User status monitoring method, device, electronic device and storage medium

Abstract

The embodiment of the present invention discloses a user status monitoring method, device, electronic device and storage medium, the method comprising: obtaining at least two target monitoring data for characterizing the user status of a target user; processing the target monitoring data based on a predetermined target data processing model to obtain a target monitoring statistic corresponding to the target monitoring data; if the target monitoring statistic is within a theoretical monitoring statistic threshold range, marking the user status of the target user as a healthy state; wherein the theoretical monitoring statistic threshold is obtained by processing sample indicator data in a sample data set based on a pre-constructed target data processing model. Through the technical solution of the embodiment of the present invention, the user status is monitored using multivariate data, which not only improves the monitoring accuracy, but also improves the user experience.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of medical health technology, and in particular to a user status monitoring method, device, electronic device and storage medium. Background Art

[0002] With the rise of Internet hospitals, online medical treatment has become a new development trend. Among the patients who seek medical treatment, those with chronic diseases such as hypertension, heart disease, diabetes, asthma, etc. need special attention from doctors because of their long course of illness and the time-series nature of the disease development.

[0003] At present, the main measures taken for the above-mentioned chronic diseases are: using the data of corresponding indicators based on the devices worn by patients, and monitoring the corresponding indicator data, so as to remind patients when a certain indicator data does not meet the requirements. For example, for diabetic patients, when blood sugar is detected to be excessive, the user can be reminded.

[0004] When implementing the technical solution based on the above method, the inventor found the following problems:

[0005] When a patient seeks medical treatment only after detecting that a certain indicator data does not meet the requirements, there is a large time lag, that is, there is a situation where medical treatment is not timely, resulting in the problem of being unable to provide timely and effective treatment for the patient. Furthermore, since the patient is monitored using univariate data, the data monitoring is inaccurate. When the patient is reminded based on inaccurate data, there are frequent or delayed reminders, which in turn causes technical problems such as poor user experience. Summary of the invention

[0006] The present invention provides a user status monitoring method, device, electronic device and storage medium to achieve the technical effect of using multivariate data to monitor the user status, which not only improves the monitoring accuracy, but also improves the user experience.

[0007] In a first aspect, an embodiment of the present invention provides a user status monitoring method, the method comprising:

[0008] Acquire at least two types of target monitoring data for characterizing a user status of a target user;

[0009] Processing the target monitoring data based on a predetermined target data processing model to obtain a target monitoring statistic corresponding to the target monitoring data;

[0010] If the target monitoring statistic is within the theoretical monitoring statistic threshold range, marking the user status of the target user as a healthy state;

[0011] The theoretical monitoring statistic threshold is obtained by processing the sample indicator data in the sample data set based on a pre-built target data processing model.

[0012] In a second aspect, an embodiment of the present invention further provides a user status monitoring device, the device comprising:

[0013] A target monitoring data acquisition module, used to acquire at least two types of target monitoring data for characterizing the user status of the target user;

[0014] A target monitoring statistic determination module, used to process the target monitoring data based on a predetermined target data processing model to obtain a target monitoring statistic corresponding to the target monitoring data;

[0015] A health status marking module, used for marking the user status of the target user as a healthy state if the target monitoring statistic is within a theoretical monitoring statistic threshold range;

[0016] The theoretical monitoring statistic threshold is obtained by processing the sample indicator data in the sample data set based on a pre-built target data processing model.

[0017] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0018] one or more processors;

[0019] a storage device for storing one or more programs,

[0020] When the one or more programs are executed by the one or more processors, the one or more processors implement the user status monitoring method as described in any one of the embodiments of the present invention.

[0021] In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer executable instructions, wherein the computer executable instructions, when executed by a computer processor, are used to execute a user status monitoring method as described in any one of the embodiments of the present invention.

[0022] The technical solution of the embodiment of the present invention obtains at least two types of target monitoring data and performs statistical analysis on the target monitoring data to comprehensively analyze the target monitoring data to obtain target monitoring statistics for measuring user status. If the target monitoring statistics is within the theoretical monitoring statistic threshold range, the user status is marked as a healthy state. This solves the problem in the prior art of judging the user status based on changes in single-variable data, which causes inaccurate judgment, resulting in frequent or delayed reminders to the user, and leads to a poor user experience. It realizes comprehensive consideration of multivariate data to monitor the user status, which not only improves the monitoring accuracy but also realizes timely reminders to users, thereby improving the technical effect of timely user medical treatment and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required to describe the embodiments. Obviously, the drawings introduced are only drawings of a part of the embodiments to be described in the present invention, rather than all the drawings. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A flowchart of a user status monitoring method provided in Embodiment 1 of the present invention;

[0025] Figure 2 A flowchart of a user status monitoring method provided by Embodiment 2 of the present invention;

[0026] Figure 3 A schematic diagram of a flow chart of a user status monitoring method provided by Embodiment 3 of the present invention;

[0027] Figure 4 A flowchart of a user status monitoring method provided by Embodiment 4 of the present invention;

[0028] Figure 5 A schematic diagram of the structure of a user status monitoring device provided by Embodiment 5 of the present invention;

[0029] Figure 6 This is a structural schematic diagram of an electronic device provided in Embodiment 6 of the present invention. DETAILED DESCRIPTION

[0030] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0031] Embodiment 1

[0032] Figure 1 This is a flow chart of a user status monitoring method provided in Example 1 of the present invention. This embodiment can be applied to analyzing and processing a variety of indicator data collected to determine the user status according to the processing results. The method can be executed by a user status monitoring device, which can be implemented in the form of software and / or hardware. The hardware can be an electronic device, and the electronic device can be a mobile terminal, a PC, etc.

[0033] like Figure 1 As shown, the method of this embodiment specifically includes the following steps:

[0034] S110: Acquire at least two types of target monitoring data for characterizing a user status of a target user.

[0035] Among them, the target user may be a patient with a chronic disease, and the target user may monitor the physical health status through the method of this embodiment. The user status may be a status used to characterize the health status of the target user, for example, it may be a healthy status or an unhealthy status, etc. The healthy status refers to the status in which the indicator data collected from the chronic disease patient is determined to be normal after processing, and the unhealthy status refers to the status in which the indicator data collected from the chronic disease patient is determined to be abnormal or may be abnormal after processing. The target monitoring data may be the physiological parameter information required for health monitoring of chronic disease patients and used to characterize body functions, such as blood pressure parameters, blood sugar parameters, heart rate parameters, etc.

[0036] Specifically, at least two physiological parameter information of the target user can be collected in real time through the information collection device, or at least two physiological parameter information of the target user can be collected periodically through the information collection device, for example: once every 1 minute or once every 5 minutes, etc. The collection frequency can be set according to the needs of the target user. In order to improve the monitoring accuracy and get timely warnings when there are problems with your own health status, you can choose to collect monitoring data in real time or collect monitoring data at a high frequency. Of course, if the target user wants to save the power consumption of the information collection device and increase the service life of the information collection device, then you can choose a data collection method that collects monitoring data at a low frequency.

[0037] It should be noted that the advantage of selecting at least two target monitoring data is that at least two target monitoring data can be comprehensively considered to improve monitoring accuracy and avoid reminding the target user when any one of the monitoring data does not meet the requirements but the target user's health is not in trouble.

[0038] S120: Process the target monitoring data based on a predetermined target data processing model to obtain a target monitoring statistic corresponding to the target monitoring data.

[0039] Among them, the target data processing model is an algorithm model obtained by statistical analysis of the sample indicator data in the sample data set, which is used to process at least two target monitoring data to obtain corresponding processing results, and then determine whether it is within a reasonable health range based on the processing results. The target monitoring statistic is the data obtained after the target monitoring data is processed by the target data processing model. The target monitoring statistic can be understood as the statistical data used to measure the status of the target user.

[0040] Specifically, the target monitoring data is input into a predetermined target data processing model, and the target monitoring data is processed to obtain target monitoring statistics corresponding to the target monitoring data. For each set of collected target monitoring data, the target monitoring statistics corresponding to each set of target monitoring data can be obtained by processing the target data processing model.

[0041] S130: If the target monitoring statistic is within a theoretical monitoring statistic threshold range, the user status of the target user is marked as a healthy status.

[0042] The theoretical monitoring statistic threshold is obtained by processing the sample indicator data in the sample data set based on the pre-built target data processing model, and the processing method can be a statistical processing method, for example: principal component analysis (PCA), independent component analysis (ICA), kernel entropy component analysis (KECA), etc. The data in the sample data set can be the monitoring data of the target user in the past period of time, or the monitoring data of multiple users in the past period of time.

[0043] Specifically, when the target monitoring statistic corresponding to the target monitoring data is within the theoretical monitoring statistic threshold range, it can be considered that the target user is in a healthy state at the current moment, and the user state of the target user is marked as a healthy state; when the target monitoring statistic corresponding to the target monitoring data is outside the theoretical monitoring statistic threshold range, it can be considered that the target user is in an unhealthy state at the current moment, and the user state of the target user is marked as an unhealthy state. Early warning information can also be issued to the target user so that the target user can seek medical treatment in time.

[0044] If the target user is bound to a fixed doctor user, the user status and monitoring data can be sent in real time or periodically to the terminal device of the doctor user corresponding to the target user, so that the doctor user can analyze the monitoring data of the target user and then understand the physical health status of the target user, so that when the target user is in an unhealthy state, the doctor user can remind the target user to seek medical treatment.

[0045] It should be noted that the methods of S120 and / or S130 of this embodiment can be integrated into a chip or processor of an information collection device, and the target monitoring data can be processed and compared to determine the user status of the target user. The advantage of this is that the user status of the target user can be analyzed even when the network is disconnected, avoiding analysis interruption. The methods of S120 and / or S130 of this embodiment can also be integrated into a terminal or server, and the target monitoring data can be collected by an information collection device, and the target monitoring data can be uploaded to the terminal or server to complete the statistical and comparative analysis of the target monitoring data on the terminal or server. The advantage of this is that the efficiency of data calculation and analysis can be improved.

[0046] It should also be noted that the theoretical monitoring statistic threshold can be a value determined by statistical analysis based on the detection data of the target user in the past period of time. When the target monitoring statistic does not exceed the theoretical monitoring statistic threshold, the user status of the target user is marked as a healthy state; when the target monitoring statistic exceeds the theoretical monitoring statistic threshold, the user status of the target user is marked as an unhealthy state. At this time, the setting method of the theoretical monitoring statistic threshold has the advantage of a high degree of matching with the target user.

[0047] It should also be noted that the theoretical monitoring statistic threshold can also be a plurality of values ​​determined by statistical analysis based on the detection data of multiple target users in the past period of time, and a slightly larger theoretical monitoring statistic threshold range can be determined based on the plurality of values. When the target monitoring statistic is within the theoretical monitoring statistic threshold range, the user status of the target user is marked as a healthy state; when the target monitoring statistic is outside the theoretical monitoring statistic threshold range, the user status of the target user is marked as an unhealthy state. This method of setting the theoretical monitoring statistic threshold has the advantages of a large amount of statistical data and a more accurate target data processing model.

[0048] The technical solution of the embodiment of the present invention obtains at least two types of target monitoring data and performs statistical analysis on the target monitoring data to comprehensively analyze the target monitoring data to obtain target monitoring statistics for measuring user status. If the target monitoring statistics is within the theoretical monitoring statistic threshold range, the user status is marked as a healthy state. This solves the problem in the prior art of judging the user status based on changes in single-variable data, which causes inaccurate judgment, resulting in frequent or delayed reminders to the user, and leads to a poor user experience. It realizes comprehensive consideration of multivariate data to monitor the user status, which not only improves the monitoring accuracy but also realizes timely reminders to users, thereby improving the technical effect of timely user medical treatment and user experience.

[0049] Embodiment 2

[0050] Figure 2 This is a flow chart of a user status monitoring method provided by Embodiment 2 of the present invention. The embodiment is based on the above embodiments. For the determination method of the theoretical monitoring statistic threshold, please refer to the technical solution of this embodiment. The explanations of the terms that are the same or corresponding to the above embodiments are not repeated here.

[0051] like Figure 2 The method of this embodiment specifically includes the following steps:

[0052] S210: Determine a theoretical monitoring statistic threshold.

[0053] In order to improve the accuracy of the theoretical monitoring statistic threshold, the theoretical monitoring statistic threshold can be determined using a sample data set and a pre-built target data processing model. The method for determining the theoretical monitoring statistic threshold can include the following steps:

[0054] Step 1: Obtain a sample data set, and standardize the sample data of multiple indicators in the sample data set to obtain a standard sample data set.

[0055] The sample data set includes a variety of indicator sample data for characterizing user status, which may include indicator sample data of the target user, and may also include indicator sample data of other users with chronic diseases. It should be noted that the data in the sample data set is obtained based on the indicator data of the target user and / or other users with chronic diseases in a healthy state.

[0056] It should also be noted that the purpose of obtaining multiple indicator data of chronic disease patients in a healthy state is to determine the theoretical monitoring statistics of the target user in a healthy state. If the multiple indicator data are mixed with indicator data of unhealthy states, it will lead to inaccurate calculation of the theoretical monitoring statistics and affect the determination of the threshold of the theoretical monitoring statistics.

[0057] A plurality of indicator data representing that the user's state is in a healthy state within a preset time period is obtained, and the plurality of indicator data are used as a set of sample data in a sample data set.

[0058] Among them, various indicator data representing the user's health status collected within the preset time period can be used to construct a sample data set. The preset time period can be a longer period of time, for example: 30 days. Various indicator data can be obtained within the preset time period, such as sampling indicator data twice a day within the preset time period, or sampling indicator data 10 times a day within the preset time period.

[0059] Specifically, multiple indicator data that characterize the user's health status within a preset time period can be obtained. Furthermore, multiple indicator data at the same sampling time are taken as a group of sample data, and all sample data can constitute a sample data set. In order to make the indicator data more intuitive, the acquired data can be displayed in a tabular form, for example, the sampling time is used as the row header, and the indicator type is used as the column header to construct an indicator data information table. The indicator data can also be counted in other forms, which are not specifically limited in this embodiment.

[0060] In order to improve the efficiency of data standardization, the data can be stored in office software, such as Excel. The column header of Excel is the indicator type, and the data of the same indicator type is stored in sequence.

[0061] In order to enhance the availability of data in the sample data set, the data in the sample data set can be filtered and cleaned, that is, expired data can be cleared, incomplete data can be completed or removed, and duplicate data can be deleted. Furthermore, the filtered and cleaned data can be stored locally and / or in the cloud for subsequent statistical analysis.

[0062] For the indicator data corresponding to the same column header in the sample data set, determine the data mean and variance corresponding to the indicator data of the current column header.

[0063] Among them, the column header can represent the indicator data type, and the indicator data corresponding to the same column header can represent the indicator data under the same indicator type.

[0064] Specifically, in the sample data set, the indicator data corresponding to each column header is obtained, that is, the indicator data of each indicator type is obtained. The data mean and variance corresponding to the indicator data of each column header are obtained by calculation, that is, the mean and variance of the indicator data corresponding to each indicator type are determined.

[0065] For example, the indicator type corresponding to the current column header is heart rate, and the heart rate data in the sample data set are 85, 89, 83, 92, 95, 87, 85, 82, 88 and 93 (unit: bmp). Through calculation, it can be determined that the data mean corresponding to the indicator data at the current column header is 87.9 and the variance is 17.1.

[0066] For each set of sample data, the data standard value of the current indicator data is determined based on the current indicator data, the corresponding data mean and variance.

[0067] The data standard value may be a value obtained by standardizing the current indicator data, and the standardization may be a difference between the current indicator data and the corresponding data mean divided by the corresponding variance.

[0068] Specifically, the column headers (indicator types) corresponding to the indicator data in each group of sample data are different. The current indicator data is subtracted from the data mean corresponding to the corresponding column header to obtain the difference, and the difference is divided by the variance corresponding to the column header to obtain the data standard value of the current indicator data. The same method can be used to process other indicator data to obtain the data standard value of each indicator data.

[0069] For example, the indicator type corresponding to the current indicator data is heart rate, and accordingly, the data corresponding to the column header heart rate has a mean value of 87.9 and a variance of 17.1. If the current heart rate indicator data is 88, the data standard value of the current heart rate indicator data can be calculated as 0.0058 by the following formula.

[0070]

[0071] For each set of sample data, standard sample data is obtained according to the data standard values ​​corresponding to the column headers in the current set of sample data.

[0072] Specifically, for each group of sample data, the data consisting of the data standard values ​​corresponding to the column headers in the current group of sample data is used as the standard sample data of the current group. It can be understood that for each group of sample data, the data standard values ​​corresponding to each indicator type in the current group of sample data are formed into a group as the standard sample data of the current group.

[0073] Based on the standard sample data corresponding to each group of sample data, a standard sample data set is obtained.

[0074] Specifically, the standard sample data corresponding to each group of sample data is combined to obtain a standard sample data set, and the size of the standard sample data set may be consistent with the size of the sample data set.

[0075] Step 2: Process the standard sample data set based on the pre-built target data processing model to obtain a sample score matrix corresponding to the standard sample data set.

[0076] Among them, the sample score matrix is ​​a matrix used to measure the importance of each component.

[0077] Specifically, the sample score matrix can be determined through the following steps.

[0078] (1) Determine the window probability density function based on the kernel function and kernel function parameters.

[0079] The independent variable in the kernel function is the standard sample data in the standard sample data set. Taking the KECA algorithm as an example, the kernel function may be the Mercer kernel function or the like.

[0080] Specifically, the standard sample data set can be recorded in matrix form, that is, the standard sample data matrix D (x1, x2, ..., x N ), where x1 represents the standard sample data corresponding to the first column header, x2 represents the standard sample data corresponding to the second column header, and x N Indicates the standard sample data corresponding to the Nth column header, and N represents the total number of columns in the standard sample data set.

[0081] The Renyi entropy in the KECA algorithm is defined as

[0082] H(p)=-log∫p 2 (x)dx

[0083] Where H is the Renyi entropy and p(x) is the probability density function of the standard sample data matrix D.

[0084] According to the above formula, since the logarithmic function is a monotonic function, we can only analyze ∫p 2 (x)dx, then ∫p 2 (x)dx is recorded as V(p). In order to estimate the value of V(p), the Parzen window probability density estimation function can be introduced:

[0085]

[0086] Among them, k σ (x,x t ) represents the Mercer kernel function, σ represents the parameter of the kernel function, x t Represents any column of data in the standard sample data matrix D.

[0087] (2) The sample mean of the standard sample data in the standard sample data set is approximated by the window probability density function to obtain the data vector matrix corresponding to the standard sample data set.

[0088] Among them, each component in the data vector matrix corresponds to the estimated value of the entropy of the eigenvector.

[0089] Each indicator data and the data volume of the indicator data are processed according to the window probability density function to obtain a vector matrix of data to be converted.

[0090] Specifically, by processing each indicator data and the amount of indicator data according to the window probability density function, the data vector matrix to be transformed corresponding to each indicator data can be obtained, which is recorded as

[0091] By performing eigendecomposition on the kernel matrix in the kernel function, an eigendecomposition vector corresponding to the kernel matrix is ​​obtained.

[0092] Among them, the eigendecomposition vector is composed of a diagonal eigenmatrix and a column eigenmatrix.

[0093] Specifically, the kernel matrix can be recorded as K, and the size of K is N×N. The Renyi entropy is estimated by the eigenvalues ​​and eigenvectors of the kernel matrix. The kernel matrix K can be eigendecomposed to obtain the eigendecomposition vector, that is, K can be decomposed into:

[0094]

[0095] Where Λ represents the eigenvalues ​​λ1, λ2, …, λ of the kernel matrix K N The diagonal characteristic matrix composed of eigenvectors e1, e2, …, e N The column feature matrix.

[0096] The data vector matrix to be transformed is processed based on the eigendecomposition vector to obtain a data vector matrix.

[0097] Specifically, since V(p) = ∫p 2 (x)dx, using the sample mean approximation to obtain the data vector matrix

[0098]

[0099] Furthermore, the above formula can be expressed through the kernel matrix K as:

[0100]

[0101] Among them, K is an N×N kernel matrix; 1 is an N×1 unit vector, and 1T is the transposed matrix of the unit vector. That is, the kernel matrix K is:

[0102]

[0103] Further, it can be deduced that

[0104]

[0105] As can be seen from the above formula each component in corresponds to an estimated value of the entropy of a feature vector, and different eigenvalue-eigenvector pairs contribute differently to the Renyi entropy.

[0106] (3) By performing a dimensionality reduction transformation on the data vector matrix, a sample score matrix of the standard sample data set is obtained.

[0107] Among them, the dimension of the sample score matrix is smaller than that of the data vector matrix.

[0108] According to the eigenvalues in the diagonal feature matrix, a to-be-processed diagonal feature matrix composed of a preset number of target eigenvalues is determined.

[0109] Among them, the preset number should be less than or equal to the dimension of the diagonal feature matrix, which can be denoted as k.

[0110] Specifically, select the top k eigenvalues with larger values in the diagonal feature matrix Λ as the main elements, and determine the eigenvectors corresponding to these k eigenvalues. Furthermore, use these k eigenvectors as the main axes of KECA to span the subspace U m , determine the subspace U m The dimension m of is the number of target eigenvalues, and the m eigenvalues can be used as target eigenvalues. According to the target eigenvalues, a diagonal feature matrix

[0111] Λ m = diag(λ1, λ2,... λ m )

[0112] Among them, Λ m represents the to-be-processed diagonal feature matrix composed of the eigenvalues λ1, λ2,..., λ m .

[0113] By performing a dimensionality reduction transformation on the to-be-processed diagonal feature matrix, a sample score matrix of the standard sample data set is obtained.

[0114] Specifically, a nonlinear mapping from the input space to the kernel feature space can be defined The manifestation form can be In this case, it can be set that Furthermore, the N-dimensional data vector matrix can be mapped through , that is, the N-dimensional data vector matrix is mapped to the subspace U spanned by k KECA main axes m (m < N), and the sample score matrix T m can be obtained:[[]]

[0115]

[0116] Among them, Λ m Represented by the eigenvalues ​​λ1, λ2, ..., λ m The diagonal feature matrix to be processed, E m =(e1, e2, ..., e m ) represents the eigenvectors e1, e2, …, e m The eigenvector matrix.

[0117] It should be noted that the number of principal components k can be determined using the cumulative variance contribution rate, that is, the variance contribution rates corresponding to the eigenvalues ​​and eigenvectors are calculated in sequence from large to small, and accumulated so that when the cumulative variance contribution rate reaches the threshold for the first time, for example: the contribution rate reaches 90%, the corresponding number of eigenvalues ​​is used as the preset number, that is, the number of principal components.

[0118] Step 3: Based on the sample score matrix, obtain the theoretical monitoring statistics.

[0119] Firstly, based on the sample score matrix and the diagonal feature matrix to be processed, the first theoretical monitoring statistic among the theoretical monitoring statistics is obtained.

[0120] Among them, the standard sum of squares of each score vector in the sample score matrix is ​​used as the first theoretical monitoring statistic.

[0121] Specifically, the first theoretical monitoring statistic T 2 It can be obtained based on the following formula

[0122] T 2 =T m Λ m -1 T m T

[0123] The first theoretical monitoring statistic T can be analyzed using the F distribution. 2 The control limits are calculated

[0124]

[0125] Among them, n is the number of samples used to build the principal component model, k is the number of principal components retained in the model, and F k，n-1，α It is the critical value of the F distribution corresponding to the test level α, degrees of freedom k, and n-1 conditions.

[0126] Secondly, based on the eigenvalues ​​in the diagonal feature matrix and the eigenvalues ​​in the sample score matrix, a second theoretical monitoring statistic in the theoretical monitoring statistics is obtained.

[0127] Among them, the second theoretical monitoring statistic represents the changes in the data that are not explained by the principal component model, and can indicate the error between the changing trend of each data sampling and the statistical model.

[0128] Specifically, the second theoretical monitoring statistic SPE can be obtained based on the following formula:

[0129]

[0130] The control limit of the second theoretical monitoring statistic SPE can be calculated by the following formula:

[0131]

[0132] in, C α is the critical value of the normal distribution at the test level α. j Represents the eigenvalues ​​of the diagonal eigenmatrix to be processed used when establishing the target data processing model.

[0133] Finally, the first theoretical monitoring statistic and the second theoretical monitoring statistic can be used as theoretical monitoring statistics, and the first theoretical monitoring statistic control limit and the second theoretical monitoring statistic control limit can be used as theoretical monitoring statistic threshold ranges.

[0134] S220: Obtain at least two types of target monitoring data for characterizing the user status of the target user.

[0135] S230: Process the target monitoring data based on a predetermined target data processing model to obtain a target monitoring statistic corresponding to the target monitoring data.

[0136] S240: If the target monitoring statistic is within a theoretical monitoring statistic threshold range, the user status of the target user is marked as a healthy status.

[0137] The technical solution of the embodiment of the present invention processes the data in the standard sample data set through KECA to obtain a sample score matrix, and then processes the sample score matrix through a statistical analysis method to obtain a theoretical detection statistic to accurately determine the threshold range of the theoretical monitoring statistic, thereby solving the problem of inaccurate judgment caused by using a single threshold to judge whether the monitoring data is healthy data in the prior art, and realizes the improvement of the accuracy of the theoretical detection statistic threshold based on KECA and statistical analysis, thereby improving the accuracy of user status judgment and improving user experience.

[0138] Embodiment 3

[0139] Figure 3This is a flow chart of a user status monitoring method provided by Embodiment 3 of the present invention. Based on the above embodiments, the specific method for determining the target monitoring statistic and the user status can refer to the technical solution of this embodiment. The explanations of the terms that are the same or corresponding to the above embodiments are not repeated here.

[0140] like Figure 3 The method of this embodiment specifically includes the following steps:

[0141] S310: Obtain at least two types of target monitoring data for characterizing a user status of a target user.

[0142] Specifically, the physiological parameter information of the target user is collected based on the information collection device, and the physiological parameter information is standardized to obtain target monitoring data for characterizing the user status.

[0143] It is understandable that the physiological parameter information of the target user collected by the information collection device is classified according to different indicator types, i.e., column headers. Then, the target monitoring data is determined according to the current physiological parameter information and the data mean and variance corresponding to the corresponding column header. It can be: the difference between the current physiological parameter information and the corresponding data mean is divided by the corresponding variance.

[0144] In order to accurately measure the user status of the target user, the target monitoring data may include at least two of blood pressure parameters, blood oxygen saturation parameters, blood sugar parameters, heart rate parameters, body fat rate parameters, uric acid parameters, urine routine parameters, total cholesterol parameters or body temperature parameters. The units of the above physiological parameter information variables are shown in Table 1.

[0145] Table 1 Physiological parameter information variables

[0146]

[0147] S320: Analyze and process the target monitoring data based on the target data processing model to obtain a target health score vector corresponding to the target monitoring data.

[0148] Specifically, the target monitoring data is input into the target data processing model, and the target monitoring data can be processed by KECA statistics, that is, the data outside the sample data set (target monitoring data) is processed by Projection to U m On, meet

[0149]

[0150] in, T′ m Each vector in is used as the target health score vector, which can be expressed as

[0151] S330. Process the target health score vector based on F distribution to obtain a first target monitoring statistic in the target monitoring statistics.

[0152] Specifically, the first target monitoring statistic can be determined according to the target health score vector and the sample score matrix. 2 The control limits are compared.

[0153] For a new sampling point, that is, the target health score vector, the first target monitoring statistic T 2 When the value of is less than the control limit, it means that the variables of the target health score vector and the data vector matrix obey the same statistical distribution; otherwise, it means that the target health score vector and the data vector matrix do not obey the same statistical distribution, and the health condition of the target user may be abnormal.

[0154] S340. Obtain a second target monitoring statistic in the target monitoring statistic by processing each vector value in the target health score vector.

[0155] Specifically, the second target monitoring statistic may be determined according to each vector value in the target health score vector, and then the second target monitoring statistic may be compared with the control limit of the second theoretical monitoring statistic SPE.

[0156] If the second target monitoring statistic of the target health score vector does not exceed the upper limit, it means that the target user is currently in a healthy state; otherwise, the target user is currently in an unhealthy state and an early warning is required for the target user.

[0157] S350: If the first target monitoring statistic is within a first theoretical monitoring statistic threshold in the theoretical monitoring statistics, and the second target monitoring statistic is within a second theoretical monitoring statistic threshold range in the theoretical monitoring statistics, then the user status of the target user is marked as a healthy status.

[0158] Specifically, if the first target monitoring statistic meets the first theoretical monitoring statistic threshold range, then it can be considered that the target user's current target monitoring data and the sample indicator data in the sample data set belong to the same statistical distribution, and the user status of the current target user can be considered to be healthy. If the second target monitoring statistic meets the second theoretical monitoring statistic threshold range, then it can be considered that the target user's current target monitoring data is within the error range of the diagonal feature matrix to be processed used in the target data processing model, and the user status of the current target user can be considered to be healthy.

[0159] In order to avoid missing the marking and warning of the unhealthy state of the target user, when the first target monitoring statistic and the second target monitoring statistic are both within the theoretical monitoring statistic threshold range, the user state of the target user is marked as a healthy state; when at least one target monitoring statistic is outside the theoretical detection statistic threshold, the user state of the target user is marked as an unhealthy state, and a warning can be issued.

[0160] The technical solution of the embodiment of the present invention performs statistical analysis on the target health score vector obtained after processing the target monitoring data based on KECA to obtain the first target monitoring statistic and the second target monitoring statistic. If the first target monitoring statistic and the second target monitoring statistic are both within the theoretical monitoring statistic threshold range, the user status is marked as a healthy status. This solves the problem in the prior art of judging the user status based on the change of univariate data, which causes inaccurate judgment, resulting in frequent or delayed reminders to the user, resulting in poor user experience. It realizes comprehensive consideration of multivariate data to monitor the user status, which not only improves the monitoring accuracy but also realizes timely reminders to users, thereby improving the technical effect of timely user medical treatment and user experience.

[0161] Embodiment 4

[0162] As an optional implementation scheme of the above embodiments, Figure 4 This is a flow chart of a user status monitoring method provided by Embodiment 4 of the present invention. The explanations of terms that are the same as or corresponding to the above embodiments are not repeated here.

[0163] like Figure 4 As shown, the user state detection method can be divided into an offline modeling stage and an online monitoring stage.

[0164] Offline modeling phase:

[0165] (1) Obtain a sample data set, where the data in the sample data set are multiple indicator data in a healthy state. The multiple indicator data in the sample data set can be used as normal training data.

[0166] (2) Standardize the normal training data, determine the mean and variance of each indicator type, and determine the standard sample data set.

[0167] (3) Based on the given kernel function and its parameters, the KECA model is constructed according to the standard sample data set, and the sample score matrix T is extracted. m =[t1, t2, …, t m ].

[0168] (4) Calculate the statistics of normal training data based on the sample score matrix, that is, the first theoretical monitoring statistic T 2and the second theoretical monitoring statistic SPE.

[0169] (5) Calculate and find the statistical control limits based on the statistics. That is, determine the first theoretical monitoring statistical control limits based on the first theoretical monitoring statistics, and determine the second theoretical monitoring statistical control limits based on the second theoretical monitoring statistics.

[0170] Online monitoring stage, that is, in the specific application stage:

[0171] (1) Collect physiological parameter information of target users and use the physiological parameter information as online test data.

[0172] (2) Based on the mean and variance of each indicator type and the standardization method determined in the offline modeling stage (2), the online test data is standardized to obtain the target monitoring data.

[0173] (3) The target monitoring data is processed by the KECA model constructed in the offline modeling stage (3) to obtain the target health score vector t′ i .

[0174] (4) Based on the target health score vector, the monitoring statistics of the online test data are calculated, namely, the first target monitoring statistics and the second target monitoring statistics.

[0175] (5) Compare the first target monitoring statistic with the first theoretical monitoring statistic control limit, and compare the second target monitoring statistic with the second theoretical monitoring statistic control limit. If at least one target monitoring statistic exceeds the theoretical monitoring statistic control limit, it means that the target user has a health problem, that is, the user status is determined to be an unhealthy state. At this time, a reminder can be generated to remind the user. Otherwise, the user status of the target user is considered to be a healthy state, that is, in good health, and the monitoring is returned to continue.

[0176] The technical solution of the embodiment of the present invention, in the offline modeling stage, builds a KECA model based on the sample data set, and calculates the statistical control limit; in the online monitoring stage, determines the target health score vector based on the physiological parameter information and the constructed KECA model, and then obtains the monitoring statistic. According to the relationship between the monitoring statistic and the statistical control limit, it is judged whether the target user has health problems, which solves the problem of inaccurate judgment when judging the user status based on the change of single variable data in the prior art, thereby causing frequent reminders or delayed reminders to the user, resulting in a poor user experience. It realizes the comprehensive consideration of multivariate data to monitor the user status, which not only improves the monitoring accuracy but also realizes timely reminders to the user, thereby improving the technical effect of timely medical treatment and user experience.

[0177] Embodiment 5

[0178] Figure 5 This is a structural schematic diagram of a user status monitoring device provided in Embodiment 5 of the present invention. The device includes: a target monitoring data acquisition module 510, a target monitoring statistic determination module 520 and a health status marking module 530.

[0179] Among them, the target monitoring data acquisition module 510 is used to obtain at least two types of target monitoring data for characterizing the user status of the target user; the target monitoring statistic determination module 520 is used to process the target monitoring data based on a predetermined target data processing model to obtain a target monitoring statistic corresponding to the target monitoring data; the health status marking module 530 is used to mark the user status of the target user as a healthy state if the target monitoring statistic is within the theoretical monitoring statistic threshold range; wherein the theoretical monitoring statistic threshold is obtained by processing the sample indicator data in the sample data set based on a pre-constructed target data processing model.

[0180] Optionally, the target monitoring data acquisition module 510 is specifically used to collect physiological parameter information of the target user based on an information collection device, and standardize the physiological parameter information to obtain target monitoring data for characterizing the user status.

[0181] Optionally, the target monitoring data includes at least two of blood pressure parameters, blood oxygen saturation parameters, blood sugar parameters, heart rate parameters, body fat percentage parameters, uric acid parameters, urine routine parameters, total cholesterol parameters or body temperature parameters.

[0182] Optionally, the target monitoring statistic determination module 520 is specifically used to analyze and process the target monitoring data based on the target data processing model to obtain a target health score vector corresponding to the target monitoring data; process the target health score vector based on F distribution to obtain a first target monitoring statistic in the target monitoring statistics; and obtain a second target monitoring statistic in the target monitoring statistics by processing each vector value in the target health score vector.

[0183] Optionally, the target monitoring statistic determination module 520 is further used to mark the user status of the target user as a healthy state if both the first target monitoring statistic and the second target monitoring statistic are within the theoretical monitoring statistic threshold range.

[0184] Optionally, the device also includes: a theoretical monitoring statistic threshold determination module, used to determine the theoretical monitoring statistic threshold; the theoretical monitoring statistic threshold determination module is specifically used to obtain a sample data set, and standardize multiple indicator sample data in the sample data set to obtain a standard sample data set; wherein the sample data set includes multiple indicator sample data for characterizing user status; the standard sample data set is processed based on a pre-constructed target data processing model to obtain a sample score matrix corresponding to the standard sample data set; based on the sample score matrix, the theoretical monitoring statistic is obtained.

[0185] Optionally, the theoretical monitoring statistic threshold determination module is also used to obtain multiple indicator data that characterize the user status as a healthy state within a preset time period, and use the multiple indicator data as a group of sample data in the sample data set; for the indicator data corresponding to the same column header in the sample data set, determine the data mean and variance corresponding to the indicator data of the current column header; for each group of sample data, determine the data standard value of the current indicator data according to the current indicator data, the corresponding data mean and variance; for each group of sample data, obtain standard sample data according to the data standard values ​​corresponding to each column header in the current group of sample data; based on the standard sample data corresponding to each group of sample data, obtain the standard sample data set.

[0186] Optionally, the theoretical monitoring statistic threshold determination module is also used to determine the window probability density function based on the kernel function and kernel function parameters; wherein the independent variable in the kernel function is the standard sample data in the standard sample data set; the sample mean is approximated by the window probability density function to obtain the data vector matrix corresponding to the standard sample data set; the sample score matrix of the standard sample data set is obtained by performing a dimensionality reduction transformation on the data vector matrix; wherein the dimension of the sample score matrix is ​​smaller than the dimension of the data vector matrix.

[0187] Optionally, the theoretical monitoring statistic threshold determination module is also used to process each indicator data and the data amount of the indicator data according to the window probability density function to obtain the data vector matrix to be converted; by performing characteristic decomposition on the kernel matrix in the kernel function, the characteristic decomposition vector corresponding to the kernel matrix is ​​obtained; wherein the characteristic decomposition vector is composed of a diagonal characteristic matrix and a column characteristic matrix; and the data vector matrix to be converted is processed based on the characteristic decomposition vector to obtain a data vector matrix.

[0188] Optionally, the theoretical monitoring statistic threshold determination module is also used to determine a diagonal feature matrix to be processed consisting of a preset number of target eigenvalues ​​based on the eigenvalues ​​in the diagonal feature matrix; and obtain a sample score matrix of the standard sample data set by performing a dimensionality reduction transformation on the diagonal feature matrix to be processed.

[0189] Optionally, the theoretical monitoring statistic threshold determination module is also used to obtain a first theoretical monitoring statistic in the theoretical monitoring statistics based on the sample score matrix and the diagonal feature matrix to be processed; and to obtain a second theoretical monitoring statistic in the theoretical monitoring statistics based on the eigenvalues ​​in the diagonal feature matrix and the eigenvalues ​​in the sample score matrix.

[0190] The technical solution of the embodiment of the present invention obtains at least two types of target monitoring data and performs statistical analysis on the target monitoring data to comprehensively analyze the target monitoring data to obtain target monitoring statistics for measuring user status. If the target monitoring statistics is within the theoretical monitoring statistic threshold range, the user status is marked as a healthy state. This solves the problem in the prior art of judging the user status based on changes in single-variable data, which causes inaccurate judgment, resulting in frequent or delayed reminders to the user, and leads to a poor user experience. It realizes comprehensive consideration of multivariate data to monitor the user status, which not only improves the monitoring accuracy but also realizes timely reminders to users, thereby improving the technical effect of timely user medical treatment and user experience.

[0191] The user status monitoring device provided in the embodiment of the present invention can execute the user status monitoring method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0192] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present invention.

[0193] Embodiment 6

[0194] Figure 6 This is a structural schematic diagram of an electronic device provided in Embodiment 6 of the present invention. Figure 6 A block diagram of an exemplary electronic device 60 suitable for implementing exemplary embodiments of the present invention is shown. Figure 6 The electronic device 60 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0195] like Figure 6As shown, the electronic device 60 is in the form of a general computing device. The components of the electronic device 60 may include but are not limited to: one or more processors or processing units 601, a system memory 602, and a bus 603 connecting different system components (including the system memory 602 and the processing unit 601).

[0196] Bus 603 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.

[0197] The electronic device 60 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 60, including volatile and non-volatile media, removable and non-removable media.

[0198] The system memory 602 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 604 and / or cache memory 605. The electronic device 60 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 606 may be used to read and write non-removable, non-volatile magnetic media ( Figure 6 not shown, usually called a "hard drive"). Although Figure 6 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 603 via one or more data medium interfaces. The system memory 602 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the embodiments of the present invention.

[0199] A program / utility 608 having a set (at least one) of program modules 607 may be stored, for example, in system memory 602, such program modules 607 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 607 generally perform the functions and / or methods of the embodiments described herein.

[0200] The electronic device 60 may also communicate with one or more external devices 609 (e.g., keyboards, pointing devices, displays 610, etc.), may communicate with one or more devices that enable a user to interact with the electronic device 60, and / or may communicate with any device that enables the electronic device 60 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface 611. Furthermore, the electronic device 60 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 612. As shown, the network adapter 612 communicates with other modules of the electronic device 60 via a bus 603. It should be understood that although Figure 6 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 60, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0201] The processing unit 601 executes various functional applications and data processing by running the programs stored in the system memory 602, such as implementing the user status monitoring method provided in the embodiment of the present invention.

[0202] Embodiment 7

[0203] Embodiment 7 of the present invention further provides a storage medium comprising computer executable instructions, wherein the computer executable instructions are used to execute a user status monitoring method when executed by a computer processor.

[0204] The method includes:

[0205] Acquire at least two types of target monitoring data for characterizing a user status of a target user;

[0206] Processing the target monitoring data based on a predetermined target data processing model to obtain a target monitoring statistic corresponding to the target monitoring data;

[0207] If the target monitoring statistic is within the theoretical monitoring statistic threshold range, marking the user status of the target user as a healthy state;

[0208] The theoretical monitoring statistic threshold is obtained by processing the sample indicator data in the sample data set based on a pre-built target data processing model.

[0209] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0210] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0211] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0212] Computer program code for performing the operation of embodiments of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0213] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A user status monitoring method, characterized in that: include: Acquire at least two types of target monitoring data for characterizing a user status of a target user; Processing the target monitoring data based on a predetermined target data processing model to obtain a target monitoring statistic corresponding to the target monitoring data; wherein the target monitoring statistic includes a first target monitoring statistic and a second target monitoring statistic; If the target monitoring statistic is within the theoretical monitoring statistic threshold range, marking the user status of the target user as a normal state; Wherein, the theoretical monitoring statistic threshold is obtained by processing the sample indicator data in the sample data set based on a pre-constructed target data processing model, the theoretical monitoring statistic threshold range includes a first theoretical monitoring statistic threshold corresponding to the first target monitoring statistic, and a second theoretical monitoring statistic threshold corresponding to the second target monitoring statistic, and the sample data set includes historical monitoring data of the target user and / or multiple users; The target monitoring data is processed based on a predetermined target data processing model to obtain a target monitoring statistic corresponding to the target monitoring data, including: Analyze and process the target monitoring data based on the target data processing model to obtain a target score vector corresponding to the target monitoring data; Processing the target score vector based on F distribution to obtain a first target monitoring statistic in the target monitoring statistics; By processing each vector value in the target score vector, a second target monitoring statistic in the target monitoring statistic is obtained.

2. The method according to claim 1, characterized in that The acquiring of at least two types of target monitoring data for characterizing the user status of the target user includes: The physiological parameter information of the target user is collected based on the information collection device, and the physiological parameter information is standardized to obtain target monitoring data for characterizing the user status.

3. The method according to claim 1 or 2, characterized in that: The target monitoring data includes at least two of blood pressure parameters, blood oxygen saturation parameters, blood sugar parameters, heart rate parameters, body fat rate parameters, uric acid parameters, urine routine parameters, total cholesterol parameters or body temperature parameters.

4. The method according to claim 1, characterized in that: If the target monitoring statistic is within the theoretical monitoring statistic threshold range, marking the user status of the target user as a state without abnormality includes: If the first target monitoring statistic is within a first theoretical monitoring statistic threshold in the theoretical monitoring statistics, and the second target monitoring statistic is within a second theoretical monitoring statistic threshold range in the theoretical monitoring statistics, the user state of the target user is marked as a state without abnormality.

5. The method according to claim 1, characterized in that Also includes: Determining the theoretical monitoring statistic threshold; The determining of the theoretical monitoring statistic threshold comprises: Acquire a sample data set, and perform standardization processing on a plurality of indicator sample data in the sample data set to obtain a standard sample data set; wherein the sample data set includes a plurality of indicator sample data for characterizing user status; Processing the standard sample data set based on a pre-built target data processing model to obtain a sample score matrix corresponding to the standard sample data set; Based on the sample score matrix, the theoretical monitoring statistic is obtained.

6. The method according to claim 5, characterized in that The step of obtaining a sample data set and performing standardization processing on multiple indicator sample data in the sample data set to obtain a standard sample data set includes: Acquire multiple indicator data indicating that the user status is not abnormal within a preset time period, and use the multiple indicator data as a set of sample data in the sample data set; For the indicator data corresponding to the same column header in the sample data set, determine the data mean and variance corresponding to the indicator data of the current column header; For each set of sample data, determine the data standard value of the current indicator data based on the current indicator data, the corresponding data mean and variance; For each group of sample data, the standard sample data is obtained according to the data standard values ​​corresponding to the column headers in the current group of sample data; Based on the standard sample data corresponding to each group of sample data, the standard sample data set is obtained.

7. The method according to claim 5, characterized in that The method of processing the standard sample data set based on the pre-built target data processing model to obtain a sample score matrix corresponding to the standard sample data set includes: Determining a window probability density function based on a kernel function and kernel function parameters; wherein the independent variable in the kernel function is the standard sample data in the standard sample data set; Performing sample mean approximation processing on the standard sample data in the standard sample data set by using the window probability density function to obtain a data vector matrix corresponding to the standard sample data set; By performing a dimensionality reduction transformation on the data vector matrix, a sample score matrix of the standard sample data set is obtained; wherein the dimension of the sample score matrix is ​​smaller than the dimension of the data vector matrix.

8. The method according to claim 7, characterized in that The method of performing sample mean approximation processing on the standard sample data in the standard sample data set by using the window probability density function to obtain a data vector matrix corresponding to the standard sample data set includes: Processing each indicator data and the data volume of the indicator data according to the window probability density function to obtain a vector matrix of data to be converted; By performing eigendecomposition on the kernel matrix in the kernel function, an eigendecomposition vector corresponding to the kernel matrix is ​​obtained; wherein the eigendecomposition vector is composed of a diagonal eigenmatrix and a column eigenmatrix; The data vector matrix to be converted is processed based on the eigendecomposition vector to obtain a data vector matrix.

9. The method according to claim 8, characterized in that The step of performing a dimensionality reduction transformation on the data vector matrix to obtain a sample score matrix of the standard sample data set includes: According to the eigenvalues ​​in the diagonal feature matrix, determining a diagonal feature matrix to be processed consisting of a preset number of target eigenvalues; By performing a dimensionality reduction transformation on the diagonal feature matrix to be processed, a sample score matrix of the standard sample data set is obtained.

10. The method according to claim 9, characterized in that The obtaining of the theoretical monitoring statistic based on the sample score matrix includes: Based on the sample score matrix and the to-be-processed diagonal feature matrix, obtaining a first theoretical monitoring statistic among the theoretical monitoring statistics; Based on the eigenvalues ​​in the diagonal feature matrix and the eigenvalues ​​in the sample score matrix, a second theoretical monitoring statistic in the theoretical monitoring statistics is obtained.

11. A user status monitoring device, characterized in that: include: A target monitoring data acquisition module, used to acquire at least two types of target monitoring data for characterizing the user status of the target user; A target monitoring statistic determination module, used to process the target monitoring data based on a predetermined target data processing model to obtain a target monitoring statistic corresponding to the target monitoring data; wherein the target monitoring statistic includes a first target monitoring statistic and a second target monitoring statistic; A user status marking module, configured to mark the user status of the target user as a normal state if the target monitoring statistic is within a theoretical monitoring statistic threshold range; Wherein, the theoretical monitoring statistic threshold is obtained by processing the sample indicator data in the sample data set based on a pre-constructed target data processing model, the theoretical monitoring statistic threshold range includes a first theoretical monitoring statistic threshold corresponding to the first target monitoring statistic, and a second theoretical monitoring statistic threshold corresponding to the second target monitoring statistic, and the sample data set includes historical monitoring data of the target user and / or multiple users; Among them, the target monitoring statistic determination module is specifically used to analyze and process the target monitoring data based on the target data processing model to obtain a target score vector corresponding to the target monitoring data; process the target score vector based on F distribution to obtain a first target monitoring statistic in the target monitoring statistics; and obtain a second target monitoring statistic in the target monitoring statistics by processing each vector value in the target score vector.

12. An electronic device, characterized in that: The electronic device comprises: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the user status monitoring method as described in any one of claims 1-10.

13. A storage medium comprising computer executable instructions, wherein the computer executable instructions are used to execute the user status monitoring method according to any one of claims 1 to 10 when executed by a computer processor.

Images