Dynamic pressure management system for cancer patient in rehabilitation period

Abstract

The invention relates to the technical field of rehabilitation pressure dynamic management, in particular to a cancer patient rehabilitation pressure dynamic management system which comprises a pressure state recognition module, a breathing mode monitoring module, a training rhythm dynamic adjustment module, a training effect feedback module and a dynamic management module. According to the method, real-time tracking of pressure state changes is achieved on the basis of dynamic calculation of the inspiration duration, the expiration duration and the I / E ratio in combination with continuous respiratory cycle data, and through single-time respiratory amplitude calculation and multi-cycle amplitude change trend analysis, the respiratory mode classification precision is enhanced, the pressure recognition stability is improved, and the accuracy of pressure recognition is improved. The training rhythm is adjusted to adapt to the current state of the patient by combining the inspiration time deviation, the I / E ratio trend and the breathing amplitude change, the pressure state is analyzed in real time, the target is guided by combining the breathing rhythm, the pressure intervention scheme can be accurately matched according to the current state of the patient, meanwhile, the interactivity of the training process is enhanced, and the training efficiency is improved. The pertinence of pressure management during the rehabilitation period is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of rehabilitation stress dynamic management, and particularly to a system for dynamic management of stress during the rehabilitation period of cancer patients. Background Art

[0002] The technical field of rehabilitation stress dynamic management includes technical means for monitoring, analyzing, and regulating physiological and psychological stress during the patient's rehabilitation process. The core content involves collecting the patient's physiological indicators, such as heart rate, blood pressure, skin conductance, etc., through various sensors to obtain data related to the stress level. In addition, this field covers assessment methods for the patient's psychological state, including questionnaire surveys, voice analysis, and facial expression recognition, etc., to quantify the degree of psychological stress. The overall technical system includes links such as data collection, stress assessment, intervention means, and feedback regulation, and usually combines computer algorithms and information processing technologies to achieve stress management during the patient's rehabilitation process and help medical institutions or individuals formulate personalized intervention plans.

[0003] Among them, the system for dynamic management of stress during the rehabilitation period of cancer patients refers to a system that uses specific means to monitor and regulate the physiological and psychological stress that cancer patients may experience during the rehabilitation stage, mainly covering real-time monitoring of physiological parameters, psychological stress assessment, and recommendation of adjustment strategies, etc. First, wearable sensing devices are used to collect data such as the patient's heart rate variability, skin temperature, and respiratory rate as the basis for measuring physiological stress. At the same time, the patient's emotional fluctuations are recorded through voice emotion analysis and self-assessment scales to assist in psychological stress assessment. Subsequently, based on the collected information, the patient's stress state is classified, and appropriate intervention means, such as breathing training, music therapy, and progressive muscle relaxation training, etc., are matched to help the patient relieve physiological and psychological stress during the rehabilitation period. In addition, it also includes an interactive guidance module, enabling the patient to independently complete relaxation training or seek further intervention from medical staff according to the adjustment suggestions provided by the system.

[0004] During the current dynamic management process of cancer patients' rehabilitation period, in terms of stress monitoring, it relies on physiological indicators such as heart rate variability and skin conductance for phased assessment, but fails to achieve real-time trend tracking based on respiratory parameters, making it difficult to accurately capture short-term stress fluctuations and resulting in a delay in the intervention timing. Psychological assessment methods such as questionnaires and self-assessment scales lack immediacy and are difficult to reflect the dynamic changes in the stress level of patients during the rehabilitation training process, affecting the adjustment of individualized intervention plans. Although the intervention means include breathing training and relaxation training, the training signals are not adjusted according to the real-time respiratory state of the patients, making the training methods relatively fixed and possibly resulting in insufficient adaptability of patients at different stages. The training feedback link is usually based on a preset range of physiological indicator changes, lacking a comprehensive analysis of dynamic data such as respiratory rhythm and inhalation-to-exhalation ratio, and unable to accurately evaluate the training effect, affecting the regulation accuracy. When formulating the regulation plan, there is a lack of real-time integration of training feedback data, resulting in insufficient personalized adaptability of stress management and causing the intervention strategy to not match the current state of the patient. Summary of the Invention

[0005] The object of the present invention is to solve the drawbacks existing in the prior art and to propose a dynamic stress management system for cancer patients during the rehabilitation period.

[0006] To achieve the above object, the present invention adopts the following technical solution: A dynamic stress management system for cancer patients during the rehabilitation period includes:

[0007] The stress state recognition module obtains the respiratory data of cancer patients during the rehabilitation period, calculates the inhalation duration and exhalation duration, calculates and collects the I / E ratio of consecutive respiratory cycles, judges the change direction of the stress state and the current stress state, and generates a stress state classification result;

[0008] The breathing pattern monitoring module calculates the single-breath amplitude based on the stress state classification result, calculates the average value, change rate and stability parameter of the amplitude change, judges the amplitude fluctuation situation, classifies the breathing pattern, and generates a breathing pattern classification result;

[0009] The training rhythm dynamic adjustment module judges the change direction of the inhalation time based on the breathing pattern classification result, sets the inhalation time guidance strategy, analyzes the stability of the breathing amplitude in consecutive cycles, adjusts the intensity of the training prompt signal, and generates a training rhythm adjustment parameter;

[0010] The training effect feedback module counts the change trend of the I / E ratio and the change trend of the breathing amplitude based on the training rhythm adjustment parameter, judges the change of the breathing amplitude when the I / E ratio rises, and generates a training effect feedback index;

[0011] The dynamic management module analyzes the current stress state during the rehabilitation period in real time based on the training effect feedback index, conducts regulation for the current stress state, and generates a dynamic regulation plan for rehabilitation stress.

[0012] As a further solution of the present invention, the pressure state classification result includes the analysis result of the increasing and decreasing trend of the I / E ratio, the change situation of the inspiratory duration, and the pressure state category classification result. The breathing mode classification result includes the single-breath amplitude, the amplitude change rate, and the breathing mode category classification result. The training rhythm adjustment parameter includes the inspiratory time guidance strategy, the training prompt signal frequency, and the breathing amplitude stability analysis result. The training effect feedback index includes the analysis result of the I / E ratio change trend, the analysis result of the breathing amplitude change trend, and the relaxation training guidance strategy. The rehabilitation pressure dynamic regulation scheme includes the determination result of the patient's current pressure state, the breathing rhythm guidance target, and the breathing regulation measures.

[0013] As a further solution of the present invention, the pressure state recognition module includes:

[0014] The breathing data acquisition sub-module acquires the breathing data of cancer patients during the rehabilitation period, records the inspiratory start time, inspiratory end time, expiratory start time, and expiratory end time, calculates the inspiratory duration and expiratory duration, records the time parameters of consecutive breathing cycles, and establishes a breathing time parameter data set;

[0015] The I / E ratio calculation sub-module calculates the I / E ratio of each cycle based on the breathing time parameter data set, analyzes the increasing and decreasing trend of the I / E ratio of adjacent cycles, compares the current inspiratory duration with the previous breathing cycle, and uses the formula:

[0016]

[0017] Calculate the inspiratory duration change amplitude value I / E Δ , and combine with the increasing and decreasing trend of the I / E ratio to obtain the I / E ratio change trend data, where I t represents the current inspiratory duration, I t-1 represents the inspiratory duration of the previous cycle, and E t-1 represents the expiratory duration of the previous cycle;

[0018] The pressure state classification sub-module calculates the average value of the I / E ratio based on the I / E ratio change trend data, sets a classification threshold, classifies the current pressure state according to the classification threshold, and obtains the pressure state classification result.

[0019] As a further solution of the present invention, the breathing mode monitoring module includes:

[0020] The breathing amplitude calculation sub-module obtains the maximum airflow velocity of a single breath based on the pressure state classification result, calculates the single-breath amplitude, records the amplitude data of consecutive breathing cycles, and establishes a breathing amplitude data set;

[0021] The amplitude change analysis sub-module, based on the respiratory amplitude data set, according to the average value, change rate and stability parameter of the amplitude change, uses the formula:

[0022]

[0023] Calculate the amplitude stability parameter S v , judge the amplitude floating situation, and obtain the amplitude change characteristic data, where A t represents the amplitude of the t-th breath, and n represents the total number of respiratory cycles;

[0024] The breathing mode classification sub-module, based on the amplitude change characteristic data, sets a breathing threshold, classifies the current breathing mode according to the breathing threshold, and obtains the breathing mode classification result.

[0025] As a further solution of the present invention, the training rhythm dynamic adjustment module includes:

[0026] The inspiratory time deviation calculation sub-module, based on the breathing mode classification result, calculates the time deviation of the inspiratory time compared with the individual mean value, judges the change direction of the inspiratory time, and obtains the inspiratory time deviation data;

[0027] The training prompt signal setting sub-module, based on the inspiratory time deviation data, uses the formula:

[0028]

[0029] Calculate the change rate T of the I / E ratio f , set the frequency and intensity of the training prompt signal, and obtain the training signal setting parameters, where I / E t represents the I / E ratio of the t-th breath, I / E t -I / E t-1 represents the I / E ratio of the (t-1)-th breath, and M represents the total number of cycles;

[0030] The training rhythm parameter adjustment sub-module, based on the training signal setting parameters, analyzes the breathing amplitude stability of consecutive cycles, adjusts the intensity of the training prompt signal, and obtains the training rhythm adjustment parameters.

[0031] As a further solution of the present invention, the training effect feedback module includes:

[0032] The I / E ratio trend calculation sub-module, based on the training rhythm adjustment parameters, collects the I / E ratio change data of consecutive multiple cycles, calculates the change trend of the I / E ratio, and obtains the I / E ratio trend data;

[0033] Based on the I / E ratio trend data, the respiratory amplitude change analysis sub-module collects respiratory amplitude change data, statistically analyzes the respiratory amplitude change trend over consecutive periods, and uses the formula:

[0034]

[0035] Calculate the respiratory amplitude skewness coefficient V s , determine the respiratory amplitude change when the I / E ratio rises, obtain the respiratory amplitude trend data, where V t represents the amplitude of the t-th breath, represents the mean value of the amplitudes, σ V represents the standard deviation of the amplitudes, and m represents the total number of breaths recorded;

[0036] Based on the respiratory amplitude trend data, the relaxation training guidance adjustment sub-module calculates the stability parameter of the respiratory rhythm, determines the respiratory regulation offset during training, adjusts the feedback delay time of the training prompt signal, determines the training adaptability level, and obtains the training effect feedback index.

[0037] As a further aspect of the present invention, the dynamic management module includes:

[0038] Based on the training effect feedback index, the stress state recognition sub-module monitors the I / E ratio trend data and respiratory amplitude trend data during the rehabilitation period of cancer patients, calculates the current stress state change amplitude, determines the real-time classification of the stress state, and obtains the current stress state parameter;

[0039] Based on the current stress state parameter, the respiratory regulation strategy setting sub-module adjusts the relaxation training guidance signal and uses the formula:

[0040]

[0041] Calculate the individualized respiratory regulation intensity R t , set the respiratory rhythm guidance target, obtain the respiratory regulation parameters, where P t represents the stress state parameter of the t-th cycle, P t -1 represents the stress state parameter of the (t - 1)-th cycle, B t represents the respiratory rhythm target of the current cycle, and K represents the total number of cycles;

[0042] Based on the respiratory regulation parameters, the rehabilitation stress regulation plan generation sub-module performs respiratory regulation on the patient for the current stress state, adjusts the training rhythm guidance feedback, and generates a rehabilitation stress dynamic regulation plan.

[0043] Compared with the prior art, the advantages and positive effects of the present invention are:

[0044] In the present invention, based on the dynamic calculation of the inhalation duration, exhalation duration, and I / E ratio, combined with continuous respiratory cycle data, real-time tracking of pressure state changes is achieved. Compared with static physiological measurements, the coherence of data is improved. Through single-breath amplitude calculation and analysis of the amplitude change trend over multiple cycles, the classification accuracy of respiratory patterns is enhanced, enabling pressure assessment to not be limited to a single physiological signal but to integrate multiple dynamic parameters, thereby improving the stability of pressure recognition. By combining the inhalation time deviation, I / E ratio trend, and respiratory amplitude change, a regulation strategy for training prompt signals is set, enabling the training rhythm to be adjusted to adapt to the patient's current state and avoiding the limitations of the fixed-duration training method. Using the cross-change trend of the I / E ratio and respiratory amplitude as the judgment basis, not only the change in pressure level is concerned, but also the adaptability of relaxation training can be adjusted. By analyzing the pressure state in real time, combined with the respiratory rhythm guidance target, the regulation means are optimized, enabling the pressure intervention plan to be accurately matched according to the patient's current state. Compared with the traditional phased physiological assessment method, continuous dynamic data monitoring is adopted, making pressure classification more time-effective, avoiding the impact of data lag on the regulation effect, and at the same time enhancing the interactivity of the training process and improving the pertinence of pressure management during rehabilitation. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 is the system flow chart of the present invention;

[0046] Figure 2 is the flow chart of the pressure state recognition module of the present invention;

[0047] Figure 3 is the flow chart of the respiratory pattern monitoring module of the present invention;

[0048] Figure 4 is the flow chart of the training rhythm dynamic adjustment module of the present invention;

[0049] Figure 5 is the flow chart of the training effect feedback module of the present invention;

[0050] Figure 6 is the flow chart of the dynamic management module of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0051] In order to make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0052] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more, unless otherwise specifically defined.

[0053] Please refer to Figure 1 , a dynamic stress management system for cancer patients during the recovery period includes:

[0054] The stress state recognition module obtains the breathing data of cancer patients during the recovery period, collects the inhalation start time, inhalation end time, exhalation start time, and exhalation end time, calculates the inhalation duration and exhalation duration, calculates and collects the I / E ratio of consecutive breathing cycles, judges the increasing and decreasing trend of the I / E ratio, analyzes the comparison of the inhalation duration with the previous breathing cycle, judges the change direction of the stress state, synchronously calculates the average value of the I / E ratio, sets the classification threshold, and judges the current stress state category according to the classification threshold to generate the stress state classification result;

[0055] The breathing pattern monitoring module calculates the single - breath amplitude based on the stress state classification result, obtains the amplitude change data of multiple consecutive breathing cycles, calculates the average value, change rate, and stability parameter of the amplitude change, judges the floating situation of the amplitude, classifies the breathing pattern, and generates the breathing pattern classification result;

[0056] The training rhythm dynamic adjustment module calculates the deviation of the inhalation time from the individual average value based on the breathing pattern classification result, judges the change direction of the inhalation time, sets the inhalation time guiding strategy, calculates the change trend of the current I / E ratio, sets the frequency and intensity of the training prompt signal, analyzes the stability of the breathing amplitude in consecutive cycles, adjusts the intensity of the training prompt signal, and generates the training rhythm adjustment parameter;

[0057] The training effect feedback module collects the I / E ratio change data and breathing amplitude change data of multiple consecutive cycles during the recovery period of cancer patients based on the training rhythm adjustment parameter, statistically analyzes the change trends of the I / E ratio and breathing amplitude, judges the change of the breathing amplitude when the I / E ratio rises, adjusts the relaxation training guiding strategy, and generates the training effect feedback index;

[0058] Based on the training effect feedback metrics, the dynamic management module determines the current stress state of cancer patients during the rehabilitation period in real time, adjusts the relaxation training guidance signal, sets the breathing rhythm guidance target, conducts breathing regulation for the current stress state, and generates a dynamic regulation plan for rehabilitation stress.

[0059] The classification results of the stress state include the analysis results of the increasing or decreasing trend of the I / E ratio, the change of the inspiratory duration, and the classification results of the stress state category. The classification results of the breathing pattern include the single breath amplitude, the amplitude change rate, and the classification results of the breathing pattern category. The training rhythm adjustment parameters include the inspiratory time guidance strategy, the frequency of the training prompt signal, and the analysis results of the breathing amplitude stability. The training effect feedback metrics include the analysis results of the I / E ratio change trend, the analysis results of the breathing amplitude change trend, and the relaxation training guidance strategy. The dynamic regulation plan for rehabilitation stress includes the determination results of the patient's current stress state, the breathing rhythm guidance target, and the breathing regulation measures.

[0060] Please refer to Figure 2 , the stress state recognition module includes:

[0061] The breathing data acquisition sub-module acquires the breathing data of cancer patients during the rehabilitation period, records the inspiratory start time, inspiratory end time, expiratory start time, and expiratory end time, calculates the inspiratory duration and expiratory duration, records the time parameters of consecutive breathing cycles, and establishes a breathing time parameter data set;

[0062] The breathing data of cancer patients during the rehabilitation period needs to be monitored in real time through high-precision sensors, including the inspiratory start time, inspiratory end time, expiratory start time, and expiratory end time. These data are obtained through gas flow sensors or chest movement detection devices. For example, a flow sensor is used to detect the flow rate change of the gas entering and leaving the lungs, or a wearable chest strap is used to detect the degree of chest expansion. Suppose the inspiratory start time of a certain patient is 1.2 seconds and the inspiratory end time is 3.6 seconds, then the inspiratory duration can be calculated as 3.6 - 1.2 = 2.4 seconds. Similarly, if the expiratory start time of this patient is 3.6 seconds and the expiratory end time is 6.1 seconds, then the expiratory duration is 6.1 - 3.6 = 2.5 seconds. These data are used to construct the breathing time parameter data set. The data recording is carried out in a fixed time window manner. For example, the time parameters of 30 breathing cycles are recorded per minute and stored in the database.

[0063] Table 1.1: Breathing time parameter data set (partial example)

[0064]

[0065] As shown in Table 1.1, this data set can be used for subsequent I / E ratio calculation and trend analysis.

[0066] The I / E ratio calculation sub-module calculates the I / E ratio for each cycle based on the respiratory time parameter dataset, analyzes the increasing and decreasing trends of the I / E ratio for adjacent cycles, compares the current inspiratory duration with the previous respiratory cycle, and uses the formula:

[0067]

[0068] Calculate the change amplitude value of the inspiratory duration I / E Δ , and combine it with the increasing and decreasing trend of the I / E ratio to obtain the I / E ratio change trend data, where I t represents the current inspiratory duration, I t-1 represents the inspiratory duration of the previous cycle, and E t-1 represents the expiratory duration of the previous cycle;

[0069] Based on the respiratory time parameter dataset, calculate the I / E ratio for each cycle, that is, the ratio of the inspiratory duration to the expiratory duration. For example, in Table 1.1, the I / E ratio of the first respiratory cycle is calculated as The I / E ratio of the second cycle is This ratio is used to analyze the patient's breathing rhythm. Further calculate the increasing and decreasing trend of the I / E ratio for adjacent cycles, and use the difference calculation formula of the I / E ratio for the previous and subsequent cycles:

[0070] Δ I / E = I / E t - I / E t-1 ;

[0071] Taking the data in Table 1 as an example, the change amount of the I / E ratio in the second cycle is 0.82 - 0.96 = -0.14, indicating that the inspiratory duration in this cycle decreases relatively or the expiratory duration increases relatively.

[0072] To more accurately evaluate the change amplitude of the inspiratory duration, introduce a formula for calculation. For example, if the inspiratory duration of the current cycle is 2.3 seconds, the previous cycle is 2.5 seconds, and the expiratory duration is 2.6 seconds, then:

[0073]

[0074] The calculated I / E ratio change trend data can be used to judge the change trend of the patient's pressure state.

[0075] The I / E ratio change trend data I / E Δ reflects the change amplitude of the ratio of the inspiratory to expiratory time between adjacent respiratory cycles. This data is used to judge the change trend of the patient's pressure state. According to the calculation, the I / E of a certain patient Δ = 0.056.

[0076] If I / E ΔIf it is positive, it indicates that the I / E ratio in the current cycle has increased compared to the previous cycle, suggesting that the inspiratory duration has relatively increased or the expiratory duration has relatively decreased, indicating that the autonomic nervous system is regulating towards the parasympathetic nerve-dominant direction and the stress state tends to decrease.

[0077] If the I / E Δ is negative, it indicates that the I / E ratio in the current cycle has decreased, suggesting that the inspiratory duration has shortened or the expiratory duration has lengthened, which may mean an increase in sympathetic nerve activity and a tendency for the stress state to increase.

[0078] Set the evaluation threshold for the I / E change trend. According to the normal respiratory rhythm fluctuation range, the change trend data of the I / E ratio is usually less than 0.05, that is:

[0079] |I / E Δ |<0.05: The change amplitude is small, indicating that the respiratory rhythm is relatively stable and there is no significant change in the stress state;

[0080] 0.05 ≤ |I / E Δ |<0.15: The change amplitude is moderate, indicating that the patient's stress state is fluctuating to a certain extent;

[0081] |I / E Δ |≥0.15: The change amplitude is large, indicating that the patient's autonomic nerve regulation has changed significantly and the stress state has changed greatly.

[0082] The calculated I / E Δ = 0.056, falling into the interval of 0.05 ≤ |I / E Δ |<0.15, indicating that the patient's current respiratory rhythm is fluctuating to a certain extent, and since the I / E Δ is positive, it means that the stress state has been relieved, that is, the patient's autonomic nervous system tends to be dominated by the parasympathetic nerve, and the stress state may change from a high or medium stress state to a lower stress level.

[0083] Finally, the I / E ratio change trend data of the patient is 0.056, indicating that there is a certain degree of relief trend in the stress state, but the change amplitude is not large, and further monitoring of subsequent changes is still needed to determine whether the stress state is stably decreasing or still fluctuating and adjusting.

[0084] The stress state classification sub-module calculates the mean value of the I / E ratio based on the I / E ratio change trend data, sets the classification threshold, and classifies the current stress state according to the classification threshold to obtain the stress state classification result;

[0085] Based on the I / E ratio change trend data, calculate the mean value of the I / E ratio and set the classification threshold to identify the patient's stress state. The formula for calculating the mean value of the I / E ratio is as follows:

[0086]

[0087] Among them, N is the total number of monitored respiratory cycles. For example, if the I / E ratios of five cycles are 0.96, 0.82, 1.00, 0.89, and 1.02 respectively, then:

[0088]

[0089] The setting of the classification threshold is based on the coupling relationship between the respiratory system and the autonomic nervous system. By analyzing the respiratory patterns in the normal state and the stress state, the typical distribution range of the I / E ratio under different stress states is determined. Specifically, a value lower than 0.85 is judged as a high stress state, a value between 0.85 and 1.00 is judged as a medium stress state, and a value higher than 1.00 is judged as a low stress state. This numerical setting is based on the relationship between the average respiratory rhythm and sympathetic nerve activity during the recovery period of cancer patients. In the high stress state, the sympathetic nerve activity increases, resulting in a shortened inspiratory duration and an extended expiratory duration, and the I / E ratio decreases; in the low stress state, the parasympathetic nerve dominates, the inspiratory duration relatively increases, and the expiratory duration relatively decreases, causing the I / E ratio to rise.

[0090] The specific numerical setting refers to the respiratory monitoring experimental data of cancer patients during the recovery period. Assuming that in the stress state scoring system, the subjective stress score of patients ranges from 10 points (extremely tense) to 0 points (completely relaxed). By monitoring the change of the I / E ratio of patients under different scores and statistically analyzing the respiratory data of 100 patients, among them, in the range of subjective scores from 8 to 10, the I / E ratio is mainly distributed in the interval of 0.70 - 0.85. Therefore, an I / E ratio lower than 0.85 is set as the high stress state; in the range of scores from 4 to 7, the I / E ratio is concentrated in the interval of 0.85 - 1.00, so it is set as the medium stress state; in the range of scores from 0 to 3, the I / E ratio is mainly higher than 1.00, so a value higher than 1.00 is set as the low stress state.

[0091] After setting the stress state classification threshold and combining the foregoing calculations, the current mean value is 0.94, which is in the medium stress state. Finally, based on the classification threshold, the current stress state is classified to obtain the stress state classification result.

[0092] Please refer to Figure 3 , the respiratory pattern monitoring module includes:

[0093] Based on the stress state classification result, the respiratory amplitude calculation sub-module obtains the maximum airflow velocity of a single breath, calculates the amplitude of a single breath, records the amplitude data of consecutive respiratory cycles, and establishes a respiratory amplitude data set;

[0094] Based on the classification results of the pressure state, it is first necessary to determine the maximum airflow velocity of a single breath. This velocity can be detected by a flow sensor to measure the change in the patient's breathing airflow, and the maximum peak on the time axis is found as the maximum airflow velocity of a single breath. For example, if the maximum airflow velocity of a single breath of a certain patient is 0.8 L / s, when calculating the amplitude of a single breath, a lung volume sensor is used to record the peak values of inhalation and exhalation. Assuming the initial breathing reference volume is 4.5 L, the inhalation peak is 5.3 L, and the exhalation peak is 3.7 L, then the calculation of the amplitude of a single breath is as follows:

[0095] A = V max - V min = 5.3 - 3.7 = 1.6 L;

[0096] Obtain the amplitude data of multiple consecutive breathing cycles to ensure data stability and trend analysis. Set the acquisition interval to 1 second, record at least 20 cycle data, and establish a breathing amplitude dataset. This dataset includes the amplitude values of each cycle, as shown in Table 2.1.

[0097] Table 2.1 Breathing Amplitude Data Table

[0098]

[0099]

[0100] As shown in Table 2.1, there are slight fluctuations in the amplitudes of different cycles. After the dataset is established, further trend analysis can be carried out to calculate the average amplitude, change rate, and stability parameters.

[0101] The amplitude change analysis sub-module is based on the breathing amplitude dataset. According to the average value, change rate, and stability parameters of the amplitude change, the formula is used:

[0102]

[0103] Calculate the amplitude stability parameter S v , judge the amplitude floating situation, and obtain the amplitude change characteristic data. Among them, A t represents the amplitude of the t-th breath, and n represents the total number of breathing cycles;

[0104] Based on the breathing amplitude dataset, calculate the average value, change rate, and stability parameters of the amplitude change. The calculation formula for the average value of the amplitude change is as follows:

[0105]

[0106] Among them, A avg is the amplitude mean value, A t is the amplitude of the t-th breath, and n is the total number of cycles. Substitute the data in Table 2.1, assuming the total number of cycles n = 20:

[0107]

[0108] Then calculate the rate of change of amplitude, using:

[0109]

[0110] Substitute some data:

[0111]

[0112] Finally, substitute into the formula to calculate the stability parameter, substituting the data:

[0113]

[0114] Obtain the amplitude stability parameter and judge the amplitude fluctuation situation. When S v > 1.5, the amplitude tends to be stable, which means that in consecutive cycles, the change amplitude of the breathing amplitude is small, indicating that the patient's breathing pattern is stable and there are no large fluctuations; when S v < 1.5, the amplitude changes greatly, indicating that the breathing state is unstable. At this time, the rate of change of amplitude A rate may be high, showing frequent fluctuations of the breathing amplitude or the disorder of regular changes.

[0115] The stability parameter S v During the determination of the critical value of 1.5, a large amount of data of cancer patients in the recovery period was selected for statistics. It was found that when S v > 1.5, in at least 80% of the consecutive breathing cycles, the rate of change of amplitude A rate is lower than 0.1 L / cycle on average, indicating a stable breathing pattern; while when S v < 1.5, more than 60% of the patients have an amplitude change of more than 0.2 L within 5 cycles, indicating an unstable breathing rhythm. Therefore, S v = 1.5 is used as the dividing line of stability. This value can effectively distinguish stable and fluctuating breathing patterns, and the data distribution supports this classification criterion. Finally, the amplitude change characteristic data are obtained.

[0116] The breathing pattern classification sub-module sets a breathing threshold based on the amplitude change characteristic data, classifies the current breathing pattern according to the breathing threshold, and obtains the breathing pattern classification result;

[0117] Based on the amplitude change characteristic data, combining the average value, rate of change and stability parameter of the amplitude change, set a breathing threshold, for example:

[0118] Stable breathing pattern: A rate < 0.1 L / cycle, S v> 1.5;

[0119] Fluctuating breathing pattern: 0.1 ≤ A rate <0.3 L / cycle, 1.2 ≤ S v ≤ 1.5;

[0120] Severe fluctuation pattern: A rate ≥ 0.3 L / cycle, S v < 1.2;

[0121] Basis for setting the breathing threshold: From the data analysis of different patients, it is found that when A rate <0.1 L / cycle, the amplitude change within the breathing cycle is about 0.1 L or less for about 85% of the cases, indicating that the rate of amplitude change is extremely low and can be considered a stable state; when 0.1 ≤ A rate <0.3 L / cycle, the amplitude fluctuations of about 70% of the patients are within this range, indicating that there is a certain fluctuation in breathing but no large-scale change; when A rate ≥ 0.3 L / cycle, the amplitude change range of more than 75% of the patients reaches 0.4 L or more, indicating that the breathing pattern shows severe fluctuations, usually associated with uneven air flow distribution or abnormal breathing rhythm. For the stability parameter S v , its classification standard is derived from the statistical analysis of patients' breathing data. When S v > 1.5, the degree of amplitude variation is low and the breathing pattern tends to be stable; when S v ≤ 1.5, the amplitude change of at least 60% of the patients reaches 0.2 L or more within 5 cycles, indicating that there are significant fluctuations in the breathing pattern.

[0122] Substitute the aforementioned calculation results into:

[0123] A rate = 0.05, S v = 1.65;

[0124] Meets the criteria for a stable breathing pattern, so the classification result is a stable breathing pattern, and the breathing pattern classification result is obtained.

[0125] Please refer to Figure 4 , the training rhythm dynamic adjustment module includes:

[0126] The inspiratory time deviation calculation sub-module calculates the time deviation of the inspiratory time compared to the individual mean based on the breathing pattern classification result, determines the change direction of the inspiratory time, and obtains the inspiratory time deviation data;

[0127] Based on the classification results of the breathing pattern, extract the historical breathing data of the individual, including the inspiration time data of at least 100 consecutive breathing cycles, calculate the average inspiration time of the individual, obtain the inspiration time of the current cycle, and calculate the time deviation of the current inspiration time compared to the individual average. If the time deviation is greater than the set threshold (such as 0.3 seconds), it is marked as an abnormal fluctuation. Further calculate the deviation trend of the past 5 cycles to judge the change direction of the inspiration time. When there are three consecutive cycles with the same direction deviation (such as consecutive increase or decrease), it is marked as a trend change. If there are more than 6 times with the same change direction in the past 10 cycles and the change amplitude is not less than 0.2 seconds, it is recorded as a stable trend. The threshold is set based on the mean standard deviation of the inspiration time in the past 100 cycles, and the calculation formula is as follows:

[0128]

[0129] If the calculated standard deviation σ I > 0.2s, it is considered that the inspiration time has a large volatility, and the sensitivity of trend judgment is increased (the trend judgment period is reduced). If σ I ≤ 0.2s, the 10-cycle trend judgment standard is maintained.

[0130] Finally, obtain the inspiration time deviation data.

[0131] Table 3.1 Example of inspiration time deviation calculation

[0132]

[0133] As shown in Table 3.1, the inspiration time in the first 3 cycles is higher than the average and continues to rise, while the 4th and 5th cycles show a downward trend. Therefore, the overall change trend of the current 5 cycles is judged as a fluctuating adjustment.

[0134] The training prompt signal setting sub-module is based on the inspiration time deviation data and uses the formula:

[0135]

[0136] Calculate the change rate T of the I / E ratio f , set the frequency and intensity of the training prompt signal, and obtain the training signal setting parameters. Among them, I / E t represents the I / E ratio of the t-th breath, I / E t - I / E t-1 represents the I / E ratio of the (t - 1)-th breath, and M represents the total number of cycles;

[0137] Based on the inspiratory time deviation data, calculate the change trend of the current I / E ratio. Select the I / E ratios of the last 10 cycles to calculate the change amplitude. Taking the historical mean value of the individual's I / E ratio (such as 1.2) as the benchmark, calculate the change amplitude of the past 10 cycles. If the change amplitude exceeds 20% of the benchmark value, then set the frequency and intensity of the training prompt signal. The frequency range is set to 0.5Hz - 2Hz, and the signal intensity range is 15 levels. This setting is based on the change trend of the I / E ratio above the standard deviation σ_{IE} of the individual. The formula is as follows:

[0138]

[0139] When the calculated σ IE > 0.15, it indicates that the individual's I / E ratio fluctuates greatly. Then the frequency adjustment amplitude is 0.3Hz, and the signal intensity is adjusted by 1 level. When σ IE ≤ 0.15, then the frequency adjustment amplitude is 0.1Hz, and the signal intensity is adjusted by 0.5 level. If the change trend is stable (the change range of the I / E ratio within the last 10 cycles is lower than 10% of σ_{IE}), then reduce the signal frequency to reduce interference.

[0140] Table 3.2 Training Prompt Signal Setting Parameters

[0141]

[0142] Substitute into the calculation:

[0143]

[0144] This result indicates that the current change rate of the I / E ratio is low. Therefore, the frequency and intensity of the training signal should be maintained at a low level to avoid excessive interference.

[0145] The training rhythm parameter adjustment sub-module analyzes the stability of the respiratory amplitude in consecutive cycles based on the training signal setting parameters, adjusts the intensity of the training prompt signal, and obtains the training rhythm adjustment parameters;

[0146] Based on the training signal setting parameters, analyze the stability of the respiratory amplitude in consecutive cycles, and calculate the standard deviation of the respiratory amplitude in the past 10 cycles. If the standard deviation exceeds 0.2, it is considered that the amplitude is unstable. This threshold is based on the standard deviation σ A of the amplitude in the past 100 cycles. The calculation formula is as follows:

[0147]

[0148] If σ A > 0.2, then enhance the training prompt signal (signal intensity +1) when the amplitude fluctuation range exceeds 10%. When σ AWhen it is ≤ 0.2 and the amplitude fluctuation range is below 5%, the training prompt signal (signal intensity -1) is reduced.

[0149] For example:

[0150] If the average value of the breathing amplitude in the past 10 cycles is 2.5, the standard deviation is 0.15, and the change range is 6%, the training signal intensity remains at the original value.

[0151] If the standard deviation rises to 0.25 and the change range reaches 12%, the training signal intensity increases by 1 level, and the amplitude change trend is recorded.

[0152] Finally, obtain the training rhythm adjustment parameter for subsequent training feedback adjustment.

[0153] Please refer to Figure 5 , the training effect feedback module includes:

[0154] The I / E ratio trend calculation sub-module, based on the training rhythm adjustment parameter, collects the I / E ratio change data of multiple consecutive cycles, calculates the change trend of the I / E ratio, and obtains the I / E ratio trend data;

[0155] Based on the training rhythm adjustment parameter, collect the I / E ratio change data of multiple consecutive cycles. For each breathing cycle, obtain the inhalation duration and exhalation duration, and calculate the I / E ratio. The inhalation duration and exhalation duration are detected by a flow sensor, and the specific values are shown in Table 4.1. For the data of multiple cycles, calculate their average value to measure the overall level of the I / E ratio, and further analyze the change direction of the I / E ratio in each cycle. By calculating the difference between the I / E ratios of adjacent cycles and counting the change trend, if the I / E ratio increases in multiple consecutive cycles, it is considered that the breathing rhythm tends to have a shorter inhalation duration, and vice versa, it tends to have a longer inhalation duration. Finally, obtain the I / E ratio trend data.

[0156] Table 4.1 I / E ratio calculation parameter table

[0157]

[0158] As shown in Table 4.1, the I / E ratio is calculated as the ratio of the inhalation duration to the exhalation duration. As the cycle increases, the I / E ratio decreases, reflecting the trend of shortening the inhalation duration. Finally, obtain the I / E ratio trend data for subsequent analysis and judgment.

[0159] The breathing amplitude change analysis sub-module, based on the I / E ratio trend data, collects the breathing amplitude change data, counts the breathing amplitude change trend of consecutive cycles, and uses the formula:

[0160]

[0161] Calculate the breathing amplitude skewness coefficient Vs When judging the change in respiratory amplitude when the I / E ratio rises, respiratory amplitude trend data is obtained. V t represents the amplitude of the t-th breath, represents the mean value of the amplitude, σ V represents the standard deviation of the amplitude, and m represents the total number of recorded breaths;

[0162] Based on the I / E ratio trend data, respiratory amplitude change data is collected. The amplitude of each respiratory cycle is measured by the amount of chest expansion. Specifically, an ultrasonic sensor is used to monitor the chest displacement, and the amplitude data of each cycle is collected, and the mean value and standard deviation are calculated, as shown in Table 4.2. By calculating the skewness coefficient of the amplitude data, it is judged whether there is an obvious deviation in the amplitude distribution.

[0163] Table 4.2 Respiratory Amplitude Parameter Table

[0164]

[0165]

[0166] As shown in Table 4.2, by calculating the amplitude skewness coefficient, it can be obtained that:

[0167]

[0168] The skewness coefficient indicates the symmetry of the data around the mean value. The closer the value is to 0, the more symmetric the distribution. Finally, the respiratory amplitude trend data is obtained, which can be used to adjust the subsequent training strategy.

[0169] The relaxation training guidance adjustment sub-module calculates the stability parameter of the respiratory rhythm based on the respiratory amplitude trend data, judges the respiratory regulation offset during the training process, sets the training guidance feedback coefficient, optimizes the dynamic adjustment range of the relaxation training, adjusts the feedback delay time of the training prompt signal, judges the training adaptability degree, and obtains the training effect feedback index;

[0170] Based on the respiratory amplitude trend data, calculate the stability parameter of the respiratory rhythm. The stability of the respiratory rhythm can be measured by the coefficient of variation of the amplitude, that is:

[0171]

[0172] Among them, Z v represents the respiratory stability parameter, σ V represents the amplitude standard deviation, represents the amplitude mean value. By calculating the coefficient of variation, it can be judged whether the respiration during the training process tends to be stable. The setting basis of this value lies in the relative dispersion degree of the respiratory amplitude. Usually, if the respiratory amplitude fluctuation of an individual is small, it means that the respiratory pattern tends to be stable. Otherwise, there are large fluctuations. Therefore, the following classification criteria are set:

[0173] If the coefficient of variation Z v <0.1, it is considered that the breathing is relatively stable, that is, the amplitude change of each breath is small, indicating that the individual's breathing rhythm is relatively uniform. For example, if the amplitudes of a certain patient in four consecutive cycles are 1.95 cm, 2.02 cm, 1.98 cm, and 2.00 cm respectively, then calculate the mean value Standard deviation σ V = 0.026 cm, and it is calculated that:

[0174]

[0175] This value is less than 0.1, indicating that the breathing pattern of this patient is relatively stable and there is no need to further adjust the frequency of the training prompt signal.

[0176] If the coefficient of variation 0.1 ≤ Z v <0.3, it is considered that there is a certain fluctuation, that is, the breathing amplitude of the individual changes within a certain range but is still controllable. For example, if the amplitudes of another patient in four consecutive cycles are 1.75 cm, 2.10 cm, 1.85 cm, and 2.05 cm respectively, then the mean value Standard deviation σ V = 0.138 cm, and it is calculated that:

[0177]

[0178] This value is between 0.1 and 0.3, indicating that there is a certain fluctuation in the breathing pattern of this patient. It is necessary to adjust the training prompt signal to make the training guidance strategy more in line with the individual situation and delay the time of training feedback to avoid excessive intervention.

[0179] If the coefficient of variation Z v ≥ 0.3, it is considered that the breathing pattern is unstable, that is, the breathing amplitude of the individual changes greatly and the rhythm fluctuates violently. It is necessary to strengthen the training guidance strategy. For example, if the amplitudes of a certain patient in four consecutive cycles are 1.60 cm, 2.30 cm, 1.70 cm, and 2.40 cm respectively, then the mean value Standard deviation σ V = 0.325 cm, and it is calculated that:

[0180]

[0181] This value is greater than 0.3, indicating that the breathing pattern of the patient is extremely unstable. It is necessary to adjust the training strategy, increase the intensity of the training prompt signal, and at the same time shorten the feedback delay time to more timely adjust the individual's breathing rhythm.

[0182] For the current data:

[0183]

[0184] It can be seen that the breathing during this training process is relatively stable. Therefore, the feedback delay time of the training prompt signal is adjusted, and the training guidance feedback coefficient is set to make the training strategy more in line with the individual situation, and finally the training effect feedback index is obtained.

[0185] Please refer to Figure 6 , the dynamic management module includes:

[0186] Based on the training effect feedback index, the pressure state recognition sub-module monitors the I / E ratio trend data and respiratory amplitude trend data during the rehabilitation period of cancer patients, calculates the current pressure state change amplitude, judges the real-time classification of the pressure state, and obtains the current pressure state parameters;

[0187] Based on the training effect feedback index, collect the I / E ratio trend data and respiratory amplitude trend data during the rehabilitation period of cancer patients. For the I / E ratio, first obtain the I / E ratio data of the patient within 10 consecutive respiratory cycles. The acquisition method of the I / E ratio is: collect the inspiratory duration and expiratory duration, and calculate the ratio. For example, the I / E ratios of a certain patient in 10 cycles are 1.2, 1.1, 1.3, 1.4, 1.2, 1.5, 1.6, 1.3, 1.4, 1.2 respectively. These data can form an I / E ratio sequence, as shown in Table 5.1.

[0188] Table 5.1 Current Monitoring Data Table of I / E Ratio

[0189]

[0190] Next, calculate the I / E ratio change trend. Calculate the change rate of adjacent two cycles and find the average value. For example, calculate the change rate of the 2nd cycle and the 1st cycle as:

[0191]

[0192] Calculate the change rate of all cycles in turn and find its average value to obtain the I / E ratio change trend parameter. For the respiratory amplitude trend data, first collect the maximum inspiratory airflow velocity of 10 consecutive cycles to reflect the change of respiratory amplitude. For example, the maximum inspiratory airflow velocity (unit: L / s) of a certain patient in 10 cycles is 0.85, 0.83, 0.87, 0.90, 0.85, 0.92, 0.95, 0.88, 0.90, 0.86, forming a data sequence, as shown in Table 5.2.

[0193] Table 5.2 Respiratory Amplitude Monitoring Data Table

[0194]

[0195] Using a similar method, calculate the amplitude change rate of consecutive cycles. For example:

[0196]

[0197] If the change rate of the I / E ratio exceeds ±10%, and at the same time the change rate of the respiratory amplitude exceeds ±5%, it is determined that there is a large fluctuation in the pressure state; otherwise, it is regarded as a stable state. The basis for setting this threshold is as follows: In a large amount of rehabilitation training data, when the change rate of the I / E ratio reaches more than 10%, it shows an obvious correlation with the change trend of the pressure state, and this change amplitude usually corresponds to the unstable respiratory regulation of the patient during the rehabilitation training. When the change rate of the respiratory amplitude exceeds 5%, it is often accompanied by abnormal respiratory rhythms. Therefore, this threshold is set to monitor abnormal fluctuations. If the change rate of the I / E ratio is lower than ±10% and the change rate of the respiratory amplitude is lower than ±5%, it is considered that the patient's respiratory state is relatively stable and there is no sudden change in physiological load. Finally, the current pressure state parameters are obtained.

[0198] The respiratory regulation strategy setting sub-module adjusts the relaxation training guidance signal based on the current pressure state parameters, using the formula:

[0199]

[0200] Calculate the individualized respiratory regulation intensity R t , set the respiratory rhythm guidance target, and obtain the respiratory regulation parameters. Among them, P t represents the pressure state parameter of the t-th cycle, P t -1 represents the pressure state parameter of the (t - 1)-th cycle, B t represents the respiratory rhythm target of the current cycle, and K represents the total number of cycles;

[0201] Based on the current pressure state parameters, adjust the relaxation training guidance signal, set a new training target according to the current I / E ratio trend, calculate using the formula, and obtain the following data. P t represents the pressure state parameter of the t-th cycle, which is calculated from the I / E ratio and respiratory amplitude data, and its mean value is set to 1.3; B t represents the respiratory rhythm target of the current cycle. Assume the current target is a respiratory rhythm of 6 breaths per minute; K is the number of data cycles, taking 10 cycles. Calculate:

[0202]

[0203] The calculated individualized breathing regulation intensity is 0.799. If this value exceeds 0.75, a new breathing rhythm target is set at 5.5 breaths per minute; otherwise, the original rhythm target of 6 breaths per minute is maintained. The basis for setting this threshold is as follows: By monitoring the patient's training status, when the individualized breathing regulation intensity approaches or exceeds 0.75, the patient's breathing rhythm shows significant fluctuations. Therefore, it is necessary to adjust the rhythm guidance target to enable the patient to gradually adapt to a more stable breathing pattern. When the value is below 0.75, it indicates that the patient's current rhythm adjustment is still within the adaptation range, so no additional adjustment is required to maintain the rhythm stability. Finally, the breathing regulation parameters are obtained.

[0204] Based on the breathing regulation parameters and for the current stress state, the rehabilitation stress regulation scheme generation sub-module conducts patient breathing regulation, adjusts the training rhythm guidance feedback, optimizes the relaxation training signal, and generates a rehabilitation stress dynamic regulation scheme;

[0205] Based on the breathing regulation parameters and for the current stress state, individualized breathing regulation is performed. First, the feedback adjustment step size is set. The step size depends on the change amplitude of the breathing rhythm target. Assume the step size formula is:

[0206]

[0207] where B new is the newly set breathing rhythm target, and B old is the old breathing rhythm target. Substitute the aforementioned data:

[0208]

[0209] If the step size exceeds 5%, the training rhythm guidance feedback is adjusted. For example, the guidance frequency of the relaxation training signal is increased; if the step size is below 5%, the current guidance method is maintained. The basis for setting this threshold is that when the step size exceeds 5%, the difficulty of the patient's breathing rhythm adjustment increases. If the guidance frequency of the training signal is not adjusted, it may lead to a decline in the patient's training adaptability. Therefore, it is necessary to increase the guidance frequency of the training signal, such as increasing the interval frequency of the audio prompt, to strengthen the sense of rhythm. When the step size is below 5%, it indicates that the patient is still within the adaptation range, so no additional adjustment is required to avoid interfering with the original training rhythm. The specific method of optimizing the relaxation training signal is as follows: If the breathing rhythm target decreases, the breathing guidance audio frequency is appropriately reduced to avoid causing discomfort to the patient due to excessive adjustment; if the target increases, the audio rhythm is appropriately increased to guide the patient to match the new rhythm. Finally, combining the aforementioned parameters, a rehabilitation stress dynamic regulation scheme is generated.

[0210] The above are only the preferred embodiments of the present invention, and are not intended to limit the present invention in other forms. Any person skilled in the art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A dynamic stress management system for cancer patients during the recovery period, characterized in that, The system includes: The pressure state recognition module obtains the breathing data of cancer patients during the recovery period, calculates the inhalation duration and exhalation duration, calculates and collects the I / E ratio of consecutive breathing cycles, determines the change direction of the pressure state and the current pressure state, and generates a pressure state classification result; The breathing pattern monitoring module calculates the single-breath amplitude based on the pressure state classification result, calculates the average value, change rate and stability parameter of the amplitude change, determines the amplitude fluctuation situation, classifies the breathing pattern, and generates a breathing pattern classification result; The training rhythm dynamic adjustment module determines the change direction of the inhalation time based on the breathing pattern classification result, sets an inhalation time guidance strategy, analyzes the stability of the breathing amplitude in consecutive cycles, adjusts the intensity of the training prompt signal, and generates a training rhythm adjustment parameter; The training effect feedback module counts the change trends of the I / E ratio and the breathing amplitude based on the training rhythm adjustment parameter, determines the change situation of the breathing amplitude when the I / E ratio rises, and generates a training effect feedback index; The dynamic management module analyzes the current pressure state during the recovery period in real time based on the training effect feedback index, conducts regulation for the current pressure state, and generates a dynamic regulation plan for the recovery pressure.

2. The dynamic stress management system for the recovery period of cancer patients according to claim 1, wherein The pressure state classification result includes the analysis result of the increase and decrease trend of the I / E ratio, the change situation of the inhalation duration, and the classification result of the pressure state category. The breathing pattern classification result includes the single-breath amplitude, the amplitude change rate, and the classification result of the breathing pattern category. The training rhythm adjustment parameter includes the inhalation time guidance strategy, the training prompt signal frequency, and the analysis result of the breathing amplitude stability. The training effect feedback index includes the analysis result of the change trend of the I / E ratio, the analysis result of the change trend of the breathing amplitude, and the relaxation training guidance strategy. The dynamic regulation plan for the recovery pressure includes the determination result of the patient's current pressure state, the breathing rhythm guidance target, and the breathing regulation measures.

3. The cancer patient convalescence stress dynamic management system according to claim 1, wherein The pressure state recognition module includes: The breathing data acquisition sub-module acquires the breathing data of cancer patients during the recovery period, records the inhalation start time, inhalation end time, exhalation start time, and exhalation end time, calculates the inhalation duration and exhalation duration, records the time parameters of consecutive breathing cycles, and establishes a breathing time parameter data set; The I / E ratio calculation sub-module calculates the I / E ratio of each cycle based on the breathing time parameter data set, analyzes the increase and decrease trend of the I / E ratio of adjacent cycles, compares the current inhalation duration with the previous breathing cycle, and uses the formula: Calculate the variation amplitude value of the inspiratory duration I / E Δ , combined with the increasing and decreasing trend of the I / E ratio, to obtain the I / E ratio variation trend data, where I t represents the current inspiratory duration, I t-1 represents the inspiratory duration of the previous cycle, and E t-1 represents the expiratory duration of the previous cycle; The pressure state classification sub-module calculates the average value of the I / E ratio based on the I / E ratio change trend data, sets a classification threshold, classifies the current pressure state according to the classification threshold, and obtains a pressure state classification result.

4. The dynamic stress management system for the recovery period of cancer patients according to claim 1, wherein The breathing pattern monitoring module includes: The breathing amplitude calculation sub-module obtains the maximum airflow velocity of a single breath based on the pressure state classification result, calculates the single-breath amplitude, records the amplitude data of consecutive breathing cycles, and establishes a breathing amplitude data set; The amplitude change analysis sub-module calculates according to the average value, change rate and stability parameter of the amplitude change based on the breathing amplitude data set, using the formula: Calculate the amplitude stability parameter S v , determine the amplitude fluctuation situation, and obtain the amplitude change characteristic data, where A t represents the amplitude of the t-th breath, and n represents the total number of respiratory cycles; The breathing pattern classification sub-module sets a breathing threshold based on the amplitude change feature data, classifies the current breathing pattern according to the breathing threshold, and obtains the breathing pattern classification result.

5. The dynamic stress management system for the recovery period of cancer patients according to claim 1, characterized in that, The training rhythm dynamic adjustment module includes: The inspiration time deviation calculation sub-module calculates the time deviation of the inspiration time compared to the individual mean based on the breathing pattern classification result, determines the change direction of the inspiration time, and obtains the inspiration time deviation data; The training prompt signal setting sub-module uses the formula based on the inspiration time deviation data: Calculate the change rate T of the I / E ratio f , set the frequency and intensity of the training prompt signal to obtain the training signal setting parameters, where I / E t represents the I / E ratio of the t-th breath, and I / E t -I / E t-1 represents the I / E ratio of the (t - 1)-th breath, and M represents the total number of cycles; The training rhythm parameter adjustment sub-module analyzes the breathing amplitude stability of consecutive cycles based on the parameters set by the training signal, adjusts the intensity of the training prompt signal, and obtains the training rhythm adjustment parameters.

6. The dynamic stress management system for the recovery period of cancer patients according to claim 1, wherein The training effect feedback module includes: The I / E ratio trend calculation sub-module collects the I / E ratio change data of consecutive multiple cycles based on the training rhythm adjustment parameters, calculates the change trend of the I / E ratio, and obtains the I / E ratio trend data; The breathing amplitude change analysis sub-module collects the breathing amplitude change data based on the I / E ratio trend data, statistically analyzes the breathing amplitude change trend of consecutive cycles, and uses the formula: Calculate the skewness coefficient V of the respiratory amplitude s , judge the change of the respiratory amplitude when the I / E ratio rises, and obtain the respiratory amplitude trend data, V t represents the amplitude of the t-th breath, represents the mean value of the amplitude, σ V represents the standard deviation of the amplitude, and m represents the total number of recorded breaths; The relaxation training guidance adjustment sub-module calculates the stability parameter of the breathing rhythm based on the breathing amplitude trend data, determines the breathing regulation deviation amount during the training process, adjusts the feedback delay time of the training prompt signal, determines the training adaptability degree, and obtains the training effect feedback index.

7. The dynamic stress management system for the recovery period of cancer patients according to claim 1, wherein The dynamic management module includes: The stress state recognition sub-module monitors the I / E ratio trend data and the breathing amplitude trend data during the recovery period of cancer patients based on the training effect feedback index, calculates the current stress state change range, determines the real-time classification of the stress state, and obtains the current stress state parameters; The breathing regulation strategy setting sub-module adjusts the relaxation training guidance signal based on the current stress state parameters, using the formula: Calculate the individualized respiratory regulation intensity R t , set the respiratory rhythm guidance target, and obtain the respiratory regulation parameters, where P t represents the pressure state parameter of the t-th cycle, and P t -1 represents the pressure state parameter of the (t-1)-th cycle, and B t represents the respiratory rhythm target of the current cycle, and K represents the total number of cycles; The rehabilitation stress regulation plan generation sub-module performs patient breathing regulation for the current stress state based on the breathing regulation parameters, adjusts the training rhythm guidance feedback, and generates a rehabilitation stress dynamic regulation plan.

Images