A digital screening and remote detection method for comprehensive assessment of the elderly

Abstract

The present invention relates to the technical field of comprehensive evaluation of the elderly, and discloses a digital screening and remote detection method for comprehensive evaluation of the elderly, the method comprising: collecting vital sign data of the elderly and performing denoising processing, performing abnormal identification on the denoised vital sign data of the elderly, dividing the vital sign data of the elderly into normal data clusters and abnormal data clusters, and removing the abnormal data clusters to obtain corrected vital sign data of the elderly; and using an elderly health evaluation model to perform remote health evaluation on different elderly people. The present invention constructs a sequence influence that characterizes the relationship between a data sequence and a surrounding sequence to correct the distance between different data sequences, calculates different weighted sign deviations according to digital indicators of data sequences corresponding to different signs, the higher the weighted sign deviation, the higher the difference between the sign and other signs, maps the weighted sign deviations of different signs, constitutes the health of the elderly, and realizes remote health detection of the elderly.

Description

Technical Field

[0001] The present invention relates to the technical field of comprehensive evaluation of the elderly, and in particular to a digital screening and remote detection method for comprehensive evaluation of the elderly. Background Art

[0002] As the global aging process accelerates, the health issues of the elderly are receiving increasing attention. As a systematic multidimensional assessment tool, comprehensive geriatric assessment aims to fully understand the physical, psychological, social and functional status of elderly patients, so as to develop personalized intervention plans to improve the quality of life of the elderly and delay functional decline. Traditional comprehensive geriatric assessment is usually conducted in a clinical setting, with the participation of a multidisciplinary team including doctors, nurses, nutritionists, psychologists and social workers. Although this method is widely recognized as effective, it faces many challenges in actual operation due to the large base of the elderly population and limited medical resources.

[0003] With the rapid development of information technology and medical technology, comprehensive elderly assessment methods based on digital and remote technologies have gradually become a research hotspot. Digital screening and remote testing can not only improve assessment efficiency, but also cover more elderly people, especially those living in remote areas or with limited mobility. Using smart devices, sensors and remote monitoring systems, the health data of the elderly can be collected, transmitted and analyzed in real time, providing more accurate data support for medical decision-making. Summary of the invention

[0004] In view of this, the present invention proposes a digital screening and remote detection method for comprehensive assessment of the elderly, which conducts multi-dimensional assessment through digitalization and remote detection technology, comprehensively understands the health status of the elderly, and provides personalized intervention measures for them.

[0005] To achieve the above-mentioned purpose, the present invention provides a digital screening and remote detection method for comprehensive evaluation of the elderly, comprising the following steps:

[0006] S1: Collecting the vital sign data of the elderly through sensors and performing denoising processing to obtain the denoised vital sign data of the elderly;

[0007] S2: performing abnormal identification on the denoised elderly vital sign data, dividing the elderly vital sign data into normal data clusters and abnormal data clusters, and removing the abnormal data clusters to obtain corrected elderly vital sign data;

[0008] S3: constructing a health assessment model for the elderly, wherein the health assessment model for the elderly takes the corrected vital sign data of the elderly as input and takes the health assessment result of the elderly as output, wherein the improved cloud model is an implementation method of the health assessment model for the elderly;

[0009] S4: Use the elderly health assessment model to conduct remote health assessment of different elderly people.

[0010] As a further improvement method of the present invention:

[0011] Optionally, collecting the vital sign data of the elderly by means of sensors in step S1 includes:

[0012] The vital sign data of the elderly are collected through sensors, where the sensors are wearable, wirelessly communicating sensor devices, including heart rate sensors, temperature sensors, and acceleration sensors. The sensor devices are worn on the elderly to collect the vital sign data of the elderly. The collected vital sign data of the elderly are in the form of:

[0013] ;

[0014] in:

[0015] represents the data sequence of the nth physical sign of the elderly collected, represents the data value of the nth physical sign of the elderly at M sampling moments, represents the data value of the nth physical sign of the elderly at the mth sampling moment; wherein N represents the number of types of physical signs of the elderly; in the embodiment of the present invention, the physical signs of the elderly include heart rate, body temperature, and accelerations of different body parts in various postures;

[0016] Indicates the collected data of vital signs of the elderly;

[0017] The elderly vital sign data x is denoised to obtain denoised elderly vital sign data X, and the denoised elderly vital sign data X is sent to a remote server via wireless transmission.

[0018] Optionally, the denoising process is performed on the elderly physical sign data x to obtain the denoised elderly physical sign data X, including:

[0019] De-noising is performed on all data sequences in the elderly's physical sign data x, where the data sequence The denoising process is as follows:

[0020] S11: Constructing a sequence for data The filter for denoising processing sets the maximum order of the filter to D, the current order to d, the initial value of d to 1, and initializes the filter coefficients of the generated filter , filter coefficient The d-order iteration result is ;

[0021] S12: Use a filter of order d to filter the data sequence Perform filtering, where the filtering result is:

[0022] ;

[0023] in:

[0024] T stands for transpose;

[0025] represents a random noise sequence;

[0026] Represents the filter with order d on the data sequence A filtering result of filtering processing;

[0027] S13: Calculate the filtering result The error:

[0028] ;

[0029] in:

[0030] Indicates the filtering result The error of

[0031] represents the L2 norm;

[0032] like If it is less than the preset threshold, ,Will As a data series The denoising result of

[0033] Otherwise, go to step S14;

[0034] S14: Update the filter order:

[0035] ;

[0036] in:

[0037] represents an exponential function with a natural constant as base;

[0038] S15: Order , return to step S12.

[0039] Optionally, in step S2, abnormality identification is performed on the denoised vital sign data of the elderly, and the vital sign data of the elderly is divided into a normal data cluster and an abnormal data cluster, including:

[0040] The remote server performs anomaly recognition on the denoised vital sign data of the elderly and divides the vital sign data of the elderly into normal data clusters and abnormal data clusters. The anomaly recognition process is as follows:

[0041] S21: The remote server obtains the denoised vital sign data X of the elderly:

[0042] ;

[0043] in:

[0044] Represents a data sequence The denoising result is Represents data value The filtering result of

[0045] S22: Calculate the sequence distance between any two sets of denoised data sequences, where the denoised data sequence and The sequence distance is:

[0046] ;

[0047] ;

[0048] in:

[0049] Represents the denoised data sequence and The sequence distance of ;

[0050] Represents the denoised data sequence and The structural similarity distance of is the denoised data sequence The mean of is the denoised data sequence The mean of is the denoised data sequence The standard deviation of is the denoised data sequence The standard deviation of

[0051] represents the mean control coefficient, Set to 0.01;

[0052] is the standard deviation control coefficient, Set to 0.02;

[0053] S23: Obtain the K nearest neighboring denoised data sequences of any denoised data sequence to form a nearest neighbor sequence set of the denoised data sequence, and calculate the distance between the denoised data sequence and the nearest neighboring denoised data sequence in the corresponding nearest neighbor sequence set, where the denoised data sequence The mean distance to all nearest denoised data sequences is , the distance standard deviation is ;

[0054] S24: Calculate the sequence influence of any denoised data sequence, where the denoised data sequence The sequence influence of is:

[0055] ;

[0056] in:

[0057] Represents the denoised data sequence The sequence influence of

[0058] S25: Convert sequence distance to sequence influence distance, where sequence distance The conversion formula is:

[0059] ;

[0060] in:

[0061] is the sequence distance The corresponding sequence influences the distance;

[0062] S26: Calculate the influence density of any denoised data sequence, where the denoised data sequence The influence density is:

[0063] ;

[0064] in:

[0065] Represents the denoised data sequence The impact density;

[0066] represents the cutoff distance;

[0067] represents the L1 norm;

[0068] Represents the denoised data sequence The set of nearest neighbor sequences of , Represents the denoised data sequence Any nearest neighbor denoised data sequence of ;

[0069] S27: Calculate the offset distance of any denoised data sequence, where the denoised data sequence The offset distance is:

[0070] ;

[0071] in:

[0072] Represents the denoised data sequence In the embodiment of the present invention, if the denoised data sequence The influence density of is the maximum value among the N denoised data sequences, then the denoised data sequence The maximum distance from all the nearest denoised data sequences is taken as the offset distance;

[0073] S28: Calculate any denoised data sequence as the cluster center index of the cluster center, where the denoised data sequence The cluster center index is:

[0074] ;

[0075] in:

[0076] Represents the denoised data sequence The cluster center index of

[0077] The denoised data sequences whose cluster center index is less than the preset threshold are regarded as abnormal data clusters, and the abnormal data clusters are eliminated to obtain the corrected vital sign data of the elderly.

[0078] Optionally, the step of removing abnormal data clusters to obtain corrected vital sign data of the elderly includes:

[0079] The abnormal data clusters are removed to obtain the corrected vital signs data of the elderly, where the corrected vital signs data of the elderly are:

[0080] ;

[0081] in:

[0082] Y represents the corrected vital sign data of the elderly, H represents the number of denoised data sequences retained, represents the hth group of denoised data sequence retained, Represents the denoised data sequence The data value at the mth sampling time.

[0083] Optionally, constructing the elderly health assessment model in step S3 includes:

[0084] A health assessment model for the elderly is constructed, wherein the health assessment model for the elderly takes the corrected vital sign data of the elderly as input and takes the health assessment result of the elderly as output, wherein the improved cloud model is the implementation method of the health assessment model for the elderly, wherein the health assessment model for the elderly comprises an input layer, a vital sign weight calculation layer, a digital feature extraction layer, a weighted vital sign deviation calculation layer and a health assessment layer, wherein the input layer is used to receive the corrected vital sign data of the elderly, the vital sign weight calculation layer is used to perform vital sign weight calculation on the received data sequence representing different vital signs of the elderly, the digital feature extraction layer is used to extract the digital features of the vital signs of the elderly, the weighted vital sign deviation calculation layer is used to calculate the sequence deviation of different vital signs of the elderly, and perform weighted processing of the sequence deviation with the vital sign weight to form a weighted vital sign deviation, and the health assessment layer is used to map the weighted vital sign deviation to the health assessment result of the elderly.

[0085] Optionally, in step S4, the health assessment model for the elderly is used to assess the health of different elderly people, including:

[0086] The remote server uses the elderly health assessment model to conduct remote health assessment on different elderly people, where the corrected elderly physical sign data The corresponding remote health assessment process for the elderly is as follows:

[0087] S41: The input layer receives the corrected vital signs data of the elderly ;

[0088] S42: The physical sign weight calculation layer calculates the physical sign weights of the received data sequences representing different physical signs of the elderly, wherein the data sequences The corresponding sign weights are:

[0089] ;

[0090] ;

[0091] ;

[0092] ;

[0093] in:

[0094] For data series The corresponding weight of the physical sign;

[0095] Represents a data sequence The abnormality, Represents a data sequence The coefficient of variation, Represents a data sequence Information entropy of

[0096] express The maximum value in Represents a data sequence Signs of elderly people, Indicates preset signs of elderly people Maximum value;

[0097] Represents a data sequence The standard deviation of

[0098] Represents a data sequence The mean of

[0099] S43: The digital feature extraction layer extracts digital features of the elderly’s physical signs. The digital feature extraction results are:

[0100] ;

[0101] ;

[0102] ;

[0103] in:

[0104] Signs of old age The corresponding digital features are For data series The entropy of For data series of super entropy;

[0105] S44: The weighted physical sign deviation calculation layer calculates the sequence deviation of different elderly physical signs, where the elderly physical signs The sequence deviation is:

[0106] ;

[0107] ;

[0108] in:

[0109] Signs of old age The sequence deviation of

[0110] Signs of old age and sequence differences;

[0111] Deviance of the sequence Perform weighted processing on the physical sign weights to form the weighted physical sign deviation :

[0112] ;

[0113] S45: The health assessment layer maps the weighted physical sign deviation to the health assessment result of the elderly:

[0114] ;

[0115] in:

[0116] Signs for the elderly The corresponding mapping weight matrix;

[0117] represents the health assessment results of the elderly. The higher the value, the healthier the elderly are. If the elderly’s health assessment result is lower than the preset health threshold, it means that the elderly may be unwell.

[0118] In order to solve the above problem, the present invention provides an electronic device, the electronic device comprising:

[0119] A memory storing at least one instruction;

[0120] Communication interface, enabling electronic equipment to communicate; and

[0121] The processor executes the instructions stored in the memory to implement the digital screening and remote detection method for comprehensive assessment of the elderly as described above.

[0122] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the digital screening and remote detection method for comprehensive assessment of the elderly as described above.

[0123] Compared with the prior art, the present invention proposes a digital screening and remote detection method for comprehensive evaluation of the elderly, which has the following advantages:

[0124] First, this scheme uses wearable and communicative sensor devices to collect data sequences of different physical signs of the elderly, realizes remote data collection of the health status of the elderly, and iterates different physical signs to obtain different filters, and performs adaptive filtering and noise reduction processing on the data sequence to avoid the noise signal of the sensor device from seriously affecting the accuracy of health status detection. In combination with the data feature distribution of the data sequence, the sequence influence that characterizes the relationship between the data sequence and the surrounding sequences is constructed, and then the distance between different data sequences is corrected. The greater the sequence influence, the greater the impact of the data sequence on other sequences. Then, the influence density of different data sequences is calculated as the degree of aggregation of the data sequence. The lower the degree of aggregation of the data sequence, the less effective information the sequence contains, the fewer surrounding sequences, and the higher the probability of being an abnormal data sequence, thereby realizing the elimination of invalid data sequences and improving the accuracy of health assessment.

[0125] At the same time, this scheme calculates different weighted sign deviations based on the digital indicators of the data sequences corresponding to different signs. The higher the weighted sign deviation, the greater the difference between the sign and other signs. The weighted sign deviations of different signs are mapped to form the health of the elderly and realize remote health detection of the elderly. BRIEF DESCRIPTION OF THE DRAWINGS

[0126] Figure 1 A flowchart of a digital screening and remote detection method for comprehensive assessment of the elderly provided by one embodiment of the present invention;

[0127] Figure 2 A schematic diagram of the structure of an electronic device for implementing a digital screening and remote detection method for comprehensive assessment of the elderly provided in one embodiment of the present invention.

[0128] In the figure: 1 electronic device, 10 processor, 11 memory, 12 program, 13 communication interface.

[0129] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0130] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0131] The embodiment of the present application provides a digital screening and remote detection method for comprehensive assessment of the elderly. The execution subject of the digital screening and remote detection method for comprehensive assessment of the elderly includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided in the embodiment of the present application. In other words, the digital screening and remote detection method for comprehensive assessment of the elderly can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0132] Embodiment 1:

[0133] S1: Collect the vital sign data of the elderly through sensors and perform denoising processing to obtain the denoised vital sign data of the elderly.

[0134] In step S1, the vital sign data of the elderly is collected by sensors, including:

[0135] The vital sign data of the elderly are collected through sensors, where the sensors are wearable, wirelessly communicating sensor devices, including heart rate sensors, temperature sensors, and acceleration sensors. The sensor devices are worn on the elderly to collect the vital sign data of the elderly. The collected vital sign data of the elderly are in the form of:

[0136] ;

[0137] in:

[0138] represents the data sequence of the nth physical sign of the elderly collected, represents the data value of the nth physical sign of the elderly at M sampling moments, represents the data value of the nth physical sign of the elderly at the mth sampling moment; wherein N represents the number of types of physical signs of the elderly; in the embodiment of the present invention, the physical signs of the elderly include heart rate, body temperature, and accelerations of different body parts in various postures;

[0139] Indicates the collected data of vital signs of the elderly;

[0140] The elderly vital sign data x is denoised to obtain denoised elderly vital sign data X, and the denoised elderly vital sign data X is sent to a remote server via wireless transmission.

[0141] The denoising process is performed on the elderly physical sign data x to obtain the denoised elderly physical sign data X, including:

[0142] De-noising is performed on all data sequences in the elderly's physical sign data x, where the data sequence The denoising process is as follows:

[0143] S11: Constructing a sequence for data The filter for denoising processing sets the maximum order of the filter to D, the current order to d, the initial value of d to 1, and initializes the filter coefficients of the generated filter , filter coefficient The d-order iteration result is ;

[0144] S12: Use a filter of order d to filter the data sequence Perform filtering, where the filtering result is:

[0145] ;

[0146] in:

[0147] T stands for transpose;

[0148] represents a random noise sequence;

[0149] Represents the filter with order d on the data sequence A filtering result of filtering processing;

[0150] S13: Calculate the filtering result The error:

[0151] ;

[0152] in:

[0153] Indicates the filtering result The error of

[0154] represents the L2 norm;

[0155] like If it is less than the preset threshold, ,Will As a data series The denoising result of

[0156] Otherwise, go to step S14;

[0157] S14: Update the filter order:

[0158] ;

[0159] in:

[0160] represents an exponential function with a natural constant as base;

[0161] S15: Order , return to step S12.

[0162] S2: Perform abnormality identification on the denoised vital sign data of the elderly, divide the vital sign data of the elderly into normal data clusters and abnormal data clusters, and eliminate the abnormal data clusters to obtain corrected vital sign data of the elderly.

[0163] In the step S2, abnormality identification is performed on the denoised vital sign data of the elderly, and the vital sign data of the elderly is divided into a normal data cluster and an abnormal data cluster, including:

[0164] The remote server performs anomaly recognition on the denoised vital sign data of the elderly and divides the vital sign data of the elderly into normal data clusters and abnormal data clusters. The anomaly recognition process is as follows:

[0165] S21: The remote server obtains the denoised vital sign data X of the elderly:

[0166] ;

[0167] in:

[0168] Represents a data sequence The denoising result is Represents data value The filtering result of

[0169] S22: Calculate the sequence distance between any two sets of denoised data sequences, where the denoised data sequence and The sequence distance is:

[0170] ;

[0171] ;

[0172] in:

[0173] Represents the denoised data sequence and The sequence distance of ;

[0174] Represents the denoised data sequence and The structural similarity distance of is the denoised data sequence The mean of is the denoised data sequence The mean of is the denoised data sequence The standard deviation of is the denoised data sequence The standard deviation of

[0175] represents the mean control coefficient, Set to 0.01;

[0176] is the standard deviation control coefficient, Set to 0.02;

[0177] S23: Obtain the K nearest neighboring denoised data sequences of any denoised data sequence to form a nearest neighbor sequence set of the denoised data sequence, and calculate the distance between the denoised data sequence and the nearest neighboring denoised data sequence in the corresponding nearest neighbor sequence set, where the denoised data sequence The mean distance to all nearest denoised data sequences is , the distance standard deviation is ;

[0178] S24: Calculate the sequence influence of any denoised data sequence, where the denoised data sequence The sequence influence of is:

[0179] ;

[0180] in:

[0181] Represents the denoised data sequence The sequence influence of

[0182] S25: Convert sequence distance to sequence influence distance, where sequence distance The conversion formula is:

[0183] ;

[0184] in:

[0185] is the sequence distance The corresponding sequence influences the distance;

[0186] S26: Calculate the influence density of any denoised data sequence, where the denoised data sequence The influence density is:

[0187] ;

[0188] in:

[0189] Represents the denoised data sequence The impact density;

[0190] represents the cutoff distance;

[0191] represents the L1 norm;

[0192] Represents the denoised data sequence The set of nearest neighbor sequences of , Represents the denoised data sequence Any nearest neighbor denoised data sequence of ;

[0193] S27: Calculate the offset distance of any denoised data sequence, where the denoised data sequence The offset distance is:

[0194] ;

[0195] in:

[0196] Represents the denoised data sequence In the embodiment of the present invention, if the denoised data sequence The influence density of is the maximum value among the N denoised data sequences, then the denoised data sequence The maximum distance from all the nearest denoised data sequences is taken as the offset distance;

[0197] S28: Calculate any denoised data sequence as the cluster center index of the cluster center, where the denoised data sequence The cluster center index is:

[0198] ;

[0199] in:

[0200] Represents the denoised data sequence The cluster center index of

[0201] The denoised data sequences whose cluster center index is less than the preset threshold are regarded as abnormal data clusters, and the abnormal data clusters are eliminated to obtain the corrected vital sign data of the elderly.

[0202] The method of eliminating abnormal data clusters to obtain corrected elderly people's vital sign data includes:

[0203] The abnormal data clusters are removed to obtain the corrected vital signs data of the elderly, where the corrected vital signs data of the elderly are:

[0204] ;

[0205] in:

[0206] Y represents the corrected vital sign data of the elderly, H represents the number of denoised data sequences retained, represents the hth group of denoised data sequence retained, Represents the denoised data sequence The data value at the mth sampling time.

[0207] S3: Constructing a health assessment model for the elderly, wherein the health assessment model for the elderly takes the corrected vital sign data of the elderly as input and takes the health assessment result of the elderly as output.

[0208] The step S3 constructs a health assessment model for the elderly, including:

[0209] A health assessment model for the elderly is constructed, wherein the health assessment model for the elderly takes the corrected vital sign data of the elderly as input and takes the health assessment result of the elderly as output, wherein the improved cloud model is the implementation method of the health assessment model for the elderly, wherein the health assessment model for the elderly comprises an input layer, a vital sign weight calculation layer, a digital feature extraction layer, a weighted vital sign deviation calculation layer and a health assessment layer, wherein the input layer is used to receive the corrected vital sign data of the elderly, the vital sign weight calculation layer is used to perform vital sign weight calculation on the received data sequence representing different vital signs of the elderly, the digital feature extraction layer is used to extract the digital features of the vital signs of the elderly, the weighted vital sign deviation calculation layer is used to calculate the sequence deviation of different vital signs of the elderly, and perform weighted processing of the sequence deviation with the vital sign weight to form a weighted vital sign deviation, and the health assessment layer is used to map the weighted vital sign deviation to the health assessment result of the elderly.

[0210] S4: Use the elderly health assessment model to conduct remote health assessment of different elderly people.

[0211] In step S4, the health assessment model for the elderly is used to assess the health of different elderly people, including:

[0212] The remote server uses the elderly health assessment model to conduct remote health assessment on different elderly people, where the corrected elderly physical sign data The corresponding remote health assessment process for the elderly is as follows:

[0213] S41: The input layer receives the corrected vital signs data of the elderly ;

[0214] S42: The physical sign weight calculation layer calculates the physical sign weights of the received data sequences representing different physical signs of the elderly, wherein the data sequences The corresponding sign weights are:

[0215] ;

[0216] ;

[0217] ;

[0218] ;

[0219] in:

[0220] For data series The corresponding weight of the physical sign;

[0221] Represents a data sequence The abnormality, Represents a data sequence The coefficient of variation, Represents a data sequence Information entropy of

[0222] express The maximum value in Represents a data sequence Signs of elderly people, Indicates preset signs of elderly people Maximum value;

[0223] Represents a data sequence The standard deviation of

[0224] Represents a data sequence The mean of

[0225] S43: The digital feature extraction layer extracts digital features of the elderly’s physical signs. The digital feature extraction results are:

[0226] ;

[0227] ;

[0228] ;

[0229] in:

[0230] Signs of old age The corresponding digital features are For data series The entropy of For data series of super entropy;

[0231] S44: The weighted physical sign deviation calculation layer calculates the sequence deviation of different elderly physical signs, where the elderly physical signs The sequence deviation is:

[0232] ;

[0233] ;

[0234] in:

[0235] Signs of old age The sequence deviation of

[0236] Signs of old age and sequence differences;

[0237] Deviance of the sequence Perform weighted processing on the physical sign weights to form the weighted physical sign deviation :

[0238] ;

[0239] S45: The health assessment layer maps the weighted physical sign deviation to the health assessment result of the elderly:

[0240] ;

[0241] in:

[0242] Signs for the elderly The corresponding mapping weight matrix;

[0243] represents the health assessment results of the elderly. The higher the value, the healthier the elderly are. If the elderly’s health assessment result is lower than the preset health threshold, it means that the elderly may be unwell.

[0244] Embodiment 2:

[0245] like Figure 2 , which is a schematic diagram of the structure of an electronic device for implementing a digital screening and remote detection method for comprehensive assessment of the elderly provided by an embodiment of the present invention.

[0246] The electronic device 1 may include a processor 10 , a memory 11 , a communication interface 13 and a bus, and may also include a computer program stored in the memory 11 and executable on the processor 10 , such as a program 12 .

[0247] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 11 may not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the program 12, etc., but also be used to temporarily store data that has been output or is to be output.

[0248] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (such as programs 12 for realizing digital screening and remote detection of comprehensive assessment of the elderly), and calls data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

[0249] The communication interface 13 may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices, and to achieve connection and communication between internal components of the electronic device.

[0250] The bus may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0251] Figure 2 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 2 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0252] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0253] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0254] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0255] The program 12 stored in the memory 11 in the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve:

[0256] The vital sign data of the elderly are collected by sensors and denoised to obtain the denoised vital sign data of the elderly;

[0257] Perform abnormal identification on the denoised vital sign data of the elderly, divide the vital sign data of the elderly into normal data clusters and abnormal data clusters, and remove the abnormal data clusters to obtain corrected vital sign data of the elderly;

[0258] Construct a health assessment model for the elderly;

[0259] The elderly health assessment model is used to conduct remote health assessment of different elderly people.

[0260] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figure 1 to Figure 2 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0261] It should be noted that the serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. And the terms "including", "comprising" or any other variants thereof in this article are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "including a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0262] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0263] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A digital screening and remote detection method for comprehensive assessment of the elderly, characterized in that: The method comprises: S1: Collecting the vital sign data of the elderly through sensors and performing denoising processing to obtain the denoised vital sign data of the elderly; S2: performing abnormal identification on the denoised elderly vital sign data, dividing the elderly vital sign data into normal data clusters and abnormal data clusters, and removing the abnormal data clusters to obtain corrected elderly vital sign data; S3: constructing a health assessment model for the elderly, wherein the health assessment model for the elderly takes the corrected physical sign data of the elderly as input and takes the health assessment result of the elderly as output; The elderly health assessment model takes the corrected elderly vital sign data as input and takes the elderly health assessment result as output, wherein the elderly health assessment model includes an input layer, a vital sign weight calculation layer, a digital feature extraction layer, a weighted vital sign deviation calculation layer and a health assessment layer, wherein the input layer is used to receive the corrected elderly vital sign data, the vital sign weight calculation layer is used to perform vital sign weight calculation on the received data sequence representing different vital signs of the elderly, the digital feature extraction layer is used to extract digital features of the elderly vital signs, the weighted vital sign deviation calculation layer is used to calculate the sequence deviation of different elderly vital signs, and perform weighted processing of the sequence deviation with the vital sign weight to form a weighted vital sign deviation, and the health assessment layer is used to map the weighted vital sign deviation to the elderly health assessment result; S4: using the elderly health assessment model to perform remote health assessment on different elderly people; The method of eliminating abnormal data clusters to obtain corrected elderly vital sign data includes: The abnormal data clusters are removed to obtain the corrected vital signs data of the elderly, where the corrected vital signs data of the elderly are: ； in: Y represents the corrected vital sign data of the elderly, H represents the number of denoised data sequences retained, represents the hth group of denoised data sequence retained, Represents the denoised data sequence The data value at the mth sampling moment; In step S4, the health assessment model for the elderly is used to assess the health of different elderly people, including: The remote server uses the elderly health assessment model to conduct remote health assessment on different elderly people, where the corrected elderly physical sign data The corresponding remote health assessment process for the elderly is as follows: S41: The input layer receives the corrected vital signs data of the elderly ; S42: The physical sign weight calculation layer calculates the physical sign weights of the received data sequences representing different physical signs of the elderly, wherein the data sequences The corresponding sign weights are: ； ； ； ； in: For data series The corresponding weight of the physical sign; Represents a data sequence The abnormality, Represents a data sequence The coefficient of variation, Represents a data sequence Information entropy of express The maximum value in Represents a data sequence Signs of elderly people, Indicates preset signs of elderly people Maximum value; Represents a data sequence The standard deviation of Represents a data sequence The mean of S43: The digital feature extraction layer extracts digital features of the elderly’s physical signs. The digital feature extraction results are: ； ； ； in: Signs of old age The corresponding digital features are For data series The entropy of For data series of super entropy; S44: The weighted physical sign deviation calculation layer calculates the sequence deviation of different elderly physical signs, where the elderly physical signs The sequence deviation is: ； ； in: Signs of old age The sequence deviation of Signs of old age and sequence differences; Deviance of the sequence Perform weighted processing on the physical sign weights to form the weighted physical sign deviation : ； S44: The health assessment layer maps the weighted physical sign deviation to the health assessment result of the elderly: ； in: Signs for the elderly The corresponding mapping weight matrix; Represents the results of health assessment of the elderly.

2. A digital screening and remote detection method for comprehensive assessment of the elderly as claimed in claim 1, characterized in that: In step S1, the vital sign data of the elderly is collected by sensors, including: The vital sign data of the elderly are collected through sensors, where the sensors are wearable, wirelessly communicating sensor devices, including heart rate sensors, temperature sensors, and acceleration sensors. The sensor devices are worn on the elderly to collect the vital sign data of the elderly. The collected vital sign data of the elderly are in the form of: ; in: represents the data sequence of the nth physical sign of the elderly collected, represents the data value of the nth physical sign of the elderly at M sampling moments, represents the data value of the nth physical sign of the elderly at the mth sampling moment; where N represents the number of types of physical signs of the elderly; Indicates the collected data of vital signs of the elderly; Vital signs data for the elderly Perform denoising to obtain the denoised vital signs data of the elderly , and the denoised vital signs data of the elderly Sent to a remote server via wireless transmission.

3. A digital screening and remote detection method for comprehensive assessment of the elderly as claimed in claim 2, characterized in that: The data on the physical signs of the elderly Perform denoising to obtain the denoised vital signs data of the elderly ,include: Vital signs data for the elderly All data sequences in are denoised, where the data sequences The denoising process is as follows: S11: Constructing a sequence for data The filter for denoising processing sets the maximum order of the filter to D, the current order to d, the initial value of d to 1, and initializes the filter coefficients of the generated filter , filter coefficient The d-order iteration result is ; S12: Use a filter of order d to filter the data sequence Perform filtering processing, where the filtering processing result is: ； in: T stands for transpose; represents a random noise sequence; Represents the filter with order d on the data sequence A filtering result of filtering processing; S13: Calculate the filtering result The error: ； in: Indicates the filtering result The error of represents the L2 norm; like If it is less than the preset threshold, ,Will As a data series The denoising result of Otherwise, go to step S14; S14: Update the filter order: ； in: represents an exponential function with a natural constant as base; S15: Order , return to step S12.

4. A digital screening and remote detection method for comprehensive assessment of the elderly as claimed in claim 2, characterized in that: In the step S2, abnormality identification is performed on the denoised vital sign data of the elderly, and the vital sign data of the elderly is divided into a normal data cluster and an abnormal data cluster, including: The remote server performs anomaly recognition on the denoised vital sign data of the elderly and divides the vital sign data of the elderly into normal data clusters and abnormal data clusters. The anomaly recognition process is as follows: S21: The remote server obtains the denoised vital sign data of the elderly : ； in: Represents a data sequence The denoising result is Represents data value The filtering result of S22: Calculate the sequence distance between any two sets of denoised data sequences, where the denoised data sequence and The sequence distance is: ； ； in: Represents the denoised data sequence and The sequence distance of ; Represents the denoised data sequence and The structural similarity distance of is the denoised data sequence The mean of is the denoised data sequence The mean of is the denoised data sequence The standard deviation of is the denoised data sequence The standard deviation of represents the mean control coefficient, Set to 0.01; is the standard deviation control coefficient, Set to 0.02; S23: Obtain the K nearest neighboring denoised data sequences of any denoised data sequence to form a nearest neighbor sequence set of the denoised data sequence, and calculate the distance between the denoised data sequence and the nearest neighboring denoised data sequence in the corresponding nearest neighbor sequence set, where the denoised data sequence The mean distance to all nearest denoised data sequences is , the distance standard deviation is ; S24: Calculate the sequence influence of any denoised data sequence, where the denoised data sequence The sequence influence of is: ； in: Represents the denoised data sequence The sequence influence of S25: Convert sequence distance to sequence influence distance, where sequence distance The conversion formula is: ； in: is the sequence distance The corresponding sequence influences the distance; S26: Calculate the influence density of any denoised data sequence, where the denoised data sequence The influence density is: ； in: Represents the denoised data sequence The impact density; represents the cutoff distance; represents the L1 norm; Represents the denoised data sequence The set of nearest neighbor sequences of , Represents the denoised data sequence Any nearest neighbor denoised data sequence of ; S27: Calculate the offset distance of any denoised data sequence, where the denoised data sequence The offset distance is: ； in: Represents the denoised data sequence In the embodiment of the present invention, if the denoised data sequence The influence density of is the maximum value among the N denoised data sequences, then the denoised data sequence The maximum distance from all the nearest denoised data sequences is taken as the offset distance; S28: Calculate any denoised data sequence as the cluster center index of the cluster center, where the denoised data sequence The cluster center index is: ； in: Represents the denoised data sequence The cluster center index of The denoised data sequences whose cluster center index is less than the preset threshold are regarded as abnormal data clusters, and the abnormal data clusters are eliminated to obtain the corrected vital sign data of the elderly.

Images