A control method for a respiratory monitor combined with sleeping posture analysis

Abstract

The present invention discloses a control method for a respiratory monitor combined with sleeping posture analysis, which relates to the technical field of respiratory monitoring devices. A cascaded sensor is introduced to determine the sleeping posture variable by collecting the state of the target user, interactively record the respiratory monitoring and explore the relative relationship between the sleeping posture - monitoring control conditions. An adaptive control module is developed in the control system of the respiratory monitor, with the sleeping posture variable as the regulation target, execute the adjustment decision based on the adaptive control module, trigger the acquisition of the conditional signal of the target user, determine the respiratory signal, transmit the respiratory signal back and perform histogram segmentation and counting, determine the respiratory state and perform feedback response control on the respiratory monitor. It is used to solve the technical problem of how to introduce sleeping posture analysis in respiratory monitoring and achieve precise adaptive control in the prior art. It realizes the adaptive respiratory monitoring regulation based on the user's posture, and can effectively improve the adaptability and accuracy of the monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of respiratory monitoring devices, and particularly to a control method for a respiratory monitor combined with sleeping posture analysis. Background Art

[0002] Currently, traditional respiratory monitoring techniques mainly focus on the analysis of respiratory signals, such as chest and abdomen movements, airflow changes, etc., often ignoring the impact of sleeping postures on respiratory states. During sleep, changes in a user's sleeping posture can directly affect the smoothness of breathing, respiratory rate, and ventilation volume. Especially in cases of sleep apnea, snoring, etc., the sleeping posture is crucial for regulating the respiratory state.

[0003] Existing respiratory monitoring techniques usually collect data through a single signal channel, limited to physiological signals such as chest and abdomen movements or airflow changes, and are unable to accurately identify and analyze the dynamic relationship between sleeping postures and respiratory states. Such traditional methods have certain limitations. Especially when faced with complex sleeping posture changes and corresponding respiratory changes, they often cannot adjust the monitoring strategy in real time and are difficult to provide personalized health management solutions.

[0004] Currently, although there are some advanced multi-parameter monitoring techniques, they often lack effective integration and collaborative processing mechanisms and cannot effectively combine the monitoring information of sleeping posture changes and respiratory states, resulting in an inability to comprehensively and accurately evaluate the user's sleep quality and health status.

[0005] Therefore, how to introduce sleeping posture analysis in respiratory monitoring and achieve precise adaptive control has become a key challenge in the current technological development. Summary of the Invention

[0006] This application provides a control method for a respiratory monitor combined with sleeping posture analysis to solve the technical problem of how to introduce sleeping posture analysis in respiratory monitoring and achieve precise adaptive control existing in the prior art.

[0007] In view of the above problems, this application provides a control method for a respiratory monitor combined with sleeping posture analysis.

[0008] The present application provides a control method for a respiratory monitor combined with sleep posture analysis. The method includes: introducing a cascaded sensor, determining a sleep posture variable by collecting the state of a target user and coupling the frame difference between the attitude point cloud data and the cascaded sensing data, wherein the cascaded sensor is used to detect the pressure data at various parts of the human body; interacting with the respiratory monitoring records and mining the relative relationship between the sleep posture - monitoring control conditions, and developing an adaptive control module within the control system of the respiratory monitor, wherein the monitoring control conditions are determined by dividing the signal channels of the respiratory monitor and grading the monitoring reference frequencies; taking the sleep posture variable as the regulation target, executing the regulation decision based on the adaptive control module, triggering the collection of conditional signals of the target user to determine the respiratory signal; transmitting back the respiratory signal and performing histogram segmentation and counting to determine the respiratory state and perform feedback response control on the respiratory monitor.

[0009] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0010] A control method for a respiratory monitor combined with sleep posture analysis provided by an embodiment of the present application introduces a cascaded sensor, determines a sleep posture variable by collecting the state of a target user and coupling the frame difference between the attitude point cloud data and the cascaded sensing data, wherein the cascaded sensor is used to detect the pressure data at various parts of the human body; interacts with the respiratory monitoring records and mines the relative relationship between the sleep posture - monitoring control conditions, and develops an adaptive control module within the control system of the respiratory monitor, wherein the monitoring control conditions are determined by dividing the signal channels of the respiratory monitor and grading the monitoring reference frequencies; takes the sleep posture variable as the regulation target, executes the regulation decision based on the adaptive control module, triggers the collection of conditional signals of the target user to determine the respiratory signal; transmits back the respiratory signal and performs histogram segmentation and counting to determine the respiratory state and perform feedback response control on the respiratory monitor. It is used to solve the technical problem of how to introduce sleep posture analysis in respiratory monitoring and achieve precise adaptive control in the prior art. It realizes the adaptive respiratory monitoring regulation based on the user's posture, and can effectively improve the adaptability and accuracy of the monitoring. Description of the Drawings

[0011] Figure 1 It is a schematic flow chart of a control method for a respiratory monitor combined with sleep posture analysis provided by the present application;

[0012] Figure 2 It is a schematic flow chart of mining the relative relationship between the sleep posture - monitoring control conditions in a control method for a respiratory monitor combined with sleep posture analysis provided by the present application. Detailed Embodiments

[0013] This application provides a control method for a respiratory monitor combined with sleep posture analysis. By introducing a cascaded sensor, the sleep posture variables are determined through state acquisition of the target user. The relative relationship between the sleep posture - monitoring control conditions is interactively recorded and mined for respiratory monitoring. An adaptive control module is developed within the control system of the respiratory monitor. With the sleep posture variables as the regulation target, the adjustment decision based on the adaptive control module is executed, triggering the acquisition of conditional signals for the target user, determining the respiratory signal, transmitting the respiratory signal back, and performing histogram segmentation and counting to determine the respiratory state and perform feedback response control on the respiratory monitor. It is used to solve the technical problem of how to introduce sleep posture analysis in respiratory monitoring and achieve precise adaptive control in the prior art.

[0014] Embodiment: As Figure 1 shown, this application provides a control method for a respiratory monitor combined with sleep posture analysis, and the method includes:

[0015] S1: Introduce a cascaded sensor, and determine the sleep posture variables by collecting the state of the target user and coupling the frame difference between the pose point cloud data and the cascaded sensing data, where the cascaded sensor is used to detect the pressure data at various parts of the human body.

[0016] In the embodiment of this application, the cascaded sensor is a structure in which multiple sensor nodes are connected in series and is used to detect the pressure data at various parts of the human body. This sensor can cover different parts of the human body and collect pressure distribution information including parts such as the back, shoulders, and waist. These pressure data help to judge the user's sleep posture and the potential impact brought by pressure changes.

[0017] Next, the state of the target user is collected. In this embodiment, the state of the target user not only refers to the user's physiological data but also includes the posture changes at different time periods during sleep. By collecting the pressure data in real time through the cascaded sensor, the system can obtain detailed information about the user's sleep posture, such as the contact area between the back and the bed surface, the pressure distribution between the shoulders and the pillow, etc., as the collected user state. It provides a basis for further analyzing the relationship between the sleep posture and the respiratory state.

[0018] Among them, the pose point cloud data is a three - dimensional data set representing the user's pose obtained through three - dimensional scanning technology, reflecting the relative positions and angular changes of various parts of the user during sleep. The pressure data provided by the cascaded sensor is combined with these pose data to form a multi - dimensional data model.

[0019] By coupling the pose point cloud data with the user state, the user's pose and force distribution can be measured, ensuring the completeness of the pose data.

[0020] Furthermore, through inter-frame difference, that is, by comparing two consecutive data and measuring the data difference, the change in the user's posture can be detected. The inter-frame difference technology can effectively distinguish the dynamic changes in sleeping postures, such as the transition from supine to side-lying or prone. The force distribution may also be different in the same posture, thereby revealing the specific variables of the sleeping posture.

[0021] Through the inter-frame difference calculation of the above data, the system can accurately determine the sleeping posture variables of the user at each time point. These variables may include information such as the user's torso angle, the positional relationship of the limbs, and the pressure contact with the bed surface. The sleeping posture variables provide an important basis for adjusting the breathing monitor, enabling it to adjust the parameters of breathing monitoring according to different sleeping postures, making the breathing monitoring more accurate and personalized.

[0022] In summary, by introducing cascaded sensors and posture point cloud data, combined with the inter-frame difference technology, the changes in the user's sleeping posture can be accurately captured and analyzed, thereby providing a more accurate basis for breathing monitoring, achieving the purpose of optimizing the monitoring effect and improving the level of health management.

[0023] Furthermore, for the determination of the sleeping posture variables, step S1 of this application includes:

[0024] Establish a communication connection between the cascaded sensor and the breathing monitor; introduce a synchronous timestamp constraint. The breathing monitor performs radar detection of the sleeping posture of the target user, synchronously triggers the transmission of the sensing data of the cascaded sensor, and determines the real-time posture point cloud and real-time cascaded sensing data; perform inter-frame difference coupling on the real-time posture point cloud and the real-time cascaded sensing data to determine the sleeping posture variables.

[0025] In this embodiment, first, a communication connection between the cascaded sensor and the breathing monitor is established. This step aims to ensure smooth data transmission between the cascaded sensor and the breathing monitor. The cascaded sensor monitors the user's pressure data through multiple sensor nodes, and the breathing monitor is responsible for collecting and processing the physiological data related to the user's breathing. To achieve data intercommunication, the cascaded sensor and the breathing monitor are connected through a wireless communication protocol (such as Wi-Fi, Bluetooth, etc.), enabling the real-time collected data to be seamlessly transmitted to the breathing monitor for further processing.

[0026] Subsequently, a synchronous timestamp constraint is introduced. The synchronous timestamp ensures the temporal consistency of the data collected by the cascaded sensor and the breathing monitor. By attaching a timestamp to each data collection point, the system can accurately identify the moment of data collection, thereby ensuring that the data from each sensor can be compared and analyzed in the same time dimension. This constraint mechanism ensures that when the system performs multi-data source analysis, it can accurately align the data from different sources, providing effective support for subsequent analysis.

[0027] Next, the respiration monitor performs radar detection of the sleeping posture of the target user. Specifically, the sleeping posture radar detection scans the sleeping posture of the target user through radar or other sensing technologies (such as infrared sensing, ultrasonic measurement, etc.), and obtains the body posture change data of the user in real time.

[0028] During this process, the sensing data transmission of the cascaded sensor is synchronously triggered. Through timestamp constraint, the acquisition actions of the respiration monitor and the cascaded sensor are synchronized to ensure that the data collected by both are strictly consistent in time. This synchronous triggering mechanism can ensure that when the respiration monitor performs sleeping posture radar detection, the cascaded sensor is simultaneously collecting the corresponding pressure data. These pressure data reflect the contact situation between various parts of the user's body and the bed surface, and can provide necessary information for further analysis of the user's sleeping posture.

[0029] Furthermore, by synchronously processing the data from the sleeping posture radar detection and the data transmitted back by the cascaded sensor, the system can obtain the real-time attitude point cloud (three-dimensional data representing the attitude) and the real-time cascaded sensing data (variation data recording the pressure of each part) of the user.

[0030] Further, inter-frame differential coupling is performed on the real-time attitude point cloud and the real-time cascaded sensing data. This step uses inter-frame differential technology to compare two consecutive frames of data to detect changes in the user's attitude and corresponding pressure changes. For example, for the attitude point cloud, by comparing the attitude point cloud data of the current frame with that of the previous frame, the body position changes of the user (such as changing from supine to lateral position, etc.) can be identified. At the same time, for the cascaded sensing data, by comparing the pressure distribution differences between the current frame and the previous frame, inter-frame difference can be used to capture minute pressure changes, so as to identify potential changes in the breathing pattern caused by attitude changes during the user's sleep.

[0031] Finally, through the results of inter-frame differential coupling, that is, the changes in the attitude point cloud and the force distribution, the sleeping posture variables of the user can be accurately calculated. These variables may include information such as the attitude angle of the user's body, the attitude change rate, and the pressure values of each part. These sleeping posture variables will be used as the basis for subsequent respiration monitoring adjustment to ensure that the respiration monitor can provide the optimal monitoring solution in different sleeping postures.

[0032] In summary, through precise data synchronization, real-time monitoring, and inter-frame differential coupling technology, this embodiment can effectively capture and analyze the changes in the user's sleeping posture, provide data support for the precise adjustment of the respiration monitor, and further optimize the effect of respiration monitoring.

[0033] Further, inter-frame differential coupling is performed on the real-time attitude point cloud and the real-time cascaded sensing data to determine the sleeping posture variables. Step S1 of this application includes:

[0034] Taking the upper attitude point cloud as the background frame and the real-time attitude point cloud as the state frame, perform inter-frame difference calculation to determine the first attitude variable; taking the upper-level cascade sensing data as the background frame and the real-time cascade sensing data as the state frame, perform inter-frame difference calculation to determine the second cascade sensing variable; couple the first attitude variable and the second cascade sensing variable based on the relative pose to determine the sleeping posture variable.

[0035] In the embodiment of the present application, taking the upper attitude point cloud as the background frame and the real-time attitude point cloud as the state frame, perform inter-frame difference calculation to determine the first attitude variable. Specifically, the attitude point cloud is obtained through sensor or radar technology, which reflects the three-dimensional coordinates and postures of various parts of the user. In this step, the background frame refers to the attitude point cloud data at the previous moment, that is, the upper attitude point cloud. The state frame refers to the attitude point cloud data at the current moment. By comparing these two point cloud data, the system can calculate the change in the user's posture between two time points. This change amount is the first attitude variable, which may include changes in the trunk angle, rotation or bending of limb positions, etc. Inter-frame difference calculation helps to capture these subtle attitude changes and provides a basis for further analyzing the user's sleeping posture.

[0036] Next, the cascade sensor monitors the pressure data of various parts of the user through multiple nodes. In this step, the background frame refers to the pressure sensing data at the previous moment, and the state frame refers to the sensing data at the current moment. By performing difference calculation on these two data, that is, comparing the previous frame frequency and the current frame frequency according to the pressure distribution position, measuring the difference amount, to determine the change in the user's body pressure distribution, and then obtaining the second cascade sensing variable. This variable may reflect the pressure changes in different parts (such as the back, shoulders, waist, etc.) between two moments, thus revealing the impact of sleeping posture changes on the body pressure distribution.

[0037] Then, combine the first attitude variable and the second cascade sensing variable, and further determine the sleeping posture variable through the coupling method of relative pose. Relative pose coupling means combining the attitude change and the corresponding pressure change for combined analysis, considering the impact of different postures on different parts of the body. For example, when the user changes from supine to side lying, the pressure distribution on the back will change, and at the same time, the angle of the trunk will also change. By combining this information, the system can accurately calculate the sleeping posture variables of the user, which may include the angle of the trunk, the pressure distribution of various parts of the body, the rate of posture change, etc.

[0038] In summary, by performing inter-frame difference calculation on the attitude point cloud and the cascade sensing data and coupling based on the relative pose, it is possible to accurately analyze the changes in the user's sleeping posture, providing an important basis for subsequent breathing monitoring and adjustment, thereby achieving more precise personalized health management.

[0039] S2: Interactively monitor and record breathing, and mine the relative relationship between the sleeping position and the monitoring control conditions. Develop an adaptive control module within the control system of the breathing monitor, where the monitoring control conditions are determined by dividing the signal channels of the breathing monitor and grading the monitoring reference frequencies.

[0040] In the embodiments of the present application, the breathing monitoring and recording refers to the real-time collection and recording of the user's breathing data through a breathing monitor. These data include physiological parameters such as breathing frequency, breathing waveform, and ventilation volume. By interactively comparing and analyzing with the user's sleeping position data, the system can mine the relative relationship between the sleeping position and the breathing monitoring conditions. For example, the system may find that certain sleeping positions (such as supine) may cause changes in breathing frequency and breathing mode (such as thoracic and abdominal breathing), then the monitoring requirements corresponding to the breathing frequency and breathing mode are the monitoring control conditions for the current sleeping position, while other sleeping positions (such as side lying) may have different effects on the breathing waveform. Mining these relative relationships provides an important basis for subsequent adjustment of the control module.

[0041] Next, develop an adaptive control module within the control system of the breathing monitor. The main function of the adaptive control module is to automatically adjust the working parameters of the system according to the real-time monitoring data to meet the needs of different users. In this embodiment, the adaptive control module can dynamically adjust the working mode of the breathing monitor according to the changes in the user's sleeping position and breathing state. For example, when the system detects a change in the user's sleeping position, the control module can automatically adjust the acquisition type, frequency, etc. of the breathing signal to ensure the accuracy and adaptability of the monitoring.

[0042] In the present application, the signal channel division refers to dividing the acquisition signals of the breathing monitor into multiple channels to process different types of physiological signals separately. For example, the breathing signal can be divided into a thoracic and abdominal movement signal channel and an airflow breathing signal channel, and can also include a breathing sound signal, etc. Among them, the thoracic and abdominal movement signal channel is used to monitor the movement changes of the chest and abdomen, and the airflow breathing signal channel is used to monitor the ventilation flow rate, temperature changes, etc. Through this division, the system can collect various types of data related to breathing more accurately.

[0043] The monitoring reference frequency grading refers to the hierarchical management of the monitoring frequency of the signal according to different physiological signal characteristics. For example, for the thoracic and abdominal movement signal, the system may choose a lower sampling frequency, while for the monitoring of airflow changes, a higher frequency may be required to capture subtle fluctuations. By adjusting the monitoring frequency, the system can optimize the accuracy and efficiency of data acquisition and reduce the acquisition of redundant data.

[0044] Through signal channel division and monitoring parameter frequency grading, the system can determine the monitoring control conditions, that is, under different sleeping postures, the corresponding signal channels and monitoring parameter frequency levels, and adjust the operation of the respiratory monitor according to these conditions. The determination of the control conditions can ensure that the monitor can always accurately obtain respiratory data under different sleeping postures and perform appropriate processing and feedback.

[0045] In summary, in this embodiment, through the mining of the relationship between the sleeping posture and the monitoring conditions, the division of the signal channels, and the monitoring frequency grading, an adaptive control module is developed, which can dynamically adjust the parameters of the respiratory monitor to ensure accurate monitoring services under different sleeping postures and respiratory states. This process greatly improves the intelligence and personalization capabilities of the monitoring system.

[0046] Furthermore, as Figure 2 shown, the step S2 of this application for mining the relative relationship between the sleeping posture - monitoring control conditions includes:

[0047] Dividing the signal channels, where the signal channels at least include a first signal channel based on chest and abdomen respiration and a second signal channel based on airflow respiration. The signal elements of the first signal channel at least include the chest and abdomen undulations, and the signal elements of the second signal channel at least include temperature change, respiratory rate, and ventilation volume; dividing multiple levels of monitoring parameter frequencies; determining the monitoring control conditions based on the signal channels - multiple levels of monitoring parameter frequencies, and combining the respiratory monitoring records to mine the relative relationship between the sleeping posture - monitoring control conditions.

[0048] In this embodiment, the respiratory monitor is optimized by the division of the signal channels and the grading of the monitoring frequencies, combined with the relative relationship between the sleeping posture and the monitoring control conditions, so as to achieve more accurate respiratory monitoring.

[0049] First, divide the signal channels, where the signal channels at least include a first signal channel based on chest and abdomen respiration and a second signal channel based on airflow respiration. The division of the signal channels is to enable the monitor to process different types of physiological signals separately. In this embodiment, the first signal channel is mainly used to monitor the respiratory activities of the chest and abdomen, especially the undulations of the chest and abdomen during the breathing process. These changes reflect the chest and abdomen respiration of the user, can reflect the user's respiratory rhythm and depth, and help monitor the stability and depth of their breathing.

[0050] The second signal channel is used to monitor signals related to the airflow, including temperature change, respiratory rate, and ventilation volume. These elements can respectively reflect the temperature fluctuations of the airflow, the number of breaths per minute of the user, and the changes in the airflow volume during each breath. These signals help capture the fluctuations of the airflow and analyze the respiratory rate and air flow volume, so as to provide more comprehensive physiological information for the monitoring system.

[0051] Next, the monitoring frequency is divided into multiple levels, that is, different monitoring frequencies are set for different types of signals. Since the changes in chest and abdominal fluctuations are relatively slow, the system can set a lower sampling frequency, while airflow signals (such as temperature, respiratory rate, and ventilation volume) may contain relatively rapid fluctuations, so a higher sampling frequency is required to capture these subtle changes. Through this hierarchical sampling, the system can optimize data collection accuracy and processing efficiency and avoid the generation of redundant data.

[0052] Then, the monitoring control conditions are determined based on the signal channel-multi-level monitoring reference frequency. That is, based on the aforementioned division of the signal channels and the setting of the sampling frequency, the system can specify a suitable reference frequency for each signal channel as a monitoring control condition. Through this control condition, the system can ensure effective monitoring of various signals in different sleeping positions while avoiding unnecessary errors. For example, when the user is in a supine position, the changes in the chest and abdomen are small, and the system can reduce the monitoring frequency of the chest and abdomen signal channels, while for the airflow signal, a higher monitoring frequency still needs to be maintained.

[0053] Finally, combined with the respiratory monitoring records, the relative relationship between sleeping posture and monitoring control conditions is mined. By analyzing the respiratory monitoring data of users in different sleeping positions, the relative relationship between sleeping posture and monitoring control conditions can be mined. For example, certain sleeping positions may cause the amplitude of the chest and abdomen fluctuation signal to increase, while the airflow signal may show different fluctuation characteristics. According to the type of signal that needs to be collected in the sleeping position, the corresponding signal channel and frequency are configured. By mining this relative relationship, the system can better adjust the monitoring conditions to adapt to different changes in sleeping posture and improve monitoring accuracy.

[0054] In summary, this embodiment ensures that the respiratory monitoring system can accurately and effectively monitor physiological signals under different sleeping positions through the division of signal channels, the setting of multi-level monitoring frequency parameters, and the mining of the relative relationship between sleeping position and monitoring control conditions, providing reliable support for personalized health management and intervention.

[0055] Furthermore, the signal channel division step S2 of the present application includes:

[0056] A third signal channel is introduced, wherein the third signal channel is an auxiliary signal channel, and the third signal source includes at least an electrocardiogram signal and a respiratory sound signal, which is used to collect any one of the third signal sources; the control system is initialized and configured with the first signal channel and the second signal channel as the main ones and the third signal channel as the auxiliary one, wherein single-channel collection, multi-channel same-frequency collection, and multi-channel difference-frequency collection are used as the collection methods.

[0057] This embodiment further optimizes the signal acquisition and processing process of the respiratory monitor, enhancing the multi-dimensional monitoring ability of the system by introducing a third signal channel and adjusting the acquisition method.

[0058] First, a third signal channel is introduced. Here, the third signal channel is an auxiliary signal channel. The introduction of the third signal channel is to supplement the monitoring range not covered by the first signal channel (thoracoabdominal respiratory signal) and the second signal channel (airflow respiratory signal). The role of this channel is to obtain other physiological signals related to respiratory health. Through the acquisition of these signals, the respiratory state and health status can be comprehensively reflected. The third signal source at least includes an electrocardiogram signal and a breath sound signal. The electrocardiogram signal can provide cardiac activity data related to the respiratory system. Especially when monitoring the interaction between respiration and cardiac health, the electrocardiogram signal is of great significance. The breath sound signal can capture the sounds emitted during respiration (such as snoring or abnormal breathing sounds), which is crucial for identifying possible respiratory disorders (such as sleep apnea).

[0059] Next, with the first signal channel and the second signal channel as the main channels and the third signal channel as the auxiliary channel, the control system is initialized and configured. In this embodiment, the first signal channel and the second signal channel are mainly responsible for the core respiratory monitoring tasks. These two channels collect data from two dimensions: the chest and abdomen undulation and the airflow change respectively. The third signal channel, as an auxiliary signal channel, is used to supplement and enrich the monitoring content. During system initialization, by configuring the first, second, and third signal channels, the control system can comprehensively consider the importance and acquisition priority of various signals, ensuring that the system makes full use of the advantages of each channel when collecting data to achieve the optimal monitoring effect.

[0060] Then, single-channel acquisition, multi-channel synchronous acquisition, and multi-channel differential acquisition are used as the acquisition methods. This step illustrates how to obtain and process signals through different acquisition methods. In the single-channel acquisition mode, the system only collects data from one signal channel (such as the thoracoabdominal undulation signal channel). This mode is suitable for monitoring a certain type of signal or specific physiological index. In the multi-channel synchronous acquisition mode, the system simultaneously collects data from multiple signal channels (such as the thoracoabdominal undulation channel and the airflow signal channel) at the same frequency. This mode can synchronously monitor multiple physiological signals, thereby improving the real-time and comprehensiveness of the data. The multi-channel differential acquisition mode collects data at different sampling frequencies between different signal channels. This mode can optimize the signal timing while reducing unnecessary data redundancy and dynamically adjust the acquisition frequency according to the signal characteristics to improve the acquisition efficiency.

[0061] In summary, with this configuration, the system can capture various signals related to the user's respiratory health more comprehensively and accurately, thus providing more precise data support for health assessment and intervention.

[0062] S3: Using the sleep posture variable as the regulation target, execute the adjustment decision based on the adaptive control module, trigger the acquisition of conditional signals for the target user, and determine the respiratory signal.

[0063] First, use the sleep posture variable as the regulation target. The sleep posture variable refers to the parameters or characteristic data obtained from sleep posture analysis, which reflect the changes in the sleep posture state of the target user. Since different sleep postures may have different effects on breathing, using the sleep posture variable as the regulation target can enable the system to dynamically adjust the monitoring strategy according to the actual sleep posture state of the user, thereby improving the accuracy and sensitivity of monitoring.

[0064] Next, execute the adjustment decision based on the adaptive control module. The adaptive control module can automatically optimize the control parameters according to the sleep posture variable of the target user and other monitoring data. The execution process of the adjustment decision includes multiple aspects, such as selecting appropriate signal acquisition channels, setting the sampling frequency, adjusting the data processing strategy, etc. This decision-making process not only considers the user's sleep posture but also comprehensively considers other physiological signals (such as chest and abdomen fluctuations, airflow changes, etc.) to ensure that the system can continuously provide high-quality monitoring under changing environments and conditions.

[0065] Then, trigger the acquisition of conditional signals for the target user. Once the optimal monitoring conditions are determined based on the sleep posture variable and the adjustment decision of the adaptive control module, the system will start signal acquisition. At this time, the system will trigger the corresponding sensors or signal channels to collect data according to the sleep posture state of the target user, the required signal channels, and the adjusted sampling frequency. For example, if the user is in the supine position, the system may preferentially collect chest and abdomen fluctuation signals; if the user is in the lateral position, it may focus more on collecting airflow change signals.

[0066] Finally, determine the respiratory signal. Through the acquisition of conditional signals, the system will process and analyze the raw data returned by the sensors, and finally determine the respiratory signal of the target user. The respiratory signal usually includes information such as chest and abdomen fluctuations, airflow changes, respiratory rate, etc., and these data can reflect the user's breathing pattern and health status. The determination of the respiratory signal not only provides basic data for subsequent health assessment but also provides real-time feedback for respiratory intervention and optimal control.

[0067] In summary, in this embodiment, the adaptive control module based on the sleep posture variable adjusts the decision-making, combines the sleep posture state of the target user and other relevant signal data, triggers appropriate signal acquisition, and thus accurately captures and determines the user's breathing signal. Through this dynamic adjustment and precise acquisition, the system can provide more personalized and accurate breathing monitoring to ensure that the health information of the target user can be effectively captured in various environments.

[0068] Further, when executing the adjustment decision based on the adaptive control module, step S3 of this application includes:

[0069] Identify the sleep posture variable, determine the first dynamic variable based on the background frame, and the second dynamic variable based on the variable value; according to the first dynamic variable, based on the relative relationship, match the baseline control condition; according to the second dynamic variable, determine the conditional variable; use the conditional variable to adjust the baseline control condition to determine the target control condition.

[0070] This embodiment relates to the identification and adjustment of dynamic variables to optimize the control conditions of the breathing monitor, thereby improving the accuracy and response speed of monitoring.

[0071] First, identify the sleep posture variable, determine the first dynamic variable based on the background frame, and the second dynamic variable based on the variable value. In this step, the sleep posture variable refers to the numerical value or parameter obtained according to the sleep posture state of the target user, such as the posture angle, position change, etc. Through the dynamic analysis of these sleep posture variables, two types of key dynamic variables can be identified: taking the sleep posture state of the user in the previous frame frequency as the background frame, since the sleep posture of the user is in dynamic change, the sleep posture state of the user in the previous frame frequency, that is, the background frame also belongs to a variable. Each time an analysis is performed, the background frame needs to be updated, that is, the previous moment of the current moment is updated as the background frame, which is used as the first dynamic variable.

[0072] The second dynamic variable is calculated based on the variable value (such as the change of real-time pose point cloud or sensing data), reflecting the immediate change of the user's sleep posture. That is, compared with the variables of the background frame, these dynamic variables provide basic data support for subsequent control decisions.

[0073] Next, according to the first dynamic variable, based on the relative relationship, match the baseline control condition. That is, according to the first dynamic variable, that is, the state of the background frame, according to the corresponding relationship, match and determine the corresponding monitoring condition under the background frame as the baseline control condition.

[0074] Subsequently, based on the second dynamic variable, a conditional variable is determined. The second dynamic variable reflects the real-time changes in the current state of the target user. By analyzing this variable, it is possible to judge the immediate fluctuations or changes in the user's sleeping posture to determine whether it is necessary to adjust the monitoring control conditions and the adjustment amount. For example, if the second dynamic variable shows that the user's posture has changed significantly (such as turning over), the monitoring strategy needs to be adjusted according to this change. The conditional variable refers to the monitoring conditions that the system needs to adjust under such immediate changes, such as increasing the acquisition frequency of the respiratory signal or adjusting the monitoring sensitivity. Preferably, when the second dynamic variable is small, it may not be necessary to adjust the monitoring conditions, and the monitoring can continue based on the baseline control conditions.

[0075] In the specific implementation process, first, based on the relative relationship, the monitoring control conditions for the current posture are determined, and the difference between it and the baseline control conditions is calculated as the conditional variable. Currently, the sleep monitor should be under the baseline control conditions and be adjusted based on the conditional variable to meet the current monitoring requirements.

[0076] Then, using the conditional variable, that is, the adjustment amount of the monitoring control conditions, an adjustment is made on the basis of the baseline control conditions, and the adjusted result is used as the target control conditions to adapt to the current state change of the user. This adjustment usually involves changes in monitoring parameters, selection of signal channels, or sampling frequencies, etc. The target control conditions refer to the final adjustment made by the system according to the immediate changes, which can respond to the user's needs and state changes in real time to ensure optimal respiratory monitoring under different sleeping postures and physiological change conditions.

[0077] In summary, through the identification and analysis of the first dynamic variable and the second dynamic variable in this embodiment, a real-time adjustment process based on the sleeping posture variable is achieved. Through this dynamic adjustment, the system can flexibly match the baseline control conditions according to the sleeping posture changes of the target user and adjust to the target control conditions when necessary, so as to ensure that the respiratory monitor always provides accurate and personalized monitoring services.

[0078] S4: Transmit the respiratory signal back and perform histogram segmentation and counting to determine the respiratory state and perform feedback response control on the respiratory monitor.

[0079] This embodiment involves further determining the user's respiratory state through the transmission of the respiratory signal and histogram analysis, and performing feedback response control on the respiratory monitor according to the analysis results.

[0080] First, the respiratory signal is transmitted back and histogram segmentation and counting are performed. Respiratory signals are typically collected by sensors and transmitted back to the respiratory monitor's control system. These signals include physical indicators of the user's breathing, such as chest and abdominal rise and fall, and airflow changes. By transmitting these signals, the system can obtain real-time respiratory data for subsequent processing.

[0081] Next, the returned respiratory signal is analyzed using histogram segmentation and counting techniques. A histogram is a statistical graph that divides the signal amplitude values into multiple intervals (i.e., "bins") and counts the signal frequency within each interval. The purpose of histogram segmentation is to identify different phases of the respiratory cycle, such as inspiration, expiration, or pause, based on the amplitude changes of the respiratory signal. Histogram counting counts the signal amplitudes occurring within each interval to determine the characteristics of the respiratory waveform. This method allows the system to clearly identify different respiratory events.

[0082] Then, based on the signal amplitude and frequency distribution in the histogram, it is identified whether there are abnormal breathing patterns, such as shallow breathing, pauses, or frequent changes. Under normal circumstances, the breathing state should remain stable, and the signal amplitude and frequency distribution should conform to the expected pattern. If the histogram analysis indicates an abnormality, the system will determine whether the breathing is within the normal range based on the preset threshold, and then determine the user's health status. For example, if the signal amplitude is too large or too small, or the frequency is too high or too low, it may mean that the user is experiencing abnormal breathing fluctuations and a timely response is required.

[0083] Next, the respiratory monitor is subjected to feedback response control. Once the system determines the user's respiratory status through histogram analysis, it will perform feedback control on the respiratory monitor based on the analysis results. Feedback control means that the system adjusts the monitoring strategy and equipment settings according to the current respiratory status to better adapt to the user's health status. For example, when an abnormal user's respiratory state is detected (such as apnea or shallow breathing), the system will adjust the monitor's sensitivity, sampling frequency or alarm threshold, and even issue an alarm if necessary. The purpose of feedback response is to ensure that the respiratory monitor can provide timely and accurate monitoring under any circumstances, and that appropriate measures can be taken immediately when an abnormality is detected.

[0084] Furthermore, the above-mentioned step S4 of performing histogram segmentation and counting to determine the respiratory state includes:

[0085] The respiratory signal is transmitted back and filtered to reduce noise to determine a respiratory waveform; the respiratory waveform is identified based on the determination of respiratory cycles and respiratory events, signal segments are segmented and counted, and a signal histogram is constructed, wherein the horizontal axis represents the amplitude value of the signal and the vertical axis represents the frequency of the amplitude value; and the respiratory state is evaluated based on the signal histogram.

[0086] In this embodiment, the breathing state of the target user is evaluated through steps such as filtering and noise reduction, waveform recognition, signal segment segmentation, and constructing a signal histogram for the transmitted breathing signal.

[0087] First, the breathing signal is transmitted back and filtered for noise reduction to determine the breathing waveform. In this step, first, the breathing signal collected from the sensor and transmitted to the control system is preprocessed. Since the original signal may be interfered by noise (such as electromagnetic interference, motion noise, etc.), it is necessary to eliminate these noises through a filtering and noise reduction algorithm to ensure the accuracy of the signal. Common filtering methods include low-pass filtering, high-pass filtering, or band-pass filtering, and the specific selection depends on the required frequency range to be extracted. After the noise reduction process, the system obtains a clearer breathing waveform, which accurately reflects the user's breathing process, including the periodic changes of inhalation and exhalation.

[0088] Next, the breathing waveform is identified based on the determined breathing cycle and the breathing events are judged. After obtaining a clear breathing waveform, the periodic characteristics of the breathing waveform are further analyzed. The breathing cycle refers to the complete process of the user inhaling, exhaling, and then inhaling again. In this process, the starting and ending points of each inhalation and exhalation are identified through periodic detection, and then a complete breathing cycle is determined. The duration of each cycle and its changes can reflect the user's breathing state. For example, an overly short or long breathing cycle may indicate an abnormal state. In addition, the system can also judge breathing events based on the amplitude changes of the waveform, such as brief breathing pauses or frequent shallow breathing.

[0089] Then, signal segment segmentation and counting are performed. Based on the previously identified breathing cycle, the system divides the entire breathing waveform into several signal segments, and each signal segment represents a complete breathing cycle. Within each signal segment, the system counts the amplitude values and frequencies of the waveform, so as to extract the features that help evaluate the breathing state. For example, the system can calculate the maximum amplitude, minimum amplitude, frequency, and the cycle stability of the waveform for each signal segment. Through the detailed statistics of each signal segment, the system can comprehensively understand the user's breathing pattern.

[0090] Next, a signal histogram is constructed. After segmenting and counting each signal segment, the system constructs a signal histogram based on these count data. The histogram is a graphical representation of the data distribution, where the horizontal axis represents the amplitude value of the signal, and the vertical axis represents the frequency that appears within that amplitude value range. By constructing the signal histogram, the system can intuitively understand the distribution of the user's breathing signal. If the histogram shows a normal distribution, it indicates that the user's breathing state is normal; while if the histogram shows an abnormal distribution, such as the frequency being concentrated in a lower or higher amplitude range, it may mean that there is a breathing abnormality.

[0091] Finally, based on the signal histogram, the respiratory state is evaluated. The system evaluates the user's respiratory state based on the constructed histogram in combination with preset health criteria. For example, if the histogram shows that most of the signal amplitudes are concentrated in a lower range, it may indicate that the user has shallow breathing; if the amplitude is too large or the frequency is too high, it may indicate that the user has tachypnea or other abnormal problems. In this way, the system can accurately evaluate the user's respiratory state and provide timely feedback and adjustment.

[0092] In summary, it is possible to comprehensively analyze the user's respiratory signals and accurately evaluate their respiratory state. The implementation of this process ensures that the monitor can real-time monitor the user's respiratory state, issue an alarm or adjust the monitoring strategy when necessary, and provide more personalized health management.

[0093] Further, for feedback response control of the respiratory monitor, step S4 of this application includes:

[0094] Configure risk thresholds, where the risk thresholds include static thresholds and dynamic thresholds; evaluate the respiratory state according to the risk thresholds, and the respiratory monitor performs state feedback response control;

[0095] Among them, the state feedback response control includes: if the static threshold is exceeded and the dynamic threshold is exceeded, generate a first warning message; if the static threshold is exceeded or the dynamic threshold is exceeded, incrementally adjust the monitoring control conditions and generate a second warning message, where the intensity of the second warning message is lower than that of the first warning message.

[0096] In this embodiment, by configuring risk thresholds and performing state feedback response control, the respiratory state of the target user is real-time monitored and adjusted to ensure their health and safety.

[0097] First, configure risk thresholds, including static thresholds and dynamic thresholds. In this step, the system sets static thresholds and dynamic thresholds for the respiratory monitor. The static threshold is usually based on the theoretical standard values of normal human respiratory parameters (such as normal respiratory rate, depth, rhythm, etc.) and is applicable to long-term stable monitoring conditions. The dynamic threshold is set according to the changes in real-time monitoring data and can flexibly respond to fluctuations in the user's breathing pattern, and is applicable to detecting short-term abnormal changes. The combination of static thresholds and dynamic thresholds ensures that the monitoring system can comprehensively evaluate the respiratory state, whether it is long-term stability or short-term volatility.

[0098] Next, evaluate the respiratory state according to the risk thresholds. After the threshold configuration is completed, the system will compare the real-time collected respiratory signals with the static threshold and the dynamic threshold respectively. If the respiratory signal exceeds the set range (such as too fast or too slow respiratory rate, abnormal respiratory amplitude, etc.), the evaluation mechanism will be triggered, and further feedback measures will be determined according to the evaluation results.

[0099] Then, the respiratory monitor performs status feedback response control. According to the evaluation result, the respiratory monitor will take feedback response control measures. These control measures include generating warning information or adjusting monitoring conditions to promptly respond to the user's abnormal breathing.

[0100] Specifically, the status feedback response control includes: if the static threshold is exceeded and the dynamic threshold is exceeded, generate the first warning information. First, when the respiratory signal not only exceeds the range of the static threshold but also exceeds the limit of the dynamic threshold, it indicates that the respiratory state is abnormal and has changed significantly. At this time, the system will generate the first warning information to inform the user or medical staff that immediate action needs to be taken. Such warning information usually has a high intensity and a high priority and belongs to an emergency alarm.

[0101] Second, if the static threshold is exceeded or the dynamic threshold is exceeded. In this case, the system believes that although the monitoring data has deviated from the normal range, the degree of deviation is relatively small. Therefore, the second warning information is generated. The intensity of the second warning information is lower than that of the first warning information and usually indicates that the abnormality is a relatively minor situation. To further optimize the monitoring effect, the system will also adjust the monitoring control conditions accordingly, such as appropriately reducing the monitoring sensitivity or adjusting the monitoring frequency to adapt to the user's current condition.

[0102] By configuring the static threshold and the dynamic threshold and combining real-time evaluation, the respiratory monitor can flexibly respond to various respiratory states, promptly feedback abnormalities, and ensure the health of the user. At the same time, through the adjustment of warning information with different intensities and monitoring control conditions, the system can make corresponding treatments according to different degrees of abnormalities to ensure the accuracy and adaptability of monitoring.

[0103] A control method for a respiratory monitor combined with sleeping posture analysis provided by this application has the following technical effects:

[0104] 1. The solution designs multiple signal channels and multiple levels of monitoring frequencies. It respectively adopts the chest and abdomen respiratory signal channel, the airflow respiratory signal channel, and the auxiliary signal channel. Through multi-channel and multi-frequency signal acquisition, the system can comprehensively capture the multi-dimensional respiratory data of the target user and optimize the monitoring strategy according to the characteristics of different signal sources. It realizes the accurate monitoring of complex physiological states and improves the reliability and accuracy of the data.

[0105] 2. By introducing cascaded sensors, combining the frame difference calculation of sleeping posture point cloud data and cascaded sensing data, determining the sleeping posture variable, and adaptively adjusting the control conditions for accurate sleeping posture monitoring, the system can automatically adjust the monitoring strategy in real time under different sleeping postures to ensure that the personalized needs of each user are responded to, thereby improving the adaptability and intelligent level of the system.

[0106] 3. Based on the recognition of the respiratory cycle and the determination of respiratory events, construct a signal histogram. Through the analysis of the signal histogram, the changes in the respiratory pattern can be intuitively displayed, supporting more refined health assessments. Configure static and dynamic thresholds for evaluating the respiratory state and perform state feedback response control. By setting multi-level risk thresholds and warning mechanisms, the system can sensitively identify abnormal states and provide timely feedback. Alarms of different intensities help distinguish the severity of abnormalities, ensuring that the system can flexibly respond to mild or severe respiratory abnormalities and safeguard the health of users.

[0107] In summary, the present technical solution realizes an accurate and personalized respiratory monitoring system. The combination of technical points improves the stability, accuracy and response ability of the system, ensuring the provision of real-time and efficient health monitoring services in a complex physiological environment.

[0108] Through the foregoing detailed description of a method for controlling a respiratory monitor combined with sleep posture analysis in this specification, those skilled in the art can clearly know a method for controlling a respiratory monitor combined with sleep posture analysis in this embodiment. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description in the method part.

[0109] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A control method for a respiratory monitor combined with sleep posture analysis, characterized in that, The method includes: Introducing a cascaded sensor, determining a sleeping posture variable by collecting the state of the target user and coupling the inter-frame difference between the attitude point cloud data and the cascaded sensing data, wherein the cascaded sensor is used to detect the pressure data at various parts of the human body; Interactively monitoring respiration, recording and mining the relative relationship between the sleeping posture - monitoring control conditions, and developing an adaptive control module in the control system of the respiration monitor, wherein the monitoring control conditions are determined by dividing the signal channels of the respiration monitor and grading the monitoring reference frequencies; Taking the sleeping posture variable as the regulation target, executing the regulation decision based on the adaptive control module, triggering the acquisition of the conditional signal of the target user, and determining the respiration signal; Transmitting back the respiration signal and performing histogram segmentation and counting, determining the respiration state and performing feedback response control on the respiration monitor; Among them, the determination of the sleeping posture variable includes: Establishing a communication connection between the cascaded sensor and the respiration monitor; Introducing a synchronous timestamp constraint, the respiration monitor performs sleeping posture radar detection of the target user, synchronously triggers the transmission of the sensing data of the cascaded sensor, and determines the real-time attitude point cloud and the real-time cascaded sensing data; Performing inter-frame difference coupling on the real-time attitude point cloud and the real-time cascaded sensing data to determine the sleeping posture variable; Among them, performing inter-frame difference coupling on the real-time attitude point cloud and the real-time cascaded sensing data to determine the sleeping posture variable includes: Taking the upper attitude point cloud as the background frame and the real-time attitude point cloud as the state frame, performing inter-frame difference calculation to determine the first attitude variable; Taking the upper cascaded sensing data as the background frame and the real-time cascaded sensing data as the state frame, performing inter-frame difference calculation to determine the second cascaded sensing variable; Performing coupling based on the relative pose on the first attitude variable and the second cascaded sensing variable to determine the sleeping posture variable; Among them, the mining of the relative relationship between the sleeping posture - monitoring control conditions includes: Dividing the signal channels, wherein the signal channels at least include a first signal channel based on chest and abdomen respiration and a second signal channel based on airflow respiration, and the signal elements of the first signal channel at least include the chest and abdomen undulation, and the signal elements of the second signal channel at least include temperature change, respiration frequency, and ventilation volume; Dividing multiple levels of monitoring reference frequencies; Determining the monitoring control conditions based on the signal channel - multiple levels of monitoring reference frequencies, and mining the relative relationship between the sleeping posture - monitoring control conditions in combination with the respiration monitoring record; Among them, executing the regulation decision based on the adaptive control module includes: Identifying the sleeping posture variable, determining a first dynamic variable based on the background frame and a second dynamic variable based on the variable value; According to the first dynamic variable, matching the baseline control conditions based on the relative relationship; According to the second dynamic variable, determining the conditional variable; Using the conditional variable to adjust the baseline control conditions to determine the target control conditions.

2. The breathing monitor control method combined with sleep posture analysis according to claim 1, characterized in that, The division of the signal channels includes: Introducing a third signal channel, wherein the third signal channel is an auxiliary signal channel, and the third signal source at least includes an electrocardiogram signal and a breath sound signal, and is used for collecting any one of the third signal sources; Initialize the configuration of the control system mainly based on the first signal channel and the second signal channel, and supplemented by the third signal channel, where the acquisition methods include single-channel acquisition, multi-channel same-frequency acquisition, and multi-channel difference-frequency acquisition.

3. The breathing monitor control method combined with sleeping posture analysis according to claim 1, characterized in that, Perform the histogram segmentation and counting to determine the respiratory state, including: Transmit the respiratory signal back and perform filtering and noise reduction to determine the respiratory waveform; Perform the identification based on the determined respiratory cycle and the determination of respiratory events on the respiratory waveform, perform signal segment segmentation and counting, and construct a signal histogram, where the horizontal axis represents the amplitude value of the signal and the vertical axis represents the amplitude value frequency; Evaluate the respiratory state according to the signal histogram.

4. The breathing monitor control method combined with sleeping posture analysis according to claim 1, wherein Perform feedback response control on the respiratory monitor, including: Configure the risk threshold, where the risk threshold includes a static threshold and a dynamic threshold; Evaluate the respiratory state according to the risk threshold, and the respiratory monitor performs state feedback response control; Among them, the state feedback response control includes: If both the static threshold and the dynamic threshold are exceeded, generate a first warning message; If either the static threshold or the dynamic threshold is exceeded, incrementally adjust the monitoring control conditions and generate a second warning message, where the intensity of the second warning message is lower than that of the first warning message.

Images