Method and device for detecting respiratory rate, terminal equipment and storage medium

Abstract

The invention is applicable to the technical field of computer application, and provides a method and a device for detecting respiratory frequency, terminal equipment and a storage medium, and the method comprises the following steps: firstly, receiving and analyzing a wireless signal in a current preset area, obtaining amplitude data corresponding to the wireless signal, and then according to the amplitude data and a preset ensemble classification model, obtaining a preset ensemble classification model; the state classification of the detected person is determined, and finally the respiratory rate of the detected person is determined according to the state classification of the detected person and a preset estimation algorithm. Therefore, according to the scheme, the problem that in a wall penetrating scene, a contact type sensor is generally needed to detect the breathing frequency of the detected person is solved, the flexibility and convenience of the breathing frequency detection method are improved, meanwhile, the breathing frequency of the detected person can be remotely monitored in real time, and the requirements of different crowds are met.

Description

Technical Field

[0001] The present application belongs to the field of computer application technology, and in particular, relates to a method, apparatus, terminal device and storage medium for detecting respiratory rate. Background Art

[0002] In recent years, respiratory detection technology has made significant progress in the fields of medical treatment, health monitoring and security. Traditional respiratory detection methods mainly rely on contact sensors or professional equipment, which limits the convenience and real-time performance of detection. Contactless respiratory detection technology has gradually become a research hotspot.

[0003] Among the related technologies, contactless breathing detection technology can adopt infrared hot line technology, camera image analysis, and microwave radar technology, etc. However, in the actual application process, the above-mentioned contactless breathing detection technologies may have different problems. For example, infrared hot line technology is more sensitive to ambient temperature and background interference, and may be affected by temperature changes and other heat sources, resulting in reduced accuracy of breathing detection; camera image analysis requires complex algorithm processing of images, which has high requirements for hardware and computing resources, and may be affected by light and background interference, and is not suitable for darker environments; microwave radar technology is more sensitive to target distance, and may have higher sensitivity for human bodies close to the radar, but the detection effect may be poor for human bodies at a longer distance. Summary of the invention

[0004] The embodiments of the present application provide a method, apparatus, terminal device and storage medium for detecting respiratory rate, which can solve the problem that in current wall penetration scenarios, a contact sensor is generally required to detect the respiratory rate of the person being detected, resulting in poor flexibility and low convenience, and difficulty in meeting the needs of different groups of people.

[0005] In a first aspect, an embodiment of the present application provides a method for detecting respiratory rate, comprising: receiving and analyzing a wireless signal within a current preset area to obtain amplitude data corresponding to the wireless signal; determining a state classification of a person being detected based on the amplitude data and a preset integrated classification model, wherein the integrated classification model is trained based on historical amplitude data; determining the respiratory rate of the person being detected based on the state classification of the person being detected and a preset estimation algorithm.

[0006] In a possible implementation manner of the first aspect, the classification status output by the preset integrated classification model is the presence of a human body or the absence of a human body, and the preset integrated classification model is composed of multiple support vector machines.

[0007] Optionally, in another possible implementation of the first aspect, determining the state classification of the subject according to the amplitude data and a preset integrated classification model includes:

[0008] Perform feature extraction on the amplitude data according to a preset data feature extraction algorithm to obtain multiple groups of feature vectors corresponding to the amplitude data;

[0009] Using each support vector machine to perform classification prediction on multiple groups of feature vectors, and obtaining the state classification corresponding to the amplitude data output by each support vector machine;

[0010] Voting is performed according to the state classification corresponding to the amplitude data output by each support vector machine to determine the state classification of the person being tested.

[0011] Optionally, in another possible implementation of the first aspect, determining the respiratory rate of the subject according to the state classification of the subject and a preset estimation algorithm includes:

[0012] When the state of the subject is classified as human body presence, the amplitude data is processed by wavelet transform to obtain the wavelet coefficients corresponding to the amplitude data;

[0013] The wavelet coefficients are calculated according to the peak-to-valley interval rate estimation algorithm to obtain the respiratory rate of the subject.

[0014] Optionally, in another possible implementation manner of the first aspect, when the state of the detected person is classified as human body presence, before the amplitude data is processed by using wavelet transform to obtain wavelet coefficients corresponding to the amplitude data, the method further includes:

[0015] The amplitude data is optimized using a signal quality optimization algorithm.

[0016] Optionally, in another possible implementation manner of the first aspect, the optimizing process of the amplitude data by using the signal quality optimization algorithm includes:

[0017] De-noising the amplitude data according to the sub-channel removal method;

[0018] The denoised amplitude data is optimized according to the subcarrier selection method.

[0019] Optionally, in another possible implementation of the first aspect, determining the respiratory rate of the subject according to the state classification of the subject and a preset estimation algorithm includes:

[0020] When the state of the subject is classified as the absence of a human body, the detection of the respiratory rate is stopped.

[0021] In a second aspect, an embodiment of the present application provides a device for detecting respiratory rate, comprising: an acquisition module, used to receive and analyze wireless signals within a current preset area, and obtain amplitude data corresponding to the wireless signals; a first determination module, used to determine a state classification of a person being detected based on the amplitude data and a preset integrated classification model, wherein the integrated classification model is trained based on historical amplitude data; a second determination module, used to determine the respiratory rate of the person being detected based on the state classification of the person being detected and a preset estimation algorithm.

[0022] In a possible implementation manner of the second aspect, the classification state output by the preset integrated classification model is human body presence or human body absence, and the preset integrated classification model is composed of multiple support vector machines.

[0023] Optionally, in another possible implementation manner of the second aspect, the first determining module includes:

[0024] A first acquisition unit, configured to perform feature extraction on the amplitude data according to a preset data feature extraction algorithm, and acquire multiple groups of feature vectors corresponding to the amplitude data;

[0025] A second acquisition unit uses each support vector machine to perform classification prediction on multiple groups of feature vectors to obtain a state classification corresponding to the amplitude data output by each support vector machine;

[0026] The determination unit is used to vote according to the state classification corresponding to the amplitude data output by each support vector machine to determine the state classification of the detected person.

[0027] Optionally, in another possible implementation manner of the second aspect, the second determining module includes:

[0028] A third acquisition unit is used to process the amplitude data using wavelet transform to obtain wavelet coefficients corresponding to the amplitude data when the state of the detected person is classified as human body presence;

[0029] The fourth acquisition unit is used to calculate the wavelet coefficients according to the peak-to-valley interval rate estimation algorithm to obtain the respiratory frequency of the subject.

[0030] Optionally, in another possible implementation manner of the second aspect, the second determining module further includes:

[0031] The optimization unit is used to optimize the amplitude data using a signal quality optimization algorithm.

[0032] Optionally, in another possible implementation manner of the second aspect, the optimization unit is specifically configured to:

[0033] De-noising the amplitude data according to the sub-channel removal method;

[0034] The denoised amplitude data is optimized according to the subcarrier selection method.

[0035] Optionally, in another possible implementation manner of the second aspect, the second determining module includes:

[0036] The stopping unit is used to stop detecting the respiratory rate when the state of the detector is classified as the absence of human body.

[0037] In a third aspect, an embodiment of the present application provides a terminal device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for detecting respiratory frequency as described above when executing the computer program.

[0038] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for detecting respiratory frequency as described above is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 It is a schematic diagram of an applicable scenario of the method for detecting respiratory frequency provided in an embodiment of the present application;

[0041] Figure 2 is a flow chart of a method for detecting respiratory frequency provided in an embodiment of the present application;

[0042] Figure 3 is a flow chart of a method for detecting respiratory rate provided by another embodiment of the present application;

[0043] Figure 4 is a flow chart of a method for detecting respiratory rate provided in yet another embodiment of the present application;

[0044] Figure 5 is a flow chart of a method for detecting respiratory frequency provided by another embodiment of the present application;

[0045] Figure 6 is a schematic diagram of the structure of a device for detecting respiratory frequency provided in an embodiment of the present application;

[0046] Figure 7It is a schematic diagram of the structure of the terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0047] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0048] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0049] It should also be understood that the term “and / or” used in the specification and appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0050] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0051] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0052] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0053] The following describes in detail with reference to the accompanying drawings the scenario diagram of the method for detecting respiratory rate, the method, apparatus, terminal device and storage medium for detecting respiratory rate provided in the present application.

[0054] Figure 1 A schematic diagram of an applicable scenario of a method for detecting respiratory frequency according to an embodiment of the present application is shown.

[0055] For example, a schematic diagram of an applicable scenario of an embodiment of the present application is as follows: Figure 1 As shown, first, the wireless signal transmitter sends a wireless signal to a preset space, and then the wireless signal receiver receives the wireless signal transmitted back from the preset space, and then analyzes the received wireless signal to extract and analyze the amplitude data in the wireless signal. After the amplitude data in the preset space is obtained, the amplitude data is sent to a pre-trained voting algorithm. The voting algorithm will determine whether there is a human body in the preset space based on the input amplitude data. When it is determined that there is no human body in the preset space, the subsequent respiratory frequency detection step will not be performed; when it is determined that there is a human body in the preset space, the above-mentioned amplitude data can first be subjected to signal processing steps such as denoising and optimization, and then the optimized amplitude data can be input into an evaluation step composed of a wavelet transform and a peak-to-valley interval rate estimation algorithm. By estimating the amplitude data, the respiratory frequency corresponding to the above-mentioned human body when there is a human body in the preset space can be finally obtained.

[0056] The schematic diagram of applicable scenarios of a method for detecting respiratory rate provided in an embodiment of the present application can solve the problem that current respiratory detection methods either use specific equipment and contact detection, or adopt contactless detection but cannot meet the needs of different groups of people. Therefore, the embodiment of the present application can improve the convenience and flexibility of respiratory detection, and realize long-distance real-time detection of respiratory rate on the basis of meeting the needs of different groups of people.

[0057] Figure 2 A flow chart of a method for detecting respiratory frequency provided in an embodiment of the present application is shown.

[0058] Step 201: Receive and analyze wireless signals in a current preset area to obtain amplitude data corresponding to the wireless signals.

[0059] Among them, the current preset area may refer to a pre-set area that can receive wireless signals. For example, the preset area may be a preset area consisting of one room or multiple rooms, or may be a preset area consisting of one closed space or multiple closed spaces. It is suitable for any closed space in a wall penetration scenario, and this application does not limit this.

[0060] Among them, wireless signals can refer to electromagnetic waves propagating through the air in wireless communications. These electromagnetic waves can transmit information in space, such as sound, images, data, etc., thereby realizing wireless communications. Wireless signals can propagate in a wide range of frequencies, including radio frequency bands and microwave bands. Common wireless communication technologies include Wi-Fi, Bluetooth, mobile communications (such as 2G, 3G, 4G, 5G), satellite communications, etc., all of which use wireless signals to transmit information between devices.

[0061] The amplitude data may refer to the data of the amplitude value in the signal, which is usually used to indicate the strength or size of the signal. For example, the amplitude data is usually used to describe the strength or power of the wireless signal. For example, in the embodiment of the present application, the amplitude data is the basis for realizing the respiratory rate detection by collecting the amplitude value in the wireless signal, and the present application does not limit this.

[0062] In the embodiment of the present application, the wireless signal in the preset area can be obtained to obtain the amplitude data corresponding to the wireless signal in the preset area, thereby providing a basis for subsequent determination of the status classification of the detected person.

[0063] Step 202, determining the state classification of the subject according to the amplitude data and a preset integrated classification model, wherein the integrated classification model is trained according to historical amplitude data.

[0064] Among them, the preset integrated classification model may refer to a model for classifying data after processing the amplitude data. The above preset integrated classification model may be obtained by integrating multiple classification models, and this application does not limit this.

[0065] The state classification may refer to a state corresponding to each data category after the amplitude data is classified by a preset integrated classification model.

[0066] For example, after the amplitude data is input into the preset integrated classification model, three different categories of data are output, namely Class A data, Class B data, and Class C data. The state corresponding to Class A data is lying, the state corresponding to Class B data is sitting, and the state corresponding to Class C data is standing. The above amplitude data is classified by the preset integrated classification model into lying, sitting, and standing.

[0067] In an embodiment of the present application, after obtaining the amplitude data corresponding to the wireless signal in the preset area, the amplitude data can be input into a preset integrated classification model to output a state classification corresponding to the amplitude data, thereby providing a better analysis basis for subsequent respiratory rate detection.

[0068] Furthermore, the state classification output by the preset integrated classification model is classified as human body presence or human body absence, and the preset integrated classification model is composed of multiple support vector machines.

[0069] Among them, support vector machine can refer to a binary classification supervised learning algorithm used to solve classification and regression problems. Its basic principle is to find an optimal hyperplane to separate data samples of different categories. In the binary classification problem, the goal of the support vector machine is to find a hyperplane with the maximum interval to maximize the distance between positive and negative samples.

[0070] For example, when given a set of labeled training sample data containing two different types (eg, positive examples and negative examples), the support vector machine will look for an optimal hyperplane to separate the two types of data samples, which is not limited in this application.

[0071] As a possible implementation method, when the preset integrated classification model is composed of 7 support vector machines, the amplitude data is input into the preset data feature extraction algorithm for calculation, and the multiple groups of feature vectors obtained are input into the preset integrated classification model, where each support vector machine will classify according to the multiple groups of feature vectors corresponding to the amplitude data. For example, when the output classification of three support vector machines is that the human body exists, and the output classification of four support vector machines is that the human body does not exist, because the number of classifications for the non-existence of the human body is greater than the number of classifications for the presence of the human body, the preset integrated classification model can determine that the status of the input amplitude data is classified as the non-existence of the human body, and no limitation is imposed on this in the application.

[0072] Step 203, determining the breathing rate of the subject according to the status classification of the subject and a preset estimation algorithm.

[0073] The preset estimation algorithm may refer to a pre-set calculation method for estimating the amplitude data to obtain the respiratory frequency of the subject.

[0074] For example, the estimation algorithm for determining the breathing frequency of the subject based on the amplitude data may include a peak-to-valley interval estimation algorithm, a power spectrum density analysis algorithm, an autocorrelation function algorithm, or a machine learning algorithm.

[0075] In an embodiment of the present application, after obtaining the state classification corresponding to the amplitude data, the amplitude data is calculated according to the state classification and a preset estimation algorithm to obtain the breathing frequency of the person being tested, thereby improving the accuracy of breathing detection.

[0076] The method for detecting respiratory frequency provided by the present application first receives and analyzes the wireless signal in the current preset area, obtains the amplitude data corresponding to the wireless signal, and then determines the state classification of the detected person based on the amplitude data and the preset integrated classification model, wherein the integrated classification model is trained based on the historical amplitude data, and finally determines the respiratory frequency of the detected person based on the state classification of the detected person and the preset estimation algorithm. Thus, by classifying and evaluating the amplitude data in the wireless signal in the preset area, the respiratory frequency of the detected person is obtained, which solves the problem that a contact sensor is generally required to detect the respiratory frequency of the detected person in the wall penetration scenario, improves the flexibility and convenience of the method for detecting the respiratory frequency, and can also monitor the respiratory frequency of the detected person in real time over a long distance, meeting the needs of different groups of people.

[0077] In a possible implementation form of the present application, in order to better detect the breathing frequency of the subject, it is necessary to first determine the real-time status of the subject in the preset space.

[0078] Combine the following Figure 3 , the method for detecting respiratory rate provided in an embodiment of the present application is further explained.

[0079] Figure 3 A flow chart of another method for detecting respiratory frequency provided in an embodiment of the present application is shown.

[0080] Step 301: Receive and analyze wireless signals in a current preset area to obtain amplitude data corresponding to the wireless signals.

[0081] The specific implementation process and principle of the above step 301 can be referred to the detailed description of the above embodiment, which will not be repeated here.

[0082] Step 302: extract features from the amplitude data according to a preset data feature extraction algorithm to obtain multiple groups of feature vectors corresponding to the amplitude data.

[0083] Among them, the preset data extraction feature algorithm may refer to a calculation method for extracting a feature vector corresponding to the amplitude data based on the amplitude data, such as the first-order difference of the eigenvalues ​​of the CSI correlation matrix across all subcarriers, and mathematical and statistical methods such as the power delay curve in the time domain, the time domain mean, and the variance.

[0084] Herein, feature extraction may refer to extracting features from amplitude data input into each preset data feature extraction algorithm.

[0085] The feature vector may refer to a feature representation output after feature extraction of the amplitude data.

[0086] As a possible implementation method, the amplitude data can be input into a preset data feature extraction algorithm to extract 12 features from the amplitude data, including the power delay profile (PDP) and the first-order difference of the subcarrier correlation matrix eigenvalues, etc., which is not limited in this application.

[0087] In an embodiment of the present application, the amplitude data within a preset area can be input into a preset data feature extraction algorithm for feature extraction, and the feature vector output after feature extraction is used as the basis for subsequent state classification, thereby improving the efficiency of respiratory rate detection.

[0088] Step 303: Use each support vector machine to perform classification prediction on multiple groups of feature vectors to obtain the state classification corresponding to the amplitude data output by each group of support vector machines.

[0089] It should be noted that each support vector machine learns the weights corresponding to different features in the amplitude data in the historical training data, and then performs state classification according to the feature vector corresponding to the input amplitude data.

[0090] In an embodiment of the present application, after the amplitude data is obtained, a support vector machine can be used to perform feature extraction, and then the support vector machine can be used to classify and predict the feature vector, and finally the state classification corresponding to the amplitude data output by each support vector machine is obtained. By classifying the amplitude data through multiple support vector machines, the accuracy and robustness of the classification can be improved.

[0091] Step 304: Voting is performed according to the state classification corresponding to the amplitude data output by each support vector machine to determine the state classification of the subject.

[0092] For example, the current preset integrated classification model has 7 support vector machines. Each support vector machine will output the corresponding state classification after classifying the amplitude data. Suppose the state classification of two of the support vector machines is that the human body does not exist, and the state classification of the remaining five support vector machines is that the human body exists. Because the state classification with the most votes is that the human body exists, the integrated classification model can determine that the classification state of the person being tested is that the human body exists.

[0093] In an embodiment of the present application, the classification results of each support vector machine can be integrated, and the final state classification can be determined based on the classification results that occupy the majority. Thus, the integrated classification model can combine the judgment results of multiple support vector machines, reduce the error rate of a single support vector machine, and thus improve the overall classification accuracy and robustness. At the same time, since the integrated classification model can balance the prediction results of multiple support vector machines, even if a classifier has an accidental error, the stability of the overall system can be guaranteed.

[0094] Step 305, determining the breathing rate of the subject according to the status classification of the subject and a preset estimation algorithm.

[0095] The specific implementation process and principle of the above step 305 can refer to the detailed description of the above embodiment, which will not be repeated here.

[0096] The method for detecting respiratory rate provided in the present application first receives and analyzes the wireless signal in the current preset area to obtain amplitude data corresponding to the wireless signal, then inputs the amplitude data into a preset data feature extraction algorithm for feature extraction to obtain multiple groups of feature vectors corresponding to the amplitude data, then uses each support vector machine to classify and predict the multiple groups of feature vectors to obtain the state classification corresponding to the amplitude data output by each support vector machine, then votes based on the state classification corresponding to the amplitude data output by each support vector machine to determine the state classification of the person being detected, and finally determines the respiratory rate of the person being detected based on the state classification of the person being detected and the preset estimation algorithm. Thus, by using each support vector machine to classify the amplitude data, the integrated classification model can more accurately obtain the state classification corresponding to the amplitude data.

[0097] In a possible implementation form of the present application, after obtaining the state classification corresponding to the amplitude data, the amplitude data is further optimized according to the state classification before the respiratory rate of the subject is detected, thereby improving the accuracy of the respiratory rate detection.

[0098] Combine the following Figure 4 , the method for detecting respiratory rate provided in an embodiment of the present application is further explained.

[0099] Figure 4 A flow chart of another method for detecting respiratory frequency provided in an embodiment of the present application is shown.

[0100] Step 401: Receive and analyze wireless signals in a current preset area to obtain amplitude data corresponding to the wireless signals.

[0101] Step 402, determining the state classification of the subject according to the amplitude data and a preset integrated classification model, wherein the integrated classification model is trained according to historical amplitude data.

[0102] The specific implementation process and principle of the above steps 401-402 can refer to the detailed description of the above embodiment, which will not be repeated here.

[0103] Step 403: Optimize the amplitude data using a signal quality optimization algorithm.

[0104] Among them, the signal quality optimization algorithm can refer to a class of algorithms and technologies used to improve the quality of signal transmission or reception. In the field of communication and signal processing, signal quality refers to the reliability, stability and accuracy of the signal transmission or reception process. The signal quality optimization algorithm aims to eliminate or reduce noise, distortion, interference and other problems that occur during signal transmission or reception, thereby improving the quality and reliability of the signal. For example, the signal quality optimization algorithm can be a channel equalization algorithm, an error correction algorithm, etc., which is not limited in this application.

[0105] In the embodiment of the present application, the amplitude data can be optimized using a signal quality optimization algorithm, so that the accuracy of the detection can be improved when the respiratory frequency is subsequently detected based on the amplitude data.

[0106] Furthermore, the above step 403 may also include:

[0107] The amplitude data is denoised according to the sub-channel removal method.

[0108] The denoised amplitude data is optimized according to the subcarrier selection method.

[0109] Among them, the subchannel removal method may refer to a technology used for signal processing, which aims to remove subchannel interference from complex signals. In wireless communication systems, signals usually pass through multiple propagation paths, resulting in multipath effects at the receiving end. The multipath effect can cause signals to interfere with each other on different frequency subchannels, affecting the transmission quality of the signal. The subchannel removal method aims to eliminate or reduce the subchannel interference caused by the multipath effect, thereby improving the reception quality of the signal.

[0110] The subcarrier selection method may refer to a subcarrier selection algorithm for optimizing an orthogonal frequency division multiplexing system. In an orthogonal frequency division multiplexing system, a signal is divided into multiple subcarriers for transmission, and each subcarrier is responsible for transmitting a portion of data. The goal of the subcarrier selection method is to select subcarriers with a higher sensing signal-to-noise ratio, thereby optimizing system performance and improving the reliability and efficiency of data transmission.

[0111] In an embodiment of the present application, the amplitude data can be subjected to signal optimization processing according to a subchannel removal method and a subcarrier selection method, thereby enabling more stable and reliable signal transmission, thereby improving the accuracy of respiratory rate detection.

[0112] Step 404: When the state of the subject is classified as human body presence, the amplitude data is processed using wavelet transform to obtain wavelet coefficients corresponding to the amplitude data.

[0113] Among them, wavelet transform can refer to a signal processing technology used to analyze the characteristics of signals at different frequencies and time scales. Wavelet transform can provide local characteristics of signals at different frequencies and times, so it has advantages in processing non-stationary signals and nonlinear signals.

[0114] Among them, wavelet coefficients can refer to a set of coefficients obtained in wavelet transform, which represent the local characteristics of the signal at different scales and times. In wavelet transform, the signal will be decomposed into wavelet basis functions at different scales, and then the similarity between the signal and the wavelet basis function is calculated by the inner product to obtain a set of coefficients, which are the wavelet coefficients.

[0115] As a possible implementation method, the DB6 wavelet function can be used to perform a wavelet transform on the amplitude data. When the length of the amplitude data signal is 9 data points, the DB6 wavelet function can be used to perform a wavelet transform on the amplitude data signal of length 9, and the signal can be decomposed into frequency components of different scales to obtain wavelet coefficients. These wavelet coefficients can be used to further perform signal processing or analysis tasks, and this application does not limit this.

[0116] In an embodiment of the present application, when it is detected that the state of the subject is classified as human presence, the amplitude data can be processed using wavelet transform to obtain wavelet coefficients corresponding to the amplitude data, which can provide a data basis for subsequent estimation of the respiratory frequency based on the wavelet coefficients.

[0117] Step 405, calculating the wavelet coefficients according to the peak-to-valley interval rate estimation algorithm to obtain the breathing frequency of the subject.

[0118] The peak-to-valley interval rate estimation algorithm may refer to an algorithm for estimating the respiratory frequency of a signal, which calculates the respiratory frequency by using the time interval between the peak and the valley in the wavelet coefficients after the amplitude data is transformed by wavelet.

[0119] In an embodiment of the present application, the peak-to-valley interval rate estimation algorithm can extract local features of the amplitude data signal through wavelet transform, thereby more accurately estimating the respiratory frequency, especially the instantaneous frequency estimation, because the wavelet transform has the advantage of time-frequency locality and can better capture the instantaneous changes in the respiratory signal.

[0120] The method for detecting respiratory rate provided by the present application first receives and analyzes the wireless signal in the current preset area, obtains the amplitude data corresponding to the wireless signal, and then determines the state classification of the detected person based on the amplitude data and the preset integrated classification model, wherein the integrated classification model is obtained by training based on historical amplitude data, and then optimizes the amplitude data using a signal quality optimization algorithm. When the state of the detected person is classified as human body presence, the amplitude data is processed using a wavelet transform to obtain the wavelet coefficient corresponding to the amplitude data, and finally the wavelet coefficient is calculated according to the peak-to-valley interval rate estimation algorithm to obtain the respiratory rate of the detected person. Thus, by evaluating the respiratory rate after optimizing the amplitude data, the acquired respiratory rate of the detected person is more accurate.

[0121] In a possible implementation form of the present application, when it is detected that no human body exists in the preset space, subsequent respiratory frequency detection can be stopped.

[0122] Combine the following Figure 5 , the method for detecting respiratory rate provided in an embodiment of the present application is further explained.

[0123] Figure 5 A flow chart of another method for detecting respiratory frequency provided in an embodiment of the present application is shown.

[0124] Step 501: Receive and analyze wireless signals in a current preset area to obtain amplitude data corresponding to the wireless signals.

[0125] Step 502, determining the state classification of the subject according to the amplitude data and a preset integrated classification model, wherein the integrated classification model is trained according to historical amplitude data.

[0126] The specific implementation process and principle of the above steps 501-502 can be referred to the detailed description of the above embodiment, which will not be repeated here.

[0127] Step 503: When the state of the detected person is classified as the absence of human body, stop detecting the breathing rate.

[0128] In an embodiment of the present application, based on the amplitude data, when the preset integrated classification model determines that the state of the above amplitude data is classified as the absence of a human body, the respiratory frequency detection is stopped, thereby improving the method of detecting the respiratory frequency, avoiding unnecessary waste of resources, and saving costs.

[0129] The method for detecting respiratory frequency provided by the present application first receives and analyzes the wireless signal in the current preset area, obtains the amplitude data corresponding to the wireless signal, and then determines the state classification of the detected person based on the amplitude data and the preset integrated classification model, the integrated classification model is trained based on the historical amplitude data, and finally stops detecting the respiratory frequency when the state classification of the detected person is that the human body does not exist. Therefore, by judging that the state classification of the amplitude data is that the human body does not exist, the respiratory frequency detection is stopped, and the efficiency of the method for detecting the respiratory frequency can be improved.

[0130] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0131] Corresponding to the determination method of the application business integration system in the above embodiment, Figure 6 A structural block diagram of a device for detecting respiratory frequency provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0132] Reference Figure 6 , the device 600 comprises:

[0133] The acquisition module 601 is used to receive and analyze the wireless signal in the current preset area to obtain the amplitude data corresponding to the wireless signal;

[0134] A first determination module 602 is used to determine the state classification of the subject according to the amplitude data and a preset integrated classification model, where the integrated classification model is trained based on historical amplitude data;

[0135] The second determination module 603 is used to determine the breathing frequency of the subject according to the state classification of the subject and a preset estimation algorithm.

[0136] In actual use, the apparatus for detecting respiratory frequency provided in the embodiment of the present application can be configured in any terminal device to execute the aforementioned method for detecting respiratory frequency.

[0137] The device for detecting respiratory frequency provided by the present application first receives and analyzes the wireless signal in the current preset area, obtains the amplitude data corresponding to the wireless signal, and then determines the state classification of the detected person based on the amplitude data and the preset integrated classification model, wherein the integrated classification model is trained based on the historical amplitude data, and finally determines the respiratory frequency of the detected person based on the state classification of the detected person and the preset estimation algorithm. Thus, by classifying and evaluating the amplitude data in the wireless signal in the preset area, the respiratory frequency of the detected person is obtained, which solves the problem that a contact sensor is generally required to detect the respiratory frequency of the detected person in the wall penetration scenario, improves the flexibility and convenience of the method for detecting the respiratory frequency, and can also monitor the respiratory frequency of the detected person in real time over a long distance, meeting the needs of different groups of people.

[0138] In a possible implementation of an embodiment of the present application, the classification status output by the above-mentioned preset integrated classification model is the presence of the human body or the absence of the human body, and the preset integrated classification model is composed of multiple support vector machines.

[0139] Furthermore, in another possible implementation of the embodiment of the present application, the first determining module 602 includes:

[0140] A first acquisition unit, configured to perform feature extraction on the amplitude data according to a preset data feature extraction algorithm, and acquire multiple groups of feature vectors corresponding to the amplitude data;

[0141] A second acquisition unit uses each support vector machine to perform classification prediction on multiple groups of feature vectors to obtain a state classification corresponding to the amplitude data output by each support vector machine;

[0142] The determination unit is used to vote according to the state classification corresponding to the amplitude data output by each support vector machine to determine the state classification of the detected person.

[0143] Furthermore, in another possible implementation of the embodiment of the present application, the second determining module 603 includes:

[0144] A third acquisition unit is used to process the amplitude data using wavelet transform to obtain wavelet coefficients corresponding to the amplitude data when the state of the detected person is classified as human body presence;

[0145] The fourth acquisition unit is used to calculate the wavelet coefficients according to the peak-to-valley interval rate estimation algorithm to obtain the respiratory frequency of the subject.

[0146] Furthermore, in another possible implementation of the embodiment of the present application, the second determining module 603 further includes:

[0147] The optimization unit is used to optimize the amplitude data using a signal quality optimization algorithm.

[0148] Furthermore, in another possible implementation of the embodiment of the present application, the above-mentioned optimization unit is specifically used to:

[0149] De-noising the amplitude data according to the sub-channel removal method;

[0150] The denoised amplitude data is optimized according to the subcarrier selection method.

[0151] Furthermore, in another possible implementation of the embodiment of the present application, the second determining module 603 includes:

[0152] The stopping unit is used to stop detecting the respiratory rate when the state of the detector is classified as the absence of human body.

[0153] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0154] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0155] In order to implement the above embodiments, the present application also proposes a terminal device.

[0156] Figure 7 A schematic diagram of the structure of a terminal device according to an embodiment of the present application.

[0157] like Figure 7 As shown, the terminal device 200 includes:

[0158] The memory 210 and at least one processor 220, a bus 230 connecting different components (including the memory 210 and the processor 220), the memory 210 stores a computer program, and when the processor 220 executes the program, the method for detecting the respiratory frequency described in the embodiment of the present application is implemented.

[0159] Bus 230 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.

[0160] The terminal device 200 typically includes a variety of electronic device readable media, which can be any available media that can be accessed by the terminal device 200, including volatile and non-volatile media, removable and non-removable media.

[0161] The memory 210 may also include computer system readable media in the form of volatile memory, such as random access memory (RAM) 240 and / or cache memory 250. The terminal device 200 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 260 may be used to read and write non-removable, non-volatile magnetic media ( Figure 7 not shown, usually called a "hard drive"). Although Figure 7 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical medium) may be provided. In these cases, each drive may be connected to bus 230 via one or more data medium interfaces. Memory 210 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present application.

[0162] A program / utility 280 having a set (at least one) of program modules 270 may be stored, for example, in the memory 210, such program modules 270 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 270 generally perform the functions and / or methods of the embodiments described herein.

[0163] The terminal device 200 can also communicate with one or more external devices 290 (e.g., keyboard, pointing device, display 291, etc.), and can also communicate with one or more devices that enable users to interact with the terminal device 200, and / or communicate with any device that enables the terminal device 200 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be carried out through an input / output (I / O) interface 292. In addition, the terminal device 200 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN) and / or public network, such as the Internet) through a network adapter 293. As shown in the figure, the network adapter 293 communicates with other modules of the terminal device 200 through a bus 230. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the terminal device 200, including but not limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive, and data backup storage system, etc.

[0164] The processor 220 executes various functional applications and data processing by running the programs stored in the memory 210 .

[0165] It should be noted that the implementation process and technical principles of the terminal device of this embodiment refer to the aforementioned explanation of the method for detecting respiratory frequency in the embodiment of the present application, and will not be repeated here.

[0166] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0167] An embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0168] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0169] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0170] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0171] In the embodiments provided in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0172] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0173] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for detecting respiratory rate, characterized in that: include: Receive and analyze wireless signals in a current preset area to obtain amplitude data corresponding to the wireless signals; Determine the state classification of the subject according to the amplitude data and a preset integrated classification model, wherein the integrated classification model is trained according to historical amplitude data; The respiratory rate of the subject is determined according to the status classification of the subject and a preset estimation algorithm.

2. The method according to claim 1, characterized in that The state classification output by the preset integrated classification model is classified as human body presence or human body absence, and the preset integrated classification model is composed of multiple support vector machines.

3. The method according to claim 2, characterized in that Determining the state classification of the subject according to the amplitude data and a preset integrated classification model includes: Perform feature extraction on the amplitude data according to a preset data feature extraction algorithm to obtain multiple groups of feature vectors corresponding to the amplitude data; Using each of the support vector machines to perform classification prediction on the multiple groups of feature vectors, and obtaining the state classification corresponding to the amplitude data output by each of the support vector machines; Voting is performed according to the state classification corresponding to the amplitude data output by each support vector machine to determine the state classification of the subject.

4. The method according to claim 1, characterized in that the step of determining the respiratory rate of the subject according to the state classification of the subject and a preset estimation algorithm comprises: When the state of the subject is classified as human body presence, the amplitude data is processed by wavelet transform to obtain wavelet coefficients corresponding to the amplitude data; The wavelet coefficients are calculated according to a peak-to-valley interval rate estimation algorithm to obtain the respiratory frequency of the subject.

5. The method according to claim 4, further comprising: before processing the amplitude data by using wavelet transform to obtain the wavelet coefficients corresponding to the amplitude data when the state of the detected person is classified as human body presence: The amplitude data is optimized using a signal quality optimization algorithm.

6. The method according to claim 5, characterized in that The optimizing process of the amplitude data by using a signal quality optimization algorithm includes: De-noising the amplitude data according to a sub-channel removal method; The amplitude data after the denoising process is optimized according to the subcarrier selection method.

7. The method according to any one of claims 1 to 6, characterized in that: Determining the respiratory rate of the subject according to the state classification of the subject and a preset estimation algorithm includes: When the state of the detected person is classified as the absence of a human body, the detection of the respiratory rate is stopped.

8. A device for detecting respiratory frequency, characterized in that: include: An acquisition module, used to receive and analyze wireless signals in a current preset area, and obtain amplitude data corresponding to the wireless signals; A first determination module, used to determine the state classification of the subject according to the amplitude data and a preset integrated classification model, wherein the integrated classification model is trained based on historical amplitude data; The second determination module is used to determine the breathing frequency of the detected person according to the state classification of the detected person and a preset estimation algorithm.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images