Breathing state detection method and device, computer equipment and readable storage medium
By preprocessing the initial respiratory data and fusion coefficient calculation, the respiratory fluctuation function is determined, which solves the problem of insufficient accuracy of respiratory state parameters in traditional technology, and achieves high-accurate respiratory state detection.
Patent Information
- Application Number
- CN202510257378.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-05
- Publication Date
- 2025-06-24
AI Technical Summary
In traditional technology, the parameters collected related to the respiratory state are not accurate enough, there is a lot of noise or poor aging, making it difficult to accurately obtain the parameters of the respiratory state.
By acquiring multiple initial breathing data in different directions, pre-processing is performed using preset functions, abnormal data and noise are removed, fusion coefficients are calculated, and the breathing fluctuation function is determined, so as to achieve accurate detection of breathing state.
It improves the accuracy of respiratory state detection, can flexibly detect respiratory states under different postures, and judges exhalation and inhalation in real time.
Smart Images
Figure CN120189098A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer technology, and in particular, to a method, device, computer device, and computer-readable storage medium for detecting a breathing state. Background Art
[0002] With the improvement of the quality of life, the monitoring of daily breathing frequency has attracted much attention. In traditional technologies, the parameters related to the breathing state collected are not accurate enough. For example, a large amount of noise is often mixed in the parameters related to the breathing state, or the timeliness of the parameter is poor, etc. Therefore, how to accurately obtain the parameters of the breathing state has become a technical problem that needs to be solved urgently. Summary of the Invention
[0003] Based on this, in view of the above technical problems, it is necessary to provide a method, device, computer device, computer-readable storage medium, and computer program product for detecting a breathing state that can accurately obtain the parameters of the breathing state.
[0004] In a first aspect, this application provides a method for detecting a breathing state, and the method includes:
[0005] Obtain a plurality of initial breathing data in different directions;
[0006] Use a preset function to preprocess the plurality of initial breathing data in different directions to obtain target breathing data in different directions;
[0007] Calculate a fusion coefficient in different directions based on the target breathing data and the initial breathing data;
[0008] Based on the fusion coefficient and the target breathing data, determine a breathing fluctuation function, and detect the breathing state based on the breathing fluctuation function.
[0009] In one embodiment, the obtaining a plurality of initial breathing data in different directions includes:
[0010] Obtain breathing acceleration data in a first direction, a second direction, and a third direction, where the first direction, the second direction, and the third direction are perpendicular to each other;
[0011] Use the breathing acceleration data as the initial breathing data.
[0012] In one embodiment, the using a preset function to preprocess the plurality of initial breathing data in different directions to obtain target breathing data in different directions includes:
[0013] Use a distributed multi-wavelet transform function to denoise the plurality of initial breathing data in different directions to obtain the target breathing data in different directions.
[0014] In one embodiment, the denoising process of the multiple initial respiration data in different directions using the distributed multi-wavelet transform function to obtain the target respiration data in different directions includes:
[0015] Normalize the multiple initial respiration data to be denoised to obtain the target respiration data in different directions.
[0016] In one embodiment, the normalizing the multiple initial respiration data to be denoised to obtain the target respiration data in different directions includes:
[0017] Divide the multiple initial respiration data to be denoised into multiple data sets;
[0018] Normalize each data set to obtain a target data set;
[0019] Concatenate each target data set to obtain the target respiration data in different directions.
[0020] In one embodiment, the normalizing the multiple initial respiration data to be denoised to obtain the target respiration data in different directions includes:
[0021] Determine the peaks and valleys in the multiple initial respiration data undergoing normalization processing;
[0022] Calculate the distance between the peaks and the valleys;
[0023] Obtain a first respiration value and a second respiration value based on the sampling rate and the distance, where the first respiration value and the second respiration value are respectively used to represent different respiration durations;
[0024] Based on the first respiration value and the second respiration value, determine the target respiration data in different directions from the multiple initial respiration data undergoing normalization processing.
[0025] In one embodiment, the calculating the fusion coefficients in different directions based on the target respiration data and the initial respiration data includes:
[0026] Based on the target respiration data and the initial respiration data, calculate the signal-to-noise ratio, root mean square error, and respiration fluctuation amplitude in each direction;
[0027] Calculate the fusion coefficients in different directions respectively based on the signal-to-noise ratio, the root mean square error, and the respiration fluctuation amplitude in different directions.
[0028] In a second aspect, the present application further provides a breathing state detection device, which includes:
[0029] An acquisition module, configured to acquire a plurality of initial breathing data in different directions;
[0030] A preprocessing module, configured to preprocess the plurality of initial breathing data in different directions using a preset function to obtain target breathing data in different directions;
[0031] A calculation module, configured to calculate fusion coefficients in different directions based on the target breathing data and the initial breathing data;
[0032] A determination module, configured to determine a breathing fluctuation function based on the fusion coefficients and the target breathing data, and detect the breathing state based on the breathing fluctuation function.
[0033] In a third aspect, the present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:
[0034] Acquire a plurality of initial breathing data in different directions;
[0035] Preprocess the plurality of initial breathing data in different directions using a preset function to obtain target breathing data in different directions;
[0036] Calculate fusion coefficients in different directions based on the target breathing data and the initial breathing data;
[0037] Determine a breathing fluctuation function based on the fusion coefficients and the target breathing data, and detect the breathing state based on the breathing fluctuation function.
[0038] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:
[0039] Acquire a plurality of initial breathing data in different directions;
[0040] Preprocess the plurality of initial breathing data in different directions using a preset function to obtain target breathing data in different directions;
[0041] Calculate fusion coefficients in different directions based on the target breathing data and the initial breathing data;
[0042] Determine a breathing fluctuation function based on the fusion coefficients and the target breathing data, and detect the breathing state based on the breathing fluctuation function.
[0043] Fifth aspect, the present application also provides a computer program product, including a computer program which, when executed by a processor, implements the following steps:
[0044] Obtain a plurality of initial respiration data in different directions;
[0045] Preprocess the plurality of initial respiration data in different directions using a preset function to obtain target respiration data in different directions;
[0046] Calculate fusion coefficients in different directions based on the target respiration data and the initial respiration data;
[0047] Determine a respiration fluctuation function based on the fusion coefficients and the target respiration data, and detect a respiration state based on the respiration fluctuation function.
[0048] The above-mentioned respiration state detection method, device, computer device, computer-readable storage medium and computer program product first obtain a plurality of initial respiration data in different directions, and preprocess the initial respiration data to obtain target respiration data, thereby removing abnormal data and noise data in the initial respiration data and improving the detection accuracy. Secondly, the present application calculates fusion coefficients in different directions to obtain a respiration fluctuation function of the respiration state in different postures, so that the respiration state can be flexibly detected. Subsequently, by repeating the multiple steps provided by the present application, exhalation and inhalation can be judged in real time. Description of the Drawings
[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.
[0050] Figures 1 to 5 It is a schematic flowchart of the respiration state detection method provided in different embodiments;
[0051] Figure 6 It is a structural block diagram of the respiration state detection device provided in one embodiment;
[0052] Figure 7 It is an internal structure diagram of a computer device provided in one embodiment. Detailed Embodiments
[0053] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0054] In one embodiment, as Figure 1 shown, a method for detecting a breathing state is provided. In this embodiment, taking the application of this method to a terminal as an example, it can be understood that this method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. As an example, the terminal can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. In this embodiment, the method includes the following steps:
[0055] Step S2: Obtain a plurality of initial breathing data in different directions.
[0056] The initial breathing data can be the raw data representing the breathing state. The initial breathing data can be directly collected from the lower jaw. As an example, the initial breathing data in two directions or three directions can be obtained. In a possible example, the initial breathing data in two opposite directions can be obtained, or the initial breathing data in two mutually perpendicular directions can also be obtained. In another possible example, the initial breathing data in three mutually perpendicular directions can be obtained.
[0057] It can be understood that in this step, a plurality of initial breathing data in each direction can be obtained. As an example, in three mutually perpendicular directions, 1024 initial breathing data in each direction can be obtained. Further, in this step, a plurality of initial breathing data in different directions can be collected in real time, and in each sampling, n new initial breathing data are collected, and the n new initial breathing data are added to the total data set of the initial breathing data, and n old initial breathing data are removed from the total data set of the initial breathing data, so as to ensure the integrity of the total data set of the initial breathing data. As an example, n can be 4, 6, 8, etc. The specific value of n is not limited in this embodiment, nor is the sampling rate limited. For example, the sampling rate can be 100 hz, 200 hz, etc. In addition, the sampling time of the initial breathing data is not limited in this embodiment, that is, this embodiment can perform sampling when the subject is active or sleeping.
[0058] Step S4: Use a preset function to preprocess the plurality of initial breathing data in different directions to obtain target breathing data in different directions.
[0059] As an example, abnormal data and noise data in multiple initial respiration data can be removed to obtain accurate target respiration data. The specific method of preprocessing is not limited in this embodiment.
[0060] Step S6: Calculate the fusion coefficients in different directions based on the target respiration data and the initial respiration data.
[0061] As an example, the fusion coefficients can be used to represent the weight ratios in different directions. As an example, when the respiration posture changes, the respiration state may change. At this time, the accurate respiration state can be obtained by adjusting the fusion coefficients.
[0062] Step S8: Determine the respiration fluctuation function based on the fusion coefficients and the target respiration data, and detect the respiration state based on the respiration fluctuation function.
[0063] As an example, the fusion coefficient in each direction can be used as the coefficient of the target respiration data in that direction, so as to obtain the respiration fluctuation functions in multiple directions. The respiration fluctuation function can reflect the respiration state in different postures.
[0064] In this embodiment, first, multiple initial respiration data in different directions are obtained, and the initial respiration data are preprocessed to obtain the target respiration data, thereby removing the abnormal data and noise data in the initial respiration data and improving the detection accuracy. Secondly, in this embodiment, the respiration fluctuation functions of the respiration states in different postures are obtained by calculating the fusion coefficients in different directions, so that the respiration state can be detected flexibly. It can be understood that by repeating the multiple steps provided in this embodiment, exhalation and inhalation can be judged in real time.
[0065] In one embodiment, as Figure 2 shown, step S2 includes:
[0066] Step S20: Obtain the respiration acceleration data in the first direction, the second direction, and the third direction, where the first direction, the second direction, and the third direction are perpendicular to each other.
[0067] As an example, a detection device corresponding to the detection method of the respiration state provided in this embodiment can be obtained. The detection device may include an Inertial Measurement Unit (IMU). The inertial measurement unit can be disposed at the lower jaw, so that the acceleration data of the inertial measurement unit can be obtained during respiration. Further, the inertial measurement unit can collect the acceleration data (three-axis acceleration data) in three mutually perpendicular directions, and the acceleration data in the three mutually perpendicular directions can be acc x 、acc y 、acc z .
[0068] Step S21: Use the respiratory acceleration data as the initial respiratory data.
[0069] In this step, the acceleration data of the inertial measurement unit can be used as the initial respiratory data. It can be understood that during breathing, the movement at the mandible can reflect the respiratory state.
[0070] In this embodiment, by collecting the acceleration data in three mutually perpendicular directions and using it as the initial respiratory data, the respiratory state can be judged quickly and in real time.
[0071] In one embodiment, step S4 includes:
[0072] Step S40: Use the distributed multi-wavelet transform function to denoise multiple initial respiratory data in different directions to obtain the target respiratory data in different directions.
[0073] In this embodiment, the specific parameters such as the wavelet dilation coefficient and translation amount of the distributed multi-wavelet transform function are not limited.
[0074] Due to the diversity of breathing, when breathing is unsmooth, the breathing amplitude and frequency change greatly in a short time. In the traditional technology, wavelet transform can capture the breathing wave with a larger amplitude and a majority of a certain breathing frequency at this time, but it will miss the breathing with an unclear wave peak. Therefore, in this embodiment, the distributed multi-wavelet transform can be used for denoising processing to obtain accurate target respiratory data.
[0075] In one embodiment, step S40 includes:
[0076] S400: Normalize the multiple initial respiratory data to be denoised to obtain the target respiratory data in different directions.
[0077] In this embodiment, by normalizing the multiple initial respiratory data to be denoised, the problem of data baseline shift is solved, and more real target respiratory data is obtained.
[0078] Specifically, as Figure 3 shown, S400 may include:
[0079] S402: Divide the multiple initial respiratory data to be denoised into multiple data sets.
[0080] As an example, the multiple initial respiratory data can be divided into 10, 20, or 50 data sets according to the time sequence.
[0081] S404: Normalize each data set to obtain the target data set.
[0082] As an example, the ranges of multiple initial respiration data within each data set can be scaled to a target scale, or the mean of the data within the data set can be adjusted to 0, and the standard deviation can be adjusted to 1, etc. The specific method of normalization processing is not limited in this embodiment.
[0083] S406: Concatenate each target data set to obtain target respiration data in different directions.
[0084] As an example, the data segments after normalization processing can be re - concatenated together to form a continuous data stream. This continuous data stream can be used as the target respiration data.
[0085] In addition, as Figure 4 shown, S400 can also include:
[0086] S412: Determine the peaks and valleys in multiple initial respiration data undergoing normalization processing.
[0087] As an example, the maximum - minimum principle can be used to determine the peaks (p) and valleys (v) in multiple initial respiration data.
[0088] S414: Calculate the distance between the peak and the valley.
[0089] As an example, the distance between adjacent peaks can be denoted as D.
[0090] S416: Obtain a first respiration value and a second respiration value based on the sampling rate and the distance. The first respiration value and the second respiration value are respectively used to represent different respiration durations.
[0091] As an example, the maximum and minimum values of D can be determined, and then the maximum and minimum values of D are divided by the sampling rate to obtain the first respiration value (the fastest respiration T min ) and the second respiration value (the slowest respiration T max ).
[0092] S418: Based on the first respiration value and the second respiration value, determine target respiration data in different directions from multiple initial respiration data undergoing normalization processing.
[0093] As an example, the first respiration value and the second respiration value can be used as the parameters of a band - pass filter to allow signals within a specific frequency range to pass through while suppressing signals of other frequencies, thereby determining target respiration data in different directions, effectively extracting signals related to respiration, while suppressing interference from other irrelevant signals, thus improving the accuracy and reliability of respiration monitoring and analysis.
[0094] In one embodiment, as Figure 5 shown, step S6 can include:
[0095] Step S60: Calculate the signal-to-noise ratio, root mean square error, and respiratory fluctuation amplitude in each direction based on the target respiratory data and the initial respiratory data.
[0096] As an example, based on the target respiratory data and the initial respiratory data, the signal-to-noise ratio (SNR), root mean square error (RMSE), and respiratory fluctuation amplitude (F) before and after denoising in each direction can be calculated. Of course, other parameters can also be calculated in this embodiment.
[0097] Step S62: Calculate the fusion coefficients in different directions respectively based on the signal-to-noise ratio, root mean square error, and respiratory fluctuation amplitude in different directions.
[0098] As an example, the signal-to-noise ratio, root mean square error, and respiratory fluctuation amplitude in multiple directions can be all substituted into a preset formula for calculation to obtain the fusion coefficients.
[0099] The following exemplarily describes the method for detecting the respiratory state provided by one or more embodiments and their combinations in the present application. First, take the three-axis acceleration data of the mandibular inertial measurement unit, which are acc x 、acc y 、acc z , and according to the sampling rate, take the amount of data required for one calculation. For example, taking a sampling rate of 100 hz as an example, 1024 data are calculated at a time, and the last 4 data are the latest 40 ms. The data is taken in a sliding manner. In the next time, the previous 4 data are removed and 4 new data are added to maintain a total of 1024 data to ensure real-time performance. Then, the improved distributed multi-wavelet transform is applied for denoising. The specific implementation principle is as follows in the formula:
[0100]
[0101] Among them, a represents the wavelet scaling coefficient, which is related to the frequency, and τ represents the translation amount. After that, the preliminary filtering result obtained above can be regionally normalized. Then, the maximum and minimum values principle is used to find the wave peaks and wave valleys, which are respectively denoted as p and v. Calculate the distance D between adjacent wave peaks, take the maximum and minimum values of D, and divide by the sampling rate to obtain the fastest respiration T min and the slowest respiration T max , and finally, band-pass filtering is implemented with T min and T max . The foregoing steps can obtain the denoised respiratory waveforms Facc x 、Facc y 、Facc z, and fuse the three-axis acceleration data. First, calculate the signal-to-noise ratio (SNR), root mean square error (RMSE), and respiratory fluctuation amplitude (F) before and after denoising for each axis, then compare them to obtain their respective ratios, and finally fuse the comparisons to obtain the final coefficient. The specific implementation is shown in the following formula:
[0102]
[0103] where n represents the number of samples, x represents the original undenoisd data, represents the denoised data. When the number of wave peaks is greater than the number of wave valleys, T represents the number of wave valleys; otherwise, T represents the number of wave peaks. p represents the set of positions of wave peaks, and v represents the set of positions of wave valleys. After calculating the above three indicators in three directions, the final fusion indicator can be obtained. The specific fusion formula is as follows:
[0104]
[0105]
[0106] The final fused respiratory fluctuation function is as follows:
[0107] W = a * Facc x + b * Facc y + c * Facc z
[0108] The respiratory fluctuation function can ensure that respiratory fluctuations can be effectively detected in various postures. It can be understood that by repeating the above method of calculating peak and valley values, exhalation and inhalation can be judged in real time.
[0109] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the arrows, these steps do not necessarily have to be executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages do not necessarily have to be executed at the same time, but can be executed at different times. The execution order of these steps or stages does not necessarily have to be sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.
[0110] Based on the same inventive concept, an embodiment of the present application further provides a breathing state detection device for implementing the breathing state detection method involved above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the breathing state detection device provided below can refer to the limitations on the breathing state detection method in the above text, and will not be elaborated here.
[0111] In an exemplary embodiment, as Figure 6 shown, a breathing state detection device is provided, including: an acquisition module, a preprocessing module, a calculation module, and a determination module, where:
[0112] The acquisition module is used to acquire a plurality of initial breathing data in different directions.
[0113] The preprocessing module is used to preprocess the plurality of initial breathing data in different directions using a preset function to obtain target breathing data in different directions.
[0114] The calculation module is used to calculate the fusion coefficient in different directions based on the target breathing data and the initial breathing data.
[0115] The determination module is used to determine the breathing fluctuation function based on the fusion coefficient and the target breathing data, and detect the breathing state based on the breathing fluctuation function.
[0116] In an embodiment, the acquisition module is used to obtain breathing acceleration data in a first direction, a second direction, and a third direction, where the first direction, the second direction, and the third direction are perpendicular to each other; and the breathing acceleration data is used as the initial breathing data.
[0117] In an embodiment, the preprocessing module is used to perform denoising processing on the plurality of initial breathing data in different directions using a distributed multi-wavelet transform function to obtain target breathing data in different directions.
[0118] In an embodiment, the preprocessing module is used to normalize the plurality of initial breathing data that have been denoised to obtain target breathing data in different directions.
[0119] In an embodiment, the preprocessing module is used to divide the plurality of initial breathing data that have been denoised into a plurality of data sets; perform normalization processing on each data set to obtain a target data set; and splice each target data set to obtain target breathing data in different directions.
[0120] In one embodiment, the preprocessing module is configured to determine peaks and valleys in a plurality of initial respiration data undergoing normalization processing; calculate the distances between the peaks and valleys; obtain a first respiration value and a second respiration value based on the sampling rate and the distances, where the first respiration value and the second respiration value are respectively used to represent different respiration durations; and determine target respiration data in different directions from the plurality of initial respiration data undergoing normalization processing based on the first respiration value and the second respiration value.
[0121] In one embodiment, the calculation module is configured to calculate the signal-to-noise ratio, root mean square error, and respiration fluctuation amplitude in each direction based on the target respiration data and the initial respiration data; and calculate the fusion coefficients in different directions respectively based on the signal-to-noise ratio, root mean square error, and respiration fluctuation amplitude in different directions.
[0122] Each module in the above-described respiration state detection device can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so as to facilitate the processor to call and execute the operations corresponding to the above-mentioned respective modules.
[0123] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 7 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the detection data of the respiration state. The input / output interface of the computer device is used for the processor to exchange information with external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method for detecting the respiration state.
[0124] Those skilled in the art can understand that Figure 7 the structure shown in
[0125] In one embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.
[0126] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.
[0127] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.
[0128] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.
[0129] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope recorded in the present application.
[0130] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims
1. A method for detecting a respiratory state, characterized in that: The method comprises: Acquire multiple initial breathing data in different directions; Preprocessing the multiple initial breathing data in different directions using a preset function to obtain target breathing data in different directions; Calculating fusion coefficients in different directions based on the target breathing data and the initial breathing data; Based on the fusion coefficient and the target respiratory data, a respiratory fluctuation function is determined, and a respiratory state is detected based on the respiratory fluctuation function.
2. The method for detecting respiratory status according to claim 1, characterized in that: The obtaining of a plurality of initial breathing data in different directions comprises: Obtaining respiratory acceleration data in a first direction, a second direction, and a third direction, wherein the first direction, the second direction, and the third direction are perpendicular to each other; The respiratory acceleration data is used as the initial respiratory data.
3. The method for detecting respiratory status according to claim 1, characterized in that: The preprocessing of the plurality of initial breathing data in different directions using a preset function to obtain target breathing data in different directions includes: The multiple initial breathing data in different directions are denoised using a distributed multiple wavelet transform function to obtain the target breathing data in different directions.
4. The method for detecting respiratory status according to claim 3, characterized in that: The step of using a distributed multiple wavelet transform function to perform denoising on the multiple initial breathing data in different directions to obtain the target breathing data in different directions includes: The multiple initial breathing data subjected to denoising are normalized to obtain the target breathing data in different directions.
5. The method for detecting respiratory status according to claim 4, characterized in that: The step of normalizing the plurality of initial breathing data subjected to denoising to obtain the target breathing data in different directions includes: dividing the plurality of initial respiratory data to be subjected to denoising processing into a plurality of data sets; Normalize each data set to obtain the target data set; Each target data set is spliced to obtain the target breathing data in different directions.
6. The method for detecting respiratory status according to claim 4, characterized in that: The step of normalizing the plurality of initial breathing data subjected to denoising to obtain the target breathing data in different directions includes: determining peaks and troughs in the plurality of initial respiratory data subjected to normalization; Calculating the distance between the peak and the trough; Obtaining a first breathing value and a second breathing value based on the sampling rate and the distance, wherein the first breathing value and the second breathing value are respectively used to represent different breathing durations; Based on the first respiration value and the second respiration value, the target respiration data in different directions are determined from the plurality of initial respiration data that are subjected to the normalization process.
7. The method for detecting respiratory status according to claim 1, characterized in that: The calculating fusion coefficients in different directions based on the target breathing data and the initial breathing data includes: Calculating the signal-to-noise ratio, root mean square error, and respiratory fluctuation amplitude in each direction based on the target respiratory data and the initial respiratory data; The fusion coefficients in different directions are calculated based on the signal-to-noise ratio, the root mean square error and the respiratory fluctuation amplitude in different directions respectively.
8. A breathing state detection device, characterized in that: The device comprises: An acquisition module, used for acquiring a plurality of initial breathing data in different directions; A preprocessing module, used for preprocessing the multiple initial breathing data in different directions using a preset function to obtain target breathing data in different directions; A calculation module, used for calculating fusion coefficients in different directions based on the target breathing data and the initial breathing data; A determination module is used to determine a respiratory fluctuation function based on the fusion coefficient and the target respiratory data, and detect a respiratory state based on the respiratory fluctuation function.
9. A respiratory status detection device, characterized in that: The respiratory state detection device comprises an inertial sensor, and the inertial sensor is used to obtain a plurality of initial respiratory data in different directions in the respiratory state detection method according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.