Joint monitoring method and device for multiple physiological parameters

Abstract

The invention discloses a combined monitoring method and device for multiple physiological parameters. The method comprises the steps that a physiological parameter signal set of a user is acquired; the physiological parameter signal set comprises a heart rate signal sequence, a pulse signal sequence, an oxyhemoglobin saturation signal sequence, an electroencephalogram signal sequence and a blood pressure signal sequence; preprocessing the physiological parameter signal set to obtain a preprocessed signal set; and performing joint monitoring processing on the preprocessed signal set to obtain joint monitoring result information. According to the invention, through fusion processing of multiple types of physiological signals of the user, rapid and accurate extraction of user features is realized.

Description

Technical Field

[0001] The present invention relates to the fields of communication and artificial intelligence, and in particular to a method and device for jointly monitoring multiple physiological parameters. Background Art

[0002] When treating users, especially emergency patients, it is often necessary to keep track of their vital signs at all times to prevent their condition from worsening. Existing vital sign detectors often only detect and process each type of physiological signal separately. However, for critically ill patients, their physiological parameters often show variable and time-varying characteristics. It is difficult to quickly and accurately monitor the user's vital signs based on only one type of physiological parameter.

[0003] How to fuse and process multiple types of user physiological signals and extract user features quickly and accurately is a problem that needs to be solved urgently. Summary of the invention

[0004] The present invention mainly solves the problem of how to fuse multiple types of physiological signals of a user and extract the physiological characteristics of the user's body quickly and accurately. The present invention discloses a joint monitoring method and device for multiple physiological parameters.

[0005] In a first aspect of an embodiment of the present invention, a method for joint monitoring of multiple physiological parameters is disclosed, comprising:

[0006] S1, collecting and obtaining a physiological parameter signal set of a user; the physiological parameter signal set includes a heart rate signal sequence, a pulse signal sequence, a blood oxygen saturation signal sequence, an electroencephalogram signal sequence, and a blood pressure signal sequence;

[0007] S2, preprocessing the physiological parameter signal set to obtain a preprocessed signal set;

[0008] S3, performing joint monitoring processing on the pre-processed signal set to obtain joint monitoring result information.

[0009] The preprocessing of the physiological parameter signal set to obtain a preprocessed signal set includes:

[0010] S21, performing abnormality detection processing on the physiological parameter signal set to obtain a first signal set;

[0011] S22, normalizing the first signal set to obtain a second signal set;

[0012] S23, performing boundary check processing on the second signal set to obtain a time domain signal set;

[0013] S24, performing transformation feature extraction processing on the time domain signal set to obtain a frequency domain signal set;

[0014] S25, performing fusion processing on the time domain signal set and the frequency domain signal set to obtain a preprocessed signal set.

[0015] The performing boundary check processing on the second signal set to obtain a time domain signal set includes:

[0016] S231, for each signal attribute of the second signal set, taking the signal acquisition information of the signal as an independent variable and the signal value of the signal as a dependent variable, performing cluster analysis processing to obtain clustering result information of the signal attribute; the clustering result information includes the clustering category to which all signals of the signal attribute belong;

[0017] S232, determining the number of signals included in each cluster category; setting a signal quantity threshold; deleting the signals included in the cluster category whose number of signals is less than the signal quantity threshold from the second signal set;

[0018] S233, execute S231 and S232 for all signals of the second signal set to obtain a time domain signal set.

[0019] The step of performing transformation feature extraction processing on the time domain signal set to obtain a frequency domain signal set includes:

[0020] S241, performing bandpass filtering on each signal in the time domain signal set according to a predefined frequency band to obtain a corresponding frequency signal;

[0021] S242, performing power spectrum calculation on the frequency signal of each signal to obtain a power spectrum characteristic signal;

[0022] S243, fusing all power spectrum feature signals to obtain a frequency domain signal set.

[0023] The performing joint monitoring processing on the pre-processed signal set to obtain joint monitoring result information includes:

[0024] S31, using a time domain monitoring model, performing joint monitoring processing on the time domain signal set to obtain a first monitoring result value;

[0025] S32, using a time-frequency joint monitoring model, performing joint monitoring processing on the preprocessed signal set to obtain a second monitoring result value;

[0026] S33, performing weighted fusion processing on the first monitoring result value and the second monitoring result value to obtain joint monitoring result information.

[0027] The using the time domain monitoring model to perform joint monitoring processing on the time domain signal set to obtain a first monitoring result value includes:

[0028] S311, obtaining a standard signal set; the standard signal set includes a heart rate signal standard sequence, a pulse signal standard sequence, a blood oxygen saturation signal standard sequence, an electroencephalogram signal standard sequence, and a blood pressure signal standard sequence;

[0029] S312, using the standard signal set and the time domain signal set, respectively construct a standard matrix and a time domain matrix; the row vector of the standard matrix is ​​a standard sequence of heart rate signals, a standard sequence of pulse signals, a standard sequence of blood oxygen saturation signals, a standard sequence of electroencephalogram signals, and a standard sequence of blood pressure signals; the row vector of the time domain matrix is ​​a sequence of heart rate signals, a sequence of pulse signals, a sequence of blood oxygen saturation signals, a sequence of electroencephalogram signals, and a sequence of blood pressure signals;

[0030] S313, performing subtraction processing on the standard matrix and the time domain matrix to obtain a difference matrix;

[0031] S314, performing cross-correlation operation processing on all vectors of the difference matrix to obtain a cross-correlation matrix; the element of the i-th row and j-th column of the cross-correlation matrix is ​​the cross-correlation value between the i-th row vector and the j-th row vector of the difference matrix;

[0032] S315, performing first eigenvector extraction processing on the cross-correlation matrix to obtain a first eigenvector;

[0033] The expression of the first feature vector extraction process is:

[0034]

[0035] Among them, m and n are the row and column dimensions of the cross-correlation matrix, z ij represents the element in the i-th row and j-th column of the cross-correlation matrix, represents the jth element of the first eigenvector, z + represents the first eigenvector;

[0036] S316, performing a second eigenvector extraction process on the cross-correlation matrix to obtain a second eigenvector;

[0037] The expression of the second feature vector extraction process is:

[0038]

[0039] in, represents the jth element of the second eigenvector, z - represents the second eigenvector;

[0040] S317, performing monitoring and evaluation processing on the first eigenvector, the second eigenvector and the mutual correlation matrix to obtain a first monitoring result value;

[0041] The expression of the monitoring and evaluation process is:

[0042]

[0043] In the formula, ω j is the preset jth monitoring weight, s is the first monitoring result value, and pi is the pi constant.

[0044] The using the time-frequency joint monitoring model to perform joint monitoring processing on the preprocessed signal set to obtain a second monitoring result value includes:

[0045] S321, representing the time domain signal set and the frequency domain signal set as a time domain matrix and a frequency domain matrix respectively; the row vector of the time domain matrix is ​​a heart rate signal sequence, a pulse signal sequence, a blood oxygen saturation signal sequence, an electroencephalogram signal sequence and a blood pressure signal sequence; the row vector of the frequency domain matrix is ​​a power spectrum characteristic signal of the heart rate signal sequence, a power spectrum characteristic signal of the pulse signal sequence, a power spectrum characteristic signal of the blood oxygen saturation signal sequence, a power spectrum characteristic signal of the electroencephalogram signal sequence and a power spectrum characteristic signal of the blood pressure signal sequence;

[0046] S322, performing cross-correlation calculation processing on the time domain matrix and the frequency domain matrix to obtain a time-frequency cross-correlation matrix; the element of the i-th row and j-th column of the time-frequency cross-correlation matrix is ​​the cross-correlation value between the i-th row vector of the time domain matrix and the j-th row vector of the frequency domain matrix;

[0047] S323, performing relationship calculation on the time-frequency mutual correlation matrix and the mutual correlation matrix to obtain a relationship vector;

[0048] The relationship calculation is expressed as follows:

[0049]

[0050] Among them, A1 ij is the element in the i-th row and j-th column of the cross-correlation matrix A1, A2 ij is the element of the i-th row and j-th column of the time-frequency cross-correlation matrix A2, p i is the i-th element of the relationship vector, M2 is the column dimension of the cross-correlation matrix A1;

[0051] S324, performing monitoring calculation processing on the relationship vector to obtain a second monitoring result value;

[0052] The monitoring calculation process, its calculation expression is:

[0053]

[0054] in, For p i , M1 is the row dimension of the cross-correlation matrix A1, and R is the second monitoring result value.

[0055] In a second aspect of an embodiment of the present invention, a device for joint monitoring of multiple physiological parameters is disclosed, the device comprising:

[0056] A memory storing executable program code;

[0057] a processor coupled to the memory;

[0058] The processor calls the executable program code stored in the memory to execute the method for jointly monitoring multiple physiological parameters.

[0059] According to a third aspect of an embodiment of the present invention, a computer storable medium is disclosed, wherein the computer storable medium stores computer instructions, and when the computer instructions are called by a computer, they are used to execute the method for jointly monitoring multiple physiological parameters.

[0060] According to a fourth aspect of the embodiments of the present invention, an information data processing terminal is disclosed, wherein the information data processing terminal is used to implement the method for jointly monitoring multiple physiological parameters.

[0061] The beneficial effects of the present invention are:

[0062] The present invention utilizes multimodal user physiological data and performs joint monitoring on multimodal data sets, thereby improving the accuracy and real-time performance of user physiological status monitoring, thereby enabling monitoring of user vital sign signals.

[0063] After obtaining a multimodal user physiological data set, the present invention performs boundary check processing on the data, thereby effectively suppressing data irrelevant to the user's physiological state and ensuring the purity of the data of the user's joint monitoring.

[0064] In the process of jointly monitoring multimodal user physiological data sets, the present invention effectively realizes the fusion of multi-domain and multi-dimensional information by jointly monitoring the data in the time domain and the time-frequency domain, thereby improving the accuracy of monitoring.

[0065] In the joint monitoring of time domain and time-frequency domain data, the present invention proposes a monitoring evaluation processing algorithm and a relationship calculation algorithm, obtains a single discriminant through rapid calculation, and discriminates the single discriminant, which effectively reduces the amount of calculation and improves the real-time nature of monitoring while ensuring the monitoring accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 It is a flow chart for implementing the method of the present invention. DETAILED DESCRIPTION

[0067] In order to better understand the content of the present invention, an embodiment is given here.

[0068] Figure 1 It is a flow chart for implementing the method of the present invention.

[0069] In order to solve the problem of how to fuse and process multiple types of physiological signals of a user and extract user characteristics quickly and accurately, the present invention discloses a joint monitoring method and device for multiple physiological parameters.

[0070] In a first aspect of the embodiments of the present application, a method for joint monitoring of multiple physiological parameters is disclosed, comprising:

[0071] S1, collecting and obtaining a physiological parameter signal set of a user; the physiological parameter signal set includes a heart rate signal sequence, a pulse signal sequence, a blood oxygen saturation signal sequence, an electroencephalogram signal sequence, and a blood pressure signal sequence;

[0072] S2, preprocessing the physiological parameter signal set to obtain a preprocessed signal set;

[0073] S3, performing joint monitoring processing on the pre-processed signal set to obtain joint monitoring result information;

[0074] The value of the joint monitoring result information is used to indicate the health status of the user, and the value range is normal, coma, and critical;

[0075] The preprocessing of the physiological parameter signal set to obtain a preprocessed signal set includes:

[0076] S21, performing abnormality detection processing on the physiological parameter signal set to obtain a first signal set;

[0077] S22, normalizing the first signal set to obtain a second signal set;

[0078] S23, performing boundary check processing on the second signal set to obtain a time domain signal set;

[0079] S24, performing transformation feature extraction processing on the time domain signal set to obtain a frequency domain signal set.

[0080] S25, performing fusion processing on the time domain signal set and the frequency domain signal set to obtain a preprocessed signal set;

[0081] The performing boundary check processing on the second signal set to obtain a time domain signal set includes:

[0082] S231, for each signal attribute of the second signal set, taking the signal acquisition information of the signal as an independent variable and the signal value of the signal as a dependent variable, performing cluster analysis processing to obtain clustering result information of the signal attribute; the clustering result information includes the clustering category to which all signals of the signal attribute belong;

[0083] S232, determining the number of signals included in each cluster category; setting a signal quantity threshold; deleting the signals included in the cluster category whose number of signals is less than the signal quantity threshold from the second signal set;

[0084] S233, executing S231 and S232 for all signals of the second signal set to obtain a time domain signal set;

[0085] The step of performing transformation feature extraction processing on the time domain signal set to obtain a frequency domain signal set includes:

[0086] S241, performing bandpass filtering on each signal in the time domain signal set according to a predefined frequency band to obtain a corresponding frequency signal;

[0087] S242, calculating the power spectrum of each frequency signal to obtain a power spectrum characteristic signal;

[0088] S243, fusing all power spectrum feature signals to obtain a frequency domain signal set.

[0089] The performing joint monitoring processing on the pre-processed signal set to obtain joint monitoring result information includes:

[0090] S31, using a time domain monitoring model, performing joint monitoring processing on the time domain signal set to obtain a first monitoring result value;

[0091] S32, using a time-frequency joint monitoring model, performing joint monitoring processing on the preprocessed signal set to obtain a second monitoring result value;

[0092] S33, performing weighted fusion processing on the first monitoring result value and the second monitoring result value to obtain joint monitoring result information.

[0093] The joint monitoring result information is used to characterize the user's physical condition.

[0094] The using the time domain monitoring model to perform joint monitoring processing on the time domain signal set to obtain a first monitoring result value includes:

[0095] S311, obtaining a standard signal set; the standard signal set includes a heart rate signal standard sequence, a pulse signal standard sequence, a blood oxygen saturation signal standard sequence, an electroencephalogram signal standard sequence, and a blood pressure signal standard sequence;

[0096] S312, using the standard signal set and the time domain signal set, respectively construct a standard matrix and a time domain matrix; the row vector of the standard matrix is ​​a standard sequence of heart rate signals, a standard sequence of pulse signals, a standard sequence of blood oxygen saturation signals, a standard sequence of electroencephalogram signals, and a standard sequence of blood pressure signals; the row vector of the time domain matrix is ​​a sequence of heart rate signals, a sequence of pulse signals, a sequence of blood oxygen saturation signals, a sequence of electroencephalogram signals, and a sequence of blood pressure signals;

[0097] S313, performing subtraction processing on the standard matrix and the time domain matrix to obtain a difference matrix;

[0098] S314, performing cross-correlation operation processing on all vectors of the difference matrix to obtain a cross-correlation matrix; the element of the i-th row and j-th column of the cross-correlation matrix is ​​the cross-correlation value between the i-th row vector and the j-th row vector of the difference matrix;

[0099] S315, performing first eigenvector extraction processing on the cross-correlation matrix to obtain a first eigenvector;

[0100] The expression of the first feature vector extraction process is:

[0101]

[0102] Among them, m and n are the row and column dimensions of the cross-correlation matrix, z ij represents the element in the i-th row and j-th column of the cross-correlation matrix, represents the jth element of the first eigenvector, z + represents the first eigenvector;

[0103] S316, performing a second eigenvector extraction process on the cross-correlation matrix to obtain a second eigenvector;

[0104] The expression of the second feature vector extraction process is:

[0105]

[0106] in, represents the jth element of the second eigenvector, z - represents the second eigenvector;

[0107] S317, performing monitoring and evaluation processing on the first eigenvector, the second eigenvector and the mutual correlation matrix to obtain a first monitoring result value;

[0108] The expression of the monitoring and evaluation process is:

[0109]

[0110] In the formula, ω j is the preset jth monitoring weight, and s is the first monitoring result value;

[0111] The using the time-frequency joint monitoring model to perform joint monitoring processing on the preprocessed signal set to obtain a second monitoring result value includes:

[0112] S321, representing the time domain signal set and the frequency domain signal set as a time domain matrix and a frequency domain matrix respectively; the row vector of the time domain matrix is ​​a heart rate signal sequence, a pulse signal sequence, a blood oxygen saturation signal sequence, an electroencephalogram signal sequence, and a blood pressure signal sequence; the row vector of the frequency domain matrix is ​​a power spectrum characteristic signal of the heart rate signal sequence, a power spectrum characteristic signal of the pulse signal sequence, a power spectrum characteristic signal of the blood oxygen saturation signal sequence, a power spectrum characteristic signal of the electroencephalogram signal sequence, and a power spectrum characteristic signal of the blood pressure signal sequence;

[0113] S322, performing cross-correlation calculation processing on the time domain matrix and the frequency domain matrix to obtain a time-frequency cross-correlation matrix; the element of the i-th row and j-th column of the time-frequency cross-correlation matrix is ​​the cross-correlation value between the i-th row vector of the time domain matrix and the j-th row vector of the frequency domain matrix;

[0114] S323, performing relationship calculation on the time-frequency mutual correlation matrix and the mutual correlation matrix to obtain a relationship vector;

[0115] The relationship calculation is expressed as follows:

[0116]

[0117] Among them, A1 ij is the element in the i-th row and j-th column of the cross-correlation matrix A1, A2 ij is the element of the i-th row and j-th column of the time-frequency cross-correlation matrix A2, p i is the i-th element of the relationship vector, and M2 is the column dimension of the cross-correlation matrix A1.

[0118] S324, performing monitoring calculation processing on the relationship vector to obtain a second monitoring result value;

[0119] The monitoring calculation process, its calculation expression is:

[0120]

[0121] in, For pi , M1 is the row dimension of the cross-correlation matrix A1, and R is the second monitoring result value.

[0122] The weighted fusion processing of the first monitoring result value and the second monitoring result value to obtain the joint monitoring result information is to use a preset weight value to perform weighted fusion processing on the first monitoring result value and the second monitoring result value to obtain the joint monitoring result value, if the value range of the joint monitoring result value is [0, R1], it is determined that the joint monitoring result information is normal, if the value range of the joint monitoring result value is (R1, R2], it is determined that the joint monitoring result information is coma, and if the value range of the joint monitoring result value is (R2, R3], it is determined that the joint monitoring result information is critical;

[0123] ω j , obtained by presetting, or by calculating the variance value of each column of the cross-correlation matrix;

[0124] The abnormality inspection process includes filling missing values, smoothing noise data, smoothing or deleting outliers; the smoothed noise data is first determined to obtain noise data, and then the noise data is smoothed according to the data before and after the noise data; the noise data is a value whose value is less than the detection sensitivity of the sensor of the observed data, or greater than the measurement upper limit of the sensor of the observed data. The outlier point can be determined by the Kalman filter method. The filling value of the missing value can be determined by averaging the measured values ​​within a certain sampling interval before and after the missing value.

[0125] The power spectrum calculation includes: calculating the root mean square of each frequency signal (which can be calculated using the built-in function rms in matlab), and then taking the logarithm of the root mean square with base 10 to obtain a power spectrum density characteristic signal.

[0126] The class information of the signal attributes includes heart rate, pulse, blood oxygen saturation, electroencephalogram, and blood pressure.

[0127] The signal acquisition information includes time information, space information or capability type information corresponding to the signal acquisition; when performing data fitting, any of the above types of information can be used as an independent variable, and the corresponding data value can be used as a dependent variable.

[0128] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for joint monitoring of multiple physiological parameters, characterized in that: include: S1, collecting a set of physiological parameter signals of the user; The physiological parameter signal set includes a heart rate signal sequence, a pulse signal sequence, a blood oxygen saturation signal sequence, an electroencephalogram signal sequence, and a blood pressure signal sequence; S2, preprocessing the physiological parameter signal set to obtain a preprocessed signal set; S3, performing joint monitoring processing on the pre-processed signal set to obtain joint monitoring result information.

2. The method for joint monitoring of multiple physiological parameters as claimed in claim 1, characterized in that: The preprocessing of the physiological parameter signal set to obtain a preprocessed signal set includes: S21, performing abnormality detection processing on the physiological parameter signal set to obtain a first signal set; S22, normalizing the first signal set to obtain a second signal set; S23, performing boundary check processing on the second signal set to obtain a time domain signal set; S24, performing transformation feature extraction processing on the time domain signal set to obtain a frequency domain signal set; S25, performing fusion processing on the time domain signal set and the frequency domain signal set to obtain a preprocessed signal set.

3. The method for joint monitoring of multiple physiological parameters as claimed in claim 2, characterized in that: The performing boundary check processing on the second signal set to obtain a time domain signal set includes: S231, for each signal attribute of the second signal set, taking the signal acquisition information of the signal as an independent variable and the signal value of the signal as a dependent variable, performing cluster analysis processing to obtain clustering result information of the signal attribute; the clustering result information includes the clustering category to which all signals of the signal attribute belong; S232, determining the number of signals included in each cluster category; setting a signal quantity threshold; deleting the signals included in the cluster category whose number of signals is less than the signal quantity threshold from the second signal set; S233, execute S231 and S232 for all signals of the second signal set to obtain a time domain signal set.

4. The method for joint monitoring of multiple physiological parameters as claimed in claim 2, characterized in that: The step of performing transformation feature extraction processing on the time domain signal set to obtain a frequency domain signal set includes: S241, performing bandpass filtering on each signal in the time domain signal set according to a predefined frequency band to obtain a corresponding frequency signal; S242, performing power spectrum calculation on the frequency signal of each signal to obtain a power spectrum characteristic signal; S243, fusing all power spectrum feature signals to obtain a frequency domain signal set.

5. The method for joint monitoring of multiple physiological parameters as claimed in claim 2, characterized in that: The performing joint monitoring processing on the pre-processed signal set to obtain joint monitoring result information includes: S31, using a time domain monitoring model, performing joint monitoring processing on the time domain signal set to obtain a first monitoring result value; S32, using a time-frequency joint monitoring model, performing joint monitoring processing on the preprocessed signal set to obtain a second monitoring result value; S33, performing weighted fusion processing on the first monitoring result value and the second monitoring result value to obtain joint monitoring result information.

6. The method for joint monitoring of multiple physiological parameters as claimed in claim 2, characterized in that: The using the time domain monitoring model to perform joint monitoring processing on the time domain signal set to obtain a first monitoring result value includes: S311, obtaining a standard signal set; the standard signal set includes a heart rate signal standard sequence, a pulse signal standard sequence, a blood oxygen saturation signal standard sequence, an electroencephalogram signal standard sequence, and a blood pressure signal standard sequence; S312, using the standard signal set and the time domain signal set, respectively construct a standard matrix and a time domain matrix; the row vector of the standard matrix is ​​a standard sequence of heart rate signals, a standard sequence of pulse signals, a standard sequence of blood oxygen saturation signals, a standard sequence of electroencephalogram signals, and a standard sequence of blood pressure signals; the row vector of the time domain matrix is ​​a sequence of heart rate signals, a sequence of pulse signals, a sequence of blood oxygen saturation signals, a sequence of electroencephalogram signals, and a sequence of blood pressure signals; S313, performing subtraction processing on the standard matrix and the time domain matrix to obtain a difference matrix; S314, performing cross-correlation operation processing on all vectors of the difference matrix to obtain a cross-correlation matrix; the element of the i-th row and j-th column of the cross-correlation matrix is ​​the cross-correlation value between the i-th row vector and the j-th row vector of the difference matrix; S315, performing first eigenvector extraction processing on the cross-correlation matrix to obtain a first eigenvector; The expression of the first feature vector extraction process is: Among them, m and n are the row and column dimensions of the cross-correlation matrix, z ij represents the element in the i-th row and j-th column of the cross-correlation matrix, represents the jth element of the first eigenvector, z + represents the first eigenvector; S316, performing a second eigenvector extraction process on the cross-correlation matrix to obtain a second eigenvector; The expression of the second feature vector extraction process is: in, represents the jth element of the second eigenvector, z - represents the second eigenvector; S317, performing monitoring and evaluation processing on the first eigenvector, the second eigenvector and the mutual correlation matrix to obtain a first monitoring result value; The expression of the monitoring and evaluation process is: In the formula, ω j is the preset jth monitoring weight, s is the first monitoring result value, and pi is the pi constant.

7. The method for joint monitoring of multiple physiological parameters as claimed in claim 6, characterized in that: The using the time-frequency joint monitoring model to perform joint monitoring processing on the preprocessed signal set to obtain a second monitoring result value includes: S321, representing the time domain signal set and the frequency domain signal set as a time domain matrix and a frequency domain matrix respectively; the row vector of the time domain matrix is ​​a heart rate signal sequence, a pulse signal sequence, a blood oxygen saturation signal sequence, an electroencephalogram signal sequence and a blood pressure signal sequence; the row vector of the frequency domain matrix is ​​a power spectrum characteristic signal of the heart rate signal sequence, a power spectrum characteristic signal of the pulse signal sequence, a power spectrum characteristic signal of the blood oxygen saturation signal sequence, a power spectrum characteristic signal of the electroencephalogram signal sequence and a power spectrum characteristic signal of the blood pressure signal sequence; S322, performing cross-correlation calculation processing on the time domain matrix and the frequency domain matrix to obtain a time-frequency cross-correlation matrix; the element of the i-th row and j-th column of the time-frequency cross-correlation matrix is ​​the cross-correlation value between the i-th row vector of the time domain matrix and the j-th row vector of the frequency domain matrix; S323, performing relationship calculation on the time-frequency mutual correlation matrix and the mutual correlation matrix to obtain a relationship vector; The relationship calculation is expressed as follows: Among them, A1 ij is the element in the i-th row and j-th column of the cross-correlation matrix A1, A2 ij is the element of the i-th row and j-th column of the time-frequency cross-correlation matrix A2, p i is the i-th element of the relationship vector, M2 is the column dimension of the cross-correlation matrix A1; S324, performing monitoring calculation processing on the relationship vector to obtain a second monitoring result value; The monitoring calculation process, its calculation expression is: in, For p i , M1 is the row dimension of the cross-correlation matrix A1, and R is the second monitoring result value.

8. A combined monitoring device for multiple physiological parameters, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the method for joint monitoring of multiple physiological parameters according to any one of claims 1 to 7.

9. A computer storable medium, characterized in that: The computer storable medium stores computer instructions, and when the computer instructions are called by a computer, they are used to execute the method for jointly monitoring multiple physiological parameters as described in any one of claims 1 to 7.

10. An information data processing terminal, characterized in that: The information data processing terminal is used to implement the joint monitoring method of multiple physiological parameters as described in any one of claims 1 to 7.

Images