehabilitation training process according to the degree of abnormality and the comprehensive training stability of each rehabilitation training process.

[0081] For any rehabilitation training process, calculate the average value of the corrected training stability of all training items in this rehabilitation training process as the comprehensive training stability of this rehabilitation training process. Thus, the comprehensive training stability of each rehabilitation training process is obtained. The greater the comprehensive training stability, the more stable the patient's physical state in this rehabilitation training process, the better the actual training effect, and the better the rehabilitation effect.

[0082] The higher the degree of abnormality of this rehabilitation training process, the worse the actual training effect of this rehabilitation training process, so the actual training effect is inversely proportional to the degree of abnormality. The higher the comprehensive training stability of this rehabilitation training process, the better the actual training effect of this rehabilitation training process, and the comprehensive training stability is directly proportional to the actual training effect. Therefore, according to the degree of abnormality of this rehabilitation training process and the comprehensive training stability of this rehabilitation training process, the actual training effect of this rehabilitation training process is obtained. In an exemplary embodiment, as Figure 7 shown, the following gives a specific acquisition process of the actual training effect: Step 4-1: Perform negative correlation on the degree of abnormality of each rehabilitation training process to obtain the training effect factor of each rehabilitation training process; Step 4-2: According to the training effect factor of each rehabilitation training process and the comprehensive training stability of each rehabilitation training process, obtain the actual training effect of each rehabilitation training process.

[0083] For any given rehabilitation training session, the degree of abnormality in that session is negatively correlated and normalized to obtain the training effect factor for that session. This yields the training effect factors for each individual rehabilitation training session. Multiplying the training effect factor of that session by the overall training stability of that session yields the actual training effect for that session.

[0084] The screening module is used to determine the optimal rehabilitation training process from each rehabilitation training session based on the actual training results.

[0085] The maximum actual training effect among the actual training effects of each rehabilitation training session is obtained, and the rehabilitation training session corresponding to the maximum actual training effect is taken as the optimal rehabilitation training session. This optimal session is then used as the next rehabilitation training session (i.e., the next future rehabilitation training session), and the patient undergoes the next rehabilitation training session according to the order of the training items in this optimal session. Furthermore, the next rehabilitation training session can be continuously updated over time using the above method.

[0086] This embodiment adjusts the rehabilitation training process based on the optimal process obtained over a historical period, ensuring that the patient's rehabilitation training continuously aligns with the body's recovery rhythm and that each training session incorporates content from the patient's best performance in previous sessions. This allows the patient to undergo rehabilitation within a more effective training sequence, further maximizing the training effect.

[0087] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0088] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A personalized intelligent rehabilitation training system for critically ill respiratory patients during their recovery period, characterized in that, include: The training stability acquisition module is used to obtain the training stability of each training item based on the actual training intensity of each training item in each rehabilitation training process during the historical time period of the respiratory critically ill patient. The abnormality level acquisition module is used to obtain the abnormality level of each rehabilitation training process based on the difference between the order of standard training items and the actual order of training items in each rehabilitation training process. The standard training program sequence is obtained from the actual comprehensive training intensity of each training program, which is obtained from the actual training intensity of the same training program for all rehabilitation training processes. The training effect acquisition module is used to obtain the actual training effect of each rehabilitation training process based on the degree of abnormality and the overall training stability of each rehabilitation training process. The overall training stability is obtained from the training stability of all training items in the same rehabilitation training process; The screening module is used to determine the optimal rehabilitation training process from each rehabilitation training session based on the actual training effect.

2. The personalized intelligent rehabilitation training system for critically ill respiratory patients during the recovery period as described in claim 1, characterized in that, Before the anomaly level acquisition module, the system further includes a training stability correction module, which is used for: The importance weight of each reference training item is obtained based on the time interval between each reference training item and the target training item; the importance weight is inversely proportional to the time interval; the target training item is any training item, and each reference training item is a training item that is in the same rehabilitation training process as the target training item and precedes the target training item. Based on the importance weight of each reference training item, the actual training intensity of each reference training item is weighted and summed to obtain the reference training intensity corresponding to the target training item. Based on the reference training intensity, the correction coefficient for the target training item is obtained; The training stability of the target training item is corrected based on the correction coefficient.

3. The personalized intelligent rehabilitation training system for critically ill respiratory patients during the recovery period as described in claim 2, characterized in that, The step of obtaining the correction coefficient for the target training item based on the reference training intensity includes: If the target training item is the first training item in the rehabilitation training process, then the correction coefficient of the target training item is set to the value 1; If the target training item is not the first training item in the rehabilitation training process, then the correction coefficient of the target training item is the result of negative correlation normalization with the degree of target interference; the degree of target interference is obtained from the reference training intensity.

4. The personalized intelligent rehabilitation training system for critically ill respiratory patients during the recovery period as described in claim 1, characterized in that, The process of obtaining the standard training item order includes: arranging the actual comprehensive training intensity of each training item in ascending order to obtain the standard training item order.

5. The personalized intelligent rehabilitation training system for critically ill respiratory patients during the recovery period as described in claim 4, characterized in that, The process of obtaining the degree of abnormality includes: Obtain the number of inversions in the actual training item sequence of each rehabilitation training session relative to the standard training item sequence; The degree of abnormality in each rehabilitation training process is obtained based on the number of inversions in each rehabilitation training process, and the degree of abnormality is proportional to the number of inversions.

6. The personalized intelligent rehabilitation training system for critically ill respiratory patients during the recovery period as described in claim 1, characterized in that, The overall training stability is the average value of the training stability of all training items in the same rehabilitation training process; The process of obtaining the actual training effect includes: By negatively correlating the degree of abnormality in each rehabilitation training session, the training effect factor of each rehabilitation training session can be obtained. Based on the training effect factors and the overall training stability of each rehabilitation training session, the actual training effect of each rehabilitation training session is obtained.

7. The personalized intelligent rehabilitation training system for critically ill respiratory patients during the recovery period as described in claim 1, characterized in that, Determining the optimal rehabilitation training process from each rehabilitation training session includes: taking the rehabilitation training process corresponding to the maximum actual training effect among the actual training effects of each rehabilitation training session as the optimal rehabilitation training process.

8. The personalized intelligent rehabilitation training system for critically ill respiratory patients during the recovery period as described in claim 1, characterized in that, The process of obtaining the actual training intensity includes: The high-intensity training sustainability factor of the training program is obtained based on the duration of respiratory rate increase within the corresponding duration of the training program and the overall rate of increase of respiratory rate in the training program. Obtain the peak respiratory rate period within the corresponding duration of the training project; the peak respiratory rate period consists of multiple consecutive peak respiratory rate moments; the peak respiratory rate moment is the moment when the respiratory rate is greater than a preset respiratory rate threshold. The continuity of peak periods in the training program is obtained by considering the duration of peak respiratory rate periods and the time interval between adjacent peak respiratory rate periods. Based on the continuity of the peak period and the overall level of the breathing rate of the training program, the maximum training intensity of the training program is obtained. By combining the high-intensity training persistence factor and the maximum training intensity, the actual training intensity of the training item is obtained.

9. The personalized intelligent rehabilitation training system for critically ill respiratory patients during the recovery period as described in claim 8, characterized in that, The process of obtaining the overall growth rate of respiratory rate includes: obtaining the slope of change between the first respiratory rate and the maximum respiratory rate within the corresponding duration of the training item, as the overall growth rate of respiratory rate.

10. The personalized intelligent rehabilitation training system for critically ill respiratory patients during the recovery period as described in claim 8, characterized in that, The training stability is obtained by combining the actual training intensity and training recovery ability of the training program. The process of acquiring the training recovery capability includes: Obtain the recovery time for respiratory rate to return to baseline at the end of the training program; The degree of fluctuation between the time intervals between any two adjacent respiratory rate increase moments in the training project is obtained; all the respiratory rate increase moments in the training project constitute the respiratory rate increase duration. The training recovery capability is obtained based on the recovery time and the degree of fluctuation.

Images