Intelligent cloud data health receiver and method supporting multiple users

Abstract

The present invention relates to the field of medical information processing technology. The present invention discloses an intelligent cloud data health receiver and method supporting multiple users, including a first processing module, a judgment module, a second processing module and an encryption transmission module. First, the first processing module and the second processing module calculate the detection deviation value and perform attention weight marking to ensure that important data elements are processed first and avoid repeated encryption and compression. The judgment module performs a consistency check on the initial detection data. If the consistency check fails, it enters the second processing module for correction. Based on the detection device information, a detection error value is generated and the initial detection data is corrected to obtain intermediate detection data. After correction, it returns to the judgment module until the consistency check passes. Finally, data compression and encryption are performed through the encryption transmission module, which effectively reduces the computing burden and the amount of transmitted data, and significantly improves the real-time transmission efficiency and data processing performance in multi-user scenarios.

Description

Technical Field

[0001] The present invention relates to the field of medical information processing technology, and more particularly, to an intelligent cloud data health receiver and method supporting multiple users. Background Art

[0002] Currently, smart health receiving devices can collect data in real time and upload it to the cloud for doctors to analyze, but there are still certain problems in actual application.

[0003] In the prior art, a Chinese patent application with publication number CN118098484A discloses a medical information sharing method based on big data. By collecting the patient's ECG signal and analyzing the frequency distribution, signal strength and waveform difference of the ECG detail signal, the ECG detail representation index and signature embedding retention coefficient are extracted. Finally, the optimal ECG detail signal is compressed and transmitted; a Chinese patent application with publication number CN115274028A discloses a data encryption processing method for nucleic acid detection. The user performs real-name authentication when registering, and after successful authentication, the encrypted personal information is stored in a cloud server.

[0004] Although relevant methods for encrypting and compressing user health data have been disclosed in the existing technology, the demand for real-time transmission of health data is more urgent in multi-user scenarios. At present, the existing technology usually adopts the method of encrypting the health data of multiple users first and then compressing and transmitting it, which undoubtedly increases the amount of calculation and affects the data transmission rate. In addition, the encrypted data usually lacks redundant information, resulting in poor compression effect, thereby further reducing the transmission efficiency.

[0005] In view of this, the present invention proposes an intelligent cloud data health receiver and method supporting multiple users to solve the above problems. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides an intelligent cloud data health receiver and method supporting multiple users.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] First, it provides a multi-user intelligent cloud data health receiver, including:

[0009] The first processing module is used to obtain detection device information and the user's initial detection data, determine a detection deviation value based on the initial detection data, and mark the attention weight of each element in the initial detection data based on the detection deviation value;

[0010] Judgment module: used to construct the corresponding weight judgment matrix based on the initial detection data, and perform consistency check on the weight judgment matrix. If the consistency check passes, it will be transferred to the encryption transmission module; if the consistency check fails, it will be transferred to the second processing module;

[0011] A second processing module is configured to generate a detection error value based on the detection device information, correct the initial detection data based on the detection error value to obtain intermediate detection data, use the intermediate detection data as the initial detection data, and return the intermediate detection data to the judgment module;

[0012] Encryption transmission module: used to compress the initial detection data to obtain target detection data, encrypt the target detection data, and send the encrypted target detection data.

[0013] Furthermore, the method for determining the detection deviation value based on the initial detection data includes:

[0014] The initial detection data is fitted to construct a detection curve graph, the Euclidean distance between each element in the initial detection data and the nearest point in the detection curve graph is calculated, and the Euclidean distance is used as the detection deviation value corresponding to each element.

[0015] Furthermore, the method of constructing a corresponding weight judgment matrix based on the initial detection data includes:

[0016] Obtain the detection time period corresponding to each element in the initial detection data, mark each element with a time weight according to the detection time period, multiply the attention weight and time weight corresponding to each element to obtain a comprehensive weight, and construct a weight judgment matrix based on the comprehensive weight corresponding to each element.

[0017] Furthermore, the method for performing consistency check on the weight judgment matrix includes:

[0018] The consistency ratio corresponding to the weight judgment matrix is ​​calculated. When the consistency ratio is less than the preset ratio threshold, the consistency test passes. When the consistency ratio is greater than or equal to the preset ratio threshold, the consistency test fails.

[0019] Furthermore, the detection device information includes average operating time, internal temperature value, average calibration times, and real-time component temperature. The method for generating the detection error value based on the detection device information includes:

[0020] The detection error value is obtained by performing deviation calculation based on the average operating time, internal temperature value, average number of calibration times and real-time component temperature.

[0021] Furthermore, the method of correcting the initial detection data based on the detection error value to obtain the intermediate detection data includes:

[0022] Input the detection error value and the initial detection data into a pre-built data correction model to obtain intermediate detection data;

[0023] The method for constructing the data correction model includes:

[0024] The preset fully connected neural network is used as the basic model. The input layer of the fully connected neural network receives the historical detection error value and the historical initial detection data. The output layer of the fully connected neural network outputs the historical intermediate detection data. When training the fully connected neural network, the cross entropy loss function is selected as the loss function. The loss function is minimized by the gradient descent method, and the weight parameters of the fully connected neural network are updated. Through iterative training, the data correction model is obtained.

[0025] Furthermore, the method of encrypting the target detection data includes:

[0026] The user's biometric information is obtained, and the target element in the target detection data is encrypted based on the biometric information and a preset encryption algorithm. The target element is an element in the target detection data whose comprehensive weight is greater than a preset weight threshold.

[0027] Furthermore, the method for encrypting the target element in the target detection data based on the biometric information and the preset encryption algorithm includes:

[0028] The timestamp and index information in the target detection data are obtained, the target element in the target detection data is determined based on the timestamp and index information, and the biometric information is embedded into the target element through a digital signature algorithm.

[0029] In a second aspect, a method for receiving healthy smart cloud data supporting multiple users is provided, which is based on the above-mentioned method for receiving healthy smart cloud data supporting multiple users and includes:

[0030] S10: Acquire detection device information and user's initial detection data, determine a detection deviation value based on the initial detection data, and mark each element in the initial detection data with an attention weight based on the detection deviation value;

[0031] S20: Construct a corresponding weight judgment matrix based on the initial detection data, and perform a consistency check on the weight judgment matrix. If the consistency check passes, the process proceeds to S40; if the consistency check fails, the process proceeds to S30.

[0032] S30: Generate a detection error value based on the detection device information, correct the initial detection data based on the detection error value to obtain intermediate detection data, use the intermediate detection data as the initial detection data, and return to S20;

[0033] S40: compressing the initial detection data to obtain target detection data, encrypting the target detection data, and sending the encrypted target detection data.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] The present invention first determines the detection deviation value based on the initial detection data, then marks the attention weight of each element in the initial detection data according to the detection deviation value, constructs a corresponding weight judgment matrix based on the initial detection data, and performs a consistency check on the weight judgment matrix. When the consistency check fails, the initial detection data is corrected. When the consistency check passes, the initial detection data is compressed to obtain target detection data, and the target detection data is encrypted. The present invention first calculates the detection deviation value and marks the attention weight, thereby ensuring that important elements in the data are processed first, avoiding repeated encryption and compression of all data, and passing the consistency check. After the initial detection data reaches consistency, compression and encryption are performed, ensuring that the compression algorithm can effectively process redundant information of the data, thereby improving compression efficiency, and ultimately reducing the computing burden and the amount of transmitted data, effectively improving real-time transmission efficiency and data processing performance in multi-user scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a schematic diagram of the structure of the intelligent cloud data health receiver supporting multiple users in the present invention;

[0037] Figure 2 Schematic diagram of the process of the intelligent cloud data health receiving method supporting multiple users in the present invention;

[0038] Figure 3 Schematic diagram of the process of constructing a corresponding weight judgment matrix based on initial detection data in the present invention;

[0039] Figure 4 Schematic diagram of the process of encrypting target detection data in the present invention. DETAILED DESCRIPTION

[0040] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0041] Example 1

[0042] See also Figure 1As shown, this embodiment discloses a smart cloud data health receiver supporting multiple users, including:

[0043] The first processing module is used to obtain detection device information and the user's initial detection data, determine the detection deviation value based on the initial detection data, and mark the attention weight of each element in the initial detection data based on the detection deviation value.

[0044] In this embodiment, the detection device refers to a device that can monitor the health of the user. The detection device can be a blood pressure meter, a blood glucose meter, a blood lipid meter, a weight scale, a urine analyzer, etc., or a composite device of the above instruments, such as a blood glucose and blood lipid monitor or a smart health monitoring bracelet, etc. The initial detection data refers to the health data about the user obtained through the detection device. Taking the detection device as a blood pressure meter as an example, the initial detection data can be the systolic blood pressure value, diastolic blood pressure value or pulse, etc.

[0045] Methods for determining a detection deviation value based on initial detection data include:

[0046] The initial detection data is fitted to construct a detection curve graph, the Euclidean distance between each element in the initial detection data and the nearest point in the detection curve graph is calculated, and the Euclidean distance is used as the detection deviation value corresponding to each element.

[0047] It should be noted that, taking the diastolic pressure value as an example of the initial detection data, each element in the initial detection data refers to the diastolic pressure value obtained in a measurement process, and the detection curve graph represents the changing trend of the diastolic pressure value. The nearest point in the detection curve graph refers to the point in the fitted detection curve graph with the smallest Euclidean distance from a certain element in the initial detection data (such as the diastolic pressure value). The fitting of the detection curve graph can be achieved through existing software such as MATLAB, and this embodiment will not go into details about this.

[0048] It should be added that, in the fitting process of the detection curve graph, each element in the initial detection data needs to be converted into an input data point of the curve fitting model, that is, each measurement value (element) of the diastolic pressure is converted into a coordinate point, and these coordinate points will be used to construct the detection curve graph in the fitting process. The nearest point in the detection curve graph refers to a point on the detection curve graph that is closest to an element (diastolic pressure value) in the initial detection data, that is, the point is the point in the detection curve graph with the smallest Euclidean distance from the actual measurement value.

[0049] The method of marking the attention weight of each element in the initial detection data based on the detection deviation value includes:

[0050] Normalize the detection deviation value, calculate the deviation ratio corresponding to the detection deviation value, and mark the attention weight according to the deviation ratio.

[0051] In this embodiment, the attention weight refers to the importance or attention of each element in the initial detection data when marking based on the detection deviation value. Specifically, the size of the attention weight reflects the relative importance or priority of a certain element (such as the diastolic blood pressure value) in the entire health monitoring data. It can be understood that the deviation ratio represents the degree of deviation of each element (such as the diastolic blood pressure value) from other elements in the initial detection data. Correspondingly, a high degree of deviation means that the element is more important in the initial detection data, and therefore a greater weight is given. The attention weight marking can allocate attention weights to each element in the initial detection data through the attention mechanism in the neural network. The attention mechanism refers to a mechanism that simulates human attention, which aims to improve data processing efficiency and effectiveness by assigning different "attention" or "weights" to different parts of the input data.

[0052] This embodiment obtains detection device information and the user's initial detection data, and combines it to determine the detection deviation value to accurately identify which elements in the initial detection data have significant deviations from the detection curve graph. This provides a basis for subsequent attention weight marking, so that important elements in the initial detection data can be given priority attention.

[0053] Judgment module: used to construct the corresponding weight judgment matrix based on the initial detection data, and perform consistency check on the weight judgment matrix. When the consistency check passes, it enters the encryption transmission module; when the consistency check fails, it enters the second processing module.

[0054] In this embodiment, Figure 3 As shown, the weight judgment matrix can be constructed by the expert scoring method in the analytic hierarchy process (AHP). The method of constructing the corresponding weight judgment matrix based on the initial detection data includes:

[0055] Obtain the detection time period corresponding to each element in the initial detection data, mark each element with a time weight according to the detection time period, multiply the attention weight and time weight corresponding to each element to obtain a comprehensive weight, and construct a weight judgment matrix based on the comprehensive weight corresponding to each element.

[0056] It should be noted that the detection time period refers to the time range or time point when health monitoring is carried out. Taking the initial detection data as the diastolic blood pressure value as an example, the detection time period can be every hour as a time period, or it can be a shorter or longer time unit, depending on the frequency of data collection and analysis requirements. Marking each element with time weight according to the detection time period means that during the health monitoring process, for each element (such as the diastolic blood pressure value), a weight value is assigned according to the detection time period to which it belongs. The weight value reflects the relative importance or impact of the time period in which the element is located on the health analysis. For example, for the diastolic blood pressure value, the morning (6:00-9:00) is a more important detection time period, because the diastolic blood pressure value in the morning is usually more relevant to health risks (such as hypertension, cardiovascular problems). Therefore, the morning time period has a greater impact on the assessment of health status.

[0057] It should be added that constructing a weight judgment matrix based on the comprehensive weight corresponding to each element means comparing the comprehensive weight corresponding to each element and using the ratio corresponding to the comprehensive weight as the value in the weight judgment matrix.

[0058] The methods for consistency testing of the weight judgment matrix include:

[0059] The consistency ratio corresponding to the weight judgment matrix is ​​calculated. When the consistency ratio is less than the preset ratio threshold, the consistency test passes. When the consistency ratio is greater than or equal to the preset ratio threshold, the consistency test fails.

[0060] The method for calculating the consistency ratio includes:

[0061]

[0062] In the formula, CR is the consistency ratio, WJ is represented by the weight judgment matrix, n is the dimension of the weight judgment matrix, λ is the eigenvalue corresponding to the weight judgment matrix, RI is the consistency index, λ max is the maximum eigenvalue corresponding to the weight judgment matrix, I is the identity matrix, and det(·) is the determinant function of the matrix.

[0063] It is not difficult to understand that if the weight judgment matrix is ​​a 5×5 matrix, then n is 5, for example:

[0064] Table 1 List of relative importance between different time periods

[0065] Time period Hour 1 Hour 2 Hour 3 Hour 4 Hour 5 Hour 1 1 1.14 0.78 1.28 1.07 Hour 2 0.88 1 0.68 1.14 1.07 Hour 3 1.28 1.47 1 1.67 1.13 Hour 4 0.78 0.88 0.60 1 0.89 Hour 5 0.93 0.93 0.89 1.12 1

[0066] It can be understood that Table 1 above is a weight judgment matrix constructed by the analytic hierarchy process (AHP), which is used to represent the relative importance between different time periods (for example, the first hour to the fifth hour). The value of the i-th row and j-th column in the weight judgment matrix (denoted as a ij ) represents the relative importance of the i-th time period and the j-th time period, a ij That is, the ratio between the comprehensive weight corresponding to the i-th time period and the comprehensive weight corresponding to the j-th time period. If n is 5, then according to the standard table in the analytic hierarchy process (AHP), the corresponding RI value is 1.12. The method to solve the consistency ratio can be to expand the WJ-λI matrix to obtain a polynomial about λ, called the characteristic polynomial. Solve this polynomial equation to obtain all the eigenvalues. The largest eigenvalue is λ max , and then the consistency ratio CR is obtained. It can be understood that the eigenvalue is an inherent property of the matrix. The eigenvalue is usually obtained by solving the formula through software tools such as Python's NumPy library. This embodiment will not go into details about this.

[0067] It should be added that the definition of the consistency ratio CR is based on the maximum eigenvalue of a real number. If the calculated maximum eigenvalue is a complex number, the consistency ratio CR will also be a complex number. Therefore, when the maximum eigenvalue obtained by solution is a complex number, if the imaginary part of the complex number is close to zero, the imaginary part can be ignored. If the imaginary part of the complex number is large, the parameters in the weight judgment matrix should be readjusted, and each element in the weight judgment matrix should be checked. The above-mentioned ratio threshold is pre-set by technical personnel in this field based on expert experience.

[0068] In this embodiment, the purpose of calculating the consistency ratio is to test whether the constructed weight judgment matrix meets the consistency requirements, so as to ensure that the relative importance relationship of the elements in the weight judgment matrix is ​​reasonable. When the consistency ratio is greater than or equal to the preset ratio threshold, it indicates that the constructed weight judgment matrix does not meet the consistency requirements, which means that the relative importance relationship of the elements in the matrix may be logically inconsistent, and the weight distribution may deviate from the actual situation, which may affect the accuracy of subsequent calculations and decisions. In order to ensure that the importance of each element of the initial detection data can be truly reflected, the unreasonable weight distribution must be adjusted. Therefore, each element in the initial detection data must be corrected so that the weight judgment matrix meets the consistency requirements, thereby ensuring that the comprehensive weight of each element in the initial detection data can accurately reflect its relative importance in health analysis.

[0069] The second processing module is used to generate a detection error value based on the detection equipment information, correct the initial detection data based on the detection error value, obtain intermediate detection data, use the intermediate detection data as the initial detection data, and return it to the judgment module.

[0070] In this embodiment, the detection device information includes average operating time, internal temperature value, average calibration times and real-time component temperature. The average operating time refers to the cumulative operating time of the detection device during use, reflecting the frequency of use of the device and its stability. The real-time component temperature refers to the surface temperature value of the core components in the detection device when working. Taking the detection device as a blood pressure monitor as an example, the core components can be pressure sensors and microprocessors, etc. The real-time component temperature can be the average temperature value obtained by weighted calculation of the surface temperature values ​​of several core components.

[0071] The method for generating a detection error value based on detection equipment information includes:

[0072] The detection error value is obtained by performing deviation calculation based on the average operating time, internal temperature value, average number of calibration times and real-time component temperature.

[0073] The specific methods for calculating the detection error value include:

[0074]

[0075] Where DEV is the detection error value, ACT is the average number of calibration times, AOT is the average operating time, CTV is rt is the real-time component temperature, CTV sd is the standard component temperature, ITV is the internal temperature value, L is a constant greater than 0, cosh(·) is the hyperbolic cosine function, sinh(·) is the hyperbolic sine function, ln[·] is the logarithmic function with e as the base, and e is a natural constant.

[0076] In this embodiment, the average number of calibrations and the real-time component temperature are used as examples. When the average number of calibrations is greater, it indicates that the detection device has undergone more calibrations, which means that the stability and measurement accuracy of the device are better. When the absolute value of the difference between the real-time component temperature and the standard component temperature is greater, it indicates that there is an abnormality in the working environment of the detection device or the status of the core components, which will cause deviations in the initial detection data. Therefore, from the above content, it can be seen that in this embodiment, the greater the detection error value, the more serious the degree of deviation in the initial detection data.

[0077] The method for correcting the initial detection data based on the detection error value to obtain the intermediate detection data includes:

[0078] The detection error value and the initial detection data are input into the pre-built data correction model to obtain intermediate detection data.

[0079] The method for constructing the data correction model includes:

[0080] The preset fully connected neural network is used as the basic model. The input layer of the fully connected neural network receives the historical detection error value and the historical initial detection data. The output layer of the fully connected neural network outputs the historical intermediate detection data. When training the fully connected neural network, the cross entropy loss function is selected as the loss function. The loss function is minimized by the gradient descent method, and the weight parameters of the fully connected neural network are updated. Through iterative training, the data correction model is obtained.

[0081] It is understandable that technicians in this field can simulate the working process of the detection equipment through experiments to obtain a sample data set. For example, during the experiment, the correspondence between the initial detection data and the standard detection data can be determined in advance. When the detection error value is large, it indicates that the deviation between the initial detection data and the standard detection data is serious. Therefore, the initial detection data needs to be callback processed to make it closer to the standard detection data, so as to obtain the corrected intermediate detection data.

[0082] This embodiment first obtains the detection equipment information and initial detection data, calculates the detection deviation value and performs attention weight marking, which can provide accurate basic data for the subsequent weight judgment matrix. Based on these data, the weight judgment matrix is ​​constructed and a consistency check is performed. If the consistency check passes, it means that the importance of each element in the initial detection data has been reasonably reflected, ensuring the reliability of data analysis. Only through this combination can it be ensured that the important elements in the initial detection data are given priority attention, thereby improving the accuracy of health analysis.

[0083] Encryption transmission module: used to compress the initial detection data to obtain target detection data, encrypt the target detection data, and send the encrypted target detection data.

[0084] It is understandable that the target detection data is the detection data obtained after the initial detection data is compressed. The purpose is to reduce the amount of data to improve data transmission efficiency and reduce the burden of storage and transmission in a multi-user environment.

[0085] like Figure 4 As shown, the method for encrypting target detection data includes:

[0086] The user's biometric information is obtained, and the target element in the target detection data is encrypted based on the biometric information and a preset encryption algorithm. The target element is an element in the target detection data whose comprehensive weight is greater than a preset weight threshold.

[0087] It should be noted that the biometric information may be the user's fingerprint information or facial information, and the encryption algorithm may be a hash algorithm or a digital signature algorithm.

[0088] The method for encrypting target elements in target detection data based on biometric information and a preset encryption algorithm includes:

[0089] The timestamp and index information in the target detection data are obtained, the target element in the target detection data is determined based on the timestamp and index information, and the biometric information is embedded into the target element through a digital signature algorithm.

[0090] It should be noted that after the initial detection data is compressed, not only the target detection data will be obtained, but also the corresponding metadata. Metadata refers to descriptive information about the target detection data. The metadata includes at least a timestamp and index information. The index information is used to identify and locate the unique identifier or offset of each element in the target detection data. Then, through the timestamp and index information, the target element can be found and encrypted without decompressing the target detection data. In this embodiment, a data signature algorithm is used for encryption. It can be understood that before encryption, the biometric information needs to be converted into a digital signature. Taking the biometric information as fingerprint information as an example, the fingerprint information needs to be converted into a set of feature points (for example, the ridges and bifurcation points of the fingerprint). These feature points represent the uniqueness of the fingerprint, and then hash processing is performed to generate the corresponding character string to complete the conversion. The digital signature algorithm is a prior art and this embodiment will not go into details about it.

[0091] This embodiment first determines the detection deviation value based on the initial detection data, then marks the attention weight of each element in the initial detection data according to the detection deviation value, constructs a corresponding weight judgment matrix based on the initial detection data, and performs a consistency check on the weight judgment matrix. When the consistency check fails, the initial detection data is corrected. When the consistency check passes, the initial detection data is compressed to obtain target detection data, and the target detection data is encrypted. This embodiment first calculates the detection deviation value and marks the attention weight, thereby ensuring that important elements in the data are processed first, avoiding repeated encryption and compression of all data, and passing the consistency check. After the initial detection data reaches consistency, compression and encryption are performed, ensuring that the compression algorithm can effectively process redundant information of the data, improving compression efficiency, and ultimately reducing the computing burden and the amount of transmitted data, effectively improving real-time transmission efficiency and data processing performance in multi-user scenarios.

[0092] Example 2

[0093] See also Figure 2 As shown, based on the same inventive concept, this embodiment discloses a method for receiving intelligent cloud data health data that supports multiple users. For details not provided in this embodiment, please refer to the description of the relevant parts in Example 1. The method includes:

[0094] S10: Acquire detection device information and the user's initial detection data, determine a detection deviation value based on the initial detection data, and mark the attention weight of each element in the initial detection data based on the detection deviation value.

[0095] Methods for determining a detection deviation value based on initial detection data include:

[0096] The initial detection data is fitted to construct a detection curve graph, the Euclidean distance between each element in the initial detection data and the nearest point in the detection curve graph is calculated, and the Euclidean distance is used as the detection deviation value corresponding to each element.

[0097] The method of marking the attention weight of each element in the initial detection data based on the detection deviation value includes:

[0098] Normalize the detection deviation value, calculate the deviation ratio corresponding to the detection deviation value, and mark the attention weight according to the deviation ratio.

[0099] S20: Construct a corresponding weight judgment matrix based on the initial detection data, and perform a consistency check on the weight judgment matrix. When the consistency check passes, the process proceeds to S40; when the consistency check fails, the process proceeds to S30.

[0100] In this embodiment, the weight judgment matrix can be constructed by the expert scoring method in the analytic hierarchy process (AHP). The method of constructing the corresponding weight judgment matrix based on the initial detection data includes:

[0101] Obtain the detection time period corresponding to each element in the initial detection data, mark each element with a time weight according to the detection time period, multiply the attention weight and time weight corresponding to each element to obtain a comprehensive weight, and construct a weight judgment matrix based on the comprehensive weight corresponding to each element.

[0102] The methods for consistency testing of the weight judgment matrix include:

[0103] The consistency ratio corresponding to the weight judgment matrix is ​​calculated. When the consistency ratio is less than the preset ratio threshold, the consistency test passes. When the consistency ratio is greater than or equal to the preset ratio threshold, the consistency test fails.

[0104] The method for calculating the consistency ratio includes:

[0105]

[0106] In the formula, CR is the consistency ratio, WJ is represented by the weight judgment matrix, n is the dimension of the weight judgment matrix, λ is the eigenvalue corresponding to the weight judgment matrix, RI is the consistency index, λ maxis the maximum eigenvalue corresponding to the weight judgment matrix, I is the identity matrix, and det(·) is the determinant function of the matrix.

[0107] S30: Generate a detection error value based on the detection device information, correct the initial detection data based on the detection error value to obtain intermediate detection data, use the intermediate detection data as the initial detection data, and return to S20.

[0108] In this embodiment, the detection device information includes average operating time, internal temperature value, average calibration times and real-time component temperature. The average operating time refers to the cumulative operating time of the detection device during use, reflecting the frequency of use of the device and its stability. The real-time component temperature refers to the surface temperature value of the core components in the detection device when working. Taking the detection device as a blood pressure monitor as an example, the core components can be pressure sensors and microprocessors, etc. The real-time component temperature can be the average temperature value obtained by weighted calculation of the surface temperature values ​​of several core components.

[0109] The method for generating a detection error value based on detection equipment information includes:

[0110] The detection error value is obtained by performing deviation calculation based on the average operating time, internal temperature value, average number of calibration times and real-time component temperature.

[0111] The specific methods for calculating the detection error value include:

[0112]

[0113] Where DEV is the detection error value, ACT is the average number of calibration times, AOT is the average operating time, CTV is rt is the real-time component temperature, CTV sd is the standard component temperature, ITV is the internal temperature value, L is a constant greater than 0, cosh(·) is the hyperbolic cosine function, sinh(·) is the hyperbolic sine function, ln[· is the logarithmic function with e as the base, and e is a natural constant.

[0114] The method for correcting the initial detection data based on the detection error value to obtain the intermediate detection data includes:

[0115] The detection error value and the initial detection data are input into the pre-built data correction model to obtain intermediate detection data.

[0116] The method for constructing the data correction model includes:

[0117] The preset fully connected neural network is used as the basic model. The input layer of the fully connected neural network receives the historical detection error value and the historical initial detection data. The output layer of the fully connected neural network outputs the historical intermediate detection data. When training the fully connected neural network, the cross entropy loss function is selected as the loss function. The loss function is minimized by the gradient descent method, and the weight parameters of the fully connected neural network are updated. Through iterative training, the data correction model is obtained.

[0118] S40: compressing the initial detection data to obtain target detection data, encrypting the target detection data, and sending the encrypted target detection data.

[0119] Methods for encrypting target detection data include:

[0120] The user's biometric information is obtained, and the target element in the target detection data is encrypted based on the biometric information and a preset encryption algorithm. The target element is an element in the target detection data whose comprehensive weight is greater than a preset weight threshold.

[0121] It should be noted that the biometric information may be the user's fingerprint information or facial information, and the encryption algorithm may be a hash algorithm or a digital signature algorithm.

[0122] The method for encrypting target elements in target detection data based on biometric information and a preset encryption algorithm includes:

[0123] The timestamp and index information in the target detection data are obtained, the target element in the target detection data is determined based on the timestamp and index information, and the biometric information is embedded into the target element through a digital signature algorithm.

[0124] The above embodiments can be implemented in whole or in part through software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired or wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, or a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0125] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0126] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0127] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only one type. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0128] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0129] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0130] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

[0131] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An intelligent cloud data health receiver that supports multiple users, characterized by: include: The first processing module is used to obtain detection device information and the user's initial detection data, determine a detection deviation value based on the initial detection data, and mark the attention weight of each element in the initial detection data based on the detection deviation value; Judgment module: used to construct the corresponding weight judgment matrix based on the initial detection data, and perform consistency check on the weight judgment matrix. If the consistency check passes, it will be transferred to the encryption transmission module; if the consistency check fails, it will be transferred to the second processing module; The method for constructing a corresponding weight judgment matrix based on the initial detection data includes: obtaining a detection time period corresponding to each element in the initial detection data, marking each element with a time weight according to the detection time period, multiplying the attention weight and the time weight corresponding to each element to obtain a comprehensive weight, and constructing a weight judgment matrix according to the comprehensive weight corresponding to each element; A second processing module is configured to generate a detection error value based on the detection device information, correct the initial detection data based on the detection error value to obtain intermediate detection data, use the intermediate detection data as the initial detection data, and return the intermediate detection data to the judgment module; Encryption transmission module: used to compress the initial detection data to obtain target detection data, encrypt the target detection data, and send the encrypted target detection data.

2. The multi-user intelligent cloud data health receiver according to claim 1, characterized in that: The method for determining the detection deviation value based on the initial detection data includes: fitting the initial detection data to construct a detection curve graph, calculating the Euclidean distance between each element in the initial detection data and the nearest point in the detection curve graph, and using the Euclidean distance as the detection deviation value corresponding to each element.

3. The multi-user intelligent cloud data health receiver according to claim 1, characterized in that: The method for performing consistency check on the weight judgment matrix includes: calculating the consistency ratio corresponding to the weight judgment matrix, when the consistency ratio is less than a preset ratio threshold, the consistency check passes, and when the consistency ratio is greater than or equal to the preset ratio threshold, the consistency check fails.

4. The multi-user intelligent cloud data health receiver according to claim 1, characterized in that: The detection equipment information includes average operating time, internal temperature value, average calibration times and real-time component temperature. The method for generating a detection error value based on the detection equipment information includes: performing deviation calculation based on the average operating time, internal temperature value, average calibration times and real-time component temperature to obtain a detection error value.

5. The multi-user intelligent cloud data health receiver according to claim 4, characterized in that: The method of correcting the initial detection data based on the detection error value to obtain the intermediate detection data includes: inputting the detection error value and the initial detection data into a pre-built data correction model to obtain the intermediate detection data; The method for constructing the data correction model includes: The preset fully connected neural network is used as the basic model. The input layer of the fully connected neural network receives the historical detection error value and the historical initial detection data. The output layer of the fully connected neural network outputs the historical intermediate detection data. When training the fully connected neural network, the cross entropy loss function is selected as the loss function. The loss function is minimized by the gradient descent method, and the weight parameters of the fully connected neural network are updated. Through iterative training, the data correction model is obtained.

6. The multi-user intelligent cloud data health receiver according to claim 1, characterized in that: The method for encrypting target detection data includes: obtaining the user's biometric information, and encrypting the target element in the target detection data based on the biometric information and a preset encryption algorithm, wherein the target element is an element in the target detection data whose comprehensive weight is greater than a preset weight threshold.

7. The multi-user intelligent cloud data health receiver according to claim 6, characterized in that: The method for encrypting the target element in the target detection data based on biometric information and a preset encryption algorithm includes: obtaining the timestamp and index information in the target detection data, determining the target element in the target detection data based on the timestamp and index information, and embedding the biometric information into the target element through a digital signature algorithm.

8. A method for receiving healthy smart cloud data supporting multiple users, which is implemented based on the intelligent cloud data health receiver supporting multiple users according to any one of claims 1 to 7, characterized in that: include: S10: Acquire detection device information and user's initial detection data, determine a detection deviation value based on the initial detection data, and mark each element in the initial detection data with an attention weight based on the detection deviation value; S20: Construct a corresponding weight judgment matrix based on the initial detection data, and perform a consistency check on the weight judgment matrix. If the consistency check passes, the process proceeds to S40; if the consistency check fails, the process proceeds to S30. S30: Generate a detection error value based on the detection device information, correct the initial detection data based on the detection error value to obtain intermediate detection data, use the intermediate detection data as the initial detection data, and return to S20; S40: compressing the initial detection data to obtain target detection data, encrypting the target detection data, and sending the encrypted target detection data.

Images