Generation method for living body detection model, living body detection method and related device

Abstract

A generation method for a living body detection model, a living body detection method and a related device. The generation method for a living body detection model comprises: according to a preset collection period, acquiring channel state information of multiple received signals of a Wi-Fi receiving device, each received signal comprising a plurality of subcarriers; respectively carrying out conjugate multiplication processing on the channel state information of any two of the multiple received signals acquired in each collection period, so as to acquire a plurality of corresponding conjugate multiplication result matrixes; respectively extracting amplitude information and phase information of the plurality of subcarriers from the plurality of conjugate multiplication result matrixes; on the basis of the amplitude information and the phase information of the plurality of subcarriers, acquiring a plurality of pieces of corresponding living body detection training data, so as to form a living body detection training data set; and using the living body detection training data in the living body detection training data set to perform learning and training, so as to acquire a corresponding living body detection model. The solution in the embodiments of the present invention can improve the accuracy of living body detection.

Description

Method for generating life body detection model, life body detection method and related equipment Technical Field

[0001] Embodiments of the present invention relate to the field of life body detection, and in particular to a method for generating a life body detection model, a life body detection method, and related equipment. Background Art

[0002] With the development of wireless communication technology, life detection has been widely used in areas such as positioning within the detection environment, personnel intrusion detection, home medical monitoring, and new human-computer interaction interfaces. Common life detection methods include those based on vision, sensors, or Wi-Fi.

[0003] Wi-Fi-based life detection methods are widely used due to their non-invasive nature. They primarily utilize signal characteristics such as the Received Signal Strength Indicator (RSSI) and Channel State Information (CSI) for life detection. Compared to RSSI, CSI contains richer multipath information, providing higher accuracy and resolution for life detection.

[0004] However, the accuracy of current Wi-Fi-based life detection methods still needs to be improved. Technical issues

[0005] The problem solved by the embodiments of the present invention is to provide a method for generating a life form detection model, a life form detection method and related equipment, which are conducive to improving the performance of the life form detection model, thereby further improving the accuracy of life form detection. Technical Solutions

[0006] To solve the above problems, an embodiment of the present invention provides a method for generating a life detection model, comprising:

[0007] Acquire channel state information of multiple received signals of a Wi-Fi receiving device according to a preset collection period, where each received signal includes multiple subcarriers;

[0008] performing conjugate multiplication processing on the channel state information of any two of the multi-channel received signals obtained in each acquisition period to obtain corresponding multiple conjugate multiplication result matrices;

[0009] Extracting amplitude information and phase information of the multiple subcarriers from the multiple conjugate multiplication result matrices respectively;

[0010] Based on the amplitude information and phase information of the multiple subcarriers, obtaining corresponding multiple pieces of life detection training data to form a life detection training data set;

[0011] The life form detection training data in the life form detection training data set is used for learning and training to obtain a corresponding life form detection model.

[0012] Optionally, the life body detection training data includes:

[0013] A respiratory frequency value of a living being calculated based on a phase difference information correlation matrix of the plurality of subcarriers;

[0014] The maximum eigenvalue, the second largest eigenvalue and the entropy of the eigenvalues ​​after normalization of the amplitude information correlation coefficient matrix of multiple subcarriers;

[0015] performing principal component analysis on the amplitude information of the multiple subcarriers to obtain an energy value of a first principal component, an energy value of a second principal component, and an energy value of a third principal component, a ratio between a variance of the first principal component and a difference value of a eigenvector corresponding to the variance of the first principal component, a ratio between a variance of the second principal component and a difference value of a eigenvector corresponding to the variance of the second principal component, and a ratio between the difference values ​​of the eigenvector corresponding to the variance of the third principal component, and a kurtosis value of the second principal component;

[0016] The maximum eigenvalue and the second largest eigenvalue of the normalized phase difference information correlation coefficient matrix of the multiple subcarriers;

[0017] The standard deviation of the maximum eigenvalue of the normalized matrix of the amplitude information correlation coefficients of multiple subcarriers corresponding to the current acquisition period and the previous (N-1) acquisition periods;

[0018] The standard deviation of the second largest eigenvalue of the normalized phase difference information correlation coefficient matrix of multiple subcarriers corresponding to the current acquisition period and the previous (N-1) acquisition periods.

[0019] Optionally, the value range of N is 5 to 10 times.

[0020] Optionally, the acquisition period is 1s to 3s in length.

[0021] Optionally, the life detection model includes a support vector machine classifier.

[0022] Optionally, the living organism includes at least one of a human body and an animal body with a breathing frequency similar to that of a human body.

[0023] Accordingly, an embodiment of the present invention further provides a module for generating a life detection model, including:

[0024] A first acquisition submodule is adapted to acquire channel state information of multiple received signals of a Wi-Fi receiving device according to a preset acquisition period, where each received signal includes multiple subcarriers;

[0025] The conjugate multiplication submodule is adapted to perform conjugate multiplication processing on the channel state information of any two of the multi-channel received signals obtained in each acquisition period to obtain a plurality of corresponding conjugate multiplication result matrices;

[0026] an information extraction submodule, adapted to extract amplitude information and phase information of the plurality of subcarriers from the plurality of conjugate multiplication result matrices respectively;

[0027] a data acquisition submodule adapted to acquire a plurality of corresponding life form detection training data based on the amplitude information and phase information of the plurality of subcarriers to form a life form detection training data set;

[0028] The model training submodule is adapted to perform learning and training using the life form detection training data in the life form detection training data set to obtain a corresponding life form detection model.

[0029] Optionally, the life detection training data acquired by the data acquisition submodule includes:

[0030] A respiratory frequency value of a living being calculated based on a phase difference information correlation matrix of the plurality of subcarriers;

[0031] The maximum eigenvalue, the second largest eigenvalue and the entropy of the eigenvalues ​​after normalization of the amplitude information correlation coefficient matrix of multiple subcarriers;

[0032] an energy value of a first principal component, an energy value of a second principal component, and an energy value of a third principal component, a ratio between a variance of the first principal component and a difference value of an eigenvector corresponding to the variance of the first principal component, a ratio between a variance of the second principal component and a difference value of an eigenvector corresponding to the variance of the second principal component, a ratio between a difference value of an eigenvector corresponding to the variance of the third principal component, and a kurtosis value of the second principal component, obtained after performing principal component analysis on the amplitude information of the multiple subcarriers;

[0033] The maximum eigenvalue and the second largest eigenvalue of the normalized phase difference information correlation coefficient matrix of the multiple subcarriers;

[0034] The standard deviation of the maximum eigenvalue of the normalized matrix of the amplitude information correlation coefficients of multiple subcarriers corresponding to the current acquisition period and the previous (N-1) acquisition periods;

[0035] The standard deviation of the second largest eigenvalue of the normalized phase difference information correlation coefficient matrix of multiple subcarriers corresponding to the current acquisition period and the previous (N-1) acquisition periods.

[0036] Optionally, the value range of N is 5 to 10 times.

[0037] Optionally, the acquisition period is 1s to 3s in length.

[0038] Optionally, the life detection model includes a support vector machine classifier.

[0039] Optionally, the living organism includes at least one of a human body and an animal body with a breathing frequency similar to that of a human body.

[0040] Accordingly, an embodiment of the present invention further provides a method for detecting a living being, comprising:

[0041] Obtain channel status information of multiple received signals of the Wi-Fi receiving device in the current detection period;

[0042] The obtained channel state information of the multi-channel received signals of the Wi-Fi receiving device in the current detection period is input into the life body detection model generated by the life body detection model generation method as described in any of the above items to obtain the corresponding life body detection result.

[0043] Optionally, the life body detection method further includes:

[0044] The life body detection model is used to obtain the entropy of the normalized eigenvalues ​​of the amplitude information correlation coefficient matrix of multiple subcarriers in the current detection period and the entropy of the normalized eigenvalues ​​of the amplitude information correlation coefficient matrix of multiple subcarriers in the previous (M-1) detection periods;

[0045] The life detection model is used to output a detection result indicating that no life exists in the environment to be detected when the entropy of the eigenvalues ​​of the normalized eigenvalue matrix of the amplitude information correlation coefficient of multiple subcarriers in the current detection period and the entropy of the normalized eigenvalue matrix of the amplitude information correlation coefficient of multiple subcarriers in the previous (M-1) detection periods are both greater than a preset threshold.

[0046] Optionally, the value range of M is 5 to 10 times.

[0047] Accordingly, an embodiment of the present invention further provides a life detection module, comprising:

[0048] An acquisition submodule adapted to acquire channel state information of multiple received signals of a Wi-Fi receiving device in a current detection period;

[0049] The detection submodule is adapted to input the acquired channel state information of the multi-channel received signals of the Wi-Fi receiving device in the current detection period into the life detection model generated by the life detection model generation method as described in any of the above items to obtain the corresponding life detection result.

[0050] Optionally, each received signal includes multiple subcarriers;

[0051] The detection submodule is further adapted to use the living body detection model to obtain the entropy of the eigenvalues ​​of the normalized amplitude information correlation coefficient matrix of multiple subcarriers in the current detection period and the entropy of the eigenvalues ​​of the normalized amplitude information correlation coefficient matrix of multiple subcarriers in the previous (M-1) detection periods; and output a detection result indicating the absence of a living body in the environment to be detected when the living body detection model is used to determine that the entropy of the eigenvalues ​​of the normalized amplitude information correlation coefficient matrix of multiple subcarriers in the current detection period and the entropy of the normalized amplitude information correlation coefficient matrix of multiple subcarriers in the previous (M-1) detection periods are both greater than a preset threshold.

[0052] Optionally, the value range of M is 5 to 10 times.

[0053] Correspondingly, an embodiment of the present invention further provides a chip on which the generation module of the life body detection model as described in any one of the above items or the life body detection module as described in any one of the above items is integrated.

[0054] Accordingly, an embodiment of the present invention also provides an electronic device comprising at least one memory and at least one processor, wherein the memory stores one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement a method for generating a life detection model as described in any one of the above items or a life detection method as described in any one of the above items.

[0055] Correspondingly, an embodiment of the present invention further provides a storage medium storing one or more computer instructions, wherein the one or more computer instructions are used to implement the method for generating a life form detection model as described in any of the above items or the life form detection method as described in any of the above items. Beneficial effects

[0056] Compared with the prior art, the technical solution of the present invention has the following advantages: the method for generating a life form detection model in the embodiment of the present invention first performs conjugate multiplication processing on the channel state information of any two of the multi-channel received signals of the Wi-Fi receiving device obtained in each acquisition cycle, which can eliminate the same phase error generated by the channel state information of different received signals. Then, the amplitude information and phase information of the multiple subcarriers are respectively extracted from the multiple conjugate multiplication result matrices. Based on the amplitude information and phase information of the multiple subcarriers, corresponding multiple life form detection training data are obtained. This can eliminate blind spots in the change of amplitude information or phase information of motion at certain locations in the environment to be detected, which correspondingly helps to improve the accuracy of the life form detection training data, thereby helping to improve the performance of the generated life form detection model, and further helping to improve the accuracy of life form detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] FIG1 is a flow chart of an embodiment of a method for generating a life form detection model according to the technical solution of the present invention;

[0058] FIG2 is a schematic structural diagram of an embodiment of a generation module of a life form detection model provided by the technical solution of the present invention;

[0059] FIG3 is a flow chart of an embodiment of a method for detecting a living being provided by the technical solution of the present invention;

[0060] FIG4 is a schematic structural diagram of an embodiment of a life detection module provided by the technical solution of the present invention;

[0061] FIG5 is a schematic diagram of an optional hardware structure of an electronic device according to an embodiment of the present invention. Modes for Carrying Out the Invention

[0062] Currently, the accuracy of current Wi-Fi-based life detection methods still needs to be improved.

[0063] To address the above technical issues, embodiments of the present invention provide a method for generating a life form detection model, comprising: acquiring channel state information of multiple received signals from a Wi-Fi receiving device according to a preset acquisition cycle, where each received signal includes multiple subcarriers; performing conjugate multiplication on the channel state information of any two of the multiple received signals acquired in each acquisition cycle to obtain multiple corresponding conjugate multiplication result matrices; extracting amplitude information and phase information of multiple subcarriers from the multiple conjugate multiplication result matrices; acquiring multiple corresponding life form detection training data based on the amplitude information and phase information of the multiple subcarriers to form a life form detection training dataset; and performing learning and training using the life form detection training data in the life form detection training dataset to obtain a corresponding life form detection model.

[0064] The embodiments of the present invention perform conjugate multiplication processing on the channel state information of any two of the multi-channel received signals of the Wi-Fi receiving device obtained in each acquisition cycle. This can eliminate the same phase error generated by the channel state information of different received signals. The amplitude information and phase information of multiple subcarriers are then extracted from the multiple conjugate multiplication result matrices. Based on the amplitude information and phase information of the multiple subcarriers, corresponding multiple pieces of life detection training data are obtained. This can eliminate blind spots in the change of amplitude information or phase information of motion at certain locations in the environment to be detected, which in turn helps to improve the accuracy of the life detection training data, thereby helping to improve the performance of the formed life detection model, and further helping to improve the accuracy of life detection.

[0065] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0066] FIG1 is a flow chart showing an embodiment of a method for generating a life form detection model provided by the technical solution of the present invention. Referring to FIG1 , a method for generating a life form detection model may include the following steps:

[0067] Step S110: Acquire channel state information of multiple received signals of a Wi-Fi receiving device according to a preset acquisition period, where each received signal includes multiple subcarriers;

[0068] Step S120: performing conjugate multiplication processing on the channel state information of any two of the multi-channel received signals obtained in each acquisition period to obtain corresponding multiple conjugate multiplication result matrices;

[0069] Step S130: extracting amplitude information and phase information of multiple subcarriers from multiple conjugate multiplication result matrices respectively;

[0070] Step S140: Based on the amplitude information and phase information of the multiple subcarriers, obtain corresponding multiple pieces of life body detection training data to form a life body detection training data set;

[0071] Step S150: using the life form detection training data in the life form detection training data set to perform learning and training to obtain a corresponding life form detection model.

[0072] Continuing with FIG. 1 , step S110 is executed to obtain channel state information of multiple received signals of a Wi-Fi receiving device according to a preset collection period, where each received signal includes multiple subcarriers.

[0073] Channel state information of multiple received signals of a Wi-Fi receiving device is obtained according to a preset collection period. Each received signal includes multiple subcarriers. This provides a basis for subsequently performing conjugate multiplication processing on the channel state information of any two of the multiple received signals obtained in each collection period to obtain corresponding multiple conjugate multiplication result matrices.

[0074] In some implementations, the Wi-Fi transmitting device uses one transmitting antenna to transmit Wi-Fi signals, and the Wi-Fi receiving device uses multiple receiving antennas to simultaneously receive the Wi-Fi signals transmitted by the Wi-Fi transmitting device.

[0075] In this embodiment, the Wi-Fi transmitting device uses one transmitting antenna to transmit Wi-Fi signals, and the Wi-Fi receiving device uses two receiving antennas to simultaneously receive the Wi-Fi signals transmitted by the Wi-Fi transmitting device.

[0076] The Wi-Fi signal is a Channel Frequency Response (CFR) data packet. Accordingly, in this embodiment, the Wi-Fi transmitting device uses one transmitting antenna to transmit the CFR data packet, and the Wi-Fi receiving device uses two receiving antennas to simultaneously receive the CFR data packet transmitted by the Wi-Fi transmitting device.

[0077] In this embodiment, each received signal includes multiple subcarriers. Accordingly, the channel state information of each received signal is the channel state information of multiple subcarriers of each receiving antenna of the Wi-Fi receiving device.

[0078] The channel state information of the multi-path received signals of a Wi-Fi receiving device reflects the amplitude and phase information of multiple subcarriers for each receiving antenna of the Wi-Fi receiving device. The location and direction of movement of a living being can cause changes in the amplitude and phase of multiple subcarriers for each receiving antenna of the Wi-Fi receiving device. Therefore, by acquiring the channel state information of the multi-path received signals of the Wi-Fi receiving device according to a preset collection period, it is possible to detect living beings.

[0079] The collection period of the channel state information of the multi-channel received signals of the Wi-Fi receiving device can be set by those skilled in the art according to the collection requirements of the channel state information of the multi-channel received signals of the Wi-Fi receiving device.

[0080] It is understandable that the collection period of the channel state information of the multi-channel received signals of the Wi-Fi receiving device should not be too long or too short. If the collection period of the channel state information of the multi-channel received signals of the Wi-Fi receiving device is too long, the real-time performance of the channel state information of the multi-channel received signals of the Wi-Fi receiving device in the acquired time dimension will be reduced, thereby reducing the real-time performance of subsequent data processing and increasing the subsequent computational complexity. If the collection period of the channel state information of the multi-channel received signals of the Wi-Fi receiving device is too short, the channel state information of the multi-channel received signals of the Wi-Fi receiving device in the complete time dimension cannot be obtained, which will correspondingly reduce the accuracy of the subsequently acquired data and affect the accuracy of the generated life detection model. To this end, in this embodiment, the collection period is 1 to 3 seconds in length.

[0081] Continuing with FIG. 1 , step S120 is executed to perform conjugate multiplication processing on the channel state information of any two of the multi-channel received signals acquired in each acquisition period to acquire a plurality of corresponding conjugate multiplication result matrices.

[0082] The channel state information of any two of the multi-channel received signals obtained in each acquisition period is conjugate multiplied to obtain corresponding multiple conjugate multiplication result matrices, which provide a basis for subsequently extracting the amplitude information and phase information of multiple subcarriers from the multiple conjugate multiplication result matrices.

[0083] Conjugate multiplication of the channel state information of any two of the multi-path received signals of the Wi-Fi receiving device obtained in each acquisition cycle can eliminate the same random phase error generated by the channel state information of multiple subcarriers of different receiving antennas, thereby improving the accuracy of the channel state information of the multiple subcarriers of the receiving antenna of the Wi-Fi receiving device. Subsequently, the amplitude information and phase information of the multiple subcarriers are extracted from the multiple conjugate multiplication result matrices, thereby improving the accuracy of the obtained amplitude information and phase information of the multiple subcarriers.

[0084] When a Wi-Fi transmitting device uses P transmitting antennas to transmit channel frequency response data packets, and a Wi-Fi receiving device uses Q receiving antennas to simultaneously receive the channel frequency response data packets transmitted by the Wi-Fi transmitting device, and the received signal of each receiving antenna includes S subcarriers, the channel frequency response matrix composed of L channel frequency response data packets transmitted within a preset acquisition period can be expressed as:

[0085] Where H represents the channel frequency response matrix, H k represents the kth channel frequency response data packet, where k is an integer greater than or equal to 1 and less than or equal to L.

[0086] Accordingly, each channel frequency response data packet simultaneously sent by each transmitting antenna of the Wi-Fi transmitting device to each receiving antenna of the Wi-Fi receiving device can be expressed as:

[0087] in, It represents the t-th channel frequency response data packet sent from the i-th transmitting antenna of the Wi-Fi transmitting device to the j-th receiving antenna of the Wi-Fi receiving device. represents channel frequency response data on the s-th subcarrier at the j-th receive antenna of the Wi-Fi receiver in the t-th channel frequency response packet sent from the ith transmit antenna of the Wi-Fi transmitter to the j-th receive antenna of the Wi-Fi receiver, where s is an integer greater than or equal to 1 and less than or equal to S.

[0088] Accordingly, the channel frequency response data packet sent simultaneously by the P transmitting antennas of the Wi-Fi transmitting device to the Q receiving antennas of the Wi-Fi receiving device can be expressed as:

[0089] Among them, H t The t-th channel frequency response data matrix represents the data sent by the P transmitting antennas of the Wi-Fi transmitting device to the Q receiving antennas of the Wi-Fi receiving device.

[0090] Correspondingly, the corresponding multiple conjugate multiplication result matrices obtained by performing conjugate multiplication processing on the channel state information of any two of the multi-channel received signals obtained in each acquisition period can be expressed as:

[0091] Among them, conj(.) represents the conjugate operation.

[0092] In this embodiment, the Wi-Fi transmitting device uses a single transmitting antenna to transmit Wi-Fi signals, and the Wi-Fi receiving device uses two receiving antennas to simultaneously receive the Wi-Fi signals transmitted by the Wi-Fi transmitting device. Accordingly, the conjugate multiplication result matrix obtained by performing conjugate multiplication on the channel state information of the two received signals obtained in each acquisition cycle can be expressed as:

[0093] Among them, H cm It represents a conjugate multiplication result matrix obtained by performing conjugate multiplication processing on the channel state information of the two received signals obtained in each acquisition period.

[0094] Continuing with FIG. 1 , step S130 is executed to extract amplitude information and phase information of multiple subcarriers from multiple conjugate multiplication result matrices.

[0095] The amplitude information and phase information of multiple subcarriers are extracted from multiple conjugate multiplication result matrices respectively, providing a basis for subsequently obtaining multiple corresponding life detection training data based on the amplitude information and phase information of multiple subcarriers to form a life detection training data set.

[0096] The steps of extracting amplitude information of multiple subcarriers from multiple conjugate multiplication result matrices respectively include: obtaining amplitude information correlation coefficient matrices of multiple subcarriers based on the conjugate multiplication result matrices respectively.

[0097] In this embodiment, the Wi-Fi transmitting device uses a single transmitting antenna to transmit Wi-Fi signals, and the Wi-Fi receiving device uses two receiving antennas to simultaneously receive the Wi-Fi signals transmitted by the Wi-Fi transmitting device. Accordingly, the step of extracting amplitude information of multiple subcarriers from multiple conjugate multiplication result matrices includes obtaining amplitude information correlation coefficient matrices of the multiple subcarriers based on the conjugate multiplication result matrices.

[0098] Specifically, the amplitude information correlation coefficient matrix of multiple subcarriers can be calculated using the following formula: am =corr(||H cm ||,||H cm T ||) (6)

[0099] Among them, R am Represents the correlation coefficient matrix of the amplitude information of multiple subcarriers, corr(.) represents the correlation coefficient operation, ||H cm || represents the conjugate multiplication result matrix H cm The amplitude operation performed, ||H cm T || represents the transposed matrix H of the conjugate multiplication result matrix cm T The magnitude operation to perform.

[0100] Correspondingly, the steps of extracting phase information of multiple subcarriers from multiple conjugate multiplication result matrices respectively include: obtaining a phase difference information correlation coefficient matrix and a phase difference information correlation matrix of multiple subcarriers based on the conjugate multiplication result matrices respectively.

[0101] Specifically, the following formula is used to calculate the phase difference information correlation coefficient matrix of multiple subcarriers: ph =corr(∠H cm ,∠H cm T ) (7)

[0102] Among them, R ph Represents the phase difference information correlation coefficient matrix of multiple subcarriers, ∠H cm Represents the conjugate multiplication result matrix H cm The phase operation performed, ∠H cm T Represents the conjugate multiplication result matrix H cm The transposed matrix H cm T The phase operation performed.

[0103] Continuing with FIG. 1 , step S140 is executed to obtain corresponding multiple pieces of life detection training data based on the amplitude information and phase information of the multiple subcarriers to form a life detection training data set.

[0104] Based on the amplitude information and phase information of multiple subcarriers, multiple corresponding life form detection training data are obtained to form a life form detection training data set, which provides a basis for subsequent learning and training using the life form detection training data in the life form detection training data set to obtain the corresponding life form detection model.

[0105] In this embodiment, the life body detection training data includes 15 features in the following six aspects:

[0106] (1) The respiratory rate value of a living being calculated based on the phase difference information correlation matrix of multiple subcarriers;

[0107] (2) The maximum eigenvalue, the second largest eigenvalue and the entropy of the eigenvalues ​​after normalization of the amplitude information correlation coefficient matrix of multiple subcarriers.

[0108] (3) The maximum eigenvalue and the second largest eigenvalue of the normalized correlation coefficient matrix of the phase difference information of multiple subcarriers;

[0109] (4) performing principal component analysis on the amplitude information of multiple subcarriers to obtain the energy value of the first principal component, the energy value of the second principal component, and the energy value of the third principal component, the ratio between the variance of the first principal component and the difference value of the eigenvector corresponding to the variance of the first principal component, the ratio between the variance of the second principal component and the difference value of the eigenvector corresponding to the variance of the second principal component, and the ratio between the difference value of the eigenvector corresponding to the variance of the third principal component, and the kurtosis value of the second principal component;

[0110] (5) the standard deviation of the maximum eigenvalue of the normalized matrix of the amplitude information correlation coefficients of multiple subcarriers corresponding to the current acquisition period and the previous (N-1) acquisition periods;

[0111] (6) The standard deviation of the second largest eigenvalue of the normalized phase difference information correlation coefficient matrix of multiple subcarriers corresponding to the current acquisition period and the previous (N-1) acquisition periods.

[0112] In a specific implementation, living beings with different degrees of movement may cause different changes between different subcarriers of each receiving antenna of a Wi-Fi receiving device, thereby affecting the maximum eigenvalue, second largest eigenvalue, and eigenvalue entropy of the amplitude information correlation coefficient matrix of multiple subcarriers of each receiving antenna of the Wi-Fi receiving device. Furthermore, the maximum eigenvalue and second largest eigenvalue of the phase difference information correlation coefficient matrix of multiple subcarriers of each receiving antenna of the Wi-Fi receiving device are affected, as well as the standard deviation of the maximum eigenvalue of the normalized amplitude information correlation coefficient matrix of multiple subcarriers corresponding to the current acquisition period and the previous (N-1) acquisition periods, and the standard deviation of the second largest eigenvalue of the normalized amplitude information correlation coefficient matrix of multiple subcarriers corresponding to the current acquisition period and the previous (N-1) acquisition periods.

[0113] To this end, in this embodiment, the maximum eigenvalue, the second largest eigenvalue and the entropy of the eigenvalues ​​of the normalized amplitude information correlation coefficient matrix of multiple subcarriers, the maximum eigenvalue and the second largest eigenvalue of the normalized phase difference information correlation coefficient matrix of multiple subcarriers, and the standard deviation of the maximum eigenvalue of the normalized amplitude information correlation coefficient matrix of multiple subcarriers corresponding to the current acquisition period and the previous (N-1) acquisition periods, and the standard deviation of the second largest eigenvalue of the normalized amplitude information correlation coefficient matrix of multiple subcarriers corresponding to the current acquisition period and the previous (N-1) acquisition periods are used to represent the dynamic and static characteristics of living organisms.

[0114] In this embodiment, the maximum eigenvalue, the second largest eigenvalue, and the entropy of the eigenvalues ​​after the normalization of the amplitude information correlation coefficient matrix of multiple subcarriers can be expressed as: amm =max(eigen(R am ) / L) (8)

[0115] e ams =smax(eigen(R am ) / L) (9) E entropy =-∑P i log(P i ) (10)

[0116] Among them, e amm Represents the maximum eigenvalue of the normalized correlation coefficient matrix of the amplitude information of multiple subcarriers, e ams Indicates the second largest eigenvalue after normalization of the amplitude information correlation coefficient matrix of multiple subcarriers, eigen(.) indicates the operation of obtaining the eigenvalue, max(.) indicates the operation of taking the maximum value, smax(.) indicates the operation of taking the second largest value, E entropy The entropy of the eigenvalues ​​after normalization of the correlation coefficient matrix of the amplitude information of multiple subcarriers, P i It represents the probability of the i-th eigenvalue of the normalized correlation coefficient matrix of the amplitude information of multiple subcarriers, and log(.) represents the logarithm operation.

[0117] In this embodiment, the maximum eigenvalue and the second largest eigenvalue of the normalized phase difference information correlation coefficient matrix of multiple subcarriers can be expressed as: phm =max(eigen(R ph ) / L) (11) e phs=smax(eigen(R ph ) / L) (12)

[0118] Among them, e phm Represents the maximum eigenvalue of the normalized correlation coefficient matrix of the phase difference information of multiple subcarriers, e phs Represents the second largest eigenvalue of the normalized correlation coefficient matrix of the phase difference information of multiple subcarriers.

[0119] According to actual needs, the value of N can be obtained by those skilled in the art based on the training requirements of the life body detection model. As an example, the value range of N is 5 to 10 times.

[0120] In a specific implementation, different degrees of movement and stillness of living beings located around the detection environment, or different degrees of movement and stillness of living beings passing through walls, will cause changes in the first principal component, the second principal component, and the third principal component obtained by performing principal component analysis on the amplitude information of multiple subcarriers.

[0121] Accordingly, principal component analysis (PCA) is performed on the amplitude information of multiple subcarriers to obtain the energy value of the first principal component, the energy value of the second principal component, the energy value of the third principal component, the ratio between the variance of the first principal component and the differential value of the eigenvector corresponding to the variance of the first principal component, the ratio between the variance of the second principal component and the differential value of the eigenvector corresponding to the variance of the second principal component, the ratio between the differential value of the eigenvector corresponding to the variance of the third principal component, and the kurtosis value of the second principal component, which are used as representations of the dynamic and static characteristics of living organisms that penetrate walls.

[0122] At the same time, performing principal component analysis on the amplitude information of multiple subcarriers can achieve dimensionality reduction of the amplitude information of multiple subcarriers and filter out low-frequency noise to a certain extent.

[0123] In this embodiment, the energy value of the first principal component obtained by performing principal component analysis on the amplitude information of multiple subcarriers can be calculated using the following formula:

[0124] and: c i =He i (15) E=eigen(C)=(e0 … e S ) (16)

[0125] Among them, g irepresents the energy value of the i-th principal component obtained by performing principal component analysis on the amplitude information of multiple subcarriers, FFT(k) represents the value of the k-th frequency component after Fourier transform of the i-th principal component, c i represents the i-th principal component obtained by performing principal component analysis on the amplitude information of multiple subcarriers, Represents the conjugate multiplication result matrix H cm Amplitude matrix with DC component removed.

[0126] In this embodiment, the ratio between the variance of the i-th principal component and the difference value of the eigenvector corresponding to the variance of the i-th principal component is calculated using the following formula:

[0127] and:

[0128] in, It represents the ratio between the variance of the ith principal component and the difference value of the eigenvector corresponding to the variance of the ith principal component, var(c i ) represents the variance operation performed on the i-th principal component, Represents the difference value of the eigenvector corresponding to the variance of the i-th principal component.

[0129] In this embodiment, the kurtosis value of the second principal component is calculated using the following formula:

[0130] Where z represents the kurtosis value of the second principal component, c2 represents the second principal component, represents the mean of the second principal component.

[0131] It should be pointed out that when there is a stationary human body in the detection environment, the dynamic and static characteristics in the detection environment are very similar to the dynamic and static characteristics of penetrating walls. At this time, the respiratory rate value of the living body calculated based on the phase difference information correlation matrix of multiple subcarriers can be used to distinguish between an environment with a stationary living body and an environment with no people.

[0132] In this embodiment, a Multiple Signal Classification (MUSIC) algorithm is used to calculate the respiratory rate value of a living body based on a phase difference information correlation matrix of multiple subcarriers.

[0133] In this embodiment, the following formula is used to calculate the phase difference information correlation matrix of multiple subcarriers:

[0134] Among them, R represents the phase difference information correlation matrix of multiple subcarriers, Represents the conjugate multiplication result matrix H cmThe phase matrix with DC component removed, Represents the conjugate multiplication result matrix H cm Phase matrix to remove DC component The transposed matrix of .

[0135] In other embodiments, other super-resolution algorithms can be used to calculate the respiratory rate of a living organism based on the phase difference information correlation matrix of multiple subcarriers. These super-resolution algorithms include the root-MUSIC algorithm, the minimum variance distortionless response (MVDR) algorithm, and the rotationally invariant signal parameter estimation technique (ESPRIT).

[0136] When calculating a living organism's respiratory rate, the sliding step size is the acquisition period. In other words, a respiratory rate value is calculated once for each acquisition period. The length of the sliding time window used to calculate the respiratory rate value is related to the living organism's respiratory rate. Specifically, the length of the sliding time window should be greater than or equal to the length of a single breath, and should be an integer multiple of the length of a single breath.

[0137] In this embodiment, to meet the needs of both Wi-Fi device communication and life detection, the life detection model is used for human detection. The human respiratory rate is generally 0.1Hz to 0.6Hz. Therefore, in this embodiment, the time length of the sliding time window is 1.7s to 10s.

[0138] In other embodiments, the life form detection model can also be used for human body detection of other animals with similar respiratory rates to humans, including cats, dogs, rabbits, pigs, horses, cows, and sheep.

[0139] Please continue to refer to FIG. 1 and execute step S150 to perform learning and training using the life form detection training data in the life form detection training data set to obtain a corresponding life form detection model.

[0140] The life form detection training data in the life form detection training data set is used for learning and training to obtain a corresponding life form detection model so that the life form detection model can be used for life form detection.

[0141] In this embodiment, human body detection training data in the human body detection training data set is used for learning and training to obtain a corresponding human body detection model.

[0142] In some embodiments, the life form detection model includes a support vector machine (SVM) classifier. Accordingly, a support vector machine algorithm is used to train the life form detection training data in the life form detection training data set to obtain a corresponding life form detection model.

[0143] In other embodiments, the life detection model can also be other classifiers, such as Adaptive Boosting (Adaboost) classifier, Bayesian classifier, Back Propagation (BP) neural network classifier, etc., or can also be other feature classification models, which are not limited here.

[0144] Correspondingly, an embodiment of the present invention further provides a module for generating a life detection model.

[0145] FIG2 is a schematic diagram illustrating an embodiment of a module for generating a life form detection model according to the technical solution of the present invention. Referring to FIG2 , a life form detection model generation module 200 includes: a first acquisition submodule 201 configured to acquire channel state information of multiple received signals from a Wi-Fi receiving device according to a preset acquisition cycle, each received signal including multiple subcarriers; a conjugate multiplication submodule 202 configured to conjugate multiply the channel state information of any two of the multiple received signals acquired during each acquisition cycle to acquire multiple corresponding conjugate multiplication result matrices; an information extraction submodule 203 configured to extract amplitude information and phase information of multiple subcarriers from the multiple conjugate multiplication result matrices; a data acquisition submodule 204 configured to acquire multiple corresponding life form detection training data based on the amplitude information and phase information of the multiple subcarriers to form a life form detection training dataset; and a model training submodule 205 configured to perform training using the life form detection training data in the life form detection training dataset to acquire a corresponding life form detection model.

[0146] The module for generating a life form detection model in the embodiments of the present invention can be used to execute the aforementioned method for generating a life form detection model, or other functional modules can be used to execute the aforementioned method for generating a life form detection model. For details about the method for generating a life form detection model, please refer to the detailed description in the previous section and will not be repeated here.

[0147] Accordingly, an embodiment of the present invention further provides a method for detecting a living being.

[0148] FIG3 is a flow chart showing an embodiment of a method for detecting life forms according to the technical solution of the present invention. Referring to FIG3 , a method for detecting life forms may include the following steps:

[0149] Step S310: Acquire channel state information of multiple received signals of a Wi-Fi receiving device in a current detection period;

[0150] Step S320: input the acquired channel state information of the multi-channel received signals of the Wi-Fi receiving device in the current detection period into the life body detection model generated by the life body detection model generation method to obtain the corresponding life body detection result.

[0151] In some embodiments, the acquired channel state information of the multi-path received signals of the Wi-Fi receiving device in the current detection period is input into a living being detection model generated by the above-described method for generating a living being detection model, so that the living being detection model can extract the 15 features in the six aspects mentioned in step S140 and determine, based on the extracted features, whether a living being exists in the environment to be detected.

[0152] In this embodiment, the life form detection model is a human body detection model. Accordingly, the acquired channel state information of the multi-path received signals of the Wi-Fi receiving device during the current detection period is input into the human body detection model, enabling the human body detection model to extract the 15 features from the six aspects mentioned in step S140 and, based on the extracted features, determine whether a human body is present in the environment to be detected.

[0153] In other embodiments, the life form detection model can also be used to detect other animals with a respiratory rate similar to that of humans.

[0154] In this embodiment, the method for detecting life forms further includes:

[0155] Step S330: using the life body detection model to obtain the entropy of the normalized eigenvalues ​​of the amplitude information correlation coefficient matrix of multiple subcarriers in the current detection period and the entropy of the normalized eigenvalues ​​of the amplitude information correlation coefficient matrix of multiple subcarriers in the previous (M-1) detection periods;

[0156] Step S340: When the life detection model is used to determine that the entropy of the eigenvalues ​​of the normalized amplitude information correlation coefficient matrix of multiple subcarriers in the current detection period and the entropy of the eigenvalues ​​of the normalized amplitude information correlation coefficient matrix of multiple subcarriers in the previous (M-1) detection periods are both greater than a preset threshold, the detection result indicating that there is no life in the environment to be detected is output.

[0157] When the entropy of the eigenvalues ​​of the normalized amplitude information correlation coefficient matrix of multiple subcarriers in the current detection period and the entropy of the eigenvalues ​​of the normalized amplitude information correlation coefficient matrix of multiple subcarriers in the previous (M-1) detection periods are determined to be greater than a preset threshold value, the detection result of no living objects in the environment to be detected is output. This can avoid the influence of neighboring living objects on the detection of living objects in the environment to be detected, prevent false alarms, and correspondingly help to further improve the accuracy of living object detection.

[0158] The value of M can be set according to the needs of life body detection. As an example, the value range of M is 5 to 10 times.

[0159] Correspondingly, an embodiment of the present invention further provides a life detection module.

[0160] FIG4 illustrates a schematic diagram of the structure of an embodiment of a life detection module provided by the technical solution of the present invention. Referring to FIG4 , a life detection module 400 includes: an acquisition submodule 401 configured to acquire channel state information of multiple received signals from a Wi-Fi receiving device during the current detection period; and a detection submodule 402 configured to input the acquired channel state information of multiple received signals from the Wi-Fi receiving device during the current detection period into a life detection model generated by a method for generating a life detection model, such as described above, to obtain corresponding life detection results.

[0161] The life detecting module in the embodiment of the present invention can be used to execute the aforementioned life detecting method, or other functional modules can be used to execute the aforementioned life detecting method.

[0162] Accordingly, an embodiment of the present invention further provides a chip on which is integrated a module for generating a life form detection model or a life form detection module as described in an embodiment of the present invention. The generation module for generating a life form detection model or the life form detection module is described in detail in the preceding section and will not be further elaborated here.

[0163] Accordingly, an embodiment of the present invention further provides a storage medium storing one or more computer instructions for implementing the method for generating a life form detection model or the life form detection method described in an embodiment of the present invention. The method for generating a life form detection model or the life form detection method are described in detail in the preceding sections and are not further elaborated here.

[0164] Accordingly, an embodiment of the present invention further provides an electronic device comprising at least one memory and at least one processor, wherein the memory stores one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method for generating a life form detection model or the life form detection method as described in an embodiment of the present invention. The method for generating a life form detection model or the life form detection method is described in detail in the preceding section and will not be repeated here.

[0165] An optional hardware structure of the electronic device provided by an embodiment of the present invention may be as shown in FIG5 , including: at least one processor 01 , at least one communication interface 02 , at least one memory 03 and at least one communication bus 04 .

[0166] In the embodiment of the present invention, the number of the processor 01 , the communication interface 02 , the memory 03 , and the communication bus 04 is at least one, and the processor 01 , the communication interface 02 , and the memory 03 communicate with each other via the communication bus 04 .

[0167] The communication interface 02 may be an interface of a communication module for network communication, such as an interface of a GSM module.

[0168] The processor 01 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0169] The memory 03 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), as an example, at least one disk memory.

[0170] The memory 03 stores one or more computer instructions, and the one or more computer instructions are executed by the processor 01 to implement the method for generating a life body detection model or the method for detecting a life body according to the embodiment of the present invention.

[0171] It should be noted that the above-mentioned terminal device may also include other devices (not shown) that may not be necessary for understanding the contents disclosed in the embodiments of the present invention; given that these other devices may not be necessary for understanding the contents disclosed in the embodiments of the present invention, the embodiments of the present invention will not introduce them one by one.

[0172] An embodiment of the present invention further provides a storage medium storing one or more computer instructions, wherein the one or more computer instructions are used to implement the method for generating a life form detection model or the life form detection method described in the embodiment of the present invention.

[0173] The embodiments of the present invention described above are combinations of elements and features of the present invention. Unless otherwise mentioned, the elements or features may be considered as optional. Each element or feature may be put into practice without being combined with other elements or features. In addition, the embodiments of the present invention may be constructed by combining some elements and / or features. The order of operations described in the embodiments of the present invention may be rearranged. Some configurations of any one embodiment may be included in another embodiment and may be replaced by the corresponding configuration of another embodiment. It is obvious to those skilled in the art that claims that do not have a clear reference relationship to each other in the appended claims may be combined into embodiments of the present invention, or may be included as new claims in amendments after submitting this application.

[0174] The embodiments of the present invention may be implemented by various means as an example of hardware, firmware, software or a combination thereof. In a hardware configuration, the method according to the exemplary embodiment of the present invention may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, etc.

[0175] In a firmware or software configuration, the embodiments of the present invention may be implemented in the form of modules, procedures, functions, and the like. Software codes may be stored in a memory unit and executed by a processor. The memory unit may be located inside or outside the processor and may send and receive data to and from the processor via various known means.

[0176] The above description of the disclosed embodiments will enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

[0177] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention should be based on the scope defined by the claims.

Claims

1. A method for generating a life detection model, characterized in that: include: Acquire channel state information of multiple received signals of a Wi-Fi receiving device according to a preset collection period, where each received signal includes multiple subcarriers; Conjugate multiplication is performed on the channel state information of any two of the multi-channel received signals obtained in each acquisition period to obtain a corresponding plurality of conjugate multiplication result matrices; Extracting amplitude information and phase information of the multiple subcarriers from the multiple conjugate multiplication result matrices respectively; Based on the amplitude information and phase information of the multiple subcarriers, obtaining corresponding multiple pieces of life detection training data to form a life detection training data set; The life form detection training data in the life form detection training data set is used for learning and training to obtain a corresponding life form detection model.

2. The method for generating a life form detection model as claimed in claim 1, characterized in that: The life body detection training data includes: A breathing frequency value of a living being calculated based on a phase difference information correlation matrix of the plurality of subcarriers; The maximum eigenvalue, the second largest eigenvalue and the entropy of the eigenvalues ​​after the normalization of the amplitude information correlation coefficient matrix of the multiple subcarriers; performing principal component analysis on the amplitude information of the multiple subcarriers to obtain an energy value of the first principal component, an energy value of the second principal component, and an energy value of the third principal component, a ratio between the variance of the first principal component and the difference value of the eigenvector corresponding to the variance of the first principal component, a ratio between the variance of the second principal component and the difference value of the eigenvector corresponding to the variance of the second principal component, and a ratio between the difference values ​​of the eigenvector corresponding to the variance of the third principal component, and a kurtosis value of the second principal component; The maximum characteristic of the normalized correlation coefficient matrix of the phase difference information of the multiple subcarriers Eigenvalue and the next largest eigenvalue; The standard deviation of the maximum eigenvalue of the normalized correlation coefficient matrix of the amplitude information of multiple subcarriers corresponding to the current acquisition period and the previous (N-1) acquisition periods; The standard deviation of the next largest eigenvalue of the normalized phase difference information correlation coefficient matrix of multiple subcarriers corresponding to the current acquisition period and the previous (N-1) acquisition periods.

3. The method for generating a life form detection model as claimed in claim 2, characterized in that: The value of N ranges from 5 to 10 times.

4. The method for generating a life form detection model according to claim 1, characterized in that: The duration of the acquisition cycle is 1 s to 3 s.

5. The method for generating a life form detection model according to claim 1, characterized in that: The life body detection model includes a support vector machine classifier.

6. The method for generating a life detection model according to any one of claims 1 to 5, characterized in that: The living body includes at least one of a human body and an animal body having a breathing frequency similar to that of a human body.

7. A generation module of a life detection model, characterized in that: include: A first acquisition submodule is adapted to acquire channel state information of multiple received signals of a Wi-Fi receiving device according to a preset acquisition period, where each received signal includes multiple subcarriers; The conjugate multiplication submodule is adapted to perform conjugate multiplication processing on the channel state information of any two of the multi-channel received signals acquired in each acquisition period to obtain a corresponding plurality of conjugate multiplication result matrices; An information extraction submodule, adapted to extract amplitude information and phase information of the plurality of subcarriers from the plurality of conjugate multiplication result matrices respectively; A data acquisition submodule, adapted to acquire a corresponding plurality of life detection training data based on the amplitude information and phase information of the plurality of subcarriers to form a life detection training data set; The model training submodule is suitable for using the life form detection training data in the life form detection training data set to perform learning and training to obtain a corresponding life form detection model.

8. The generation module of the life body detection model according to claim 7, characterized in that: The life detection training data acquired by the data acquisition submodule includes: A breathing frequency value of a living being calculated based on a phase difference information correlation matrix of the plurality of subcarriers; The maximum eigenvalue, the second largest eigenvalue and the entropy of the eigenvalues ​​after the normalization of the amplitude information correlation coefficient matrix of multiple subcarriers; an energy value of the first principal component, an energy value of the second principal component, and an energy value of the third principal component, a ratio between the variance of the first principal component and the difference value of the eigenvector corresponding to the variance of the first principal component, a ratio between the variance of the second principal component and the difference value of the eigenvector corresponding to the variance of the second principal component, and a ratio between the difference values ​​of the eigenvector corresponding to the variance of the third principal component, and a kurtosis value of the second principal component, obtained after performing principal component analysis on the amplitude information of the multiple subcarriers; The maximum eigenvalue and the second largest eigenvalue of the normalized phase difference information correlation coefficient matrix of the multiple subcarriers; The standard deviation of the maximum eigenvalue of the normalized correlation coefficient matrix of the amplitude information of multiple subcarriers corresponding to the current acquisition period and the previous (N-1) acquisition periods; The standard deviation of the next largest eigenvalue of the normalized phase difference information correlation coefficient matrix of multiple subcarriers corresponding to the current acquisition period and the previous (N-1) acquisition periods.

9. The generation module of the life body detection model according to claim 7, characterized in that: The value of N ranges from 5 to 10 times.

10. The generation module of the life body detection model according to claim 6, characterized in that: The duration of the acquisition cycle is 1 s to 3 s.

11. The generation module of the life body detection model according to claim 6, characterized in that: The life body detection model includes a support vector machine classifier.

12. The generation module of the life body detection model according to any one of claims 7 to 11, characterized in that: The living body includes at least one of a human body and an animal body having a breathing frequency similar to that of a human body.

13. A method for detecting a living being, characterized in that: include: Obtain channel status information of multiple received signals of a Wi-Fi receiving device in the current detection period; The obtained channel state information of the multi-path receiving signal of the Wi-Fi receiving device in the current detection period is input into the life body detection model generated by the life body detection model generation method as described in any one of claims 1 to 6 to obtain the corresponding life body detection result.

14. The method for detecting life forms according to claim 13, wherein: Each of the received signals includes multiple subcarriers; The life body detection method also includes: The life body detection model is used to obtain the entropy of the normalized eigenvalues ​​of the amplitude information correlation coefficient matrix of multiple subcarriers in the current detection period and the entropy of the normalized eigenvalues ​​of the amplitude information correlation coefficient matrix of multiple subcarriers in the previous (M-1) detection periods; When the life form detection model is used to determine that the entropy of the normalized eigenvalues ​​of the amplitude information correlation coefficient matrix of multiple subcarriers in the current detection period and the entropy of the normalized eigenvalues ​​of the amplitude information correlation coefficient matrix of multiple subcarriers in the previous (M-1) detection periods are both greater than a preset threshold, a detection result indicating that there is no life form in the environment to be detected is output.

15. The method for detecting life forms according to claim 14, wherein: The value range of M is 5 to 10 times.

16. A life detection module, characterized in that: include: An acquisition submodule, adapted to acquire channel state information of multi-channel receiving signals of a Wi-Fi receiving device in a current detection period; The detection submodule is adapted to input the channel state information of the multi-path receiving signal of the Wi-Fi receiving device in the current detection period into the life cycle as claimed in any one of claims 1 to 6. A life body detection model is generated by a life body detection model generation method, and a corresponding life body detection result is obtained.

17. The life detection module according to claim 16, characterized in that: Each of the received signals includes multiple subcarriers; The detection submodule is further adapted to use the life form detection model to obtain the entropy of the eigenvalues ​​of the normalized amplitude information correlation coefficient matrix of multiple subcarriers in the current detection period and the entropy of the eigenvalues ​​of the normalized amplitude information correlation coefficient matrix of multiple subcarriers in the previous (M-1) detection period; and when the life form detection model is used to determine that the entropy of the eigenvalues ​​of the normalized amplitude information correlation coefficient matrix of multiple subcarriers in the current detection period and the entropy of the eigenvalues ​​of the normalized amplitude information correlation coefficient matrix of multiple subcarriers in the previous (M-1) detection period are both greater than a preset threshold, output a detection result that there is no life form in the environment to be detected.

18. The life detection module according to claim 17, characterized in that: The value range of M is 5 to 10 times.

19. A chip, characterized in that: The chip is integrated with a generation module of a life detection model as described in any one of claims 7 to 12 or a life detection module as described in any one of claims 16 to 18.

20. An electronic device, characterized in that: It includes at least one memory and at least one processor, the memory stores one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method for generating a life detection model as described in any one of claims 1 to 6 or the life detection method as described in any one of claims 13 to 15.

21. A storage medium, characterized in that: The storage medium stores one or more computer instructions, and the one or more computer instructions are used to implement the method for generating a life detection model as described in any one of claims 1 to 6 or the life detection method as described in any one of claims 13 to 15.

Images