Digital twinborn health management system

Abstract

The invention relates to the technical field of health management, in particular to a digital twin health management system. Comprising a health management platform, a doctor end and a user end, wherein the health management platform comprises a data acquisition module, a health analysis module and a distribution module; the data acquisition module is used for acquiring health data and sending the health data to the server for storage; comprehensive analysis is carried out according to the sleep parameters, the motion parameters and the physiological parameters of the user to obtain the health abnormal value for measuring the body state of the user, and the health state of the user can be evaluated more comprehensively; the qualification information of the doctor and the diagnosis record of the doctor are analyzed to obtain the processing value for comprehensively measuring the diagnosis capability of the doctor, and the processing value is matched with the health abnormal value of the user to be diagnosed to intelligently distribute the user to the most suitable target doctor, so that the diagnosis accuracy and quality are improved; therefore, further professional and accurate diagnosis of the physical state of the user with great health risk is realized, and health management of the user is enhanced.

Description

Technical Field

[0001] This invention relates to the field of health management technology, specifically a digital twin health management system. Background Technology

[0002] Digital twins refer to the concept of connecting a physical entity or process in the real world with its digital virtual model through digital and simulation technologies. A digital twin health management system applies digital twin technology to the field of health management to achieve personalized health monitoring, diagnosis, and prediction. Therefore, health management based on digital twins is particularly important.

[0003] Current digital twin health management systems are in a relatively early stage of analyzing and predicting health data for each individual. Due to the complexity of human biological structure and biochemical reactions, especially in the diagnosis of complex diseases such as chronic diseases, the diagnostic results are prone to errors, thus failing to effectively protect the user's health. Summary of the Invention

[0004] The purpose of this invention is to provide a digital twin health management system to solve the problems mentioned in the background art.

[0005] The objective of this invention can be achieved through the following technical solution: a digital twin health management system, comprising: a health management platform, a doctor's terminal, and a user terminal; wherein the health management platform includes a data acquisition module, a health analysis module, and an allocation module; the data acquisition module is used to collect health data and send it to a server for storage;

[0006] The user terminal refers to the mobile device terminal applied to the user, including but not limited to smartwatches;

[0007] The doctor's end refers to the mobile terminal used by doctors, including but not limited to smartwatches, smartphones, smart tablets, and computers. The doctor's end collects qualification information and sends it to the health management platform.

[0008] The health analysis module performs in-depth analysis of health data to obtain abnormal health values, and generates diagnostic signals or health warning notifications accordingly; the diagnostic signals are then sent to the diagnostic allocation module.

[0009] The diagnosis allocation module parses the received diagnostic signals to obtain the user to be diagnosed and the corresponding health abnormality value of the user, and then allocates the user to the target doctor based on this information. Specifically:

[0010] 101: Obtain the user to be diagnosed and the corresponding abnormal health value, and select the user terminal with the largest abnormal health value as the target user terminal;

[0011] 102: Select any doctor's account and retrieve the corresponding qualification information, including length of service, education level and professional title level. Perform quantitative analysis on education level and professional title level to obtain education weight value and professional title weight value.

[0012] 103: Obtain the number of diagnoses, as well as the start and end times of each diagnosis, and perform quantitative analysis to obtain the average diagnosis time;

[0013] 104: Obtain the number of diagnoses (F5), the number of follow-up diagnoses (F6), and the number of users awaiting diagnosis (F7), and substitute these values ​​with the following weightings: length of service (F1), education level (F2), professional title (F2), and average diagnosis time (F4) into the set formula. The processing value FZ of the doctor is calculated, where f1, f2, f3, f4 and f5 are the set proportional coefficients. The processing value of each doctor is obtained in the same way. The doctor with the largest processing value is selected as the target doctor and the target user is assigned to the target doctor. The number of diagnoses of the target doctor increases by one and the number of users to be diagnosed increases by one.

[0014] 105: Repeat steps 101-104 above until all users awaiting diagnosis have been assigned. Once a diagnosis is completed, the number of users awaiting diagnosis for that doctor is reduced by one.

[0015] Preferably, the health analysis module performs in-depth analysis of health data to obtain abnormal health values, and generates diagnostic signals or health warning notifications accordingly. The specific steps are as follows:

[0016] 201: By conducting in-depth analysis of users' sleep parameters, we can determine whether their sleep is regular and sufficient, and obtain a sleep disorder index;

[0017] 202: By analyzing users' exercise data, the user's exercise status is measured, and an exercise index is obtained;

[0018] 203: By conducting in-depth analysis of users' physiological parameters, we can determine their daily health status and obtain physiological indices;

[0019] 204: Retrieve the sleep disturbance index TMZ and exercise index RMZ closest to the time corresponding to the analysis node, and substitute them and the physiological index SHk corresponding to that analysis node into the set formula. The abnormal health value is denoted as YZk, where y1 and y2 are the set proportional coefficients. When the abnormal health value is within the abnormal range, a health warning notification is generated and sent to the corresponding user terminal. When the abnormal health value is greater than the maximum value in the set abnormal range, the user is recorded as a user to be diagnosed.

[0020] 205: Obtain the historical target doctor information from the user's historical diagnosis information, and send the target doctors corresponding to all historical target doctor information to the user for selection. When the user selects any historical target doctor, the historical target doctor is recorded as the target doctor for the user's current diagnosis, and the user is assigned to the corresponding target doctor. The number of diagnoses and the number of follow-up diagnoses for that target doctor are each increased by one. Otherwise, a diagnosis signal is generated and sent to the diagnosis allocation module.

[0021] Preferably, the sleep parameters of the user are analyzed in depth to determine whether the user's sleep is regular and sufficient, and a sleep disorder index is obtained. The specific steps are as follows:

[0022] 301: Retrieve sleep parameters, including sleep start time, sleep end time, and deep sleep duration: Calculate the time difference between the sleep start time and sleep end time to obtain the sleep duration T1i for this sleep, and record the corresponding deep sleep duration as T2i, where i = 1, 2, 3...n1, n1 is a positive integer, n1 represents the total number of sleeps, and i represents the sequence number of any one sleep; and so on to obtain the sleep duration and deep sleep duration for each sleep session of the user;

[0023] 302: Calculate the time difference between the start time of sleep i and the end time of sleep i-1 to obtain the sleep interval between sleep i-1 and sleep i, denoted as . And substitute it into the set formula. Calculate to obtain the sleep interval deviation value TM3. This represents the average duration of sleep intervals;

[0024] 303: Substitute the sleep duration T1i, deep sleep duration T2i, and sleep interval deviation value TM3 into the set formula. The Sleep Disorder Index (TMZ) is calculated, where m1, m2, m3, and m4 are set proportional coefficients, and TM1 and TM2 are the deviation values ​​of sleep duration and deep sleep duration, respectively. This represents the average sleep duration. This represents the average duration of deep sleep.

[0025] Preferably, the user's daily health status is determined by in-depth analysis of the user's physiological parameters, and a physiological index is obtained. The specific steps are as follows:

[0026] 401: Retrieve motion parameters, and denote the motion duration and motion speed as R1j and R2j respectively, where j = 1, 2, 3...n2, n2 is a positive integer, n2 represents the total number of motions, and j represents the sequence number of any one of the motions;

[0027] 402: Arrange the exercise durations in chronological order of the corresponding exercise times, and calculate the difference between the exercise durations of adjacent exercise times to obtain the exercise interval duration, denoted as . And substitute it into the set formula. Calculations are performed to obtain the motion fluctuation value RM1. This represents the average duration of the exercise intervals;

[0028] 403: Substitute the motion fluctuation value RM1, motion duration R1j, and motion speed R2j into the set formula. The motion index RMZ is calculated, where r1 and r2 are the proportional coefficients.

[0029] Preferably, the user's daily health status is determined by conducting in-depth analysis of the user's physiological parameters, and physiological indices and the latest analysis interval are obtained. The specific steps are as follows:

[0030] 501: Assume there is an analysis interval, obtain the latest analysis interval; obtain the time corresponding to the analysis node closest to the current system time, and calculate the time difference between it and the current system time to obtain the actual interval duration. When the actual interval duration is equal to the latest analysis interval, record that time as analysis node k and execute step 502, where k = 1, 2, 3...n3, n3 is a positive integer, n3 represents the total number of analysis nodes; k represents the sequence number of any analysis node;

[0031] 502: Retrieve physiological parameters collected during the analysis interval between this analysis node and the previous analysis node; denote the collection time as z, where z = 1, 2, 3...n4, n4 is a positive integer, n4 represents the total number of collection times, and z represents the sequence number of any one of the collection times; substitute the heart rate H1 kz, blood pressure H2 kz, ​​and blood oxygen saturation H3 kz into the set formula. The physiological fluctuation coefficient βk of this analysis node is calculated, where h1, h2, and h3 are the set proportionality coefficients, respectively. This represents the average heart rate at all acquisition times within the analysis interval corresponding to the analysis node with sequence number k. This represents the average blood pressure at all data collection times within the analysis interval corresponding to analysis node k. This represents the average blood oxygen saturation at all acquisition times within the analysis interval corresponding to the analysis node with serial number k.

[0032] 503: A standard parameter is defined, including a standard heart rate interval, a standard blood pressure interval, and a standard blood oxygen saturation interval. A line graph is constructed with the data acquisition time as the x-axis and heart rate, blood pressure, and blood oxygen saturation as the y-axis, respectively, to represent the physiological parameters over time. The standard heart rate interval, standard blood pressure interval, and standard blood oxygen saturation interval are then labeled on the line graph to obtain the shaded areas formed by the standard heart rate interval, standard blood pressure interval, and standard blood oxygen saturation interval and their corresponding physiological parameter changes over time. These shaded areas are then denoted as the heart rate excess area, blood pressure excess area, and blood oxygen saturation excess area, respectively. The shaded areas of these three areas are then calculated and denoted as the heart rate excess area, blood pressure excess area, and blood oxygen saturation excess area.

[0033] 504: Substitute the physiological fluctuation coefficient βk, heart rate excess area S1k, blood pressure excess area S2k, and blood oxygen saturation excess area S3k into the set formula SHk=βk×(h4×S1k+h5×S2k+h6×S3k) to calculate the physiological index SHk of the analysis node, where h4, h5, and h6 are the set proportional coefficients; multiply the physiological index of the analysis node by the set interval conversion coefficient to obtain the latest analysis interval, and update it to step 501.

[0034] The beneficial effects of this invention are:

[0035] 1. By comprehensively analyzing users' sleep parameters, exercise parameters, and physiological parameters to obtain health abnormality values ​​that measure users' physical condition, it is possible to more comprehensively assess users' health status, thereby more accurately judging users' overall health status and laying the foundation for providing users with more accurate and timely health management.

[0036] 2. By analyzing doctors' qualification information and diagnostic records, a comprehensive value is obtained to measure the doctor's diagnostic ability. This value is then matched with the abnormal health values ​​of the users to be diagnosed, so that users are intelligently assigned to the most suitable target doctor. This improves the accuracy and quality of diagnosis, enables further professional and accurate diagnosis of the physical condition of users with significant health risks, and strengthens the health management of users. Attached Figure Description

[0037] The invention will now be further described with reference to the accompanying drawings.

[0038] Figure 1 This is a schematic diagram of the system module connections of the present invention;

[0039] Figure 2This is a schematic diagram of the heart rate change over time according to the present invention. Detailed Implementation

[0040] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0041] It should be noted that all information (including but not limited to users' physiological parameters, exercise parameters, and sleep parameters) and data (including but not limited to data used for display and analysis) disclosed herein are information and data authorized by the user or fully authorized by all parties.

[0042] Please see Figure 1 As shown, this invention is a digital twin health management system, comprising: a health management platform, a doctor's terminal, and a user terminal; wherein the health management platform includes a data acquisition module, a health analysis module, and an allocation module; the data acquisition module acquires real-time health data of the user through sensors mounted on the user terminal and sends it to the server for storage; the health data includes the user's physiological parameters, sleep quality parameters, and exercise parameters; wherein the physiological parameters include heart rate, blood pressure, blood oxygen saturation, and emotional stress value; sleep parameters include sleep start time, sleep end time, and deep sleep duration; exercise parameters include exercise duration and exercise speed; it should be noted that sleep parameters are parameters obtained when the user is asleep, exercise parameters are parameters obtained when the user is exercising, and physiological parameters refer to the user's daily parameters excluding sleep and exercise states;

[0043] The sensors include optical sensors and gyroscope sensors. The optical sensors are used to acquire heart rate and blood oxygen saturation, and the blood pressure monitoring sensor is used to acquire blood pressure. The gyroscope sensors are used to acquire sleep parameters and exercise parameters. It should be noted that the blood pressure here refers to the average of systolic and diastolic blood pressure in medical terms.

[0044] The user terminal refers to the mobile device terminal applied to the user, including but not limited to smartwatches;

[0045] The doctor's end refers to the mobile terminal used by doctors, including but not limited to smartwatches, smartphones, smart tablets, and computers. The doctor's end collects qualification information and sends it to the health management platform.

[0046] The health analysis module analyzes health data and builds an individual's digital twin model to initially determine their health status, and generates analysis intervals accordingly to achieve adaptive monitoring of the user's health status; specifically:

[0047] P1: By conducting in-depth analysis of users' sleep parameters to determine whether their sleep is regular and sufficient, and obtaining a sleep disorder index, the user's sleep can be monitored and evaluated; specifically:

[0048] P11: Retrieve sleep parameters, including sleep start time, sleep end time, and deep sleep duration: Calculate the time difference between the sleep start time and sleep end time to obtain the sleep duration T1i for this sleep, and record the corresponding deep sleep duration as T2i, where i = 1, 2, 3...n1, n1 is a positive integer, n1 represents the total number of sleeps, and i represents the sequence number of any one sleep; and so on to obtain the sleep duration and deep sleep duration for each sleep session of the user;

[0049] P12: Retrieve the start and end times of each sleep cycle, calculate the time difference between the start time of sleep cycle i and the end time of sleep cycle i-1 to obtain the interval between sleep cycles i-1 and i, denoted as . Using the set formula Calculate to obtain the sleep interval deviation value TM3. The average duration of sleep intervals is denoted as 1; the sleep interval deviation value refers to the degree of deviation of the user's sleep time. The larger the sleep interval deviation value, the higher the degree of irregularity of the user's sleep time.

[0050] P13: The sleep duration T1i, deep sleep duration T2i, and sleep interval deviation TM3 are recorded using a set formula. The Sleep Disorder Index (TMZ) is calculated, where m1, m2, m3, and m4 are set proportional coefficients, and TM1 and TM2 are the deviation values ​​of sleep duration and deep sleep duration, respectively. T1 is the mean sleep duration. The TM1, TM2, and TM3 values ​​represent the average duration of deep sleep. The greater the deviation in sleep duration, the more volatile the sleep duration becomes, indicating a higher likelihood of insufficient or excessive sleep. Similarly, the greater the deviation in deep sleep duration, the more volatile the deep sleep duration becomes, indicating poor sleep quality. As the formula shows, larger TM1, TM2, and TM3 values ​​(indicating greater deviations in sleep time, duration, and deep sleep duration, and more irregular, insufficient, or excessive sleep) indicate a higher sleep disorder index. The closer the sleep interval duration, sleep duration, and deep sleep duration are to the average, the better the sleep quality for that particular sleep period; conversely, the greater the difference, the higher the sleep disorder index. A higher sleep disorder value indicates poorer sleep quality for that particular sleep period.

[0051] P2: By analyzing users' exercise data, the user's exercise status is measured, and an exercise index is obtained; specifically:

[0052] Retrieve the motion parameters and denote the motion duration and motion speed as R1j and R2j respectively, where j = 1, 2, 3...n2, n2 is a positive integer, n2 represents the total number of motions, and j represents the sequence number of any one of the motions;

[0053] The exercise durations are arranged in chronological order, and the difference between the exercise durations of adjacent exercise times is calculated to obtain the exercise interval duration, which is denoted as . Using the set formula Calculations are performed to obtain the motion fluctuation value RM1. The average duration of the exercise interval is 1; the exercise fluctuation value is used to measure the degree of fluctuation in the user's exercise. The more regular the user's exercise, the smaller the exercise fluctuation value; the more irregular the user's exercise, the larger the exercise fluctuation value.

[0054] The motion fluctuation value RM1, motion duration R1j, and motion speed R2j are calculated using a predefined formula. The exercise index RMZ is calculated, where r1 and r2 are set as proportional coefficients. The exercise index is a comprehensive indicator that measures the effectiveness of this exercise. As can be seen from the formula, the smaller the exercise fluctuation value, the stronger the regularity of the user's exercise, and the larger the exercise index. The longer the exercise duration and the greater the exercise intensity, the larger the exercise index. When the exercise index is larger, it means that the user's exercise effect is better.

[0055] P3: By conducting in-depth analysis of the user's physiological parameters to determine the user's daily health status and obtain physiological indices, specifically:

[0056] P31: Assume there is an analysis interval. Obtain the latest analysis interval, which is the interval between two adjacent analysis nodes. Obtain the time corresponding to the analysis node closest to the current system time, and calculate the time difference between it and the current system time to obtain the actual interval duration. When the actual interval duration equals the latest analysis interval, record that time as analysis node k and execute 502, where k = 1, 2, 3...n3, n3 is a positive integer, n3 represents the total number of analysis nodes, and k represents the sequence number of any analysis node.

[0057] P32: Retrieve physiological parameters collected within the analysis interval between the current analysis node and the previous analysis node. The analysis interval includes several acquisition times, each with corresponding physiological parameters. The acquisition times are denoted as z, where z = 1, 2, 3…n4, where n4 is a positive integer representing the total number of acquisition times, and z represents the sequence number of any one of those acquisition times. Heart rate, blood pressure, and blood oxygen saturation are denoted as H1kz, H2kz, and H3kz, respectively. It should be noted that H1kz represents the heart rate at acquisition time z within the analysis interval corresponding to analysis node k, H2kz represents the blood pressure at acquisition time z within the analysis interval corresponding to analysis node k, and H3kz represents the blood oxygen saturation at acquisition time z within the analysis interval corresponding to analysis node k. This is achieved through a set formula. The physiological fluctuation coefficient βk of this analysis node is calculated, where h1, h2, and h3 are the set proportionality coefficients, respectively. This represents the average heart rate at all acquisition times within the analysis interval corresponding to the analysis node with sequence number k. This represents the average blood pressure at all data collection times within the analysis interval corresponding to analysis node k. This represents the average blood oxygen saturation at all acquisition times within the analysis interval corresponding to the analysis node with serial number k.

[0058] P33: A standard parameter is defined, which includes a standard heart rate range, a standard blood pressure range, and a standard blood oxygen saturation range. It should be noted that the standard heart rate range is usually between 60-100 beats / minute, the standard blood pressure range is usually between 120-80 mmHg, and the standard blood oxygen saturation range is 95-100%. Long-term physiological parameters exceeding the standard parameter range can have negative health effects. For example, long-term high blood pressure may increase the risk of heart disease and stroke, while long-term low blood pressure may affect the blood supply to organs and tissues.

[0059] Using the time of data collection as the x-axis and heart rate, blood pressure, and blood oxygen saturation as the y-axis, line graphs of physiological parameters changing over time are constructed. These line graphs include those for heart rate, blood pressure, and blood oxygen saturation. Standard heart rate, blood pressure, and blood oxygen saturation intervals are marked on the line graphs to obtain shaded areas formed by these intervals and their corresponding physiological parameter changes over time. These shaded areas are denoted as the excess heart rate, excess blood pressure, and excess blood oxygen saturation, respectively. The shaded areas of these excess areas are calculated and denoted as the excess heart rate area S1k, excess blood pressure area S2k, and excess blood oxygen saturation area S3k. Specifically, taking heart rate as an example... Figure 2 As shown, the standard heart rate range is marked on the line graph of heart rate change over time to obtain the portion of the heart rate that exceeds the range. The shaded area of ​​the portion of the heart rate that exceeds the range is recorded as the heart rate excess area. The larger the heart rate excess area, the greater the possibility of an abnormal heart rate and the greater the health risk.

[0060] P34: The physiological index SHk of the analysis node is calculated using the set formula SHk=βk×(h4×S1k+h5×S2k+h6×S3k), where h4, h5 and h6 are set proportional coefficients; the physiological index of the analysis node is multiplied by the set interval conversion coefficient to obtain the latest analysis interval, and then updated to S31; the interval conversion coefficient is set by those skilled in the art.

[0061] P4: Retrieve the sleep disturbance index TMZ and exercise index RMZ closest to the time corresponding to the analysis node, and compare them with the physiological index SHk corresponding to that analysis node using the set formula. The resulting health anomaly value is denoted as YZk, where y1 and y2 are set proportional coefficients. The health anomaly value is compared and analyzed with a set anomaly range. When the health anomaly value is less than the maximum value within the set anomaly range, it indicates that the user's overall health is good, and no action is required. When the health anomaly value is within the anomaly range, it indicates a minor health risk, and a health warning notification is generated and sent to the corresponding user to alert them to pay attention to their health status and adjust their work and rest habits to maintain good physical fitness. When the health anomaly value is greater than the maximum value within the set anomaly range, it indicates a significant health risk. If a user's health risk requires professional diagnosis, they are recorded as a user awaiting diagnosis. The system retrieves the user's historical diagnosis information, including a directory and the corresponding historical target doctor for each diagnosis record. All target doctors from these historical doctors are sent to the user for selection. If the user selects any historical target doctor, that doctor is recorded as the target doctor for the current diagnosis, and the user is assigned to that doctor. The number of diagnoses and follow-up diagnoses by that doctor are increased by one. Otherwise, a diagnosis signal is generated and sent to the diagnosis allocation module.

[0062] By comprehensively analyzing users' sleep parameters, exercise parameters, and physiological parameters to obtain health anomaly values ​​that measure users' physical condition, a more comprehensive assessment of users' health status can be achieved. This allows for a more accurate judgment of users' overall health status, enabling a preliminary diagnosis of users' overall health status and laying the foundation for providing users with more accurate, timely, and personalized health management services.

[0063] The diagnosis allocation module parses the received diagnostic signals to obtain the user to be diagnosed and their corresponding health abnormalities. Based on this, it allocates the user to the target doctor's end, establishing a dialogue channel between the user's end and the target doctor's end for further professional diagnosis. Specifically:

[0064] V1: Obtain the user to be diagnosed and the corresponding abnormal health value, and select the user terminal with the largest abnormal health value as the target user terminal;

[0065] V2: Select any doctor's client and retrieve the corresponding qualification information, which includes the length of practice, educational level, and professional title level. The length of practice is recorded as F1. It should be noted that the educational level includes undergraduate, master's, and doctoral degrees; the professional title level includes junior professional title, intermediate professional title, associate senior professional title, and senior professional title.

[0066] Each educational level and professional title level is assigned a corresponding educational weight value and a professional title weight value. The educational level and professional title level are extracted and matched with all the assigned educational level and professional title level to obtain the corresponding educational weight value and professional title weight value, which are denoted as F2 and F3 respectively. It should be noted that the educational weight values ​​for undergraduate, master's and doctoral degrees increase sequentially, and similarly, the professional title weight values ​​for junior professional titles, intermediate professional titles, associate senior professional titles and senior professional titles increase sequentially.

[0067] V3: Obtain the number of diagnoses and the start and end times of each diagnosis. Calculate the time difference between the start and end times to obtain the diagnosis duration. Average the diagnosis durations of all diagnoses to obtain the average diagnosis duration, denoted as F4.

[0068] V4: Obtain the number of diagnoses, the number of follow-up diagnoses, and the number of users awaiting diagnosis, and record them as F5, F6, and F7 respectively; use the set formula The processing value FZ of the doctor is calculated, where f1, f2, f3, f4 and f5 are the set proportional coefficients. The processing value of each doctor is obtained in the same way. The doctor with the largest processing value is selected as the target doctor and the target user is assigned to the target doctor. The number of diagnoses of the target doctor increases by one and the number of users to be diagnosed increases by one.

[0069] V5: Repeat V1-V4 until all users awaiting diagnosis have been assigned. Thus, each doctor's end corresponds to a list of users awaiting diagnosis. The order of users awaiting diagnosis in the list is arranged in descending order of their corresponding abnormal health values. Session channels are constructed sequentially according to the order of users awaiting diagnosis in the list so that doctors can perform further health diagnoses for users. When a diagnosis is completed, the number of users awaiting diagnosis for that doctor is reduced by one.

[0070] By analyzing doctors' qualification information and diagnostic records, a comprehensive value is obtained to measure the doctor's diagnostic ability. This value is then matched with the abnormal health values ​​of the users to be diagnosed, so that users are intelligently assigned to the most suitable target doctor. This improves the accuracy and quality of diagnosis, enables further professional and accurate diagnosis of the physical condition of users with significant health risks, and strengthens the health management of users.

[0071] The above description is merely an example and illustration of the structure of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the structure of the invention or exceed the scope defined in the claims, all of which should fall within the protection scope of the present invention.

Claims

1. A digital twin health management system, comprising a health management platform, characterized in that, The health management platform includes a health analysis module and a diagnosis allocation module; The health analysis module performs in-depth analysis of health data to identify abnormal health values ​​and generates diagnostic signals or health warning notifications accordingly. The diagnostic signals are then sent to the diagnostic allocation module. The specific steps are as follows: 201: By conducting in-depth analysis of users' sleep parameters, a sleep disorder index is obtained based on sleep duration, deep sleep duration, and sleep interval deviation. 202: By analyzing users' exercise data, an exercise index is obtained based on exercise fluctuation values, exercise duration, and exercise speed; 203: By conducting in-depth analysis of the user's physiological parameters, a physiological index is obtained based on the physiological fluctuation coefficient, heart rate excess area, blood pressure excess area, and blood oxygen saturation excess area; 204: Retrieve the sleep disturbance index and exercise index that are closest to the time corresponding to the analysis node, and perform a comprehensive analysis with the physiological index corresponding to the analysis node to obtain the health abnormality value; When a health abnormal value is within the abnormal range, a health warning notification is generated and sent to the corresponding user terminal; when a health abnormal value is greater than the maximum value in the set abnormal range, the user is recorded as a user to be diagnosed. 205: Obtain the historical target doctor information from the user's historical diagnosis information, and send the target doctors corresponding to all historical target doctor information to the user's terminal for the user to choose from. When the user selects any historical target doctor, the historical target doctor is recorded as the target doctor for the user's current diagnosis, and the user is assigned to the corresponding target doctor terminal; otherwise, a diagnosis signal is generated and sent to the diagnosis allocation module. The diagnosis and allocation module parses the received diagnostic signals to obtain the user to be diagnosed and the corresponding abnormal health value of the user, and then allocates the user to the target doctor based on this.

2. The digital twin health management system according to claim 1, characterized in that, The specific steps for assigning the data to the target doctor are as follows: 101: Obtain the user to be diagnosed and the corresponding abnormal health value, and select the user terminal with the largest abnormal health value as the target user terminal; 102: Select any doctor's account and retrieve the corresponding qualification information, including length of service, education level and professional title level. Perform quantitative analysis on education level and professional title level to obtain education weight value and professional title weight value. 103: Obtain the number of diagnoses, as well as the start and end times of each diagnosis, and perform quantitative analysis to obtain the average diagnosis time; 104: Obtain the number of diagnoses, the number of follow-up diagnoses, and the number of users awaiting diagnosis. Combine these with the length of service, education level weight, professional title weight, and average diagnosis time to calculate the processing value. Repeat this process to obtain the processing value for each doctor. Select the doctor with the highest processing value and mark it as the target doctor. Assign the target users to the target doctor. 105: Repeat steps 101-104 above until all users to be diagnosed have been assigned.

3. The digital twin health management system according to claim 2, characterized in that, The specific steps to obtain the sleep disorder index are as follows: 301: Calculate the sleep duration by taking the time difference between the start and end times of sleep; and so on to obtain the sleep duration of each sleep cycle. 302: Calculate the time difference between the start time of sleep i and the end time of sleep i-1 to obtain the sleep interval duration between sleep i-1 and sleep i, where i = 1, 2, 3...n1, n1 is a positive integer, n1 represents the total number of sleeps, and i represents the sequence number of any sleep; calculate and analyze the sleep interval duration using a formula to obtain the sleep interval deviation value. 303: The sleep disorder index is obtained by formulaically calculating and analyzing the deviation values ​​of sleep duration, deep sleep duration, and sleep interval.

4. The digital twin health management system according to claim 3, characterized in that, To obtain the exercise index, the specific steps are as follows: 401: Retrieve motion parameters and denote the motion duration and motion speed as R1j and R2j respectively, where j = 1, 2, 3...n2, n2 represents the total number of motions, and j represents the sequence number of any one of the motions; 402: Arrange the exercise durations in chronological order of the corresponding exercise times, calculate the difference between the exercise durations of adjacent exercise times to obtain the exercise interval duration, and then perform formulaic calculation and analysis to obtain the exercise fluctuation value; 403: The exercise index is obtained by comprehensively analyzing the exercise fluctuation value, exercise duration and exercise speed.

5. A digital twin health management system according to claim 4, characterized in that, The specific steps for obtaining physiological indices and the latest analysis intervals are as follows: 501: Assume there is an analysis interval, obtain the latest analysis interval; obtain the time corresponding to the analysis node closest to the current system time, and calculate the time difference between it and the current system time to obtain the actual interval duration. When the actual interval duration equals the analysis interval, record that time as analysis node k and execute step 502, where k = 1, 2, 3...n3, n3 represents the total number of analysis nodes; k represents the sequence number of any analysis node. 502: Retrieve the physiological parameters collected during the analysis interval between this analysis node and the previous analysis node; record the collection time as z, where z = 1, 2, 3...n4, n4 represents the total number of collection times, and z represents the sequence number of any one of the collection times; perform comprehensive formulaic calculation and analysis of heart rate, blood pressure, and blood oxygen saturation to obtain the physiological fluctuation coefficient of this analysis node; 503: Assume there is a standard parameter, which includes a standard heart rate range, a standard blood pressure range, and a standard blood oxygen saturation range; construct a line graph of physiological parameters changing over time with the acquisition time as the x-axis and heart rate, blood pressure, and blood oxygen saturation as the y-axis respectively; mark the standard heart rate range, standard blood pressure range, and standard blood oxygen saturation range on the line graph of physiological parameters changing over time to obtain the shaded parts formed by the standard heart rate range, standard blood pressure range, and standard blood oxygen saturation range and the corresponding physiological parameter changing over time line graphs, respectively, and record them as the heart rate excess part, blood pressure excess part, and blood oxygen saturation excess part; The shaded areas of the excess heart rate, excess blood pressure, and excess blood oxygen saturation are recorded as the excess heart rate area, excess blood pressure area, and excess blood oxygen saturation area, respectively. 504: The physiological fluctuation coefficient, heart rate excess area, blood pressure excess area, and blood oxygen saturation excess area are calculated and analyzed in a formulaic manner to obtain the physiological index; the physiological index of the analysis node is multiplied by the set interval conversion coefficient to obtain the latest analysis interval, and then updated to step 501.

Images