Thoracic surgery postoperative respiratory function rehabilitation training monitoring method and system based on internet of things

Abstract

The application provides a thoracic surgery postoperative respiratory function rehabilitation training monitoring method and system based on the Internet of Things, relates to the technical field of the Internet of Things, and collects initial respiratory physiological data of a thoracic surgery postoperative patient; generates abdominal breathing rehabilitation training guidance and pursed-lip breathing rehabilitation training guidance by using a multi-feature matching algorithm; collects training respiratory physiological data of the thoracic surgery postoperative patient in the process of carrying out respiratory function rehabilitation training under the abdominal breathing rehabilitation training guidance and the pursed-lip breathing rehabilitation training guidance, calculates a breathing amplitude; when the breathing amplitude is lower than a preset postoperative rehabilitation standard breathing amplitude, intervention feedback data is acquired; the abdominal breathing rehabilitation training guidance, the pursed-lip breathing rehabilitation training guidance, the verified training respiratory physiological data, and the intervention feedback data are subjected to correlation analysis to obtain a correlation analysis result; based on the result, a training progress file of the thoracic surgery postoperative patient is updated, and intelligent management of the patient's respiratory function rehabilitation training is realized.

Description

Technical Field

[0001] This application relates to the field of Internet of Things (IoT) technology, and in particular to an IoT-based method and system for monitoring and training respiratory function rehabilitation after thoracic surgery. Background Technology

[0002] Remote monitoring of respiratory function rehabilitation training for post-thoracic surgery patients in a home IoT environment has become an important need to improve the quality of post-operative recovery and reduce the incidence of complications. However, if rehabilitation training is not timely or standardized, it can lead to serious consequences such as lung infection and atelectasis. Therefore, there is an urgent need for an intelligent monitoring system that can continuously and accurately collect patients' respiratory physiological signals, dynamically adjust training programs based on individual recovery status, and provide feedback on training effects.

[0003] Among the existing mainstream solutions, there are respiratory rehabilitation monitoring systems based on the combination of wearable inertial sensors and wireless communication modules. However, these systems have some significant drawbacks. For example, relying solely on indirect measurements of body surface movement and single-dimensional respiratory parameter thresholds makes it difficult to accurately reflect the complex respiratory mechanics changes in postoperative patients. Furthermore, training recommendations lack detailed identification of the specific recovery stage of the patient, making it impossible to generate individualized and dynamic rehabilitation guidance content. Summary of the Invention

[0004] The purpose of this application is to provide an IoT-based method and system for monitoring and training respiratory function rehabilitation after thoracic surgery, in order to solve the problems in existing technologies such as the inability to accurately reflect the complex respiratory mechanics changes in postoperative patients and the inability to generate individualized and dynamic rehabilitation guidance content.

[0005] To address the aforementioned technical problems, in a first aspect, this application provides a method for monitoring postoperative respiratory function rehabilitation training in thoracic surgery based on the Internet of Things, including:

[0006] Collect initial respiratory physiological data of patients after thoracic surgery under natural breathing conditions;

[0007] Using a multi-feature matching algorithm, the initial respiratory physiological data and the corresponding recovery period data reference range in the preset standard parameter library are compared to determine the target recovery period of the patient after thoracic surgery, so as to generate abdominal breathing rehabilitation training guidance and pursed-lip breathing rehabilitation training guidance corresponding to the target recovery period.

[0008] Collect respiratory physiological data of the patients after thoracic surgery during respiratory function rehabilitation training under the guidance of abdominal breathing rehabilitation training and pursed-lip breathing rehabilitation training. Verify the respiratory physiological data and calculate the respiratory amplitude of the patients after thoracic surgery based on the verified respiratory physiological data.

[0009] When the respiratory amplitude is lower than the preset postoperative rehabilitation standard respiratory amplitude, a respiratory depth adjustment reminder is sent to the thoracic surgery postoperative patient via the Internet of Things, and the intervention feedback data of the thoracic surgery postoperative patient is obtained.

[0010] The abdominal breathing rehabilitation training guidelines, the pursed-lip breathing rehabilitation training guidelines, the verified training respiratory physiological data, and the intervention feedback data were correlated to obtain the correlation analysis results.

[0011] Based on the correlation analysis results, the training progress file of the postoperative thoracic surgery patient is updated to monitor the respiratory function rehabilitation training of the postoperative thoracic surgery patient.

[0012] Optionally, a multi-feature matching algorithm is used to compare the initial respiratory physiological data with the corresponding data reference range in a preset standard parameter library to determine the target recovery period for the patient after thoracic surgery. This allows for the generation of abdominal breathing rehabilitation training guidelines and pursed-lip breathing rehabilitation training guidelines corresponding to the target recovery period, including:

[0013] Initial chest expansion characteristics and initial respiratory rate characteristics were extracted from the initial respiratory physiological data.

[0014] Using a multi-feature matching algorithm, the initial chest expansion feature is compared with the chest expansion reference range for each recovery period in the preset standard parameter library to obtain the chest expansion feature comparison result. The initial respiratory rate feature is also compared with the respiratory rate reference range for each recovery period in the preset standard parameter library to obtain the respiratory rate feature comparison result. Each recovery period includes the early recovery period, the middle recovery period, and the late recovery period.

[0015] Based on the comparison results of the chest expansion feature, the first percentage of the data points of the initial chest expansion feature that are within the reference range of chest expansion in each recovery period is calculated, and the first percentage is used as the chest expansion matching degree. Based on the comparison results of the respiratory rate feature, the second percentage of the data points of the initial respiratory rate feature that are within the reference range of respiratory rate in each recovery period is calculated, and the second percentage is used as the respiratory rate matching degree.

[0016] The recovery period in which both the chest expansion and respiratory rate matching degree reach the preset matching threshold is selected as the target recovery period for patients after thoracic surgery. If there are multiple recovery periods that meet the preset matching thresholds for both chest expansion and respiratory rate matching degree, the recovery period with the highest average matching degree is selected as the target recovery period.

[0017] The target breathing characteristics corresponding to the target recovery period are retrieved from the preset table of breathing characteristics during the recovery period, and based on the target breathing characteristics, diaphragmatic breathing rehabilitation training guidance and pursed-lip breathing rehabilitation training guidance corresponding to the target recovery period are generated.

[0018] Optionally, a target breathing characteristic corresponding to the target recovery period is retrieved from a preset table of respiratory characteristics during the recovery period, and based on the target breathing characteristic, diaphragmatic breathing rehabilitation training guidance and pursed-lip breathing rehabilitation training guidance corresponding to the target recovery period are generated, including:

[0019] Extract the respiratory characteristics corresponding to the target recovery period from the preset table of respiratory characteristics during the recovery period. The respiratory characteristics include the form of respiratory manifestation and factors affecting respiratory function.

[0020] Based on the preoperative baseline information and surgical record information of patients after thoracic surgery, information on chest wall mobility sensitivity is added to the respiratory characteristics to obtain the target respiratory characteristics.

[0021] Based on the respiratory manifestations of the target breathing characteristics, the basic breathing depth and frequency parameters for abdominal breathing rehabilitation training are determined, and combined with the information on chest wall activity sensitivity, preliminary basic guidance for abdominal breathing training is generated.

[0022] Based on the respiratory manifestations of the target respiratory characteristics, determine the ratio of expiratory to inspiratory duration for pursed-lip breathing rehabilitation training, and combine this with respiratory resistance information related to the target respiratory characteristics to generate preliminary basic guidance for pursed-lip breathing training.

[0023] The basic guidelines for preliminary abdominal breathing training and the basic guidelines for preliminary pursed-lip breathing training are matched and calibrated with the training intensity requirements corresponding to the target recovery period to form guidelines for abdominal breathing rehabilitation training and guidelines for pursed-lip breathing rehabilitation training.

[0024] Optionally, the training respiratory physiological data is validated to calculate the respiratory amplitude of the post-thoracic surgery patient based on the validated training respiratory physiological data, including:

[0025] The training respiratory physiological data is transmitted to the edge computing node of the Internet of Things via the Bluetooth communication link of the Internet of Things, so as to perform timestamp integrity and consistency verification on the time series data of training chest expansion and training respiratory frequency in the training respiratory physiological data, and obtain the verified training respiratory physiological data.

[0026] Based on the preset recovery time corresponding to the target recovery period, the verified training respiratory physiological data is divided into multiple sub-training respiratory physiological data.

[0027] Based on the recovery period-related parameters in the preset standard parameter library, the standard respiratory amplitude-related parameters corresponding to the target recovery period are determined. Combined with the time series data of the training thoracic expansion in each sub-training respiratory physiological data, the average respiratory amplitude of the verified training respiratory physiological data is calculated as the respiratory amplitude of the post-thoracic surgery patient.

[0028] Optionally, the abdominal breathing rehabilitation training guidance, the pursed-lip breathing rehabilitation training guidance, the validated training respiratory physiological data, and the intervention feedback data are correlated to obtain correlation analysis results, including:

[0029] Based on the abdominal breathing rehabilitation training guidance, the pursed-lip breathing rehabilitation training guidance, the verified training respiratory physiological data, and the intervention feedback data, the dimensions of training guidance execution matching degree, respiratory physiological data change trend, and intervention feedback response status are determined.

[0030] The breathing depth training parameter is extracted from the abdominal breathing rehabilitation training guide. The breathing amplitude of each sub-training respiratory physiological data is compared with the breathing depth training parameter to obtain multiple depth difference values. The breathing frequency training parameter is extracted from the pursed-lip breathing rehabilitation training guide. The training breathing frequency of each sub-training respiratory physiological data is compared with the breathing frequency training parameter to obtain multiple frequency difference values.

[0031] Based on the depth difference value and the frequency difference value, the training guidance execution matching degree of each sub-training respiratory physiological data is calculated;

[0032] A time-series change analysis was performed on the respiratory amplitude and respiratory frequency of each sub-training respiratory physiological data to obtain the trend of respiratory physiological data changes.

[0033] The sub-training respiratory physiological data and intervention feedback data are correlated and processed to obtain the intervention feedback response analysis results;

[0034] The training guidance execution matching degree, the respiratory physiological data change trend results, and the intervention feedback response analysis results are integrated to form a correlation analysis result.

[0035] Optionally, a time-series variation analysis is performed on the respiratory amplitude and training respiratory frequency of each sub-training respiratory physiological data to obtain the results of the respiratory physiological data change trends, including:

[0036] Based on the timestamps of each sub-training respiratory physiological data, the respiratory amplitude and training respiratory frequency of all sub-training respiratory physiological data are arranged separately to form a respiratory amplitude sequence and a training respiratory frequency sequence.

[0037] Adjacent respiratory amplitudes in the respiratory amplitude sequence are compared to determine the direction and rate of change of respiratory amplitude. The difference between the maximum and minimum respiratory amplitudes in the respiratory amplitude sequence is taken as the range of respiratory amplitude fluctuation. The direction of change of respiratory amplitude includes the direction of increase and the direction of decrease of respiratory amplitude.

[0038] Adjacent training respiratory frequencies in the training respiratory frequency sequence are compared to determine the direction and rate of change of respiratory frequency. The frequency difference between the maximum and minimum respiratory frequencies in the training respiratory frequency sequence is taken as the range of respiratory frequency fluctuation. The direction of change of respiratory frequency includes the direction of increase and the direction of decrease of respiratory frequency.

[0039] By integrating the direction of respiratory amplitude change, the range of respiratory amplitude fluctuation, the rate of change of respiratory amplitude, the range of respiratory frequency fluctuation, and the rate of change of respiratory frequency, the trend of respiratory physiological data change is obtained.

[0040] Optionally, the sub-training respiratory physiological data and intervention feedback data are correlated to obtain intervention feedback response analysis results, including:

[0041] Based on the timestamps of each sub-training respiratory physiological data, determine the target sub-training respiratory physiological data corresponding to the sending time of the respiratory depth adjustment reminder;

[0042] Establish a matching relationship between the sending time of the breathing depth adjustment reminder, the respiratory physiological data of the target sub-training, and the adjusted breathing amplitude and adjustment response time in the intervention feedback data;

[0043] Calculate the difference between the adjusted respiratory amplitude and the respiratory amplitude in the corresponding target sub-training respiratory physiological data, and use the difference as the respiratory amplitude improvement value;

[0044] Calculate the average value of all respiratory amplitude improvement values ​​within the adjustment response time, and aggregate the average value and the distribution of respiratory amplitude improvement values ​​within the adjustment response time to obtain the correlation analysis conclusion;

[0045] The matching relationship, the improvement value of respiratory amplitude, and the conclusion of the correlation analysis are integrated to obtain the intervention feedback response analysis results.

[0046] Secondly, this application provides an Internet of Things-based postoperative respiratory function rehabilitation training monitoring system for thoracic surgery, including:

[0047] The data acquisition module is used to collect initial respiratory physiological data of patients after thoracic surgery under natural breathing conditions.

[0048] The comparison module is used to compare the initial respiratory physiological data with the data reference range of the corresponding recovery period in the preset standard parameter library using a multi-feature matching algorithm to determine the target recovery period of the patient after thoracic surgery, so as to generate abdominal breathing rehabilitation training guidance and pursed-lip breathing rehabilitation training guidance corresponding to the target recovery period.

[0049] The verification module is used to collect the respiratory physiological data of the post-thoracic surgery patient during the respiratory function rehabilitation training under the guidance of abdominal breathing rehabilitation training and the guidance of pursed-lip breathing rehabilitation training, verify the training respiratory physiological data, and calculate the respiratory amplitude of the post-thoracic surgery patient based on the verified training respiratory physiological data.

[0050] The sending module is used to send a breathing depth adjustment reminder to the thoracic surgery postoperative patient via the Internet of Things when the breathing amplitude is lower than the preset postoperative rehabilitation standard breathing amplitude, and to obtain the intervention feedback data of the thoracic surgery postoperative patient;

[0051] The analysis module performs correlation analysis on the abdominal breathing rehabilitation training guidance, the pursed-lip breathing rehabilitation training guidance, the verified training respiratory physiological data, and the intervention feedback data to obtain the correlation analysis results.

[0052] The update module is used to update the training progress file of the postoperative thoracic surgery patient based on the correlation analysis results, so as to realize the monitoring of the respiratory function rehabilitation training of the postoperative thoracic surgery patient.

[0053] Thirdly, this application provides an electronic device, comprising:

[0054] Memory, used to store computer programs;

[0055] A processor is configured to execute the computer program to implement the steps of the IoT-based postoperative respiratory function rehabilitation training monitoring method for thoracic surgery as described in the first aspect above.

[0056] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the steps of the IoT-based postoperative respiratory function rehabilitation training monitoring method for thoracic surgery described in the first aspect above.

[0057] The IoT-based monitoring method for postoperative respiratory function rehabilitation training in thoracic surgery provided in this application collects initial respiratory physiological data of postoperative thoracic surgery patients under natural breathing conditions; using a multi-feature matching algorithm, the initial respiratory physiological data is compared with the data reference range corresponding to the recovery period in a preset standard parameter library to determine the target recovery period of the postoperative thoracic surgery patient, thereby generating abdominal breathing rehabilitation training guidance and pursed-lip breathing rehabilitation training guidance corresponding to the target recovery period; and the method collects training respiratory physiological data of the postoperative thoracic surgery patient during respiratory function rehabilitation training under the abdominal breathing rehabilitation training guidance and the pursed-lip breathing rehabilitation training guidance, and analyzes the training respiratory... Physiological data is validated, and the respiratory amplitude of the postoperative thoracic surgery patient is calculated based on the validated training respiratory physiological data. When the respiratory amplitude is lower than the preset postoperative rehabilitation standard respiratory amplitude, a respiratory depth adjustment reminder is sent to the postoperative thoracic surgery patient via the Internet of Things, and the intervention feedback data of the postoperative thoracic surgery patient is obtained. The abdominal breathing rehabilitation training guidance, the pursed-lip breathing rehabilitation training guidance, the validated training respiratory physiological data, and the intervention feedback data are correlated and analyzed to obtain the correlation analysis results. Based on the correlation analysis results, the training progress file of the postoperative thoracic surgery patient is updated to realize the monitoring of the respiratory function rehabilitation training of the postoperative thoracic surgery patient. By collecting the initial respiratory physiological data of the postoperative thoracic surgery patient in a natural breathing state, an objective basis is provided for the subsequent individualized rehabilitation program. It realizes the refined identification of the patient's recovery stage, improves the scientificity and individual fit of the stage assessment, enhances the pertinence and clinical rationality of the training content, ensures the accuracy and data reliability of the subsequent respiratory amplitude calculation, and lays the foundation for quantitative evaluation of training effect. It strengthens guidance and interactive support during training execution; it achieves the fusion and dynamic tracking of multi-source information, improving the systematicness and continuity of remote monitoring. Furthermore, it conducts in-depth fusion analysis of abdominal breathing rehabilitation training guidance, pursed-lip breathing rehabilitation training guidance, verified training respiratory physiological data, and intervention feedback data from three dimensions: training guidance execution matching degree, respiratory physiological data change trend, and intervention feedback response. This solves the problem of one-sided rehabilitation assessment caused by the lack of multi-dimensional dynamic correlation in existing solutions, overcomes the misjudgment and intervention lag caused by relying solely on instantaneous physiological threshold judgments, improves the intelligence level and clinical practicality of remote rehabilitation monitoring, and provides key technical support for achieving truly personalized, closed-loop home respiratory rehabilitation management. Attached Figure Description

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

[0059] Figure 1 A flowchart illustrating the IoT-based postoperative respiratory function rehabilitation training monitoring method for thoracic surgery provided in this application embodiment;

[0060] Figure 2 A schematic diagram illustrating a specific implementation of the IoT-based postoperative respiratory function rehabilitation training and monitoring method for thoracic surgery provided in this application embodiment;

[0061] Figure 3 This is a schematic diagram of the structure of the IoT-based postoperative respiratory function rehabilitation training and monitoring system for thoracic surgery provided in an embodiment of this application. Detailed Implementation

[0062] Addressing the urgent need for precise and intelligent remote monitoring of respiratory function rehabilitation training for post-thoracic surgery patients in a home IoT environment, existing solutions rely solely on indirect measurements of body surface movement and single respiratory parameter threshold judgments. These methods fail to comprehensively depict the complex respiratory mechanics of post-operative patients, and the training programs lack personalization and adaptability. This application proposes an IoT-based method and system for monitoring post-thoracic surgery respiratory function rehabilitation training. By collecting initial respiratory physiological data from patients in their natural breathing state, and comparing this data with a pre-set standard parameter library using a multi-feature matching algorithm, it generates training guidance for diaphragmatic breathing and pursed-lip breathing, enabling individualized customization of the rehabilitation program. Through multi-dimensional correlation analysis of the training guidance, validated physiological data, and intervention feedback, it achieves intelligent management of the entire process from state identification, guidance generation, process monitoring to effect evaluation. This overcomes the limitations of existing solutions, such as crude stage identification, a single feedback mechanism, and superficial data utilization.

[0063] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are merely some embodiments of the present application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0064] The core of this application is to provide an IoT-based method for monitoring and training respiratory function rehabilitation after thoracic surgery. A flowchart of one specific implementation is shown below. Figure 1 As shown, the method includes:

[0065] Step 101: Collect initial respiratory physiological data of patients after thoracic surgery under natural breathing conditions.

[0066] In this step, initial respiratory physiological data refers to physiological indicators that reflect the respiratory function status of patients after thoracic surgery, collected by professional sensing devices under natural breathing conditions without any respiratory function rehabilitation training.

[0067] In this embodiment of the application, the patient is first placed in a quiet environment without breathing training after thoracic surgery to ensure that the patient maintains a natural breathing state. Then, the patient's physiological indicators during natural breathing are continuously collected through a respiratory sensing device connected to the Internet of Things. These indicators are the initial respiratory physiological data.

[0068] Step 102: Using a multi-feature matching algorithm, the initial respiratory physiological data and the corresponding recovery period data reference range in the preset standard parameter library are compared to determine the target recovery period of the patient after thoracic surgery, so as to generate abdominal breathing rehabilitation training guidance and pursed-lip breathing rehabilitation training guidance corresponding to the target recovery period.

[0069] In this step, the multi-feature matching algorithm refers to an algorithm that extracts multiple key feature indicators from the initial respiratory physiological data, compares these feature indicators one by one with the corresponding feature indicator reference ranges in the preset standard parameter library for the recovery period, calculates the feature matching degree, and thus accurately determines the patient's current rehabilitation stage. The preset standard parameter library refers to a library established in advance based on a large amount of clinical rehabilitation data from thoracic surgery patients. The target recovery period refers to the specific rehabilitation stage that the thoracic surgery patient is currently in, determined by comparing the initial respiratory physiological data with the data reference ranges in the preset standard parameter library using the multi-feature matching algorithm. The abdominal breathing rehabilitation training guidance refers to a plan developed based on the patient's target recovery period, guiding the patient to perform breathing training with abdominal movements as the main focus. The pursed-lip breathing rehabilitation training guidance refers to a plan developed based on the patient's target recovery period, guiding the patient to perform breathing training by controlling the exhalation rate through pursed lips.

[0070] Step 103: Collect respiratory physiological data of the post-thoracic surgery patient during respiratory function rehabilitation training under the guidance of abdominal breathing rehabilitation training and pursed-lip breathing rehabilitation training. Verify the respiratory physiological data and calculate the respiratory amplitude of the post-thoracic surgery patient based on the verified respiratory physiological data.

[0071] In this step, training respiratory physiological data refers to respiratory physiological index data collected by sensing devices during respiratory function rehabilitation training for post-thoracic surgery patients, following the guidelines for abdominal breathing rehabilitation training and pursed-lip breathing rehabilitation training. Verified training respiratory physiological data refers to respiratory physiological index data that has been processed to ensure data integrity and accuracy after removing abnormal data and supplementing missing data. Respiratory amplitude refers to an index calculated based on the verified training respiratory physiological data, reflecting the range of chest and abdominal movement during training, and is used to assess respiratory depth.

[0072] Step 104: When the respiratory amplitude is lower than the preset postoperative rehabilitation standard respiratory amplitude, a respiratory depth adjustment reminder is sent to the postoperative thoracic surgery patient via the Internet of Things, and the intervention feedback data of the postoperative thoracic surgery patient is obtained.

[0073] In this step, the preset postoperative rehabilitation standard respiratory amplitude refers to the baseline value of respiratory amplitude set in advance according to the rehabilitation goals of different recovery stages after thoracic surgery, which is used to judge whether the patient's respiratory function rehabilitation training effect has met the standard; the Internet of Things (IoT) refers to a network system that connects the data acquisition terminal, data processing terminal and user interaction terminal through information sensing devices to realize data transmission and device interconnection; the respiratory depth adjustment reminder refers to the information sent to the patient through the IoT when the patient's respiratory amplitude is lower than the preset postoperative rehabilitation standard respiratory amplitude, prompting the patient to adjust the respiratory depth to meet the standard requirements; the intervention feedback data refers to the information fed back by the patient through the smart terminal after receiving the respiratory depth adjustment reminder, such as whether the breathing has been adjusted according to the reminder and the subjective feeling after the adjustment.

[0074] In this embodiment, the patient's respiratory amplitude is compared with a preset postoperative rehabilitation standard respiratory amplitude, which is determined based on the patient's target recovery period. When the patient's respiratory amplitude is lower than the preset standard, the data processing terminal sends a respiratory depth adjustment reminder to the patient's smart terminal via the Internet of Things. The reminder includes the current respiratory amplitude and specific adjustment methods. After receiving the reminder, the patient adjusts their breathing according to the prompts and provides feedback through the smart terminal's interactive interface. The information collected by the system constitutes the intervention feedback data.

[0075] Step 105: Perform correlation analysis on the abdominal breathing rehabilitation training guidance, the pursed-lip breathing rehabilitation training guidance, the verified training respiratory physiological data, and the intervention feedback data to obtain the correlation analysis results.

[0076] In this step, the correlation analysis results refer to the comprehensive analysis of the abdominal breathing rehabilitation training guidance, pursed-lip breathing rehabilitation training guidance, verified training respiratory physiological data, and intervention feedback data. After mining the correlation between the data, the analytical conclusions about the training effect, the suitability of the guidance plan, and the effectiveness of the intervention are drawn.

[0077] Step 106: Based on the correlation analysis results, update the training progress file of the post-thoracic surgery patient to monitor the respiratory function rehabilitation training of the post-thoracic surgery patient.

[0078] In this step, the training progress record refers to the record of the patient's basic information, target recovery period, abdominal breathing rehabilitation training guidance, pursed-lip breathing rehabilitation training guidance, verified training respiratory physiological data, intervention feedback data, and correlation analysis results after thoracic surgery. It is used to continuously track the patient's rehabilitation training progress and evaluate the rehabilitation effect.

[0079] In this embodiment, based on the correlation analysis results, key information of this training is supplemented and recorded in the patient's training progress file, including the target recovery period corresponding to this training, the abdominal breathing and pursed-lip breathing rehabilitation training guidance content used, the verified training respiratory physiological data, intervention feedback data, and correlation analysis conclusions; at the same time, the rehabilitation recommendations in the file are updated according to the correlation analysis results. By updating the training progress file, the recording and tracking of each rehabilitation training process of the patient can be realized. Combined with historical training data, the patient's rehabilitation progress can be dynamically evaluated, thereby realizing the whole process monitoring of respiratory function rehabilitation training for patients after thoracic surgery.

[0080] This application demonstrates the ability to identify and intervene in insufficient breathing depth during training, accurately track rehabilitation progress, improve the pertinence and effectiveness of respiratory function rehabilitation training, and reduce the risk of postoperative respiratory dysfunction.

[0081] This application provides a specific embodiment, such as Figure 2 As shown, step 102 involves using a multi-feature matching algorithm to compare the initial respiratory physiological data with the corresponding recovery period data reference range in a preset standard parameter library to determine the target recovery period for the patient after thoracic surgery. This process generates abdominal breathing rehabilitation training guidelines and pursed-lip breathing rehabilitation training guidelines corresponding to the target recovery period. Specifically, this includes the following steps:

[0082] Step 201: Extract the initial chest expansion features and initial respiratory rate features from the initial respiratory physiological data.

[0083] In this step, the initial chest expansion feature refers to the characteristic index extracted from the initial respiratory physiological data that reflects the size of the chest expansion range of the patient under natural breathing conditions after thoracic surgery; the initial respiratory rate feature refers to the characteristic index extracted from the initial respiratory physiological data that reflects the number of breaths per unit time of the patient under natural breathing conditions after thoracic surgery.

[0084] In this embodiment of the application, raw data related to thoracic expansion are selected from the collected initial respiratory physiological data. The initial thoracic expansion characteristics are obtained by calculating the difference between the maximum and minimum thoracic expansion values ​​within a natural respiratory cycle. At the same time, raw data related to respiratory rate are selected. The initial respiratory rate characteristics are obtained by counting the number of complete cycles of airflow fluctuation per unit time.

[0085] Step 202: Using a multi-feature matching algorithm, the initial thoracic expansion feature is compared with the thoracic expansion reference range for each recovery period in the preset standard parameter library to obtain the thoracic expansion feature comparison result. The initial respiratory rate feature is compared with the respiratory rate reference range for each recovery period in the preset standard parameter library to obtain the respiratory rate feature comparison result. Each recovery period includes the early recovery period, the middle recovery period, and the late recovery period.

[0086] In this step, the reference range for chest expansion refers to the numerical range set in the preset standard parameter library for each recovery period, which conforms to the normal chest expansion level of patients after thoracic surgery at that stage; the respiratory rate characteristic comparison result refers to the judgment result of whether the initial respiratory rate characteristic is within the corresponding reference range after comparing it with the respiratory rate reference range for each recovery period in the preset standard parameter library; the early recovery period refers to the initial stage of recovery for patients after thoracic surgery, in which patients' respiratory function is relatively weak, and chest expansion and respiratory rate have not yet returned to normal levels; the intermediate recovery period refers to the middle stage of recovery for patients after thoracic surgery, in which patients' respiratory function gradually improves, and chest expansion and respiratory rate approach normal levels; the late recovery period refers to the late stage of recovery for patients after thoracic surgery, in which patients' respiratory function is close to normal, and chest expansion and respiratory rate have basically reached normal levels.

[0087] In this embodiment, a preset standard parameter library is first invoked to obtain the reference ranges for chest expansion and respiratory rate corresponding to the early, middle, and late recovery periods, respectively. Then, a multi-feature matching algorithm is started to compare the initial chest expansion feature with the chest expansion reference ranges for the three recovery periods one by one, and the results of each comparison are recorded to form a chest expansion feature comparison result. At the same time, the initial respiratory rate feature is compared with the respiratory rate reference ranges for the three recovery periods one by one, and the results are also recorded to form a respiratory rate feature comparison result.

[0088] Step 203: Based on the comparison results of the thoracic expansion feature, calculate the first percentage of the data points of the initial thoracic expansion feature that are within the reference range of thoracic expansion in each recovery period, and use the first percentage as the thoracic expansion matching degree. Based on the comparison results of the respiratory rate feature, calculate the second percentage of the data points of the initial respiratory rate feature that are within the reference range of respiratory rate in each recovery period, and use the second percentage as the respiratory rate matching degree.

[0089] In this step, the first percentage refers to the ratio of the number of data points of the initial chest expansion feature that fall within the reference range of chest expansion in a certain recovery period to the total number of data points of the initial chest expansion feature during the comparison of chest expansion features; the chest expansion matching degree refers to the degree of fit between the initial chest expansion feature and the reference range of chest expansion in a certain recovery period, expressed by the first percentage; the second percentage refers to the ratio of the number of data points of the initial respiratory rate feature that fall within the reference range of respiratory rate in a certain recovery period to the total number of data points of the initial respiratory rate feature during the comparison of respiratory rate features; the respiratory rate matching degree refers to the degree of fit between the initial respiratory rate feature and the reference range of respiratory rate in a certain recovery period, expressed by the second percentage.

[0090] In this embodiment, regarding the comparison results of the thoracic expansion feature, the total number of data points of the initial thoracic expansion feature is first counted, and then the number of data points of the feature that fall within the reference range of thoracic expansion in the early recovery period, the middle recovery period, and the late recovery period is counted separately. The calculation formula is: First quantity percentage = Number of data points of the initial thoracic expansion feature that fall within the reference range of the middle thoracic expansion period ÷ Total number of data points of the initial thoracic expansion feature. This first quantity percentage is directly used as the matching degree between the initial thoracic expansion feature and the thoracic expansion in the middle recovery period. Regarding the comparison results of the respiratory rate feature, the calculation formula is: Second quantity percentage = Number of data points of the initial respiratory rate feature that fall within the reference range of the respiratory rate in a certain recovery period ÷ Total number of data points of the initial respiratory rate feature. This second quantity percentage is used as the matching degree between the initial respiratory rate feature and the respiratory rate in the corresponding recovery period. Finally, the matching degree of thoracic expansion and the matching degree of respiratory rate are obtained for each recovery period.

[0091] Step 204: Select the recovery period in which both the chest expansion matching degree and respiratory rate matching degree reach the preset matching threshold as the target recovery period for patients after thoracic surgery. If there are multiple recovery periods that meet the preset matching thresholds for both chest expansion matching degree and respiratory rate matching degree, select the recovery period with the highest average matching degree as the target recovery period.

[0092] In this step, the preset matching threshold refers to the minimum matching value set in advance to determine whether the initial respiratory physiological data matches the reference range of a certain recovery period data; the mean matching value refers to the value obtained by adding the matching degree of chest expansion and the matching degree of respiratory rate corresponding to each recovery period that meets the conditions when the matching degree of chest expansion and the matching degree of respiratory rate of multiple recovery periods both reach the preset matching threshold.

[0093] In this embodiment, a preset matching threshold is first retrieved, and the matching degree of chest expansion and respiratory rate of each recovery period are compared with the threshold. If there is only one recovery period where the matching degree of chest expansion and respiratory rate are both greater than or equal to the preset matching threshold, then the recovery period is directly determined as the target recovery period. If there are two or more recovery periods that meet the conditions, the average matching degree of each recovery period that meets the conditions is calculated. The calculation formula is: average matching degree = (chest expansion matching degree + respiratory rate matching degree) ÷ 2. The intermediate recovery period with the highest average matching degree is selected as the target recovery period.

[0094] Step 205: Retrieve the target breathing characteristics corresponding to the target recovery period from the preset recovery period breathing characteristics correspondence table, so as to generate abdominal breathing rehabilitation training guidance and pursed-lip breathing rehabilitation training guidance corresponding to the target recovery period based on the target breathing characteristics.

[0095] In this step, the preset recovery period respiratory characteristics correspondence table refers to a pre-established table that stores the respiratory function characteristics corresponding to the early recovery period, the middle recovery period, and the late recovery period respectively; the target respiratory characteristics refer to the respiratory function characteristics that are uniquely corresponding to the target recovery period and retrieved from the preset recovery period respiratory characteristics correspondence table, which are used to guide the generation of an appropriate rehabilitation training program.

[0096] The embodiments of this application address the shortcomings of existing technologies, such as vague judgment of the recovery period and strong universality of rehabilitation guidance.

[0097] For example, the initial respiratory physiological data of patient A after thoracic surgery has been collected. From this data, the initial chest expansion is extracted as 2.5 cm, and the initial respiratory rate is 18 breaths / min. A pre-defined standard parameter library is used to obtain reference ranges: early recovery period (chest expansion 1.0-2.0 cm, respiratory rate 20-24 breaths / min), mid-recovery period (chest expansion 2.0-3.0 cm, respiratory rate 16-20 breaths / min), and late recovery period (chest expansion 3.0-4.0 cm, respiratory rate 12-16 breaths / min). After comparison using a multi-feature matching algorithm, the chest expansion feature comparison results are: early stage not matching, mid-stage matching, and late stage not matching; the respiratory rate feature comparison results are: early stage not matching, mid-stage matching, and late stage not matching. The initial chest expansion is then statistically analyzed. There are 300 feature data points in total, of which 255 are within the mid-term reference range. The calculation formula is: First quantity percentage = 255 ÷ 300 = 85%, which is the mid-term chest expansion matching degree. There are 300 initial respiratory rate feature data points in total, of which 246 are within the mid-term reference range. The calculation formula is: Second quantity percentage = 246 ÷ 300 = 82%, which is the mid-term respiratory rate matching degree. The preset matching threshold is 80%. If both mid-term matching degrees meet the standard and there are no other matching conditions, the target recovery period is determined as the mid-term recovery period. The target respiratory characteristics of the mid-term recovery period are retrieved from the preset recovery period respiratory characteristics correspondence table. Based on these characteristics, abdominal breathing rehabilitation training guidance is generated, with a breathing depth of 2 to 3 cm and a frequency of 16 to 18 breaths / min. Avoid excessive force and pursed-lip breathing. The rehabilitation training guidance is to inhale for 2 seconds and exhale with pursed lips for 4 seconds.

[0098] This application provides a specific embodiment. Step 205 involves retrieving the target breathing characteristics corresponding to the target recovery period from a preset table of respiratory characteristics during the recovery period, and generating abdominal breathing rehabilitation training guidance and pursed-lip breathing rehabilitation training guidance corresponding to the target recovery period based on the target breathing characteristics. The specific steps include:

[0099] Step 211: Extract the respiratory characteristics corresponding to the target recovery period from the preset recovery period respiratory characteristics correspondence table. The respiratory characteristics include respiratory manifestations and respiratory influencing factors.

[0100] In this step, respiratory manifestations refer to the external characteristics of respiratory function in post-thoracic surgery patients during the target recovery period, such as the stability or trend of respiratory depth and frequency; respiratory influencing factors refer to the key factors affecting respiratory function in post-thoracic surgery patients during the target recovery period.

[0101] In this embodiment of the application, access to a preset table of respiratory characteristics during the recovery period is enabled. Based on the target recovery period, an entry that uniquely corresponds to the target recovery period is searched in the table, and the corresponding respiratory manifestations and respiratory influencing factors are read and extracted from the entry.

[0102] Step 212: Based on the patient's preoperative baseline information and surgical record information after thoracic surgery, supplement the respiratory characteristics with information on chest wall movement sensitivity to obtain the target respiratory characteristics.

[0103] In this step, preoperative basic information refers to the basic health data of the patient before thoracic surgery; surgical record information refers to the document that records key information of the patient's surgical process after thoracic surgery; and chest wall movement sensitivity information refers to information reflecting the sensitivity of different chest wall regions to movement stimuli after thoracic surgery.

[0104] In this embodiment, a preset patient medical information database is invoked to retrieve the preoperative basic information and surgical record information of patients after thoracic surgery. The surgical incision location information in the surgical record information is examined in detail. If the surgical record information shows that the surgical incision location is on the left side of the thoracic wall, the respiratory influencing factors in the respiratory characteristics are supplemented with information on the sensitivity of left thoracic wall movement, which indicates that pain is more likely to occur when the left thoracic wall moves and the range of movement needs to be controlled. If the surgical incision location is on the right side of the thoracic wall, information on the sensitivity of right thoracic wall movement, which indicates that pain is more likely to occur when the right thoracic wall moves and the range of movement needs to be controlled, is supplemented. After the supplementation is completed, the original respiratory characteristics are combined with the newly added thoracic wall movement sensitivity information to form the target respiratory characteristics.

[0105] Step 213: Based on the breathing characteristics of the target breathing pattern, determine the basic breathing depth and frequency parameters for abdominal breathing rehabilitation training, and generate preliminary basic guidance for abdominal breathing training by combining the chest wall activity sensitivity information.

[0106] In this step, the basic breathing depth refers to the baseline value of breathing depth set in abdominal breathing rehabilitation training that conforms to the target recovery period respiratory function level; the frequency parameter refers to the baseline value of breathing frequency set in abdominal breathing rehabilitation training that conforms to the target recovery period respiratory function level; and the preliminary abdominal breathing training basic guidance refers to the preliminary framework of the abdominal breathing rehabilitation training program based on the breathing performance and chest wall activity sensitivity information of the target breathing characteristics.

[0107] In this embodiment, the respiratory manifestations of the target breathing characteristics are analyzed, and the basic breathing depth and frequency parameters for abdominal breathing rehabilitation training are determined based on these manifestations. At the same time, the chest wall activity sensitivity information in the target breathing characteristics is combined with the training precautions on the basis of the basic breathing depth and frequency parameters. The determined basic breathing depth and frequency parameters and the supplementary precautions are integrated to form a preliminary basic guide for abdominal breathing training.

[0108] Step 214: Based on the respiratory manifestation of the target breathing characteristics, determine the ratio parameter of expiratory duration to inspiratory duration for pursed-lip breathing rehabilitation training, and combine it with the respiratory resistance information of the target breathing characteristics to generate preliminary basic guidance for pursed-lip breathing training.

[0109] In this step, expiratory duration refers to the duration of exhalation set in pursed-lip breathing rehabilitation training; inspiratory duration refers to the duration of inspiratory duration set in pursed-lip breathing rehabilitation training; the proportional parameter refers to the ratio of expiratory duration to inspiratory duration in pursed-lip breathing rehabilitation training; respiratory resistance related information refers to the characteristic information of airflow resistance during the breathing process of thoracic surgery postoperative patients during the target recovery period, such as whether the airway resistance is too high; preliminary basic guidance for pursed-lip breathing training refers to the preliminary framework of the pursed-lip breathing rehabilitation training program based on the respiratory manifestations and respiratory resistance related information of the target breathing characteristics.

[0110] In this embodiment, based on the respiratory manifestation of the target respiratory characteristics, the ratio parameter of expiratory duration to inspiratory duration for pursed-lip breathing rehabilitation training is determined; at the same time, the respiratory resistance-related information in the target respiratory characteristics is analyzed, and operational requirements are supplemented based on the ratio parameter; the determined expiratory duration, inspiratory duration, ratio parameter and supplementary operational requirements are integrated to form a preliminary basic guide for pursed-lip breathing training, ensuring that the guide can specifically improve respiratory resistance problems during the recovery period and improve expiratory stability.

[0111] Step 215: Match and calibrate the preliminary abdominal breathing training basic guidance and the preliminary pursed-lip breathing training basic guidance with the training intensity requirements corresponding to the target recovery period to form abdominal breathing rehabilitation training guidance and pursed-lip breathing rehabilitation training guidance.

[0112] In this step, the training intensity requirement refers to the preset intensity standard of respiratory function rehabilitation training that matches the target recovery period.

[0113] In this embodiment, a preset recovery period training intensity standard library is invoked, and the corresponding training intensity requirements are retrieved according to the target recovery period. The basic guidance for preliminary abdominal breathing training is matched and calibrated with the training intensity requirements, keeping the basic breathing depth, frequency parameters, and precautions unchanged. The basic guidance for preliminary pursed-lip breathing training is also matched and calibrated with the training intensity requirements, keeping the inhalation-exhalation ratio parameters and operational requirements unchanged. After calibration, the final abdominal breathing rehabilitation training guidance and pursed-lip breathing rehabilitation training guidance are formed.

[0114] This application's embodiments enhance the personalization and adaptability of rehabilitation training guidance, providing a guarantee for the safe and efficient conduct of respiratory function rehabilitation training for subsequent patients.

[0115] This application provides a specific embodiment. Step 103 involves verifying the training respiratory physiological data to calculate the respiratory amplitude of the post-thoracic surgery patient based on the verified training respiratory physiological data. This specifically includes the following steps:

[0116] Step 301: Transmit the training respiratory physiological data to the edge computing node of the Internet of Things via the Bluetooth communication link of the Internet of Things, so as to perform timestamp integrity and consistency verification on the time-series data of training thoracic expansion and training respiratory frequency in the training respiratory physiological data, and obtain the verified training respiratory physiological data.

[0117] In this step, the Bluetooth communication link refers to the Bluetooth technology communication channel in the Internet of Things (IoT) used to transmit training respiratory physiological data, enabling short-range wireless data transmission between the data acquisition end and the computing end; the edge computing node in the IoT refers to the computing device in the IoT that is close to the training respiratory physiological data acquisition end, which can quickly process the acquired data to reduce data transmission latency; the training chest expansion time series data refers to the dataset that continuously records the changes in chest expansion of patients after thoracic surgery during respiratory function rehabilitation training in chronological order.

[0118] In this embodiment, when a patient undergoes respiratory function rehabilitation training after thoracic surgery, the respiratory sensing device worn by the patient wirelessly transmits the collected training respiratory physiological data to the edge computing node of the Internet of Things (IoT) via the Bluetooth communication link. After receiving the data, the edge computing node first performs a timestamp integrity check to determine whether there are any missing timestamps in the training chest expansion time-series data and training respiratory frequency data. If there are any missing timestamps, they are supplemented by interpolation with adjacent timestamp data. Then, a timestamp consistency check is performed to verify whether the timestamps of the training chest expansion time-series data and training respiratory frequency data at the same time are completely consistent. If they are inconsistent, the data is adjusted to synchronize with the same time reference. After completing the two checks, the verified training respiratory physiological data with complete data and time synchronization is obtained.

[0119] Step 302: Based on the preset recovery time corresponding to the target recovery period, divide the verified training respiratory physiological data into multiple sub-training respiratory physiological data.

[0120] In this step, the preset recovery time refers to the pre-set time for dividing the training respiratory physiological data into segments corresponding to the target recovery period. The preset recovery time is different for different target recovery periods. The sub-training respiratory physiological data refers to the segmented training respiratory physiological data obtained by dividing the verified training respiratory physiological data according to the preset recovery time. Each segment of data corresponds to a training time period of a preset recovery time.

[0121] In this embodiment, a preset recovery time corresponding to the target recovery period is first retrieved; then, based on the preset recovery time, the verified training respiratory physiological data is processed by time segmentation, and the continuous verified training respiratory physiological data is cut into multiple continuous and non-overlapping segment data according to the preset recovery time. Each segment data contains the time sequence data of training chest expansion and training respiratory frequency within the corresponding training time period. These segment data are multiple sub-training respiratory physiological data.

[0122] Step 303: Based on the recovery period correlation parameters in the preset standard parameter library, determine the standard respiratory amplitude correlation parameters corresponding to the target recovery period, and combine the training chest expansion time series data in each sub-training respiratory physiological data to calculate the average respiratory amplitude of the verified training respiratory physiological data as the respiratory amplitude of the post-thoracic surgery patient.

[0123] In this step, the recovery period-related parameters in the preset standard parameter library refer to the basic parameters related to respiratory amplitude calculation stored in the preset standard parameter library for each recovery period; the standard respiratory amplitude-related parameters refer to the basic parameters for respiratory amplitude calculation that are uniquely corresponding to the target recovery period and retrieved from the recovery period-related parameters in the preset standard parameter library; the average respiratory amplitude refers to the value obtained by averaging the respiratory amplitudes calculated from multiple sub-training respiratory physiological data, which is used to represent the overall respiratory amplitude level of the patient in this respiratory function rehabilitation training after thoracic surgery.

[0124] In this embodiment, a preset standard parameter library is first invoked, and the corresponding standard respiratory amplitude correlation parameter is retrieved from the recovery period correlation parameters stored in the library according to the target recovery period. Then, for each sub-training respiratory physiological data, the time series data of the training thoracic expansion is extracted, and the respiratory amplitude corresponding to the sub-data is calculated. The calculation formula is: Sub-training respiratory amplitude = Maximum value of the time series data of the training thoracic expansion in the sub-training respiratory physiological data - Minimum value of the time series data of the training thoracic expansion in the sub-training respiratory physiological data. After the corresponding sub-training respiratory amplitudes of all sub-training respiratory physiological data have been calculated, the average respiratory amplitude is calculated. The calculation formula is: Average respiratory amplitude = Sum of all sub-training respiratory amplitudes ÷ Total number of sub-training respiratory physiological data. This average respiratory amplitude is used as the respiratory amplitude for the current respiratory function rehabilitation training of the post-thoracic surgery patient.

[0125] The embodiments of this application ensure the accuracy and reliability of respiratory amplitude calculation, avoid misjudgment of respiratory amplitude due to abnormal data or rough calculation, lay a data foundation for timely detection of insufficient respiratory depth problems and accurate sending of respiratory depth adjustment reminders, and improve the accuracy of respiratory function rehabilitation training monitoring.

[0126] This application provides a specific embodiment. Step 105 involves performing a correlation analysis on the abdominal breathing rehabilitation training guidance, the pursed-lip breathing rehabilitation training guidance, the verified training respiratory physiological data, and the intervention feedback data to obtain the correlation analysis results. This specifically includes the following steps:

[0127] Step 501: Based on the abdominal breathing rehabilitation training guidance, the pursed-lip breathing rehabilitation training guidance, the verified training respiratory physiological data, and the intervention feedback data, determine the dimensions of training guidance execution matching degree, respiratory physiological data change trend, and intervention feedback response status.

[0128] In this step, the training guidance execution matching dimension refers to the analytical perspective used to assess the degree of fit between the actual training data of patients after thoracic surgery and the parameters set in the abdominal breathing rehabilitation training guidance and the pursed-lip breathing rehabilitation training guidance; the respiratory physiological data change trend dimension refers to the analytical perspective used to analyze the pattern or trend of the verified training respiratory physiological data of patients after thoracic surgery changing over time during the training process; and the intervention feedback response dimension refers to the analytical perspective used to assess the correspondence between the changes in the training respiratory physiological data of patients after thoracic surgery and the intervention feedback data after receiving the respiratory depth adjustment reminder.

[0129] In this embodiment, based on the set parameters in the abdominal breathing rehabilitation training guidance and the pursed-lip breathing rehabilitation training guidance, and combined with the verified training respiratory physiological data and intervention feedback data, the training guidance execution matching degree dimension focuses on the degree of fit between the actual training and the guidance parameters; the respiratory physiological data change trend dimension focuses on the time change pattern of respiratory data during the training process; and the intervention feedback response dimension focuses on the correspondence between the data changes after the intervention reminder and the feedback.

[0130] Step 502: Extract the breathing depth training parameter from the abdominal breathing rehabilitation training guide, compare the breathing amplitude of each sub-training respiratory physiological data with the breathing depth training parameter to obtain multiple depth difference values, extract the breathing frequency training parameter from the pursed-lip breathing rehabilitation training guide, compare the training breathing frequency of each sub-training respiratory physiological data with the breathing frequency training parameter to obtain multiple frequency difference values.

[0131] In this step, the respiratory depth training parameter refers to the standard respiratory depth value that the patient should achieve during training, as set in the abdominal breathing rehabilitation training guide; the depth difference value refers to the difference between the respiratory amplitude of each sub-training respiratory physiological data and the respiratory depth training parameter; the respiratory rate training parameter refers to the standard respiratory rate value that the patient should maintain during training, as set in the pursed-lip breathing rehabilitation training guide; and the frequency difference value refers to the difference between the training respiratory rate of each sub-training respiratory physiological data and the respiratory rate training parameter.

[0132] In this embodiment, a specific breathing depth training parameter is extracted from the abdominal breathing rehabilitation training guide. For each sub-training respiratory physiological data in the step, the corresponding breathing amplitude is subtracted from the breathing depth training parameter to obtain the depth difference value of each sub-data. At the same time, a breathing frequency training parameter is extracted from the pursed-lip breathing rehabilitation training guide. The training breathing frequency of each sub-training respiratory physiological data is subtracted from this parameter to obtain the frequency difference value of each sub-data.

[0133] Step 503: Based on the depth difference value and the frequency difference value, calculate the training guidance execution matching degree of each sub-training respiratory physiological data.

[0134] In this step, the training instruction execution matching degree refers to the numerical value used to measure the overall degree of fit between the respiratory physiological data of each sub-training and the parameters set in the abdominal breathing rehabilitation training instruction and the pursed-lip breathing rehabilitation training instruction.

[0135] In this embodiment, for each sub-training respiratory physiological data, the absolute values ​​of depth difference and frequency difference are first taken; then the weight ratios of respiratory depth and respiratory frequency are set, and the calculation formula is: training guidance execution matching degree = 1 - [(absolute value of depth difference × 50% + absolute value of frequency difference × 50%) ÷ (respiratory depth training parameter × 50% + respiratory frequency training parameter × 50%)], to obtain the training guidance execution matching degree of each sub-training respiratory physiological data.

[0136] Step 504: Perform time-series variation analysis on the respiratory amplitude and training respiratory frequency of each sub-training respiratory physiological data to obtain the trend results of respiratory physiological data changes.

[0137] In this step, the trend of respiratory physiological data refers to the conclusions about the increase, decrease, or stabilization of the respiratory amplitude and training respiratory frequency of each sub-training respiratory physiological data after analyzing them in chronological order.

[0138] Step 505: Correlate the sub-training respiratory physiological data and intervention feedback data to obtain the intervention feedback response analysis results.

[0139] In this step, the intervention feedback response analysis result refers to the analytical conclusion obtained after correlating the sub-training respiratory physiological data with the intervention feedback data, regarding whether the patient's respiratory physiological data changes accordingly after receiving the respiratory depth adjustment reminder.

[0140] Step 506: Integrate the training guidance execution matching degree, the respiratory physiological data change trend results, and the intervention feedback response analysis results to form a correlation analysis result.

[0141] In this embodiment, the training guidance execution matching degree, respiratory physiological data change trend results, and intervention feedback response analysis results of each sub-training respiratory physiological data are aggregated and integrated; the correlation between the overall level and change trend of training guidance execution matching degree is analyzed, and combined with the conclusion that the intervention response is effective, a correlation analysis result is formed.

[0142] This application's embodiments comprehensively evaluate the implementation of respiratory function rehabilitation training, data change patterns, and intervention effects from multiple perspectives, avoiding the one-sidedness of single-dimensional analysis. This provides a comprehensive and accurate analytical basis for subsequent updates to training progress records and optimization of rehabilitation guidance, thereby improving the scientific nature and effectiveness of rehabilitation training monitoring.

[0143] This application provides a specific embodiment. Step 504 involves performing a time-series change analysis on the respiratory amplitude and training respiratory frequency of each sub-training respiratory physiological data to obtain the trend results of the respiratory physiological data changes. This specifically includes the following steps:

[0144] Step 511: Based on the timestamps of each sub-training respiratory physiological data, arrange the respiratory amplitude and training respiratory frequency of all sub-training respiratory physiological data separately to form a respiratory amplitude sequence and a training respiratory frequency sequence.

[0145] In this step, the respiratory amplitude sequence refers to the sequence formed by arranging the respiratory amplitudes of all sub-training respiratory physiological data in chronological order according to their corresponding timestamps; the training respiratory frequency sequence refers to the sequence formed by arranging the training respiratory frequencies of all sub-training respiratory physiological data in chronological order according to their corresponding timestamps.

[0146] In this embodiment, the timestamps of each sub-training respiratory physiological data are obtained, and the respiratory amplitudes of each sub-training respiratory physiological data are arranged sequentially according to the timestamps from early to late to form a respiratory amplitude sequence; at the same time, the training respiratory frequencies of each sub-training respiratory physiological data are arranged sequentially according to the same timestamp order to form a training respiratory frequency sequence.

[0147] Step 512: Compare adjacent respiratory amplitudes in the respiratory amplitude sequence to determine the direction and rate of change of respiratory amplitude. The difference between the maximum and minimum respiratory amplitudes in the respiratory amplitude sequence is taken as the range of respiratory amplitude fluctuation. The direction of change of respiratory amplitude includes the direction of increase and the direction of decrease of respiratory amplitude.

[0148] In this step, the direction of respiratory amplitude change refers to the increase or decrease relationship between two adjacent respiratory amplitudes in the respiratory amplitude sequence; the rate of change of respiratory amplitude refers to the ratio of the degree of change between two adjacent respiratory amplitudes in the respiratory amplitude sequence to the previous respiratory amplitude; the maximum respiratory amplitude refers to the respiratory amplitude with the largest value in the respiratory amplitude sequence; the minimum respiratory amplitude refers to the respiratory amplitude with the smallest value in the respiratory amplitude sequence; the amplitude difference refers to the difference between the maximum and minimum respiratory amplitudes; the range of respiratory amplitude fluctuation refers to the overall range of respiratory amplitude changes in the respiratory amplitude sequence expressed by the amplitude difference; the direction of increase in respiratory amplitude refers to the relationship that the subsequent respiratory amplitude in the respiratory amplitude sequence is greater than the previous respiratory amplitude; the direction of decrease in respiratory amplitude refers to the relationship that the subsequent respiratory amplitude in the respiratory amplitude sequence is less than the previous respiratory amplitude.

[0149] In this embodiment of the application, for the respiratory amplitude sequence, adjacent respiratory amplitudes are compared to determine the direction of amplitude change; the rate of change of respiratory amplitude is calculated, and the calculation formula is: rate of change of respiratory amplitude = (next respiratory amplitude - previous respiratory amplitude) ÷ previous respiratory amplitude; the maximum and minimum respiratory amplitudes are found from the respiratory amplitude sequence, the amplitude difference is calculated, and it is taken as the range of respiratory amplitude fluctuation. The direction of change, rate of change and range of fluctuation of respiratory amplitude are integrated to obtain the direction of change, rate of change and range of fluctuation of respiratory amplitude.

[0150] Step 513: Compare adjacent training respiratory frequencies in the training respiratory frequency sequence to determine the direction of respiratory frequency change and the rate of respiratory frequency change. The frequency difference between the maximum and minimum respiratory frequencies in the training respiratory frequency sequence is taken as the respiratory frequency fluctuation range. The direction of respiratory frequency change includes the direction of increasing respiratory frequency and the direction of decreasing respiratory frequency.

[0151] In this step, adjacent training breathing frequencies refer to two training breathing frequencies that are temporally adjacent in the training breathing frequency sequence; the direction of breathing frequency change refers to the increasing or decreasing relationship between two adjacent training breathing frequencies in the training breathing frequency sequence; the rate of change of breathing frequency refers to the ratio of the degree of change of two adjacent training breathing frequencies in the training breathing frequency sequence to the previous training breathing frequency; the maximum breathing frequency refers to the training breathing frequency with the largest value in the training breathing frequency sequence; the minimum breathing frequency refers to the training breathing frequency with the smallest value in the training breathing frequency sequence; the frequency difference refers to the difference between the maximum breathing frequency and the minimum breathing frequency; the breathing frequency fluctuation range refers to the overall range of changes in the training breathing frequency in the training breathing frequency sequence, expressed by the frequency difference; the direction of increasing breathing frequency refers to the relationship where the later training breathing frequency in the training breathing frequency sequence is greater than the previous training breathing frequency; the direction of decreasing breathing frequency refers to the relationship where the later training breathing frequency in the training breathing frequency sequence is less than the previous training breathing frequency.

[0152] In this embodiment, for the training respiratory frequency sequence, adjacent training respiratory frequencies are compared to determine the direction of respiratory frequency change; the rate of change of respiratory frequency is calculated using the formula: rate of change of respiratory frequency = (next training respiratory frequency - previous training respiratory frequency) / previous training respiratory frequency. The maximum and minimum respiratory frequencies are found from the training respiratory frequency sequence, and the frequency difference is calculated and used as the range of respiratory frequency fluctuation. The direction of change, rate of change, and range of fluctuation of respiratory frequency are then integrated to obtain the respiratory frequency change direction, rate of change, and range of fluctuation.

[0153] Step 514: Integrate the direction of respiratory amplitude change, the range of respiratory amplitude fluctuation, the rate of change of respiratory amplitude, the range of respiratory frequency fluctuation, and the rate of change of respiratory frequency to obtain the trend results of respiratory physiological data change.

[0154] In this embodiment, the direction of change of respiratory amplitude, the range of fluctuation of respiratory amplitude, and the rate of change of respiratory amplitude are aggregated with the direction of change of respiratory frequency, the range of fluctuation of respiratory frequency, and the rate of change of respiratory frequency. The correlation between the indicators is analyzed, such as the increase of respiratory frequency when respiratory amplitude decreases. This information is integrated into a comprehensive description that includes the direction of change, the range of fluctuation, and the rate of change of respiratory amplitude and training respiratory frequency, forming a result of respiratory physiological data change trend, which comprehensively reflects the dynamic change law of respiratory physiological indicators during training.

[0155] This application embodiment captures the dynamic changes in respiratory indicators over training time, providing detailed and comprehensive evidence for evaluating training effectiveness and detecting abnormal changes in respiratory function, thereby improving the dynamism and accuracy of respiratory function rehabilitation training monitoring.

[0156] This application provides a specific embodiment. Step 505 involves correlating the sub-training respiratory physiological data and intervention feedback data to obtain intervention feedback response analysis results, specifically including the following steps:

[0157] Step 521: Based on the timestamps of each sub-training respiratory physiological data, determine the target sub-training respiratory physiological data corresponding to the sending time of the respiratory depth adjustment reminder.

[0158] In this step, the target sub-training respiratory physiological data refers to the sub-training respiratory physiological data that matches the time of the respiratory depth adjustment reminder.

[0159] In this embodiment, the timestamps of each sub-training respiratory physiological data are obtained, and the sending time of the breathing depth adjustment reminder is recorded. The sending time is compared with the timestamp range of each sub-training respiratory physiological data to determine which sub-training respiratory physiological data time period the sending time belongs to, and the corresponding target sub-training respiratory physiological data is determined.

[0160] Step 522: Establish a matching relationship between the sending time of the breathing depth adjustment reminder, the respiratory physiological data of the target sub-training, and the adjusted breathing amplitude and adjustment response time in the intervention feedback data.

[0161] In this step, the adjusted respiratory amplitude refers to the respiratory amplitude after the thoracic surgery patient receives the respiratory depth adjustment reminder and makes the adjustment; the adjustment response time refers to the time from when the respiratory depth adjustment reminder is sent to when the patient completes the respiratory adjustment and produces an effective change in respiratory amplitude; the matching relationship refers to the one-to-one correspondence established between the sending time of the respiratory depth adjustment reminder, the target sub-training respiratory physiological data, the adjusted respiratory amplitude, and the adjustment response time.

[0162] In this embodiment of the application, the target sub-training respiratory physiological data is clearly defined, and the adjusted breathing amplitude and adjustment response time corresponding to the breathing depth adjustment reminder are extracted from the intervention feedback data. The sending time of the breathing depth adjustment reminder, the target sub-training respiratory physiological data, the adjusted breathing amplitude and adjustment response time are associated and bound to form a corresponding record containing these four pieces of information. This record is the established matching relationship.

[0163] Step 523: Calculate the difference between the adjusted breathing amplitude and the breathing amplitude in the corresponding target sub-training respiratory physiological data, and use the difference as the breathing amplitude improvement value.

[0164] In this step, the breathing amplitude improvement value refers to the difference between the adjusted breathing amplitude and the breathing amplitude in the target sub-training respiratory physiological data, which is used to measure the degree of breathing improvement after the breathing depth adjustment reminder.

[0165] In this embodiment of the application, the respiratory amplitude and the corresponding adjusted respiratory amplitude in the target sub-training respiratory physiological data are extracted from the matching relationship; the degree of respiratory improvement after the respiratory depth adjustment reminder is determined by calculating the difference between the two. The calculation formula is: respiratory amplitude improvement value = adjusted respiratory amplitude - respiratory amplitude in the target sub-training respiratory physiological data.

[0166] Step 524: Calculate the average value of all respiratory amplitude improvement values ​​within the adjustment response time, and aggregate the average value and the distribution of respiratory amplitude improvement values ​​within the adjustment response time to obtain the correlation analysis conclusion.

[0167] In this step, the correlation analysis conclusion refers to the conclusions about the average level and distribution of the improvement values ​​obtained after statistical analysis of the improvement values ​​of respiratory amplitude within the adjustment response time.

[0168] In this embodiment of the application, for the adjustment response duration, all respiratory amplitude improvement values ​​within that duration are collected; the average value of these respiratory amplitude improvement values ​​is calculated using the formula: average value = sum of all respiratory amplitude improvement values ​​÷ number of respiratory amplitude improvement values; at the same time, the distribution of respiratory amplitude improvement values ​​within the adjustment response duration is counted; the calculated average value and the distribution are aggregated to form a correlation analysis conclusion.

[0169] Step 525: Integrate the matching relationship, the improvement value of respiratory amplitude, and the correlation analysis conclusion to obtain the intervention feedback response analysis results.

[0170] In this embodiment of the application, the matching relationship, the improvement value of breathing amplitude, and the conclusion of the correlation analysis are integrated. By sorting out the inherent relationship between these information, such as the sending time corresponding to the target data, the improvement value brought by the adjustment amplitude, and the improvement value having a specific distribution within the time, a comprehensive description including the details of the matching relationship, the size of the improvement value, and the conclusion of the correlation analysis is formed, namely the intervention feedback response analysis result.

[0171] The embodiments of this application provide strong evidence for optimizing intervention strategies and improving the pertinence of respiratory function rehabilitation training.

[0172] Figure 3 This is a schematic diagram of a specific embodiment of the IoT-based postoperative respiratory function rehabilitation training and monitoring system for thoracic surgery provided in this application. (Refer to...) Figure 3 The system may include:

[0173] The data acquisition module 21 is used to collect the initial respiratory physiological data of patients after thoracic surgery in a natural breathing state;

[0174] The comparison module 22 is used to compare the initial respiratory physiological data with the data reference range of the corresponding recovery period in the preset standard parameter library using a multi-feature matching algorithm to determine the target recovery period of the patient after thoracic surgery, so as to generate abdominal breathing rehabilitation training guidance and pursed-lip breathing rehabilitation training guidance corresponding to the target recovery period.

[0175] Verification module 23 is used to collect the respiratory physiological data of the post-thoracic surgery patient during the respiratory function rehabilitation training under the guidance of abdominal breathing rehabilitation training and the guidance of pursed-lip breathing rehabilitation training, verify the training respiratory physiological data, and calculate the respiratory amplitude of the post-thoracic surgery patient based on the verified training respiratory physiological data.

[0176] The sending module 24 is used to send a breathing depth adjustment reminder to the thoracic surgery postoperative patient via the Internet of Things when the breathing amplitude is lower than the preset postoperative rehabilitation standard breathing amplitude, and to obtain the intervention feedback data of the thoracic surgery postoperative patient.

[0177] Analysis module 25 performs correlation analysis on the abdominal breathing rehabilitation training guidance, the pursed-lip breathing rehabilitation training guidance, the verified training respiratory physiological data, and the intervention feedback data to obtain correlation analysis results;

[0178] The update module 26 is used to update the training progress file of the postoperative thoracic surgery patient based on the correlation analysis results, so as to realize the monitoring of the respiratory function rehabilitation training of the postoperative thoracic surgery patient.

[0179] The IoT-based postoperative respiratory function rehabilitation training monitoring system for thoracic surgery in this application is used to implement the aforementioned IoT-based postoperative respiratory function rehabilitation training monitoring method for thoracic surgery. Therefore, the specific implementation of the IoT-based postoperative respiratory function rehabilitation training monitoring system for thoracic surgery can be found in the embodiment section of the IoT-based postoperative respiratory function rehabilitation training monitoring method for thoracic surgery mentioned above. The specific implementation can be referred to the description of the corresponding embodiments, which will not be repeated here.

[0180] This application also provides an electronic device, comprising: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of the above-described Internet of Things-based postoperative respiratory function rehabilitation training and monitoring method for thoracic surgery.

[0181] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of any of the above-described IoT-based postoperative respiratory function rehabilitation training and monitoring methods for thoracic surgery.

[0182] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory, random access memory, portable hard drives, magnetic disks, or optical disks.

[0183] Embodiments of the present invention also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in any of the embodiments of the Internet of Things-based postoperative respiratory function rehabilitation training and monitoring method for thoracic surgery.

[0184] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0185] The foregoing has provided a detailed description of the IoT-based postoperative respiratory function rehabilitation training monitoring method and system for thoracic surgery provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are merely for the purpose of helping to understand the method and its core ideas. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from its principles, and these improvements and modifications also fall within the protection scope of this application.

Claims

1. A method for monitoring postoperative respiratory function rehabilitation training in thoracic surgery based on the Internet of Things, characterized in that, include: Collect initial respiratory physiological data of patients after thoracic surgery under natural breathing conditions; Using a multi-feature matching algorithm, the initial respiratory physiological data and the corresponding recovery period data reference range in the preset standard parameter library are compared to determine the target recovery period of the patient after thoracic surgery, so as to generate abdominal breathing rehabilitation training guidance and pursed-lip breathing rehabilitation training guidance corresponding to the target recovery period. Initial chest expansion characteristics and initial respiratory rate characteristics were extracted from the initial respiratory physiological data. Using a multi-feature matching algorithm, the initial chest expansion feature is compared with the chest expansion reference range for each recovery period in the preset standard parameter library to obtain the chest expansion feature comparison result. The initial respiratory rate feature is also compared with the respiratory rate reference range for each recovery period in the preset standard parameter library to obtain the respiratory rate feature comparison result. Each recovery period includes the early recovery period, the middle recovery period, and the late recovery period. Based on the comparison results of the chest expansion feature, the first percentage of the data points of the initial chest expansion feature that are within the reference range of chest expansion in each recovery period is calculated, and the first percentage is used as the chest expansion matching degree. Based on the comparison results of the respiratory rate feature, the second percentage of the data points of the initial respiratory rate feature that are within the reference range of respiratory rate in each recovery period is calculated, and the second percentage is used as the respiratory rate matching degree. The recovery period in which both the chest expansion and respiratory rate matching degree reach the preset matching threshold is selected as the target recovery period for patients after thoracic surgery. If there are multiple recovery periods that meet the preset matching thresholds for both chest expansion and respiratory rate matching degree, the recovery period with the highest average matching degree is selected as the target recovery period. The target breathing characteristics corresponding to the target recovery period are retrieved from the preset table of breathing characteristics during the recovery period, so as to generate abdominal breathing rehabilitation training guidance and pursed-lip breathing rehabilitation training guidance corresponding to the target recovery period based on the target breathing characteristics. Collect respiratory physiological data of the patients after thoracic surgery during respiratory function rehabilitation training under the guidance of abdominal breathing rehabilitation training and pursed-lip breathing rehabilitation training. Verify the respiratory physiological data and calculate the respiratory amplitude of the patients after thoracic surgery based on the verified respiratory physiological data. When the respiratory amplitude is lower than the preset postoperative rehabilitation standard respiratory amplitude, a respiratory depth adjustment reminder is sent to the thoracic surgery postoperative patient via the Internet of Things, and the intervention feedback data of the thoracic surgery postoperative patient is obtained. The abdominal breathing rehabilitation training guidelines, the pursed-lip breathing rehabilitation training guidelines, the verified training respiratory physiological data, and the intervention feedback data were correlated to obtain the correlation analysis results. Based on the correlation analysis results, the training progress file of the postoperative thoracic surgery patient is updated to monitor the respiratory function rehabilitation training of the postoperative thoracic surgery patient.

2. The method according to claim 1, characterized in that, The system retrieves the target breathing characteristics corresponding to the target recovery period from a preset table of respiratory characteristics during the recovery period, and generates abdominal breathing rehabilitation training guidance and pursed-lip breathing rehabilitation training guidance corresponding to the target recovery period based on the target breathing characteristics, including: Extract the respiratory characteristics corresponding to the target recovery period from the preset table of respiratory characteristics during the recovery period. The respiratory characteristics include the form of respiratory manifestation and factors affecting respiratory function. Based on the preoperative baseline information and surgical record information of patients after thoracic surgery, information on chest wall mobility sensitivity is added to the respiratory characteristics to obtain the target respiratory characteristics. Based on the respiratory manifestations of the target breathing characteristics, the basic breathing depth and frequency parameters for abdominal breathing rehabilitation training are determined, and combined with the information on chest wall activity sensitivity, preliminary basic guidance for abdominal breathing training is generated. Based on the respiratory manifestations of the target respiratory characteristics, determine the ratio of expiratory to inspiratory duration for pursed-lip breathing rehabilitation training, and combine this with respiratory resistance information related to the target respiratory characteristics to generate preliminary basic guidance for pursed-lip breathing training. The basic guidelines for preliminary abdominal breathing training and the basic guidelines for preliminary pursed-lip breathing training are matched and calibrated with the training intensity requirements corresponding to the target recovery period to form guidelines for abdominal breathing rehabilitation training and guidelines for pursed-lip breathing rehabilitation training.

3. The method according to claim 1, characterized in that, The training respiratory physiological data is validated, and the respiratory amplitude of the postoperative thoracic surgery patient is calculated based on the validated training respiratory physiological data, including: The training respiratory physiological data is transmitted to the edge computing node of the Internet of Things via the Bluetooth communication link of the Internet of Things, so as to perform timestamp integrity and consistency verification on the time series data of training chest expansion and training respiratory frequency in the training respiratory physiological data, and obtain the verified training respiratory physiological data. Based on the preset recovery time corresponding to the target recovery period, the verified training respiratory physiological data is divided into multiple sub-training respiratory physiological data. Based on the recovery period-related parameters in the preset standard parameter library, the standard respiratory amplitude-related parameters corresponding to the target recovery period are determined. Combined with the time series data of the training thoracic expansion in each sub-training respiratory physiological data, the average respiratory amplitude of the verified training respiratory physiological data is calculated as the respiratory amplitude of the post-thoracic surgery patient.

4. The method according to claim 1, characterized in that, The abdominal breathing rehabilitation training guidelines, the pursed-lip breathing rehabilitation training guidelines, the validated training respiratory physiological data, and the intervention feedback data were correlated to obtain the correlation analysis results, including: Based on the abdominal breathing rehabilitation training guidance, the pursed-lip breathing rehabilitation training guidance, the verified training respiratory physiological data, and the intervention feedback data, the dimensions of training guidance execution matching degree, respiratory physiological data change trend, and intervention feedback response status are determined. The breathing depth training parameter is extracted from the abdominal breathing rehabilitation training guide. The breathing amplitude of each sub-training respiratory physiological data is compared with the breathing depth training parameter to obtain multiple depth difference values. The breathing frequency training parameter is extracted from the pursed-lip breathing rehabilitation training guide. The training breathing frequency of each sub-training respiratory physiological data is compared with the breathing frequency training parameter to obtain multiple frequency difference values. Based on the depth difference value and the frequency difference value, the training guidance execution matching degree of each sub-training respiratory physiological data is calculated; A time-series change analysis was performed on the respiratory amplitude and respiratory frequency of each sub-training respiratory physiological data to obtain the trend of respiratory physiological data changes. The sub-training respiratory physiological data and intervention feedback data are correlated and processed to obtain the intervention feedback response analysis results; The training guidance execution matching degree, the respiratory physiological data change trend results, and the intervention feedback response analysis results are integrated to form a correlation analysis result.

5. The method according to claim 4, characterized in that, A time-series analysis of the respiratory amplitude and respiratory frequency of each sub-training respiratory physiological data was performed to obtain the trend results of the respiratory physiological data changes, including: Based on the timestamps of each sub-training respiratory physiological data, the respiratory amplitude and training respiratory frequency of all sub-training respiratory physiological data are arranged separately to form a respiratory amplitude sequence and a training respiratory frequency sequence. Adjacent respiratory amplitudes in the respiratory amplitude sequence are compared to determine the direction and rate of change of respiratory amplitude. The difference between the maximum and minimum respiratory amplitudes in the respiratory amplitude sequence is taken as the range of respiratory amplitude fluctuation. The direction of change of respiratory amplitude includes the direction of increase and the direction of decrease of respiratory amplitude. Adjacent training respiratory frequencies in the training respiratory frequency sequence are compared to determine the direction and rate of change of respiratory frequency. The frequency difference between the maximum and minimum respiratory frequencies in the training respiratory frequency sequence is taken as the range of respiratory frequency fluctuation. The direction of change of respiratory frequency includes the direction of increase and the direction of decrease of respiratory frequency. By integrating the direction of respiratory amplitude change, the range of respiratory amplitude fluctuation, the rate of change of respiratory amplitude, the range of respiratory frequency fluctuation, and the rate of change of respiratory frequency, the trend of respiratory physiological data change is obtained.

6. The method according to claim 4, characterized in that, The sub-training respiratory physiological data and intervention feedback data are correlated and processed to obtain the intervention feedback response analysis results, including: Based on the timestamps of each sub-training respiratory physiological data, determine the target sub-training respiratory physiological data corresponding to the sending time of the respiratory depth adjustment reminder; Establish a matching relationship between the sending time of the breathing depth adjustment reminder, the respiratory physiological data of the target sub-training, and the adjusted breathing amplitude and adjustment response time in the intervention feedback data; Calculate the difference between the adjusted respiratory amplitude and the respiratory amplitude in the corresponding target sub-training respiratory physiological data, and use the difference as the respiratory amplitude improvement value; Calculate the average value of all respiratory amplitude improvement values ​​within the adjustment response time, and aggregate the average value and the distribution of respiratory amplitude improvement values ​​within the adjustment response time to obtain the correlation analysis conclusion; The matching relationship, the improvement value of respiratory amplitude, and the conclusion of the correlation analysis are integrated to obtain the intervention feedback response analysis results.

7. A monitoring system for postoperative respiratory function rehabilitation training in thoracic surgery based on the Internet of Things, characterized in that, include: The data acquisition module is used to collect initial respiratory physiological data of patients after thoracic surgery under natural breathing conditions. The comparison module is used to compare the initial respiratory physiological data with the data reference range of the corresponding recovery period in the preset standard parameter library using a multi-feature matching algorithm to determine the target recovery period of the patient after thoracic surgery, so as to generate abdominal breathing rehabilitation training guidance and pursed-lip breathing rehabilitation training guidance corresponding to the target recovery period. The verification module is used to collect the respiratory physiological data of the post-thoracic surgery patient during the respiratory function rehabilitation training under the guidance of abdominal breathing rehabilitation training and the guidance of pursed-lip breathing rehabilitation training, verify the training respiratory physiological data, and calculate the respiratory amplitude of the post-thoracic surgery patient based on the verified training respiratory physiological data. The sending module is used to send a breathing depth adjustment reminder to the thoracic surgery postoperative patient via the Internet of Things when the breathing amplitude is lower than the preset postoperative rehabilitation standard breathing amplitude, and to obtain the intervention feedback data of the thoracic surgery postoperative patient; The analysis module performs correlation analysis on the abdominal breathing rehabilitation training guidance, the pursed-lip breathing rehabilitation training guidance, the verified training respiratory physiological data, and the intervention feedback data to obtain the correlation analysis results. The update module is used to update the training progress file of the postoperative thoracic surgery patient based on the correlation analysis results, so as to realize the monitoring of the respiratory function rehabilitation training of the postoperative thoracic surgery patient. Initial chest expansion characteristics and initial respiratory rate characteristics were extracted from the initial respiratory physiological data. Using a multi-feature matching algorithm, the initial chest expansion feature is compared with the chest expansion reference range for each recovery period in the preset standard parameter library to obtain the chest expansion feature comparison result. The initial respiratory rate feature is also compared with the respiratory rate reference range for each recovery period in the preset standard parameter library to obtain the respiratory rate feature comparison result. Each recovery period includes the early recovery period, the middle recovery period, and the late recovery period. Based on the comparison results of the chest expansion feature, the first percentage of the data points of the initial chest expansion feature that are within the reference range of chest expansion in each recovery period is calculated, and the first percentage is used as the chest expansion matching degree. Based on the comparison results of the respiratory rate feature, the second percentage of the data points of the initial respiratory rate feature that are within the reference range of respiratory rate in each recovery period is calculated, and the second percentage is used as the respiratory rate matching degree. The recovery period in which both the chest expansion and respiratory rate matching degree reach the preset matching threshold is selected as the target recovery period for patients after thoracic surgery. If there are multiple recovery periods that meet the preset matching thresholds for both chest expansion and respiratory rate matching degree, the recovery period with the highest average matching degree is selected as the target recovery period. The target breathing characteristics corresponding to the target recovery period are retrieved from the preset table of breathing characteristics during the recovery period, and based on the target breathing characteristics, diaphragmatic breathing rehabilitation training guidance and pursed-lip breathing rehabilitation training guidance corresponding to the target recovery period are generated.

8. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the IoT-based postoperative respiratory function rehabilitation training monitoring method for thoracic surgery as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, enables the implementation of the Internet of Things-based postoperative respiratory function rehabilitation training and monitoring method for thoracic surgery as described in any one of claims 1 to 6.

Images