Breathing quality detection method and device and breathing equipment

Abstract

A breathing quality detection method, device and breathing equipment relate to the technical field of medical instruments, and the scheme is as follows: firstly, acquiring a motion scene of a user, acquiring weight configuration matched with the motion scene, then acquiring target monitoring parameters acquired in the breathing process of the user, normalizing the target monitoring parameters, and determining the breathing quality of the user according to the normalized target monitoring parameters. And based on a normalization processing result and a weight value corresponding to each target monitoring parameter in weight configuration, carrying out weighted fusion processing to obtain a weighted fusion processing result, and finally, obtaining a respiration quality score matched with the weighted fusion processing result. Therefore, the user or other workers can clearly and intuitively know the breathing state of the user according to the breathing quality score, so that the behavior and posture of the user or the working state of auxiliary breathing equipment (such as an oxygen pipe) can be timely adjusted based on the breathing state.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, specifically to a method, apparatus, and respiratory equipment for detecting respiratory quality. Background Technology

[0002] Respiratory monitoring devices, as key tools for real-time or continuous measurement and analysis of human respiratory parameters, play a crucial role in accurately monitoring basic indicators such as respiratory rate, tidal volume, and blood oxygen saturation, as well as advanced indicators such as end-expiratory carbon dioxide partial pressure. They also provide timely warnings of risks such as sleep apnea and hypoxemia through abnormal threshold alerts, providing critical data support for the diagnosis, treatment, and surgical anesthesia management of diseases such as asthma, COPD, and sleep-disordered breathing. At the same time, they assist patients with chronic diseases in long-term self-management and prevention of disease progression.

[0003] Monitoring the breathing quality of users when wearing respiratory equipment is crucial. The sealing of the respiratory equipment directly affects its protective effect. Poor sealing can lead to the intrusion of external contaminants or leakage of internal gas. If the breathing resistance of the respiratory equipment is too high, it can cause breathing difficulties for users and even lead to health risks. In a confined space, abnormal air supply or exhaust may lead to hypoxia or carbon dioxide retention. Therefore, how to monitor the breathing quality of users when wearing respiratory equipment is one of the technical problems that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method, apparatus, and breathing device for detecting respiratory quality, so as to realize the detection of a user's respiratory quality.

[0005] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0006] A respiratory quality detection method, applied in a respiratory device, includes the following steps:

[0007] Obtain the user's breathing context;

[0008] Obtain the weight configuration that matches the breathing scenario;

[0009] Acquire target monitoring parameters during the respiratory process, wherein the weight configuration contains weight values ​​configured for each target monitoring parameter;

[0010] The target monitoring parameters are normalized.

[0011] Weighted fusion is performed based on the weight configuration and the normalized target monitoring parameters;

[0012] Obtain a respiratory quality score that matches the weighted fusion result.

[0013] Optionally, in the above-mentioned respiratory quality detection methods, obtaining a respiratory quality score that matches the weighted fusion result includes:

[0014] Obtain a respiratory quality score that matches the weighted fusion result and the user's target features, which include at least the user's age and weight.

[0015] Optionally, in the above-described respiratory quality detection method, the target monitoring parameter includes a combination of at least one or more of the following:

[0016] Steady-state indices of carbon dioxide concentration curve during respiration;

[0017] Steady-state indices of oxygen concentration curve during respiration;

[0018] Ventilation rate per unit time;

[0019] The coefficient of variation refers to the fluctuation coefficient of the maximum respiratory flow rate over N consecutive cycles, where N is greater than 1.

[0020] The respiratory flow irregularity index during respiration;

[0021] The respiratory ratio is the ratio of the duration of inhalation to the duration of exhalation in one respiratory cycle.

[0022] Optionally, in the above-mentioned respiratory quality detection method, weighted fusion is performed based on the weight configuration and the normalized target monitoring parameters, including:

[0023] Substitute the normalized target monitoring parameters into the formula:

[0024] RXI_raw = w1×(1-EtCO 2_tilde ) + w2×FiO 2_tilde + w3×MV _tilde + w4×(1-CV _tilde ) + w5×(1-FRI _tilde ) + w6×I _div_E_tilde ;

[0025] Let RXI_raw be the weighted fusion result;

[0026] Where w1 is the steady-state index EtCO of the carbon dioxide concentration curve. 2_tilde The corresponding weighting coefficients;

[0027] w2 is the steady-state index of the oxygen concentration curve, FiO2. 2_tilde The corresponding weighting coefficients;

[0028] w3 represents the ventilation rate MV per unit time. _tildeThe corresponding weighting coefficients;

[0029] w4 is the coefficient of variation (CV) _tilde The corresponding weighting coefficients;

[0030] w5 is the respiratory flow irregularity index (FRI). _tilde The corresponding weighting coefficients;

[0031] w6 is the respiratory ratio I _div_E_tilde The corresponding weighting coefficients.

[0032] Optionally, in the above-mentioned respiratory quality detection method, the respiratory scenarios include at least exercise scenarios, sleep scenarios, anesthesia scenarios, and standard scenarios.

[0033] Optionally, in the above breathing quality detection method, when the breathing scenario is a sports scenario, the values ​​of w1 and w2 are dynamically adjusted based on the breathing flow irregularity index, wherein the larger the breathing flow irregularity index, the smaller the values ​​of w1 and w2.

[0034] Optionally, in the above respiratory quality detection method, when the respiratory scenario is an anesthesia scenario, the update frequency of the target monitoring parameters is increased.

[0035] Optionally, in the above-mentioned respiratory quality detection method, the target monitoring parameters obtained during the respiratory process include:

[0036] Acquire sensor readings during the breathing process;

[0037] The detection results are compensated based on the leakage coefficient at the current moment;

[0038] The target monitoring parameters are determined based on the compensated detection results.

[0039] A respiratory quality detection device, used in respiratory equipment, the device comprising:

[0040] Scene acquisition unit, used to acquire the user's breathing scene;

[0041] The weight determination unit is used to obtain a weight configuration that matches the breathing scenario;

[0042] The target parameter acquisition unit acquires target monitoring parameters during the breathing process, and the weight configuration includes weight values ​​for each target monitoring parameter.

[0043] The scoring unit is used to normalize the target monitoring parameters, perform weighted fusion based on the weight configuration and the normalized target monitoring parameters, and obtain a respiratory quality score that matches the weighted fusion result.

[0044] A respiratory device, comprising the above-mentioned respiratory quality detection device.

[0045] Based on the above technical solution, by configuring different weight values ​​for each target monitoring parameter in different scenarios, when evaluating the user's breathing quality, the user's motion scenario is first obtained, and a weight configuration matching the motion scenario is obtained. Then, the target monitoring parameters collected during the user's breathing process are obtained, and the target monitoring parameters are normalized. Based on the normalization result and the weight values ​​corresponding to each target monitoring parameter in the weight configuration, a weighted fusion process is performed to obtain a weighted fusion result. Finally, a breathing quality score matching the weighted fusion result is obtained, so that the user or other staff can clearly and intuitively understand the user's breathing status based on the breathing quality score, so as to make timely adjustments to the user's behavior, posture, or the working status of auxiliary breathing equipment (such as oxygen tubes) based on the breathing status. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0047] Figure 1 A schematic flowchart of the respiratory quality detection method provided in the embodiments of this application;

[0048] Figure 2 This is a schematic diagram of the compensation process disclosed in an embodiment of this application;

[0049] Figure 3 This is a schematic diagram of the respiratory quality detection device provided in the embodiments of this application. Detailed Implementation

[0050] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0051] To monitor a user's breathing quality in real time, this application provides a breathing quality detection method, see [link to relevant documentation]. Figure 1 The method may include:

[0052] Step S101: Obtain the user's breathing scenario.

[0053] The values ​​of the target monitoring parameters detected during a user's breathing process vary in different breathing scenarios, and the degree of emphasis placed on the target monitoring parameters when detecting a user's breathing quality also differs in different breathing scenarios.

[0054] Step S102: Obtain the weight configuration that matches the breathing scenario.

[0055] In this embodiment, weights can be configured for each target monitoring parameter in different breathing scenarios based on prior data. The weight values ​​configured for the same target monitoring parameter are different in different scenarios. In some scenarios, the weight values ​​of one or more target monitoring parameters can be 0. Weight configurations matching each scenario are generated based on the weight values ​​of each target monitoring parameter in each scenario.

[0056] Step S103: Obtain target monitoring parameters during the breathing process, wherein the weight configuration contains weight values ​​configured for each target monitoring parameter.

[0057] In this step, relevant sensors and processors are used to collect and calculate various target monitoring parameters during the user's breathing process to obtain the current value of each target monitoring parameter.

[0058] Step S104: Normalize the target monitoring parameters.

[0059] To facilitate subsequent weighted fusion calculations, this step requires normalization of the target monitoring parameters. Normalization is a key step in data preprocessing, aiming to convert data of different scales or ranges to a unified standard in order to eliminate the influence of dimensions, improve model performance, or simplify calculations.

[0060] Step S105: Perform weighted fusion based on the weight configuration and the normalized target monitoring parameters.

[0061] In this step, the weight values ​​of each target monitoring parameter are extracted from the weight configuration. Based on the normalized target monitoring parameters and their respective weight values, a weighted fusion process is performed to obtain the weighted fusion result. Weighted fusion is a method that combines information or prediction results from different data sources or models by assigning weights to them. The formula for weighted fusion is: Fused Result = ∑i=1nwi·xi, where wi is the weight and xi is the input value (i.e., the normalized target monitoring parameter in this application). Typically, the sum of the weights is required to be 1 (∑wi = 1) to ensure the consistency of the results in terms of scale.

[0062] Step S106: Obtain the respiratory quality score that matches the weighted fusion result.

[0063] After obtaining the weighted fusion result, a respiratory quality score matching the weighted fusion result is determined, wherein the larger the value of the weighted fusion result, the higher the respiratory quality score.

[0064] In this embodiment, by configuring different weight values ​​for each target monitoring parameter in different scenarios, when evaluating the user's breathing quality, the user's motion scenario is first obtained, and a weight configuration matching the motion scenario is obtained. Then, after obtaining the target monitoring parameters collected during the user's breathing process, the target monitoring parameters are normalized. Based on the normalization result and the weight values ​​corresponding to each target monitoring parameter in the weight configuration, a weighted fusion process is performed to obtain a weighted fusion result. Finally, a breathing quality score matching the weighted fusion result is obtained, so that the user or other staff can clearly and intuitively understand the user's breathing status based on the breathing quality score, so as to make timely adjustments to the user's behavior, posture, or the working status of auxiliary breathing equipment (such as oxygen tubes) based on the breathing status.

[0065] In this embodiment, considering the different physical conditions of different users, the evaluation criteria for their breathing quality scores will also differ. For example, users A and B may obtain the same weighted fusion result during breathing, but user A is an elderly user and user B is a young user. Their physical fitness and metabolic rate are different, so even under the same breathing conditions, their breathing quality scores will be different. Therefore, in the above-disclosed solution, when obtaining a breathing quality score that matches the weighted fusion result, it is also necessary to consider the user's target characteristics. The target characteristics may include relevant data used to characterize the user's physical health, such as user age, weight, gender, disease severity, and other data related to the user's metabolism. Therefore, in the above solution, obtaining a breathing quality score that matches the weighted fusion result may specifically include: obtaining a breathing quality score that matches the weighted fusion result and the user's target characteristics, where the target characteristics include at least user age and weight. In this process, different correction coefficients can be pre-configured for different target characteristics. After determining the breathing quality score corresponding to the weighted fusion result, the breathing quality score is corrected based on the correction coefficients to obtain the user's actual breathing quality score. Alternatively, a correction factor can be used to correct the weighted fusion result, and then the respiratory quality score can be determined based on the corrected weighted fusion result.

[0066] The parameter type and weight configuration of the target monitoring parameters directly affect the reliability of the respiratory quality score. In order to accurately detect the user's respiratory quality, it is necessary to select reasonable target monitoring parameters for weighted fusion. In the technical solution disclosed in this embodiment, the target monitoring parameters include at least one or more of the following combinations:

[0067] The steady-state index of carbon dioxide concentration curve during respiration is obtained by detecting the degree of fluctuation of carbon dioxide concentration curve during respiration.

[0068] The steady-state index of the oxygen concentration curve during respiration is obtained by detecting the degree of fluctuation of the oxygen concentration curve during respiration.

[0069] The ventilation rate per unit time is obtained by integrating the flow rate value detected by the flow sensor per unit time.

[0070] The coefficient of variation refers to the fluctuation coefficient of the maximum respiratory flow rate over N consecutive cycles, where N is greater than 1.

[0071] The flow regularity index (FRI) during the breathing process can be calculated from the normalized energy percentage of the breathing flow Q(t) detected by the flow sensor in the >2Hz frequency band, or from the timing jitter of the peak of the respiratory cycle.

[0072] The respiratory ratio is the ratio of the duration of inhalation to the duration of exhalation in one respiratory cycle.

[0073] In this embodiment, all the above-mentioned data are used as the target monitoring parameters. Specifically, the target monitoring parameters include the steady-state indices of the carbon dioxide concentration curve during respiration, the steady-state indices of the oxygen concentration curve during respiration, the ventilation per unit time, the coefficient of variation, the respiratory flow irregularity index, and the respiratory ratio. A weighted fusion is performed based on the weighted configuration and the normalized target monitoring parameters. Specifically, the normalized target monitoring parameters are substituted into the weighted fusion formula to obtain the weighted fusion result RXI_raw. The weighted fusion formula is as follows:

[0074] RXI_raw = w1×(1-EtCO 2_tilde ) + w2×FiO 2_tilde + w3×MV _tilde + w4×(1-CV _tilde ) + w5×(1-FRI _tilde ) + w6×I _div_E_tilde ;

[0075] w1 is the steady-state index EtCO of the carbon dioxide concentration curve. 2_tilde The weighting coefficients corresponding to the steady-state index of carbon dioxide concentration during respiration;

[0076] w2 is the steady-state index of the oxygen concentration curve, FiO2.2_tilde The weighting coefficients corresponding to the steady-state index of oxygen concentration during respiration;

[0077] w3 represents the ventilation rate MV per unit time. _tilde The corresponding weighting coefficients;

[0078] w4 is the coefficient of variation (CV) _tilde The corresponding weighting coefficients;

[0079] w5 is the respiratory flow irregularity index (FRI). _tilde The corresponding weighting coefficients;

[0080] w6 is the respiratory ratio I _div_E_tilde The corresponding weighting coefficients.

[0081] In the technical solution of this embodiment, the breathing scenario can be divided into multiple scenarios based on the different breathing conditions of the user. In this embodiment, the breathing scenario can be divided into exercise scenario, sleep scenario, anesthesia scenario and standard scenario. The standard scenario is the breathing scenario when the user is awake and has not engaged in strenuous exercise. The weight configuration of the target monitoring parameters corresponding to the breathing scenario is different. Of course, other special scenarios can also be used as the breathing scenarios to be considered in this application, and reasonable weight configuration can be made for these breathing scenarios.

[0082] In this embodiment, different weight configurations are adapted for different breathing scenarios. The weight values ​​of each target monitoring parameter differ in the different weight configurations corresponding to different scenarios. For example, when the breathing scenario is an exercise scenario, the values ​​of w3 and w4 are greater than the values ​​of w3 and w4 in other scenarios (sleep scenario, anesthesia scenario, and standard scenario), and the values ​​of w3 and w4 are greater than the values ​​of w1, w2, w5, and w6. Furthermore, based on the respiratory flow irregularity index, the detection results of concentration sensors (oxygen concentration sensor and carbon dioxide concentration sensor) during breathing can be detected. To ensure reliability, the higher the value of the respiratory flow irregularity index (RFI), the less reliable the concentration sensor's detection results. In exercise scenarios, the values ​​of w1 and w2 can be dynamically adjusted based on the RFI value; the higher the RFI, the lower the values ​​of w1 and w2. Specifically, when the RFI is higher than the first calibration value, the values ​​of w1 and w2 are decreased, while the values ​​of w3, w4, w5, and w6 are increased. When the RFI is lower than the first calibration value, the values ​​of w1, w2, w3, w4, w5, and w6 are restored to their initial state. In sleep scenarios, the values ​​of w1 and w2 are greater than those in exercise and standard scenarios, and the values ​​of w1 and w2 are also greater than those of w3, w4, w5, and w6. Furthermore, when the RFI is detected to be higher than the second calibration value in a sleep scenario, it can be considered that the user's breathing is abnormal, and an alarm signal can be issued. In anesthesia scenarios, the values ​​of w1 and w2 are greater than those in a sleep scenario. Furthermore, in respiratory scenarios, the timeliness and accuracy of respiratory quality detection results are directly related to the user's personal safety. Therefore, when the respiratory scenario is an anesthesia scenario, it is necessary to increase the update frequency of the target monitoring parameters.

[0083] In this embodiment, users can adjust the breathing scene configuration according to their actual needs. For example, users can switch between the various scenes by operating the relevant keys.

[0084] Considering that wearing or fitting issues may lead to a non-perfect fit between the breathing mask and the face, potentially causing gas leakage, the data collected by the sensors may not correspond to the actual data applied to the user. Therefore, to ensure the reliability of the sensor detection results and breathing quality detection results, it is necessary to compensate the sensor detection results based on the leakage coefficient at the current moment, and determine the target monitoring parameters based on the compensated detection results. This process can be implemented by a processor. Specifically, the method described above also uses a processor to acquire the data collected by the oxygen concentration sensor, carbon dioxide concentration sensor, and gas flow sensor, and compensates the detection results of the oxygen concentration sensor, carbon dioxide concentration sensor, and gas flow sensor based on the leakage coefficient corresponding to the current wearing state of the breathing mask. Then, the target monitoring parameters are determined based on the compensated data. The leakage coefficient refers to the gas leakage index when a user breathes through a breathing device (e.g., a breathing mask) using the breathing quality detection method; the greater the gas leakage, the higher the leakage index.

[0085] For details, see Figure 2 The compensation process may include:

[0086] Step S201: Obtain the oxygen concentration detected by the oxygen concentration sensor, the carbon dioxide concentration detected by the carbon dioxide concentration sensor, and the flow rate Q(t) detected by the gas flow sensor;

[0087] In this step, the flow rate Q(t) measured by the gas flow sensor, the oxygen concentration measured by the carbon dioxide concentration sensor, and the oxygen concentration measured by the oxygen concentration sensor are collected from various sensors. The sampling frequencies for the flow rate Q(t), carbon dioxide concentration, and oxygen concentration can be set according to requirements. For example, the sampling frequency for the flow rate Q(t) can be any frequency between 100 and 200 Hz, and the sampling frequencies for the carbon dioxide concentration and oxygen concentration can be 5 Hz.

[0088] The flow rate Q(t) is smoothed to construct a waveform corresponding to Q(t). Multiple-sample termination and moving average processing is applied to the carbon dioxide and oxygen concentrations. Based on the processing results, the flow rate Q(t), carbon dioxide concentration, and oxygen concentration at the current time are determined.

[0089] Step S202: Based on formula L _k = +w _k Determine the leakage coefficient L at the current moment. _k ;

[0090] in, w represents the leakage coefficient at the previous moment._k The process noise is the flow rate Q(t) detected by the gas flow sensor at the current moment; in this application, w _k Set to zero mean Gaussian: w _k ~ N(0, σ_w 2 ).

[0091] σ _w = σ _0 × (1 +β1×FRI), where FRI is the irregularity index of the measured flow rate Q(t), and β1 is the calibration coefficient;

[0092] Step S203: Based on the leakage coefficient L at the current moment _k The detection results of the oxygen concentration sensor, carbon dioxide concentration sensor, and gas flow sensor are compensated.

[0093] Specifically, based on the leakage coefficient L at the current moment _k Compensation is performed on the detection results of the oxygen concentration sensor, carbon dioxide concentration sensor, and gas flow sensor, specifically including:

[0094] Substitute the oxygen concentration and carbon dioxide concentration detected by the oxygen concentration sensor and carbon dioxide concentration sensor respectively into the formula: C _true_hat(t) = (C _meas(t) -L _k ×C _amb ) / (1-L _k + ε), to obtain the compensated oxygen and carbon dioxide concentrations;

[0095] Wherein, the C _true_hat(t) The C is the compensated oxygen / carbon dioxide concentration. _meas(t) The C represents the oxygen and carbon dioxide concentrations detected at the current moment. _amb The oxygen / carbon dioxide volume fraction is a pre-calibrated value. For example, it can be the pre-calibrated volume fraction of oxygen / carbon dioxide in a standard gas or indoor air. In this scheme, the oxygen volume fraction is taken as 0.209 and the carbon dioxide volume fraction is taken as 0.0004. ε is a pre-calibrated numerical stability term.

[0096] Substitute the flow rate Q(t) detected by the gas flow sensor into the formula:

[0097] Q _alveolar_hat(t)= The compensated flow Q _alveolar_hat(t) ;

[0098] Among them, Q _meas(t)This represents the flow rate detected by the gas flow sensor at the current moment, where k1 and k2 represent preset fitting coefficients, and dQ / dt represents the flow rate Q at the current moment. _meas(t) Time integral.

[0099] Furthermore, in this embodiment, to further ensure the reliability of the compensated sensor data, this application can also correct the compensated data in the following ways. Specifically, after compensating the detection results of the oxygen concentration sensor, carbon dioxide concentration sensor, and gas flow sensor, the method further includes:

[0100] Obtain the correction value of the target data determined based on the detection results of the compensated oxygen concentration sensor, carbon dioxide concentration sensor, and gas flow sensor; obtain the standard value of the target data that matches the leakage compensation coefficient at the current moment; determine whether the difference between the correction value and the standard value is within a preset range. If it is not within the preset range, correct the leakage compensation coefficient at the current moment, and continue to determine whether the difference between the compensated target data and the standard value of the target data is within the preset range. The standard value is a pre-configured prior data that corresponds one-to-one with the compensation coefficient L.

[0101] In this scheme, the target data includes at least ρ _k τ _decay_k r _{CO2,Q} ,、s _plat_k CV _VT_k A combination of at least one or more of HFE_k;

[0102] ρ _k The current inhalation-exhalation symmetry index decreases significantly during leakage, ρ _k = A _out / A _in A _out and A _in These represent the expiratory and inspiratory volumes calculated based on the compensated flow rate for a single respiratory process, which can be obtained by integrating the flow rate detected during the respiratory process.

[0103] τ _decay_kThis represents the rate of expiratory decay at the current moment; leakage often causes faster decay (τ decreases). Its determination process includes: finding the peak time t_pk and the end time t_e_end during exhalation. The target sequence y(t) is chosen: either the envelope of Q_abs(t) = max(-Q(t), 0), or the decrease in carbon dioxide concentration after the plateau (the last 30–40% of the duration). The time difference from the peak to 1 / e is calculated; if noise is high, an exponential fit is used: y(t)≈y0×exp(-(t-t0) / τ)+b, and τ is taken at each time point obtained from the fit.

[0104] r _{CO2,Q（t）} This represents the coupling degree between the current carbon dioxide concentration and the compensated flow rate. _{CO2,Q} = corr(C _CO2(t), Q_abs(t) (interval [t]) _e_start , t _e_end Specifically, r _{CO2,Q} The calculation process is as follows: in a single expiratory phase [t _e_start , t _e_end [Internal CO2 concentration sequence C] _CO2_true_hat(t) Given a sequence of flows Q(t), let Q_ abs(t) =max(-Q(t), 0) (If exhalation is considered positive, then use max(Q(t), 0)); align the two sequences according to the same timestamp to obtain the exhalation segment r. _{CO2,Q} , t _e_start , t _e_end These indicate the start and end times of exhalation.

[0105] s _plat_k This indicates the stability of the carbon dioxide concentration platform at the current moment; a leak could cause the platform to tilt downwards or become passive.

[0106] CV _VT_k This represents the coefficient of variation of tidal volume at the current moment. In a sequence of N consecutive breaths, {V} _T,i On}, μ _VT = (1 / N)×Σ _{i=1..N} V _T,i , σ _VT = sqrt( (1 / (N-1))×Σ_{i=1..N} (V _T,i -μ _VT ) 2 ), CV _{VT} = σ _VT / (μ _VT +ε)(ε≈1×10 −3 (To prevent the denominator from being too small); the larger the value, the greater the V. _T The greater the fluctuations during the week.

[0107] HFE _k This represents the proportion of high-frequency energy at the current moment. The spectrum Q is obtained by performing an FFT on Q(t) within a window covering 3–8 periods. _hat(f) Let the cutoff frequency be f. _c = 2 Hz: E _total = Σ _{f≥0} |Q_hat(f)| 2 E _high = Σ_{f≥f _c}|Q _hat(f) | 2 HFE = E _high / (E _total +ε); The larger the HFE, the more high-frequency disturbances there are and the more irregular the waveform.

[0108] In this embodiment, when the calculated compensation coefficient L is detected to meet the preset conditions, a prompt to re-wear / adjust posture is triggered. The preset conditions include: L>0.25 and lasting for >3 seconds.

[0109] Corresponding to the above method, this embodiment also discloses a respiratory quality detection device, which can be applied to respiratory equipment. For the specific working content of each unit in the device, please refer to the content of the above method embodiment.

[0110] The respiratory quality detection device provided in the embodiments of the present invention will be described below. The respiratory quality detection device described below can be referred to in correspondence with the respiratory quality detection method described above. See also Figure 3 The aforementioned device may include:

[0111] Scene acquisition unit 10 is used to acquire the user's breathing scene, which corresponds to step S101 in the above scheme;

[0112] The weight determination unit 20 is used to obtain a weight configuration that matches the breathing scenario, which corresponds to step S102 in the above scheme;

[0113] The target parameter acquisition unit 30 acquires target monitoring parameters during the breathing process, and the weight configuration includes weight values ​​for each target monitoring parameter.

[0114] Scoring unit 40 is used to normalize the target monitoring parameters, perform weighted fusion based on the weight configuration and the normalized target monitoring parameters, and obtain a respiratory quality score that matches the weighted fusion result, which corresponds to steps S103-S106 in the above scheme.

[0115] Corresponding to the aforementioned respiratory quality detection device, this application also discloses a breathing device that may include the aforementioned respiratory quality detection device. This breathing device may be a breathing mask or other auxiliary breathing equipment.

[0116] For ease of description, the above system is described by dividing it into various modules based on their functions. Of course, in implementing this invention, the functions of each module can be implemented in one or more software and / or hardware components.

[0117] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for system or system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the descriptions in the method embodiments. The systems and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0118] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0119] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0120] It should also be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0121] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method of breath quality detection, characterized by, Applied in a respiratory device, the method comprises: obtaining a user's respiratory scene; obtaining a weight configuration matched with the respiratory scene; obtaining target monitoring parameters in a respiratory process, the weight configuration being configured with weight values of each target monitoring parameter configuration; normalizing the target monitoring parameters; performing weighted fusion based on the weight configuration and the normalized target monitoring parameters; obtaining a respiratory quality score matched with the weighted fusion result.

2. The respiratory quality detection method of claim 1, wherein, Obtaining a respiratory quality score matched with the weighted fusion result comprises: obtaining a respiratory quality score matched with the weighted fusion result and a target feature of the user, the target feature being data for representing the user's metabolism.

3. The respiratory quality detection method of claim 1, wherein, The target monitoring parameters comprise at least one or a combination of the following: a steady-state index of a carbon dioxide concentration curve in a respiratory process; a steady-state index of an oxygen concentration curve in a respiratory process; a ventilation volume per unit time; a coefficient of variation, the coefficient of variation being a fluctuation coefficient of a maximum value of respiratory flow rate in adjacent N cycles, the N being greater than 1; a respiratory flow irregularity index in a respiratory process; a respiratory ratio, the respiratory ratio being a ratio of an inhalation time to an exhalation time in a respiratory cycle.

4. The respiratory quality detection method of claim 3, wherein, Performing weighted fusion based on the weight configuration and the normalized target monitoring parameters comprises: substituting the normalized target monitoring parameters into a formula: RXI_raw = w1 x (1 - EtCO 2_tilde ) + w2 x FiO 2_tilde + w3 x MV _tilde + w4 x (1 - CV _tilde ) + w5 x (1 - FRI _tilde ) + w6 x I _div_E_tilde ; taking RXI_raw as the weighted fusion result. wherein w1 is a steady state index EtCO2of the carbon dioxide concentration curve 2_tilde corresponding weight coefficient; w2 is the steady state indicator of the oxygen concentration curve FiO 2_tilde corresponding weight coefficient; w3 is the minute ventilation MV in a unit of time _tilde corresponding weight coefficient; w4 is the coefficient of variation CV _tilde corresponding weight coefficient; w5 is the flow rate irregularity index FRI _tilde corresponding weight coefficient; w6 is the respiratory ratio I _div_E_tilde corresponding weight coefficients.

5. The respiratory quality detection method of claim 4, wherein, The respiratory scene comprises at least a sports scene, a sleep scene, an anesthesia scene and a standard scene.

6. The respiratory quality detection method of claim 5, wherein, When the respiratory scene is a sports scene, the values of w1 and w2 are dynamically adjusted based on the respiratory flow irregularity index, wherein the greater the respiratory flow irregularity index, the smaller the values of w1 and w2.

7. The respiratory quality detection method of claim 5, wherein, When the respiratory scene is an anesthesia scene, the update frequency of the target monitoring parameters is increased.

8. The respiratory quality detection method of claim 1, wherein, Obtaining target monitoring parameters in a respiratory process comprises: obtaining a detection result of a sensor in a respiratory process; compensating the detection result based on a current time's leakage coefficient; determining the target monitoring parameters based on the compensated detection result.

9. A respiratory quality detection device, characterized by, Applied in a respiratory device, the device comprises: a scene acquisition unit for obtaining a user's respiratory scene; a weight determination unit for obtaining a weight configuration matched with the respiratory scene; a target parameter acquisition unit for obtaining target monitoring parameters in a respiratory process, the weight configuration being configured with weight values of each target monitoring parameter configuration; a scoring unit for normalizing the target monitoring parameters, performing weighted fusion based on the weight configuration and the normalized target monitoring parameters, and obtaining a respiratory quality score matched with the weighted fusion result.

10. A breathing apparatus characterized by The respiratory quality detection device of claim 9 is included.

Images