Intelligent monitoring system and method for respiratory training device

Abstract

The invention provides an intelligent monitoring system and method for a respiratory training device, and the method comprises the steps: extracting a plurality of abnormal operation features in a respiratory training process from abnormal operation data, carrying out the correlation analysis of all abnormal operation features, obtaining a coupling relation between the abnormal operation states of the respiratory training device, and carrying out the detection of the abnormal operation states of the respiratory training device. Determining the fluctuation correlation degree of the respiratory training device in the abnormal operation state through the coupling relation; determining the diversity of the operation states of the respiratory training device under different training intensities based on the baseline data, and determining the parameter deviation of the respiratory training device under the normal operation state according to the diversity and the normal operation data; determining a state change index of the current operation state of the respiratory training device through the fluctuation correlation degree and the parameter deviation; and monitoring the abnormal operation state of the respiratory training device according to the state change index, and sending state early warning to a monitoring center. By means of the scheme, dynamic anomaly recognition can be achieved in the operation process of the respiratory training device, and therefore the intelligent monitoring capacity of the respiratory training device is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent monitoring technology, and more specifically, to an intelligent monitoring system and method for a respiratory trainer. Background Art

[0002] A breathing trainer is a device that helps users improve respiratory health, lung function, and exercise endurance by adjusting their breathing patterns. Its design is usually based on simulating different breathing resistances to strengthen respiratory muscles, increase lung capacity, or improve specific health problems such as asthma and chronic obstructive pulmonary disease.

[0003] Intelligent monitoring of a respiratory trainer refers to the use of integrated sensors, data analysis and real-time feedback technology to achieve real-time monitoring, evaluation and feedback of the working mode, training intensity and operating status of the respiratory trainer, thereby optimizing the respiratory training effect, improving safety, and providing a scientific basis for health management, helping users improve lung function and breathing ability; however, in the prior art, in the process of intelligent monitoring of a respiratory trainer, since the abnormal operating status of the existing respiratory trainer is often determined by the excess of a single parameter, it is easy to ignore the potential correlation between multiple abnormal operating states, and it is impossible to fully reflect the comprehensive operating status of the respiratory trainer during respiratory training, resulting in false alarms or omissions of abnormal states of the respiratory trainer. Because the operating status of the respiratory trainer is difficult to detect, once an abnormal situation occurs, it can only be forced to shut down for inspection, which reduces work efficiency and increases maintenance costs. Therefore, how to realize dynamic abnormality recognition during the operation of the respiratory trainer and thus improve the intelligent monitoring capability of the respiratory trainer has become a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides an intelligent monitoring system and method for a respiratory trainer, which can realize dynamic abnormality recognition during the operation of the respiratory trainer, thereby improving the intelligent monitoring capability of the respiratory trainer.

[0005] In a first aspect, the present application provides an intelligent monitoring method for a monitoring center to monitor the status of a breathing trainer, wherein the monitoring center and the breathing trainer construct a wireless monitoring ad hoc network through Z-Wave, and the method comprises the following steps: Monitoring the operating parameters of the breathing trainer in the wireless monitoring ad hoc network during the breathing training process, thereby obtaining normal operating data and abnormal operating data of the breathing trainer; Extracting multiple abnormal operation features in the breathing training process from the abnormal operation data, and then performing correlation analysis on all the abnormal operation features to obtain the coupling relationship between the abnormal operation states of the breathing trainer during the breathing training, and determining the fluctuation correlation degree of the breathing trainer in the wireless monitoring ad hoc network under the abnormal operation state through the coupling relationship; Collecting baseline data of a breathing trainer in a wireless monitoring ad hoc network under normal operating conditions, determining differences in operating conditions of the breathing trainer under different training intensities based on the baseline data and interaction information between the breathing trainer and the user, and determining parameter deviations of the breathing trainer in the wireless monitoring ad hoc network under normal operating conditions based on the differences and a change trend of operating parameters in the normal operating data; Determine the state change index of the current operating state of the breathing trainer in the wireless monitoring ad hoc network through the fluctuation correlation and the parameter deviation; The abnormal operation state of the breathing trainer is monitored according to the state change index, and a state warning is sent to a monitoring center through a wireless monitoring ad hoc network.

[0006] In some embodiments, extracting multiple abnormal operation features during the breathing training process from the abnormal operation data specifically includes: Performing abnormal classification on the abnormal operation data to obtain multiple abnormal state classes; Extract the main frequency component of each abnormal state class based on spectrum analysis; Multiple abnormal operating characteristics during breathing training were identified through all main frequency components.

[0007] In some embodiments, correlation analysis is performed on all abnormal operation characteristics to obtain coupling relationships between abnormal operation states of the breathing trainer during breathing training, specifically including: Determine the correlation between various abnormal operation characteristics; Determine the correlation matrix between each abnormal operation feature from all the correlations; The coupling relationship between abnormal operating states of the breathing trainer during breathing training is determined according to the correlation matrix.

[0008] In some embodiments, determining the fluctuation correlation of the breathing trainer in the wireless monitoring ad hoc network in an abnormal operating state through the coupling relationship specifically includes: Determine the dynamic interaction intensity between abnormal operation states of the breathing trainer in the wireless monitoring ad hoc network when performing breathing training based on the coupling relationship; The fluctuation correlation degree of the breathing trainer in the wireless monitoring ad hoc network under abnormal operation state is determined by the dynamic interaction strength.

[0009] In some embodiments, determining the differences in the operating states of the breathing trainer at different training intensities based on the baseline data and the interaction information between the breathing trainer and the user specifically includes: Obtaining interaction information between the breathing trainer and the user; Extracting difference factors of the breathing trainer at various training intensities based on the interaction information and the baseline data; The differences in the operating status of the breathing trainer under different training intensities are determined by all difference factors.

[0010] In some embodiments, determining the state change index of the current operating state of the breathing trainer in the wireless monitoring ad hoc network by using the fluctuation correlation and the parameter deviation specifically includes: Obtain the current training intensity parameters of the breathing trainer in the wireless monitoring ad hoc network; Determine a state matching value between the current running state and the standard running state of the breathing trainer by using the training intensity parameter and the fluctuation correlation degree; The state change index of the current running state of the breathing trainer in the wireless monitoring ad hoc network is determined by the state matching value and the parameter deviation.

[0011] In some embodiments, monitoring the abnormal operating state of the breathing trainer according to the state change index specifically includes: Determine anomaly thresholds for a breathing trainer in a wireless monitoring ad hoc network; When the state change index exceeds the abnormal threshold, the current operating state of the breathing trainer is determined to be an abnormal operating state.

[0012] In a second aspect, the present application provides an intelligent monitoring system for a respiratory trainer, including a monitoring center and a respiratory trainer, wherein the monitoring center and the respiratory trainer construct a wireless monitoring ad hoc network through Z-Wave, wherein the monitoring center includes a state monitoring unit, and the state monitoring unit includes: A monitoring module is used to monitor the operating parameters of the breathing trainer in the wireless monitoring ad hoc network during the breathing training process, and then obtain the normal operating data and abnormal operating data of the breathing trainer; A processing module, for extracting a plurality of abnormal operation features in the breathing training process from the abnormal operation data, and then performing correlation analysis on all the abnormal operation features to obtain a coupling relationship between abnormal operation states of the breathing trainer when the breathing trainer performs breathing training, and determining a fluctuation correlation degree of the breathing trainer in the wireless monitoring ad hoc network in the abnormal operation state through the coupling relationship; The processing module is further used to collect baseline data of the breathing trainer in the wireless monitoring ad hoc network under normal operating conditions, determine the differences in the operating conditions of the breathing trainer under different training intensities based on the baseline data and the interaction information between the breathing trainer and the user, and determine the parameter deviation of the breathing trainer in the wireless monitoring ad hoc network under normal operating conditions based on the differences and the change trend of the operating parameters in the normal operating data; The processing module is further used to determine the state change index of the current operating state of the breathing trainer in the wireless monitoring ad hoc network through the fluctuation correlation degree and the parameter deviation; The execution module is used to monitor the abnormal operation state of the breathing trainer according to the state change index, and send a state warning to the monitoring center through the wireless monitoring ad hoc network.

[0013] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned intelligent monitoring method.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer implements the above-mentioned intelligent monitoring method when executed.

[0015] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects: In the present application, the normal operation data and abnormal operation data of the breathing trainer are obtained by monitoring the operating parameters of the breathing trainer in the breathing training process in the wireless monitoring ad hoc network; a plurality of abnormal operation features in the breathing training process are extracted from the abnormal operation data, and then all the abnormal operation features are subjected to correlation analysis to obtain the coupling relationship between the abnormal operation states of the breathing trainer during the breathing training, and the fluctuation correlation degree of the breathing trainer in the wireless monitoring ad hoc network under the abnormal operation state is determined by the coupling relationship; the baseline data of the breathing trainer in the wireless monitoring ad hoc network under the normal operation state is collected, and the difference of the operation state of the breathing trainer under different training intensities is determined based on the baseline data and the interaction information between the breathing trainer and the user, and the parameter deviation of the breathing trainer in the wireless monitoring ad hoc network under the normal operation state is determined by the difference and the change trend of the operation parameters in the normal operation data; the state change index of the current operation state of the breathing trainer in the wireless monitoring ad hoc network is determined by the fluctuation correlation degree and the parameter deviation; the abnormal operation state of the breathing trainer is monitored according to the state change index, and a state warning is sent to a monitoring center through the wireless monitoring ad hoc network.

[0016] It can be seen that in the present application, firstly, through the correlation analysis of abnormal operation characteristics, the potential connection between different abnormal operation states can be found, that is: the coupling relationship between abnormal operation states can reveal the mutual influence between abnormal problems of different equipment in the respiratory training process; secondly, the fluctuation correlation degree of the respiratory trainer in the wireless monitoring ad hoc network under the abnormal operation state is determined through the coupling relationship, and the mutual influence and dependence between different abnormal operation states can be identified, which provides mathematical support for the rapid identification of dynamic anomalies, especially when multiple abnormal operation states occur at the same time, it can avoid false alarms and missed alarms, and improve the reliability and accuracy of intelligent monitoring; then, the parameter deviation of the respiratory trainer in the wireless monitoring ad hoc network under the normal operation state is determined through the difference of the operating state of the respiratory trainer under different training intensities, which improves the adaptability to different usage scenarios of the respiratory trainer, so as to identify the abnormal operation states under different training intensities. The possible equipment abnormalities can timely detect whether there are potential problems with the breathing trainer. The parameter deviation can provide real-time feedback for dynamic abnormality detection so as to quickly respond to abnormalities. Furthermore, the state change index of the current operating state of the breathing trainer in the wireless monitoring ad hoc network is determined through the fluctuation correlation and the parameter deviation, so that abnormality identification is more flexible and can adapt to changes in different states of the breathing trainer to achieve intelligent identification of dynamic abnormalities. Finally, the abnormal operating state of the breathing trainer is monitored according to the state change index, which improves the accuracy of abnormality identification, and can find potential problems when the breathing trainer is running, and then send status warnings to the monitoring center through the wireless monitoring ad hoc network so as to repair or adjust it in time, thereby effectively reducing downtime and reducing maintenance costs. In summary, the scheme can realize dynamic abnormality identification during the operation of the breathing trainer, thereby improving the intelligent monitoring capability of the breathing trainer. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0018] Figure 1 is an exemplary flow chart of an intelligent monitoring method according to some embodiments of the present application; Figure 2 is an exemplary flow chart of classified operating parameters according to some embodiments of the present application; Figure 3 is an exemplary flow chart of extracting abnormal operation features according to some embodiments of the present application; Figure 4is a schematic diagram of the structure of a status monitoring unit according to some embodiments of the present application; Figure 5 It is a structural diagram of a computer device for implementing an intelligent monitoring method according to some embodiments of the present application. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0020] refer to Figure 1 , which is an exemplary flow chart of an intelligent monitoring method according to some embodiments of the present application, wherein the intelligent monitoring method 100 is used by a monitoring center to monitor the status of a breathing trainer, wherein the monitoring center and the breathing trainer construct a wireless monitoring ad hoc network through Z-Wave, and the intelligent monitoring method 100 mainly comprises the following steps: In step 101, the operating parameters of a breathing trainer in a wireless monitoring ad hoc network during breathing training are monitored to obtain normal operating data and abnormal operating data of the breathing trainer.

[0021] It should be noted that in the present application, a data processing module for operating parameters is provided in the breathing trainer in the wireless monitoring ad hoc network. The data processing module can be used to preliminarily classify the operating parameters of the breathing trainer during the breathing training process obtained by real-time monitoring into normal operating parameters and abnormal operating parameters, and then combine all normal operating parameters into normal operating data of the breathing trainer, and combine all abnormal operating parameters into abnormal operating data of the breathing trainer. Figure 2 As shown, this figure is an exemplary flow chart of classified operating parameters in some embodiments of the present application, wherein the algorithm framework of the data processing module may adopt a neural network algorithm, and in other embodiments, the algorithm framework of the data processing module may also adopt other algorithm structures, such as: support vector machine, decision tree and random forest, etc., which are not limited here.

[0022] In specific implementation, sensors (such as pressure sensors, flow sensors, temperature sensors) can be equipped in the breathing trainer to monitor and collect the operating parameters of the breathing trainer in the wireless monitoring ad hoc network during the breathing training process in real time. The operating parameters include: airflow velocity (gas flow rate per unit time), air pressure value (pressure generated during training), temperature value (temperature generated by the breathing trainer during breathing training), training rhythm (number of breaths and its cycle), etc., and then the normal operating data and abnormal operating data of the breathing trainer in the wireless monitoring ad hoc network are obtained through the data processing module of the breathing trainer. Among them, when the operating parameters of the breathing trainer in the wireless monitoring ad hoc network are collected, the sampling frequency of the present application can be set between 20-50Hz, and can also be set to other frequencies in other embodiments, which are not limited here.

[0023] It should be noted that the normal operating data in the present application refers to the set of all operating parameters of the breathing trainer that meet the training requirements during the breathing training process, and the abnormal operating data refers to the set of all operating parameters of the breathing trainer that exceed the normal range and behave unstable during the breathing training process.

[0024] In step 102, a plurality of abnormal operation features in the breathing training process are extracted from the abnormal operation data, and then a correlation analysis is performed on all the abnormal operation features to obtain a coupling relationship between abnormal operation states of the breathing trainer when performing breathing training, and the fluctuation correlation degree of the breathing trainer in the wireless monitoring ad hoc network under abnormal operation state is determined through the coupling relationship.

[0025] In some embodiments, reference Figure 3 As shown in FIG. 1 , this figure is an exemplary flow chart of extracting abnormal operation features in some embodiments of the present application. In this embodiment, extracting multiple abnormal operation features in the breathing training process from the abnormal operation data can be implemented by the following steps: First, in step 1021, the abnormal operation data is classified into abnormal categories to obtain multiple abnormal status categories; Secondly, in step 1022, the main frequency component of each abnormal state class is extracted based on spectrum analysis; Finally, in step 1023, multiple abnormal operation features during the breathing training process are determined through all main frequency components.

[0026] In specific implementation, the abnormal operation data is abnormally classified to obtain multiple abnormal state classes, which can be achieved in the following manner, namely: an existing clustering algorithm (for example: K-means clustering algorithm K-means) can be used to cluster the abnormal operation data based on the abnormal operation state type corresponding to the operation parameters, and all operation parameters belonging to the same abnormal operation state type are grouped into an abnormal state class, thereby obtaining multiple abnormal state classes of the breathing trainer during the breathing training process, wherein each abnormal operation state type corresponds to an abnormal state class, and the abnormal operation state type is, for example: excessive fluctuation of airflow rate, excessive pressure change, overheating of equipment, disordered training rhythm, etc. In other embodiments, other methods can also be used for determination, which is not limited here. In addition, it should be noted that the abnormal state class in the present application represents a set of all operation parameters of the breathing trainer under the corresponding abnormal operation state type, which will not be repeated here.

[0027] In specific implementation, the main frequency component in the present application represents the core feature of the abnormal state class; the main frequency component of each abnormal state class extracted based on spectrum analysis can be implemented in the following manner, namely: each abnormal state class can be converted from the time domain to the frequency domain through Fourier transform, and then the frequency component with the highest energy (i.e., the highest amplitude) in the frequency domain of each abnormal state class is identified, and the identified frequency component is used as the main frequency component of each abnormal state class. In other embodiments, other methods can also be used for determination, which is not limited here; determining multiple abnormal operation characteristics in the breathing training process through all main frequency components can be implemented in the following manner, namely: the energy value (i.e., the square of the amplitude) corresponding to each main frequency component is used as an abnormal operation feature in the breathing training process, thereby obtaining multiple abnormal operation characteristics in the breathing training process. In other embodiments, other methods can also be used for determination, which is not limited here.

[0028] It should be noted that the abnormal operation characteristics in the present application are characteristic parameters used to describe the abnormal operation state of the breathing trainer.

[0029] In some embodiments, correlation analysis is performed on all abnormal operation characteristics to obtain the coupling relationship between abnormal operation states of the breathing trainer when performing breathing training, which can be achieved by the following steps: Determine the correlation between various abnormal operation characteristics; Determine the correlation matrix between each abnormal operation feature from all the correlations; The coupling relationship between abnormal operating states of the breathing trainer during breathing training is determined according to the correlation matrix.

[0030] In specific implementation, the correlation between each abnormal operation feature can be determined in the following manner, namely: select an abnormal operation feature as the selected abnormal operation feature, and use the Pearson correlation coefficient between the selected abnormal operation feature and each abnormal operation feature as the correlation between the selected abnormal operation feature and each abnormal operation feature, and continue to determine the correlation between the remaining abnormal operation features and each abnormal operation feature. In other embodiments, other methods can also be used for determination, which is not limited here; determining the correlation matrix between each abnormal operation feature from all the correlations can be implemented in the following manner, namely: arrange all the correlations rij in rows and columns into a matrix form, and use the obtained matrix as the correlation matrix between each abnormal operation feature, wherein the diagonal elements in the correlation matrix are all 1 (i.e., the corresponding The correlation between two identical abnormal operation features is 1), the off-diagonal element rij represents the correlation between the abnormal operation feature i and the abnormal operation feature j; determining the coupling relationship between the abnormal operation states when the breathing trainer performs breathing training according to the correlation matrix can be implemented in the following manner, namely: the degree of influence of the abnormal operation state type corresponding to each abnormal operation feature by the abnormal operation state type corresponding to other abnormal operation features can be evaluated based on the correlation matrix by an existing evaluation algorithm, and the influence value corresponding to each abnormal operation feature obtained by the evaluation is used to form the coupling relationship between the abnormal operation states when the breathing trainer performs breathing training, wherein the evaluation algorithm is, for example, cross-validation, genetic algorithm, and machine learning, etc., and other methods can also be used for determination in other embodiments, which are not limited here.

[0031] It should be noted that the correlation in the present application represents the strength of the relationship between two abnormal operation characteristics. The larger the correlation, the greater the strength of the relationship between the two abnormal operation characteristics, and the smaller the correlation, the smaller the strength of the relationship between the two abnormal operation characteristics. In addition, the correlation matrix is ​​a matrix representing the correlation between all abnormal operation characteristics. The coupling relationship represents the inherent interactive influence relationship between the abnormal operation states when the breathing trainer performs breathing training.

[0032] In some embodiments, determining the fluctuation correlation of the breathing trainer in the wireless monitoring ad hoc network under abnormal operation state through the coupling relationship can be implemented by the following steps: Determine the dynamic interaction intensity between abnormal operation states of the breathing trainer in the wireless monitoring ad hoc network when performing breathing training based on the coupling relationship; The fluctuation correlation degree of the breathing trainer in the wireless monitoring ad hoc network under abnormal operation state is determined by the dynamic interaction strength.

[0033] In specific implementation, determining the dynamic interaction strength between abnormal operating states of the breathing trainer in the wireless monitoring ad hoc network when performing breathing training by the coupling relationship can be implemented in the following manner, namely: the common change degree between the various abnormal operating state types of the breathing trainer can be measured based on all the influence values ​​in the coupling relationship through deep learning, and then the obtained result is used as the dynamic interaction strength between the abnormal operating states of the breathing trainer in the wireless monitoring ad hoc network when performing breathing training. In other embodiments, other methods can also be used for determination, which is not limited here; determining the fluctuation correlation degree of the breathing trainer in the wireless monitoring ad hoc network under abnormal operating state by the dynamic interaction strength can be implemented in the following manner, namely: the correlation density between all abnormal operating states of the breathing trainer can be calculated based on the dynamic interaction strength by a BP neural network model, and the calculated result is used as the fluctuation correlation degree of the breathing trainer in the wireless monitoring ad hoc network under abnormal operating state. In other embodiments, other methods can also be used for determination, which is not limited here.

[0034] It should be noted that the dynamic interaction intensity described in the present application represents the degree of coordinated change between different abnormal operating states when the breathing trainer operates abnormally. Therefore, the interactive relationship between the abnormal operating states of the breathing trainer can be understood through the dynamic interaction intensity; in addition, the fluctuation correlation in the present application represents the mutual dependence between different abnormal operating states of the breathing trainer during the dynamic change process. The larger the value corresponding to the fluctuation correlation, the greater the degree of fluctuation influence between different abnormal operating states when the breathing trainer operates abnormally, and the smaller the value corresponding to the fluctuation correlation, the smaller the degree of fluctuation influence between different abnormal operating states when the breathing trainer operates abnormally. It will not be repeated here.

[0035] In step 103, baseline data of the breathing trainer in the wireless monitoring ad hoc network under normal operating conditions is collected, and the differences in the operating conditions of the breathing trainer under different training intensities are determined based on the baseline data and the interaction information between the breathing trainer and the user. The parameter deviation of the breathing trainer in the wireless monitoring ad hoc network under normal operating conditions is determined based on the differences and the changing trend of the operating parameters in the normal operating data.

[0036] It should be noted that the baseline data in the present application represents the standard operating parameters of the breathing trainer under normal conditions, and the baseline data is an important basis for determining whether the breathing trainer in the wireless monitoring ad hoc network has a fault or abnormality. In specific implementation, the airflow rate, pressure, temperature and other data can be collected when the breathing trainer in the wireless monitoring ad hoc network is in stable operation and without faults, and the user uses the breathing trainer normally. All the obtained data will constitute the baseline data of the breathing trainer in the wireless monitoring ad hoc network under normal operating conditions.

[0037] In some embodiments, determining the differences in the operating states of the breathing trainer at different training intensities based on the baseline data and the interaction information between the breathing trainer and the user can be achieved by using the following steps: Obtaining interaction information between the breathing trainer and the user; Extracting difference factors of the breathing trainer at various training intensities based on the interaction information and the baseline data; The differences in the operating status of the breathing trainer under different training intensities are determined by all difference factors.

[0038] It should be noted that the interaction information between the breathing trainer and the user includes the user's behavioral data when using the breathing trainer, such as: training intensity (such as light, medium, and heavy), training time (training duration), user feedback (such as breathing difficulty, heart rate, etc.), and device response data (such as adjustment of airflow rate, pressure changes, temperature changes, etc.); in specific implementation, it can be obtained through the interface of the breathing trainer or the connection method with the breathing trainer device (such as mobile phone App, smart wearable device, etc.), and other methods can also be used to obtain in other embodiments, which is not limited here.

[0039] In specific implementation, the difference factor in the present application represents the parameter change characteristics of the breathing trainer at different training intensities, which is used to measure the impact of the training intensity on the operating state of the breathing trainer; extracting the difference factor of the breathing trainer at each training intensities based on the interaction information and the baseline data can be implemented in the following manner, namely: first, the difference between the device response data of the breathing trainer at each training intensity and the baseline data can be calculated based on the interaction information and the baseline data through deep learning and reinforcement learning, wherein the difference can be quantified using methods such as Euclidean distance and root mean square error (RMSE), and the quantified difference value is used as the difference factor of the breathing trainer at each training intensity. In other embodiments, other methods can also be used for determination, which is not limited here; determining the difference of the operating state of the breathing trainer at different training intensities through all difference factors can be implemented in the following manner, namely: the average value of all difference factors can be used as the difference of the operating state of the breathing trainer at different training intensities. In other embodiments, other methods can also be used for determination, which is not limited here.

[0040] It should be noted that the dissimilarity in the present application indicates the degree of difference between the operating states of the breathing trainer under different training intensities. The greater the dissimilarity, the greater the degree of difference between the operating states of the breathing trainer under different training intensities. The smaller the dissimilarity, the smaller the degree of difference between the operating states of the breathing trainer under different training intensities. Therefore, the change in the operating state of the breathing trainer under different training intensities can be understood through the dissimilarity.

[0041] In some embodiments, determining the parameter deviation of the breathing trainer in the wireless monitoring ad hoc network under normal operating conditions based on the difference and the change trend of the operating parameters in the normal operating data can be achieved by using the following steps: determining a time series of an operating parameter in the normal operating data; Extracting the variation of the operating parameters of the breathing trainer from the time series, and using the variation as the variation trend of the operating parameters in the normal operation data; The parameter deviation of the breathing trainer in the wireless monitoring ad hoc network under normal operating conditions is determined by the difference and the variation.

[0042] In specific implementation, the time series in the present application represents the sequence of all operating parameters of the breathing trainer under normal working conditions changing with time. Determining the time series of the operating parameters in the normal operating data can be implemented in the following manner, namely, sorting the operating parameters in the normal operating data in chronological order, thereby obtaining the time series of the operating parameters in the normal operating data; extracting the variation of the operating parameters of the breathing trainer from the time series can be implemented in the following manner, namely, using a statistical analysis method (such as a sliding average method, a weighted moving average, a linear regression, etc.) to identify and extract the degree of variation of the operating parameters in the time series, and using the extracted result as the variation of the operating parameters of the breathing trainer. In other embodiments, other methods can also be used for extraction, which is not limited here; determining the parameter deviation of the breathing trainer in the wireless monitoring ad hoc network under normal operating conditions by the dissimilarity and the variation can be implemented in the following manner, namely, adding the variation trend to the value 1 to obtain the sum, and then multiplying the sum by the dissimilarity to obtain the result as the parameter deviation of the breathing trainer in the wireless monitoring ad hoc network under normal operating conditions. In other embodiments, other methods can also be used for determination, which is not limited here.

[0043] It should be noted that the change trend in the present application represents the change of the operating parameters of the breathing trainer under normal operating conditions; in addition, the parameter deviation represents the degree of deviation between the actual operating parameters of the breathing trainer and the expected ones. The larger the parameter deviation, the greater the deviation between the actual operating parameters of the breathing trainer and the expected ones, and the smaller the parameter deviation, the smaller the deviation between the actual operating parameters of the breathing trainer and the expected ones.

[0044] In step 104, a state change index of the current operating state of the breathing trainer in the wireless monitoring ad hoc network is determined by the fluctuation correlation degree and the parameter deviation.

[0045] In some embodiments, determining the state change index of the current running state of the breathing trainer in the wireless monitoring ad hoc network by using the fluctuation correlation and the parameter deviation can be implemented by the following steps: Obtain the current training intensity parameters of the breathing trainer in the wireless monitoring ad hoc network; Determine a state matching value between the current running state and the standard running state of the breathing trainer by using the training intensity parameter and the fluctuation correlation degree; The state change index of the current running state of the breathing trainer in the wireless monitoring ad hoc network is determined by the state matching value and the parameter deviation.

[0046] In specific implementation, the training intensity parameter in the present application represents a parameter related to the breathing training intensity in the breathing trainer. Acquiring the current training intensity parameter of the breathing trainer in the wireless monitoring ad hoc network can be implemented in the following manner, namely: the training intensity parameter currently set by the user can be acquired from the user interface (such as a display screen, a touch screen, etc.) of the breathing trainer in the wireless monitoring ad hoc network, including parameters such as the duration of inhalation and exhalation, airflow rate, and pressure level; the state matching value represents the degree of matching between the current operating state of the breathing trainer and the standard operating state. The larger the state matching value, the higher the degree of matching between the current operating state of the breathing trainer and the standard operating state. The smaller the state matching value, the lower the degree of matching between the current operating state of the breathing trainer and the standard operating state. Determining the state matching value between the current operating state of the breathing trainer and the standard operating state by using the training intensity parameter and the fluctuation correlation degree can be implemented in the following manner, namely: first, obtaining the state matching value from the breathing trainer. The method comprises the steps of: obtaining a standard operating state of the breathing trainer (including: standard operating parameters and performance indicators of the breathing trainer) from the instruction manual of the breathing trainer, and then quantifying the degree of matching between the current operating state of the breathing trainer and the standard operating state based on the training intensity parameter and the fluctuation correlation through a machine learning model, and using the obtained quantification result as a state matching value between the current operating state of the breathing trainer and the standard operating state, wherein the algorithm framework of the machine learning model can adopt a support vector regression algorithm, and other algorithm structures can also be adopted in other embodiments, which are not limited here; determining the state change index of the current operating state of the breathing trainer in the wireless monitoring ad hoc network by the state matching value and the parameter deviation can be implemented in the following manner, that is, the product value of the state matching value and the parameter deviation can be used as the state change index of the current operating state of the breathing trainer in the wireless monitoring ad hoc network, and other methods can also be used to determine it in other embodiments, which are not limited here.

[0047] It should be noted that the state change index in the present application indicates the degree of change of the current operating state of the breathing trainer. The larger the state change index, the higher the degree of variation of the current operating state of the breathing trainer. The smaller the state change index, the lower the degree of variation of the current operating state of the breathing trainer. Therefore, the state change index is used to judge the health status or operating risk of the breathing trainer.

[0048] In step 105, the abnormal operation state of the breathing trainer is monitored according to the state change index, and a state warning is sent to a monitoring center through a wireless monitoring ad hoc network.

[0049] In some embodiments, monitoring the abnormal operation state of the breathing trainer according to the state change index can be achieved by the following steps: Determine anomaly thresholds for a breathing trainer in a wireless monitoring ad hoc network; When the state change index exceeds the abnormal threshold, the current operating state of the breathing trainer is determined to be an abnormal operating state.

[0050] It should be noted that the abnormal threshold in the present application is a key indicator for determining whether the breathing trainer is in an abnormal operating state. As a preferred embodiment, determining the abnormal threshold of the breathing trainer in the wireless monitoring ad hoc network can be achieved in the following manner, namely: the abnormal threshold of the breathing trainer in the wireless monitoring ad hoc network can be set based on the experience of experts in related fields and historical experimental data (the degree of abnormality of the breathing trainer that operated abnormally in historical experiments) through a machine learning algorithm. In other embodiments, other methods can also be used for determination, which is not limited here; when the state change index exceeds the abnormal threshold, the current operating state of the breathing trainer is determined to be an abnormal operating state, and the determination result is sent to the monitoring center through the wireless monitoring ad hoc network, providing comprehensive support for the subsequent maintenance of the breathing trainer and user health management.

[0051] In some embodiments, if the state change index does not exceed the abnormal threshold, continuous monitoring of the breathing trainer in the wireless monitoring ad hoc network is maintained to ensure that any abnormal changes are discovered in time during subsequent operation, and the changes in the operating state of the breathing trainer are fed back to users and technicians, which can improve the user experience and fault prevention capabilities of the breathing trainer.

[0052] In addition, in another aspect of the present application, in some embodiments, the present application provides an intelligent monitoring system for a breathing trainer, the system comprising a monitoring center and a breathing trainer, the monitoring center and the breathing trainer construct a wireless monitoring ad hoc network through Z-Wave, the monitoring center comprises a state monitoring unit, reference Figure 4, which is a schematic diagram of the structure of a state monitoring unit according to some embodiments of the present application, the state monitoring unit 400 includes: a monitoring module 401, a processing module 402 and an execution module 403, which are described as follows: Monitoring module 401, in the present application, monitoring module 401 is mainly used to monitor the operating parameters of the breathing trainer in the wireless monitoring ad hoc network during the breathing training process, and then obtain the normal operating data and abnormal operating data of the breathing trainer; Processing module 402, in the present application, the processing module 402 is mainly used to extract multiple abnormal operation features in the breathing training process from the abnormal operation data, and then perform correlation analysis on all the abnormal operation features to obtain the coupling relationship between the abnormal operation states of the breathing trainer when the breathing trainer performs breathing training, and determine the fluctuation correlation degree of the breathing trainer in the wireless monitoring ad hoc network under the abnormal operation state through the coupling relationship; The processing module 402 in the present application is also used to collect baseline data of the breathing trainer in the wireless monitoring ad hoc network under normal operating conditions, determine the differences in the operating conditions of the breathing trainer under different training intensities based on the baseline data and the interaction information between the breathing trainer and the user, and determine the parameter deviation of the breathing trainer in the wireless monitoring ad hoc network under normal operating conditions based on the differences and the change trend of the operating parameters in the normal operating data; The processing module 402 in the present application is also used to determine the state change index of the current operating state of the breathing trainer in the wireless monitoring ad hoc network through the fluctuation correlation and the parameter deviation; Execution module 403, in the present application, execution module 403 is mainly used to monitor the abnormal operation state of the breathing trainer according to the state change index, and send a state warning to the monitoring center through the wireless monitoring ad hoc network.

[0053] The above describes in detail the examples of the intelligent monitoring system and method of the breathing trainer provided by the embodiments of the present application. It can be understood that in order to realize the above functions, the corresponding device includes hardware structures and / or software modules corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

[0054] In some embodiments, the present application also provides a computer device, which includes a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned intelligent monitoring method.

[0055] In some embodiments, reference Figure 5 , the dotted line in the figure indicates that the unit or the module is optional, and the figure is a schematic diagram of the structure of the computer device implementing the intelligent monitoring method of the present application. The intelligent monitoring method in the above embodiment can be Figure 5 The computer device 500 shown in the figure is implemented, and the computer device 500 includes at least one processor 501, a memory 502 and at least one communication unit 505. The computer device 500 can be a terminal device, a server or a chip.

[0056] The processor 501 may be a general-purpose processor or a special-purpose processor. For example, the processor 501 may be a central processing unit (CPU), which may be used to control the computer device 500, execute software programs, and process data of the software programs. The computer device 500 may also include a communication unit 505 to implement signal input (reception) and output (transmission).

[0057] For example, the computer device 500 may be a chip, the communication unit 505 may be an input and / or output circuit of the chip, or the communication unit 505 may be a communication interface of the chip, and the chip may be a component of a terminal device, a network device, or other devices.

[0058] For another example, the computer device 500 may be a terminal device or a server, and the communication unit 505 may be a transceiver of the terminal device or the server, or the communication unit 505 may be a transceiver circuit of the terminal device or the server.

[0059] The computer device 500 may include one or more memories 502, on which a program 504 is stored. The program 504 can be executed by the processor 501 to generate instructions 503, so that the processor 501 performs the method described in the above method embodiment according to the instructions 503. Optionally, data (such as a target audit model) can also be stored in the memory 502. Optionally, the processor 501 can also read the data stored in the memory 502, and the data can be stored at the same storage address as the program 504, or the data can be stored at a different storage address from the program 504.

[0060] The processor 501 and the memory 502 may be provided separately or integrated together, for example, integrated on a system on chip (SOC) of the terminal device.

[0061] It should be understood that each step of the above method embodiment can be completed by a hardware-based logic circuit or software-based instructions in the processor 501. The processor 501 can be a CPU, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, such as discrete gates, transistor logic devices or discrete hardware components.

[0062] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0063] For example, in some embodiments, the present application also provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer implements the above-mentioned intelligent monitoring method when executing.

[0064] In summary, in the intelligent monitoring system and method of the breathing trainer disclosed in the embodiment of the present application, the operating parameters of the breathing trainer in the wireless monitoring ad hoc network during the breathing training process are monitored to obtain the normal operating data and abnormal operating data of the breathing trainer; multiple abnormal operating features in the breathing training process are extracted from the abnormal operating data, and then all the abnormal operating features are subjected to correlation analysis to obtain the coupling relationship between the abnormal operating states of the breathing trainer when performing breathing training, and the fluctuation correlation degree of the breathing trainer in the wireless monitoring ad hoc network under the abnormal operating state is determined through the coupling relationship; the baseline data of the breathing trainer in the wireless monitoring ad hoc network under the normal operating state is collected , based on the baseline data and the interactive information between the breathing trainer and the user, the differences in the operating states of the breathing trainer under different training intensities are determined, and the parameter deviation of the breathing trainer in the wireless monitoring ad hoc network under normal operating conditions is determined by the differences and the change trend of the operating parameters in the normal operating data; the state change index of the current operating state of the breathing trainer in the wireless monitoring ad hoc network is determined by the fluctuation correlation and the parameter deviation; the abnormal operating state of the breathing trainer is monitored according to the state change index, and a state warning is sent to a monitoring center through the wireless monitoring ad hoc network; dynamic abnormality recognition can be realized during the operation of the breathing trainer, thereby improving the intelligent monitoring capability of the breathing trainer.

[0065] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0066] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. An intelligent monitoring method, used for a monitoring center to monitor the status of a breathing trainer, wherein the monitoring center and the breathing trainer construct a wireless monitoring ad hoc network through Z-Wave, characterized in that: The method comprises the following steps: Monitoring the operating parameters of the breathing trainer in the wireless monitoring ad hoc network during the breathing training process, thereby obtaining normal operating data and abnormal operating data of the breathing trainer; Extracting multiple abnormal operation features in the breathing training process from the abnormal operation data, and then performing correlation analysis on all the abnormal operation features to obtain the coupling relationship between the abnormal operation states of the breathing trainer during the breathing training, and determining the fluctuation correlation degree of the breathing trainer in the wireless monitoring ad hoc network under the abnormal operation state through the coupling relationship; Collecting baseline data of a breathing trainer in a wireless monitoring ad hoc network under normal operating conditions, determining differences in operating conditions of the breathing trainer under different training intensities based on the baseline data and interaction information between the breathing trainer and the user, and determining parameter deviations of the breathing trainer in the wireless monitoring ad hoc network under normal operating conditions based on the differences and a change trend of operating parameters in the normal operating data; Determine the state change index of the current operating state of the breathing trainer in the wireless monitoring ad hoc network through the fluctuation correlation and the parameter deviation; The abnormal operation state of the breathing trainer is monitored according to the state change index, and a state warning is sent to a monitoring center through a wireless monitoring ad hoc network.

2. The method according to claim 1, characterized in that Extracting multiple abnormal operation features during the breathing training process from the abnormal operation data specifically includes: Performing abnormal classification on the abnormal operation data to obtain multiple abnormal state classes; Extract the main frequency component of each abnormal state class based on spectrum analysis; Multiple abnormal operating characteristics during breathing training were identified through all main frequency components.

3. The method according to claim 1, characterized in that The correlation analysis of all abnormal operation characteristics is carried out to obtain the coupling relationship between the abnormal operation states of the breathing trainer during breathing training, which specifically includes: Determine the correlation between various abnormal operation characteristics; Determine the correlation matrix between each abnormal operation feature from all the correlations; The coupling relationship between abnormal operating states of the breathing trainer during breathing training is determined according to the correlation matrix.

4. The method according to claim 1, characterized in that Determining the fluctuation correlation of the breathing trainer in the wireless monitoring ad hoc network under abnormal operation state through the coupling relationship specifically includes: Determine the dynamic interaction intensity between abnormal operation states of the breathing trainer in the wireless monitoring ad hoc network when performing breathing training based on the coupling relationship; The fluctuation correlation degree of the breathing trainer in the wireless monitoring ad hoc network under abnormal operation state is determined by the dynamic interaction strength.

5. The method according to claim 1, characterized in that Determining the differences in the operating states of the breathing trainer under different training intensities based on the baseline data and the interaction information between the breathing trainer and the user specifically includes: Obtaining interaction information between the breathing trainer and the user; Extracting difference factors of the breathing trainer at various training intensities based on the interaction information and the baseline data; The differences in the operating status of the breathing trainer under different training intensities are determined by all difference factors.

6. The method according to claim 1, characterized in that Determining the state change index of the current operating state of the breathing trainer in the wireless monitoring ad hoc network by using the fluctuation correlation and the parameter deviation specifically includes: Obtain the current training intensity parameters of the breathing trainer in the wireless monitoring ad hoc network; Determine a state matching value between the current running state and the standard running state of the breathing trainer by using the training intensity parameter and the fluctuation correlation degree; The state change index of the current running state of the breathing trainer in the wireless monitoring ad hoc network is determined by the state matching value and the parameter deviation.

7. The method according to claim 1, characterized in that Monitoring the abnormal operation state of the breathing trainer according to the state change index specifically includes: Determine anomaly thresholds for a breathing trainer in a wireless monitoring ad hoc network; When the state change index exceeds the abnormal threshold, the current operating state of the breathing trainer is determined to be an abnormal operating state.

8. An intelligent monitoring system for a breathing trainer, comprising a monitoring center and a breathing trainer, wherein the monitoring center and the breathing trainer construct a wireless monitoring ad hoc network via Z-Wave, and the monitoring center comprises a state monitoring unit, characterized in that: The state monitoring unit comprises: A monitoring module is used to monitor the operating parameters of the breathing trainer in the wireless monitoring ad hoc network during the breathing training process, and then obtain the normal operating data and abnormal operating data of the breathing trainer; A processing module, for extracting a plurality of abnormal operation features in the breathing training process from the abnormal operation data, and then performing correlation analysis on all the abnormal operation features to obtain a coupling relationship between abnormal operation states of the breathing trainer when the breathing trainer performs breathing training, and determining a fluctuation correlation degree of the breathing trainer in the wireless monitoring ad hoc network in the abnormal operation state through the coupling relationship; The processing module is further used to collect baseline data of the breathing trainer in the wireless monitoring ad hoc network under normal operating conditions, determine the differences in the operating conditions of the breathing trainer under different training intensities based on the baseline data and the interaction information between the breathing trainer and the user, and determine the parameter deviation of the breathing trainer in the wireless monitoring ad hoc network under normal operating conditions based on the differences and the change trend of the operating parameters in the normal operating data; The processing module is further used to determine the state change index of the current operating state of the breathing trainer in the wireless monitoring ad hoc network through the fluctuation correlation degree and the parameter deviation; The execution module is used to monitor the abnormal operation state of the breathing trainer according to the state change index, and send a state warning to the monitoring center through the wireless monitoring ad hoc network.

9. A computer device, characterized in that: The computer device comprises a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the intelligent monitoring method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions or codes, and when the instructions or codes are executed on a computer, the computer implements the intelligent monitoring method according to any one of claims 1 to 7.

Images