Multi-dimensional health data collaborative analysis method and device and storage medium

Abstract

The present application relates to the technical field of health data analysis, and particularly relates to a multi-dimensional health data collaborative analysis method and device and a storage medium, the method comprising: collecting user type, sleep data, diet data and wearable monitoring data of a user; determining heart rate and respiration coupling degree, emotional interference factor and diet influence coefficient of the user based on the sleep data, diet data and wearable monitoring data; establishing a sleep quality baseline matrix according to the user type, and performing deviation degree evaluation according to the heart rate and respiration coupling degree, emotional interference factor and diet influence coefficient of the user to obtain individual deviation degree, group deviation degree and standard deviation degree; constructing a health score model based on the individual deviation degree, group deviation degree and standard deviation degree to obtain a user comprehensive score; and judging the health status of the user according to the user comprehensive score. The present application realizes accurate analysis of the health status based on multi-dimensional data such as user emotion, sleep and diet.

Description

Technical Field

[0001] This invention relates to the field of health data analysis technology, and in particular to a method, apparatus and storage medium for multi-dimensional collaborative analysis of health data. Background Technology

[0002] With the growing demand for health management, traditional single-indicator analysis can no longer meet the needs for accurate judgment. Multi-dimensional health data analysis has emerged, which integrates data from multiple sources such as physiology, psychology, and lifestyle, and uses big data and AI technology to deeply mine the data, so as to comprehensively and accurately assess the user's health status.

[0003] Existing health data analysis technologies have the following shortcomings: traditional methods usually rely on a single data source, making it difficult to comprehensively reflect health status; they lack the ability to process dynamic data in real time, making it impossible to capture health changes in a timely manner; they do not consider user types and individual differences, resulting in assessment results that are out of touch with actual needs; they only provide a description of health status and lack graded early warning and targeted intervention suggestions. Summary of the Invention

[0004] The purpose of this invention is to provide a method, apparatus and storage medium for collaborative analysis of multi-dimensional health data, so as to solve at least one of the problems existing in the prior art.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: A multi-dimensional collaborative analysis method for health data includes: Collect user data, including user type, sleep data, diet data, and wearable monitoring data; Based on sleep data, dietary data, and wearable monitoring data, the user's heart rate-respiratory coupling degree, emotional interference factor, and dietary influence coefficient were determined. A sleep quality baseline matrix was established based on user type, and deviation was assessed based on the user's heart rate-respiration coupling degree, emotional interference factor, and dietary influence coefficient to obtain individual deviation, group deviation, and standard deviation. A health scoring model is constructed based on individual deviation, group deviation, and standard deviation to obtain a comprehensive user score; The user's health status is determined based on the user's overall rating.

[0006] Preferably, the heart rate-respiration coupling degree of the user is analyzed based on respiratory signals and heart rate signals. The instantaneous phase of the respiratory signals and heart rate signals is extracted using Hilbert transform. The phase difference between the heart rate signal and the respiratory signal at each acquisition node is used as the node phase difference, and the heart rate-respiration coupling degree is analyzed based on the node phase difference.

[0007] Preferably, the user's body movement type is determined based on the amplitude of sleep body movement. The body movement type includes normal and abnormal. The number of times the user's body movement type is abnormal during nighttime sleep is counted as the number of abnormal body movements. The user's emotional interference factor is analyzed based on the number of abnormal body movements and the daytime heart rate signal variability. The expression of the emotional interference factor is: Q=α1×σ(HRV) / μ(HRV)+α2×NM / nm, where Q represents the emotional interference factor, HRV represents the daytime heart rate signal variability, NM represents the number of abnormal body movements, nm represents the preset number of abnormalities, α1 represents the daytime weight, α2 represents the nighttime weight, and α1+α2=1.

[0008] Preferably, the time interval between mealtime and sleep time is used as the bedtime meal interval, and the user's dietary influence coefficient is analyzed based on the bedtime meal interval, food type, and food quantity.

[0009] Preferably, the individual deviation is analyzed based on the sleep quality baseline matrix and the heart rate-respiration coupling degree. The expression for the individual deviation degree is: A1=|R / r(v)-1|, where A1 represents the individual deviation degree, r(v) represents the heart rate-respiration coupling degree baseline, v represents the user type, and R represents the heart rate-respiration coupling degree.

[0010] Preferably, users with the same user type are grouped into the same group, and the group deviation is analyzed based on the emotional interference factors of users in the same group as the currently analyzed user. The expression for the group deviation is: A2=|[Q-μ(Q|v)] / σ(Q|v)|, where A2 represents the group deviation, μ(Q|v) represents the average emotional interference factor of users in the same group as the currently analyzed user, and σ(Q|v) represents the standard deviation of the emotional interference factor of users in the same group as the currently analyzed user.

[0011] Preferably, based on the baseline of the dietary influence coefficient and the standard deviation of the dietary influence coefficient analysis, if P≤p(v), the expression for the standard deviation is set as: A3=0; otherwise, the expression for the standard deviation is set as: A3=ln(P / p(v)), where A3 represents the standard deviation, p(v) represents the baseline of the dietary influence coefficient, and P represents the dietary influence coefficient.

[0012] Preferably, the individual deviation, group deviation, and standard deviation are weighted according to user type to obtain a comprehensive user score. The user's health status is then determined based on the comprehensive user score. If the comprehensive user score is less than a first score threshold, the user's health status is determined to be normal. If the comprehensive user score is greater than or equal to the first score threshold and less than a second score threshold, the user's health status is determined to be slightly abnormal. If the comprehensive user score is greater than or equal to the second score threshold, the user's health status is determined to be significantly abnormal.

[0013] On the other hand, the present invention also provides a multi-dimensional health data collaborative analysis device, comprising: The data acquisition module is used to collect user data, including user type, sleep data, dietary data, and wearable monitoring data. The parameter analysis module is used to determine the user's heart rate-respiratory coupling degree, emotional interference factor, and dietary influence coefficient based on sleep data, dietary data, and wearable monitoring data. The deviation analysis module is used to establish a sleep quality baseline matrix based on user type, and to evaluate the deviation based on the user's heart rate-respiration coupling degree, emotional interference factor, and dietary influence coefficient to obtain individual deviation, group deviation, and standard deviation. The comprehensive scoring module is used to build a health scoring model based on individual deviation, group deviation, and standard deviation to obtain a comprehensive score for the user. The status assessment module is used to determine the user's health status based on the user's overall score.

[0014] On the other hand, the present invention also provides a storage medium characterized in that it stores instructions that, when run on a computer, cause the computer to execute the multi-dimensional health data collaborative analysis method described above.

[0015] The beneficial effects of this invention are as follows: Through multi-dimensional data collaborative analysis, a comprehensive and accurate assessment of the user's health status is achieved. It integrates sleep, diet, mood, and physiological data to avoid the one-sidedness of a single data source. Based on user type and historical data, a baseline is established to achieve differentiated health assessment. Data is collected and analyzed in real time to reflect changes in health status in a timely manner. Through quantitative scoring and grading, it provides users with clear directions for health improvement. By combining with smart devices to automatically collect data, manual intervention is reduced and analysis efficiency is improved. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart of the multi-dimensional health data collaborative analysis method in this embodiment.

[0018] Figure 2 This is a flowchart of the multi-dimensional data parameter analysis method in this embodiment.

[0019] Figure 3 This is a flowchart of the parameter deviation evaluation method in this embodiment.

[0020] Figure 4 This is a schematic diagram of the multi-dimensional health data collaborative analysis device in this embodiment. Detailed Implementation

[0021] To more clearly illustrate the present invention, the following description, in conjunction with preferred embodiments and accompanying drawings, further explains the invention. Similar components in the drawings are indicated by the same reference numerals. Those skilled in the art should understand that the specific description below is illustrative rather than restrictive and should not be construed as limiting the scope of protection of the present invention.

[0022] It should be noted that although the terms first, second, third, etc., may be used in the embodiments of this application for description, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of this application, first can also be referred to as second, and similarly, second can also be referred to as first.

[0023] Please see Figure 1 As shown, this is the multi-dimensional health data collaborative analysis method of this embodiment, including: Step S1: Collect user type, sleep data, dietary data, and wearable monitoring data. The user type includes, but is not limited to, healthy young and middle-aged adults, anxiety patients, and the elderly. The sleep data includes sleep body movement amplitude, respiratory signals, and heart rate signals. The sleep data is collected through the smart mattress used by the user during sleep at a frequency of 50Hz. The sleep body movement amplitude is the rate of change of the overlapping area of ​​the human body contour between adjacent collection nodes. The dietary data includes food type, food quantity, and food time. The dietary data is the user's food consumption data within 3 hours before bedtime, collected through the user's smart refrigerator using image recognition barcodes and weight sensors. The food type includes high-fat foods and high-sugar foods. The food type classification is based on defining foods with a glycemic index greater than 70 as high-sugar foods and foods with a fat content greater than 20g / 100g as high-fat foods. The unit of food quantity is g. The wearable monitoring data includes daytime heart rate signal variability, which is collected by the smart bracelet worn by the user.

[0024] Specifically, in step S1 of this embodiment, this step integrates user type, sleep data, dietary data, and wearable monitoring data to achieve comprehensive collection of multi-source health data. Sleep data is collected at high frequency through a smart mattress, ensuring the accuracy of respiratory and heart rate signal data. Dietary data is acquired through image recognition and weight sensors of a smart refrigerator, avoiding subjective errors from manual recording. Wearable monitoring data is obtained by real-time monitoring of daytime heart rate signal variability through a smart bracelet, providing dynamic physiological indicators for subsequent analysis to improve the comprehensiveness and reliability of health status analysis.

[0025] Please continue reading. Figure 1 As shown, the multi-dimensional health data collaborative analysis method also includes: Step S2: Determine the user's heart rate-respiration coupling degree, emotional interference factor, and dietary influence coefficient based on sleep data, dietary data, and wearable monitoring data.

[0026] Please see Figure 2 As shown, this is a method for analyzing multi-dimensional data parameters, including: Step S21: Determine the user's heart rate-respiration coupling degree based on sleep data.

[0027] Specifically, in step S21 of this embodiment, the user's heart rate-respiration coupling degree is analyzed based on the respiratory signal and heart rate signal. The instantaneous phase of the respiratory signal and heart rate signal is extracted using Hilbert transform. The phase difference between the heart rate signal and the respiratory signal at each acquisition node is used as the node phase difference, and the heart rate-respiration coupling degree is analyzed based on the node phase difference. The expression for the heart rate-respiration coupling degree is: In the formula, R represents the heart rate-respiration coupling degree, ΔL(t) represents the node phase difference, t represents the acquisition node number, Nt represents the number of acquisition nodes, and μ() represents the average value of the data in parentheses. The acquisition node number is defined as the number of the acquisition node corresponding to the acquisition time that distinguishes different sleep data.

[0028] Please continue reading. Figure 2 As shown, the analysis method for the multi-dimensional data parameters further includes: Step S22: Determine the user's body movement type based on sleep data, and determine the user's emotional interference factors based on the body movement type and wearable monitoring data.

[0029] Specifically, in step S22 of this embodiment, the user's body movement type is determined based on the amplitude of sleep body movement. If the amplitude of sleep body movement is greater than the amplitude threshold, the user's body movement type is determined to be abnormal; otherwise, the user's body movement type is determined to be normal.

[0030] Specifically, in this embodiment, the amplitude threshold is set to 0.15. This embodiment does not impose specific limitations on the setting of the amplitude threshold. Those skilled in the art can set it freely. The amplitude threshold setting should satisfy the condition of being within [0.1, 0.2].

[0031] Specifically, in step S22 of this embodiment, the number of times the user's body movement type is abnormal during nighttime sleep is counted as the number of abnormal body movements. Based on the number of abnormal body movements and the daytime heart rate signal variability, the user's emotional interference factor is analyzed. The expression of the emotional interference factor is: Q=α1×σ(HRV) / μ(HRV)+α2×NM / nm, where Q represents the emotional interference factor, HRV represents the daytime heart rate signal variability, NM represents the number of abnormal body movements, nm represents the preset number of abnormalities, α1 represents the daytime weight, α2 represents the nighttime weight, α1+α2=1, and σ() represents the standard deviation of the data in parentheses.

[0032] Specifically, in this embodiment, the preset number of anomalies is set to 5, the daytime weight is set to 0.6, and the nighttime weight is set to 0.4. This embodiment does not impose specific limitations on the preset number of anomalies, daytime weight, and nighttime weight. Those skilled in the art can set them freely, as long as they meet the requirements for analyzing emotional interference factors. The setting of daytime weight and nighttime weight is related to the user's emotions. For example, if the user has a history of anxiety, the daytime weight can be set to 0.4 and the nighttime weight to 0.6 to expand the influence of nighttime data on the analysis of emotional interference factors.

[0033] Please continue reading. Figure 2 As shown, the analysis method for the multi-dimensional data parameters further includes: Step S23: Determine the user's dietary influence coefficient based on dietary data.

[0034] Specifically, in step S23 of this embodiment, the time interval between the meal time and the user's sleep time is taken as the pre-sleep meal interval, and the user's dietary influence coefficient is analyzed based on the pre-sleep meal interval, food type, and food quantity. The expression for the dietary influence coefficient is as follows: In the formula, P represents the dietary influence coefficient, GI(k) represents the glycemic index of high-sugar foods, ΔT(k) represents the bedtime eating interval of high-sugar foods, λ represents the time decay parameter, k represents the dietary data number of high-sugar foods, Fat(m) represents the amount of high-fat foods, ΔT(m) represents the bedtime eating interval of high-fat foods, and m represents the dietary data number of high-fat foods. The bedtime eating interval is in hours.

[0035] Specifically, in step S2 of this embodiment, complex physiological and behavioral data are transformed into quantifiable health indicators by calculating heart rate-respiration coupling degree, emotional interference factor, and dietary influence coefficient. Heart rate-respiration coupling degree reflects the coordination of cardiopulmonary function, while emotional interference factor, combined with the number of abnormal body movements and heart rate signal variability, can accurately capture the interference of emotions on sleep. Dietary influence coefficient quantifies the impact of pre-sleep diet on sleep quality.

[0036] Please continue reading. Figure 1 As shown, the multi-dimensional health data collaborative analysis method also includes: Step S3: Establish a sleep quality baseline matrix based on user type, and evaluate the deviation based on the user's heart rate-respiration coupling degree, emotional interference factor, and dietary influence coefficient to obtain individual deviation, group deviation, and standard deviation.

[0037] Please see Figure 3 As shown, this is a method for evaluating parameter deviation, including: Step S31: Establish a sleep quality baseline matrix based on user type.

[0038] Specifically, in step S31 of this embodiment, sleep quality baselines are set for different user types. The sleep quality baselines include the heart rate-respiration coupling baseline, the emotional interference factor baseline, and the dietary influence coefficient baseline. In this embodiment, if the user type is a healthy young adult, the heart rate-respiration coupling baseline is set to 0.75, the emotional interference factor baseline is set to 0.3, and the dietary influence coefficient baseline is set to 20. If the user type is an anxious patient, the heart rate-respiration coupling baseline is set to 0.65, the emotional interference factor baseline is set to 0.6, and the dietary influence coefficient baseline is set to 15. If the user type is an elderly person, the heart rate-respiration coupling baseline is set to 0.7, the emotional interference factor baseline is set to 0.4, and the dietary influence coefficient baseline is set to 25.

[0039] It is understood that this embodiment does not specifically limit the setting of the sleep quality baseline. Those skilled in the art can set it freely according to different user types, as long as it satisfies the construction of the sleep quality baseline matrix.

[0040] Please continue reading. Figure 3 As shown, the deviation evaluation method for the parameters further includes: Step S32: Analyze individual deviations based on the sleep quality baseline matrix and heart rate-respiration coupling degree.

[0041] Specifically, in step S32 of this embodiment, the individual deviation is analyzed based on the sleep quality baseline matrix and the heart rate-breathing coupling degree. The expression for the individual deviation degree is: A1=|R / r(v)-1|, where A1 represents the individual deviation degree, r(v) represents the heart rate-breathing coupling degree baseline, and v represents the user type.

[0042] Please continue reading. Figure 3 As shown, the deviation evaluation method for the parameters further includes: Step S33: Analyze group deviation based on the sleep quality baseline matrix and emotional interference factors.

[0043] Specifically, in step S33 of this embodiment, users with the same user type are divided into the same group, and the group deviation is analyzed based on the emotional interference factors of users in the same group as the currently analyzed user. The expression for the group deviation is: A2=|[Q-μ(Q|v)] / σ(Q|v)|, where A2 represents the group deviation, μ(Q|v) represents the average value of the emotional interference factors of users in the same group as the currently analyzed user, and σ(Q|v) represents the standard deviation of the emotional interference factors of users in the same group as the currently analyzed user.

[0044] Please continue reading. Figure 3 As shown, the deviation evaluation method for the parameters further includes: Step S34: Analyze the standard deviation based on the sleep quality baseline matrix and the dietary influence coefficient.

[0045] Specifically, in step S34 of this embodiment, based on the baseline of the dietary influence coefficient and the standard deviation of the dietary influence coefficient analysis, if P≤p(v), the expression for the standard deviation is set as: A3=0; otherwise, the expression for the standard deviation is set as: A3=ln(P / p(v)), where A3 represents the standard deviation and p(v) represents the baseline of the dietary influence coefficient.

[0046] Specifically, in step S3 of this embodiment, a sleep quality baseline matrix is ​​established based on user type. Through individual deviation, group deviation, and standard deviation, a personalized assessment of the user's health status is achieved. Individual deviation reflects the difference between the user and their own baseline, group deviation is compared with the average level of similar users, and standard deviation measures the rationality of dietary behavior. Using multi-level deviation assessment, health risks can be identified more accurately, avoiding the limitations of single indicator analysis.

[0047] Please continue reading. Figure 1 As shown, the multi-dimensional health data collaborative analysis method also includes: Step S4: Construct a health scoring model based on individual deviation, group deviation, and standard deviation to obtain a comprehensive user score.

[0048] Specifically, in step S4 of this embodiment, the individual deviation, group deviation and standard deviation are weighted according to the user type to obtain the user comprehensive score. The expression of the user comprehensive score is: S=w1×A1+w2×A2+w3×A3, where S represents the user comprehensive score, w1 represents the heart rate signal respiratory coupling weight, w2 represents the emotional influence weight, w3 represents the dietary influence weight, and w1+w2+w3=1.

[0049] Specifically, in this embodiment, the settings of the heart rate signal respiratory coupling weight, emotional influence weight, and dietary influence weight are related to the user type and their medical history. For example, the respiratory coupling weight is set to 0.4, the emotional influence weight is set to 0.3, and the dietary influence weight is set to 0.3 for healthy young adults. When the user is a diabetic patient, the dietary influence weight can be increased to 0.5. When the user is an anxiety patient, the emotional influence weight can be set to 0.6, etc. In this embodiment, there are no specific limitations on the settings of the heart rate signal respiratory coupling weight, emotional influence weight, and dietary influence weight. Those skilled in the art can set them freely, as long as they meet the requirements for analyzing the user's comprehensive score.

[0050] Specifically, in step S4 of this embodiment, the individual, group, and standard deviation are integrated into a comprehensive score through weight allocation to achieve a quantitative expression of health status. The weights can be dynamically adjusted according to user type and medical history to adapt to the health management needs of different groups and improve the relevance and practicality of the score.

[0051] Please continue reading. Figure 1 As shown, the multi-dimensional health data collaborative analysis method also includes: Step S5: Determine the user's health status based on the user's overall score.

[0052] Specifically, in step S5 of this embodiment, the user's health status is determined based on the user's comprehensive score. If the user's comprehensive score is less than the first score threshold, the user's health status is determined to be normal. If the user's comprehensive score is greater than or equal to the first score threshold and less than the second score threshold, the user's health status is determined to be slightly abnormal. If the user's comprehensive score is greater than or equal to the second score threshold, the user's health status is determined to be significantly abnormal.

[0053] Specifically, in this embodiment, the first scoring threshold is set to 0.3 and the second scoring threshold is set to 0.6. This embodiment does not impose specific limitations on the setting of the scoring thresholds. Those skilled in the art can set them freely, as long as they meet the requirements for judging the user's health status.

[0054] Specifically, in this embodiment, when the user's health status is slightly abnormal, the user can be guided to adjust their breathing signal based on the user's heart rate-breath coupling degree so that the heart rate-breath coupling degree satisfies R > 0.7. When the user's health status is significantly abnormal, emotional or dietary interventions can be performed on the user. When the user's Q > 0.8 indicates that the user's emotions significantly interfere with sleep, mindfulness breathing tutorials can be pushed to the user to help them relax. When the user's dietary influence coefficient is greater than the baseline dietary influence coefficient, the user should be prohibited from eating high-fat or high-sugar foods before bedtime.

[0055] Specifically, in step S5 of this embodiment, health status levels are divided according to the comprehensive score, and intervention suggestions are provided for different levels. The graded judgment mechanism is used to promptly identify health problems and provide users with personalized improvement suggestions to enhance the effectiveness of health management.

[0056] Please see Figure 4 As shown, this is the multi-dimensional health data collaborative analysis device of this embodiment, including: The data acquisition module is used to collect user data, including user type, sleep data, dietary data, and wearable monitoring data. The parameter analysis module is used to determine the user's heart rate-respiratory coupling degree, emotional interference factor, and dietary influence coefficient based on sleep data, dietary data, and wearable monitoring data. The deviation analysis module is used to establish a sleep quality baseline matrix based on user type, and to evaluate the deviation based on the user's heart rate-respiration coupling degree, emotional interference factor, and dietary influence coefficient to obtain individual deviation, group deviation, and standard deviation. The comprehensive scoring module is used to build a health scoring model based on individual deviation, group deviation, and standard deviation to obtain a comprehensive score for the user. The status assessment module is used to determine the user's health status based on the user's overall score.

[0057] This application also provides a computer-readable storage medium storing instructions that, when run on a computer, cause the computer to perform the multi-dimensional health data collaborative analysis method as described in the above method embodiments.

[0058] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable programs, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically contain computer-readable programs, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0059] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the implementation of the present invention. For those skilled in the art, other variations or modifications can be made based on the above description. It is impossible to exhaustively list all the implementation methods here. All obvious variations or modifications derived from the technical solutions of the present invention are still within the protection scope of the present invention.

Claims

1. A method for collaborative analysis of multi-dimensional health data, characterized in that, include: Collect user data, including user type, sleep data, dietary data, and wearable monitoring data; Based on sleep data, dietary data, and wearable monitoring data, the user's heart rate-respiratory coupling degree, emotional interference factor, and dietary influence coefficient were determined. A sleep quality baseline matrix was established based on user type, and deviation was assessed based on the user's heart rate-respiration coupling degree, emotional interference factor, and dietary influence coefficient to obtain individual deviation, group deviation, and standard deviation. A health scoring model is constructed based on individual deviation, group deviation, and standard deviation to obtain a comprehensive user score; Determine a user's health status based on their overall rating. The user's body movement type is determined based on the amplitude of sleep body movement. The body movement type includes normal and abnormal. The number of times the user's body movement type is abnormal during nighttime sleep is counted as the number of abnormal body movements. The user's emotional interference factor is analyzed based on the number of abnormal body movements and the daytime heart rate signal variability. The expression of the emotional interference factor is: Q=α1×σ(HRV) / μ(HRV)+α2×NM / nm, where Q represents the emotional interference factor, HRV represents the daytime heart rate signal variability, NM represents the number of abnormal body movements, nm represents the preset number of abnormalities, α1 represents the daytime weight, α2 represents the nighttime weight, and α1+α2=1. The time interval between meal times and user sleep times is defined as the bedtime meal interval, and the user's dietary influence coefficient is analyzed based on the bedtime meal interval, food type, and food quantity. Individual deviation is analyzed based on the sleep quality baseline matrix and heart rate-respiration coupling degree. The expression for the individual deviation degree is: A1=|R / r(v)-1|, where A1 represents the individual deviation degree, r(v) represents the heart rate-respiration coupling degree baseline, v represents the user type, and R represents the heart rate-respiration coupling degree. Users with the same user type are grouped into the same group, and the group deviation is analyzed based on the emotional interference factors of users in the same group as the currently analyzed user. The expression for the group deviation is: A2=|[Q-μ(Q|v)] / σ(Q|v)|, where A2 represents the group deviation, μ(Q|v) represents the average emotional interference factor of users in the same group as the currently analyzed user, and σ(Q|v) represents the standard deviation of the emotional interference factor of users in the same group as the currently analyzed user. Based on the baseline of the dietary influence coefficient and the standard deviation of the dietary influence coefficient analysis, if P≤p(v), the expression for the standard deviation is set as: A3=0; otherwise, the expression for the standard deviation is set as: A3=ln(P / p(v)), where A3 represents the standard deviation, p(v) represents the baseline of the dietary influence coefficient, and P represents the dietary influence coefficient.

2. The multi-dimensional health data collaborative analysis method according to claim 1, characterized in that, The heart rate-respiration coupling degree of the user is analyzed based on respiratory and heart rate signals. The instantaneous phase of the respiratory and heart rate signals is extracted using Hilbert transform. The phase difference between the heart rate and respiratory signals at each acquisition node is taken as the node phase difference, and the heart rate-respiration coupling degree is analyzed based on the node phase difference.

3. The multi-dimensional health data collaborative analysis method according to claim 1, characterized in that, The weights of individual deviation, group deviation, and standard deviation are assigned according to user type to obtain a comprehensive user score. The user's health status is then judged based on the comprehensive user score. If the comprehensive user score is less than the first score threshold, the user's health status is judged as normal. If the comprehensive user score is greater than or equal to the first score threshold and less than the second score threshold, the user's health status is judged as slightly abnormal. If the comprehensive user score is greater than or equal to the second score threshold, the user's health status is judged as significantly abnormal.

4. A multi-dimensional health data collaborative analysis device, applied to the multi-dimensional health data collaborative analysis method as described in any one of claims 1-3, characterized in that, include: The data acquisition module is used to collect user data, including user type, sleep data, dietary data, and wearable monitoring data. The parameter analysis module is used to determine the user's heart rate-respiratory coupling degree, emotional interference factor, and dietary influence coefficient based on sleep data, dietary data, and wearable monitoring data. The deviation analysis module is used to establish a sleep quality baseline matrix based on user type, and to evaluate the deviation based on the user's heart rate-respiration coupling degree, emotional interference factor, and dietary influence coefficient to obtain individual deviation, group deviation, and standard deviation. The comprehensive scoring module is used to build a health scoring model based on individual deviation, group deviation, and standard deviation to obtain a comprehensive score for the user. The status assessment module is used to determine the user's health status based on the user's overall score.

5. A storage medium, characterized in that, The system stores instructions that, when run on a computer, cause the computer to perform the multidimensional health data collaborative analysis method as described in any one of claims 1-3.

Images