Management platform based on medical health big data

Abstract

The invention discloses a management platform based on medical health big data, and the platform comprises the steps: carrying out the statistics of time node data of residents in a target community entering and exiting the community at ordinary times, evaluating the average going-out time of the residents in the target community, and obtaining the average going-out efficiency of the residents in the target community; and analyzing the actual fatigue value of the resident in the target community, and detecting the medical health condition of the resident in the target community, so that the operation difficulty of monitoring the fatigue value of the resident in the target community is reduced by evaluating the average going-out time of the resident in the target community; analyzing a fatigue value of the resident in the target community based on the average outgoing efficiency of the resident in the target community, detecting a non-fatigue value of the resident in the target community, and buffering the non-fatigue value relative to the fatigue value; the medical health big data management platform has the advantages of being high in humanization degree and high in medical monitoring and adjusting capacity.

Description

Technical Field

[0001] The present invention relates to the technical field of community health management, and particularly to a management platform based on medical and health big data. Background Technique

[0002] The main work content of medical and health is to study the health problems of humans in the process of engaging in various occupational labors. Its purpose is to protect the health of employees from being infringed by harmful factors during the occupational activities, including the impact of the working environment on the health of workers and the countermeasures to prevent occupational hazards. More importantly, the collection, storage, management, calculation, and analysis of medical and health data have not developed with the rapid development of Internet, cloud computing, big data, and artificial intelligence technologies.

[0003] In some communities where the main residents are middle-aged and young people, most residents need to travel long distances to work. Especially frequent long-distance commuting will increase the physical and mental burden of the residents. In the prior art, by detecting the work of the residents and investigating the fatigue situation of the community residents through collecting user data, but the frequent going out of users, whether near or far, will increase the fatigue feeling of the residents, and the collected user data cannot intuitively reflect the health status of the residents. The fatigue value of the resident group is very high, and the possibility of having health problems will also become higher. Especially for some residents, after high-intensity work, they still do not get enough sleep time, resulting in more serious health problems. Therefore, it is very necessary to design a management platform based on medical and health big data with high humanization and strong medical monitoring and adjustment capabilities. Summary of the Invention

[0004] The purpose of the present invention is to provide a management platform based on medical and health big data to solve the problems raised in the above background technique.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: A management platform based on medical and health big data, including:

[0006] Statistical analysis of the time node data of the target community residents' usual entry and exit from the community, evaluating the average going-out time of the target community residents based on the time node data of entering and exiting the community, obtaining the average going-out efficiency of the target community residents and analyzing it, and the average going-out efficiency is used to monitor the energy required for the residents to go out;

[0007] Analyzing the actual fatigue value of the target community residents based on the average going-out efficiency of the target community residents, detecting and testing the medical and health conditions corresponding to the actual fatigue value of the target community residents. If the medical and health value corresponding to the detected actual fatigue value of the target community residents is lower than the limit value, medical assistance will be provided to the target community residents regularly.

[0008] According to the above technical solution, the time node data of the target community residents entering and leaving the community usually is statistically analyzed, the average going-out time of the target community residents is evaluated based on the time node data of entering and leaving the community, and the average going-out efficiency of the target community residents is obtained and analyzed, including:

[0009] A monitor is set at the entrance and exit of the community. The monitor is used to obtain the time node and passing time of the residents entering and leaving the community. Subtracting the time node of leaving the community from the time node of entering the community to obtain the going-out time T of the residents, and the average going-out time of the target community residents n is the number of samples of the residents' going-out time obtained by the monitor, and T i is the going-out time of multiple residents obtained by the monitor;

[0010] Within the monitoring range of the monitor, the passing time of the resident is obtained as t, and the straight-line distance within the monitoring range of the monitor is L, where L is a variable value. Then the going-out efficiency of the resident where φ1 is the influence coefficient preset for the average going-out time of the target community residents, φ2 is the influence coefficient preset for the passing time of the obtained residents, and ε is a unit conversion parameter;

[0011] Based on the average going-out efficiency S of the target community residents, the fatigue value of the target community residents is analyzed. At the same time, the non-fatigue value of the target community residents is detected and the non-fatigue value is buffered relative to the fatigue value.

[0012] According to the above technical solution, the analysis of the fatigue value of the target community residents based on the average going-out efficiency S of the target community residents includes:

[0013] The situation of the residents passing through the monitoring area is obtained through the monitor, including real-time monitoring, historical data query, and fatigue value monitoring model switching;

[0014] Among them, the fatigue value monitoring model includes data processing and storage. The image and video data of the residents passing through the monitoring range are processed. The image and video data are used to identify the eye characteristics of the residents passing through the monitoring area. In the fatigue value detection model, the first eye characteristic of the resident leaving the monitoring range is compared with the second eye characteristic of the resident entering the monitoring range, and the fatigue value change influence factor Q corresponding to the absolute value of the difference between the first eye characteristic and the second eye characteristic is obtained through the historical data query. Then the fatigue value Z of the target community residents = QS.

[0015] According to the above technical solution, the detection of the non-fatigue value of the target community residents and the buffering of the non-fatigue value relative to the fatigue value include:

[0016] Obtain the bright light situation within the target community area through the lighting system set in the target community, where the target community area includes the street lights and the lighting range of households within the community, and the target community area does not include the external road lighting range;

[0017] When it is detected that the proportion of the moving time period of the time period from the current time node to the leaving community time node within the time curve exceeds 10%, it is recorded as a change time node. The change time node includes the moving time period moving forward within the time curve and the moving time period moving backward within the time curve. The moving time period moving forward within the time curve corresponds to a non-fatigue value, and the moving time period moving backward within the time curve corresponds to a fatigue value;

[0018] According to the change time node, adjust the fatigue value with the non-fatigue value in a preset model to obtain the actual fatigue value of the household.

[0019] According to the above technical solution, the obtaining of the bright light situation within the target community area includes:

[0020] Based on the lighting system, detect the brightness value within the target community area, evaluate the number of light rays directly hitting the unit area according to the brightness value of the unit area within the target community area, and corresponding to the number of light rays, screen out the number of street lights in the unit area according to a preset lighting illumination brightness model, and obtain the number of households without lights out in the unit area;

[0021] Record the number of households without lights out in multiple unit areas within the target community area in sequence and stack them in sequence to obtain the total number of households without lights out in the target community area. When it is detected for the first time that the preset value of the total number of households without lights out is lower than the limit value every day, record the current time node and select the time period from the current time node to the leaving community time node.

[0022] According to the above technical solution, the detecting of the actual fatigue value corresponding medical and health condition of the target community households and conducting an inspection includes:

[0023] After further obtaining the authorization of the household, conduct a physiological index detection on the household, and obtain the medical and health value of the target community household according to the inspection of the physiological index, including:

[0024] Heart Rate index, including:

[0025] After a day of intense work by the household, as muscle contractions increase, the cardiovascular load also increases. The heart needs to pump more blood throughout the body, and the amount of blood flowing to the muscles gradually increases. The heart needs to increase its cardiac output. The heart cannot instantaneously increase its stroke volume, so it increases the heart rate to improve blood transportation;

[0026] Classify the HR based on its response to the severity of the body's workload.

[0027] Combine the heart rate index with other physiological parameters to improve the prediction ability of fatigue level, including;

[0028] Body temperature (TEMP) index, including: monitoring skin temperature through an infrared temperature sensor and related temperature regulation changes during the development of fatigue;

[0029] Electromyogram (EMG) index, including: Physical fatigue of local muscles can be detected by analyzing changes in the median frequency or root mean square amplitude of surface electromyogram signals;

[0030] By placing two bipolar surface electrodes on the target muscle, the corresponding electromyogram signals can be measured to estimate muscle activity;

[0031] Jerk metric, including: Applying a wearable IMU motion capture system integrated with a magnetometer, an accelerometer, and a gyroscope, which can be used to detect the speed, acceleration, and body orientation of the household's fatigue jerk.

[0032] According to the above technical solution, the management system based on medical and health big data includes:

[0033] An analysis module, which is used to statistically analyze the time node data of the target community residents' usual entry and exit from the community, evaluate the average going-out time of the target community residents based on the entry and exit time node data, obtain the average going-out efficiency of the target community residents and analyze it. The average going-out efficiency is used to monitor the energy required for the residents to go out;

[0034] A medical detection module, which is used to analyze the actual fatigue value of the target community residents based on the average going-out efficiency of the target community residents, detect the medical and health conditions corresponding to the actual fatigue value of the target community residents and conduct inspections. If the medical and health value corresponding to the actual fatigue value of the target community residents is lower than the threshold value, medical assistance will be provided to the target community residents regularly.

[0035] According to the above technical solution, the analysis module includes:

[0036] The first analysis module is used to set up a monitor at the entrance and exit of the community. The monitor is used to obtain the time nodes and passing times when residents enter and leave the community. The time node of entering the community is subtracted from the time node of leaving the community to obtain the time T that the resident goes out. The average going-out time of the residents in the target community n is the number of samples of the going-out time of the residents obtained by the monitor, and T i are the going-out times of multiple residents obtained by the monitor; within the monitoring range of the monitor, the passing time of the resident is obtained as t, and the straight-line distance within the monitoring range of the monitor is L, where L is a variable value. Then the going-out efficiency of the resident where φ1 is the preset influence coefficient of the average going-out time of the residents in the target community, φ2 is the preset influence coefficient of the passing time of the obtained resident, and ε is the unit conversion parameter;

[0037] The second analysis module is used to analyze the fatigue value of the residents in the target community based on the average going-out efficiency S of the residents in the target community. At the same time, it detects the non-fatigue value of the residents in the target community and buffers the non-fatigue value relative to the fatigue value; through the monitor, it obtains the situation of the residents passing through the monitoring area, including real-time monitoring, historical data query, and fatigue value monitoring model switching; among them, the fatigue value monitoring model includes data processing and storage, processes the image and video data of the residents passing through the monitoring range, and the image and video data are used to identify the eye characteristics of the residents passing through the monitoring area. In the fatigue value detection model, the first eye characteristics when the resident leaves the monitoring range are compared with the second eye characteristics when the resident enters the monitoring range, and the fatigue value change influence factor Q corresponding to the absolute value of the difference between the first eye characteristics and the second eye characteristics is obtained through historical data query. Then the fatigue value Z of the residents in the target community = QS.

[0038] According to the above technical solution, the medical detection module includes:

[0039] The first medical detection module is used to obtain the bright light situation in the area of the target community through the lighting system set in the target community. Among them, the area of the target community includes the street lights in the community and the lighting range of the residents' houses, and the area of the target community does not include the lighting range of the external roads; if it is detected that the proportion of the moving time period of the selected time period from the current time node to the time node of leaving the community within the time curve exceeds 10%, it is recorded as the changed time node. The changed time node includes the moving time period moving forward in the time curve and the moving time period moving backward in the time curve. The moving time period moving forward in the time curve corresponds to the non-fatigue value, and the moving time period moving backward in the time curve corresponds to the fatigue value;

[0040] According to the change time node, adjust the non-fatigue value to the fatigue value in a preset model to obtain the actual fatigue value of the household;

[0041] A second medical detection module, which is used to detect the brightness value in the target community area based on the lighting system, evaluate the number of light rays directly hitting the unit area in the target community area according to the brightness value of the unit area, and corresponding to the number of light rays, screen and remove the number of street lights in the unit area according to a preset lighting illumination brightness model, and obtain the number of households without lights out in the unit area; record the number of households without lights out in multiple unit areas in the target community area in sequence and stack them in sequence to obtain the total number of households without lights out in the target community area. When the preset value of the total number of households without lights out is detected to be lower than the threshold value for the first time every day, record the current time node and select the time period from the current time node to the time node of leaving the community.

[0042] According to the above technical solution, the medical detection module further includes:

[0043] An output module, which is used to further detect the physiological indicators of the household after obtaining the authorization of the household, and obtain the medical and health value of the household in the target community according to the physiological index test, including:

[0044] Heart Rate index, including:

[0045] After a household has carried out a day of high-intensity work, as muscle contraction increases, the cardiovascular load also increases. The heart needs to pump more blood to the whole body, and the amount of blood flowing to the muscles gradually increases. The heart needs to increase its cardiac output. The heart cannot instantaneously increase its stroke volume, so it increases the heart rate to improve blood transportation;

[0046] Classify HR based on the reaction of HR to the severity of physical workload;

[0047] Combine the heart rate index with other physiological parameters to improve the prediction ability of fatigue level, including;

[0048] Temperature (TEMP) index, including: monitoring skin temperature and related temperature regulation changes during the development of fatigue through an infrared temperature sensor;

[0049] Electromyogram (EMG) index, including: local muscle physical fatigue can be detected by analyzing changes in the median frequency or root mean square amplitude of surface electromyogram signals;

[0050] By placing two bipolar surface electrodes on the target muscle, the corresponding electromyogram signals can be measured to estimate muscle activity;

[0051] Jerk metric, including: applying a wearable IMU motion capture system integrated with a magnetometer, an accelerometer, and a gyroscope, which can be used to detect the speed, acceleration, and body orientation of the household fatigue jerk.

[0052] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: in the present invention, by evaluating the average going-out time of the households in the target community, the operation difficulty of monitoring the fatigue value of the households in the target community is reduced due to the way the households enter and leave the community. Based on the average going-out efficiency S of the households in the target community, the fatigue value of the households in the target community is analyzed. At the same time, the non-fatigue value of the households in the target community is detected and buffered relative to the fatigue value; quickly enabling users to access the living status they need, providing a favorable basis for the platform to have a powerful data processing ability and an efficient storage mechanism, and improving the detection accuracy of the medical and health big data management platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the drawings:

[0054] Figure 1 is a flowchart of a management platform based on medical and health big data provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0055] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0056] Please refer to Figure 1 , a flowchart of a management platform based on medical and health big data provided by an embodiment of the present invention. As Figure 1 can be seen, the management platform based on medical and health big data includes:

[0057] Step S1: Statistically analyze the time node data of the target community households' usual entry and exit from the community, evaluate the average going-out time of the target community households based on the entry and exit time node data, obtain the average going-out efficiency of the target community households and analyze it. The average going-out efficiency is used to monitor the energy required for the households to go out.

[0058] Step S2: Analyze the actual fatigue value of the residents in the target community based on the average going-out efficiency of the residents in the target community, detect the medical and health conditions corresponding to the actual fatigue value of the residents in the target community and conduct an inspection. If the medical and health value corresponding to the detected actual fatigue value of the residents in the target community is lower than the threshold value, provide medical assistance to the residents in the target community regularly.

[0059] In the embodiment of the present invention, by evaluating the average going-out time of the residents in the target community, the operation difficulty of monitoring the fatigue value of the residents in the target community can be reduced due to the way the residents enter and leave the community. Analyze the fatigue value of the residents in the target community based on the average going-out efficiency S of the residents in the target community. At the same time, detect the non-fatigue value of the residents in the target community and buffer the non-fatigue value relative to the fatigue value; quickly enable users to access the living status they need, which provides a favorable basis for the platform to have strong data processing capabilities and efficient storage mechanisms, and improves the detection accuracy of the medical and health big data management platform.

[0060] In some preferred embodiments, the time node data of the target community residents' usual entry and exit from the community is statistically analyzed, the average going-out time of the target community residents is evaluated based on the time node data of entering and leaving the community, and the average going-out efficiency of the target community residents is obtained and analyzed, including:

[0061] Step S11: Set a monitor at the entrance and exit of the community. The monitor is used to obtain the time node and passing time of the residents entering and leaving the community. Subtract the time node of leaving the community from the time node of entering the community to get the going-out time T of the residents. The average going-out time of the residents in the target community n is the number of samples of the residents' going-out time obtained by the monitor, T i is the going-out time of multiple residents obtained by the monitor;

[0062] Step S12: Within the monitoring range of the monitor, obtain the passing time t of the resident. The straight-line distance within the monitoring range of the monitor is L, where L is a variable value. The specific value of L is obtained according to the vertical distance of the resident passing through the center point of the monitoring range obtained by the monitor. Within the monitoring range of the monitor, the effective monitoring range of the monitor is circular. The probability that the resident drives a motor vehicle is relatively high at the center point of the monitoring range, and gradually decreases to non-motor vehicles and pedestrians on both sides. Then the going-out efficiency of the resident where φ1 is the preset influence coefficient of the average going-out time of the residents in the target community, φ2 is the preset influence coefficient of the passing time of the obtained resident, and ε is the unit conversion parameter;

[0063] Step S13: Analyze the fatigue value of the residents in the target community based on the average going-out efficiency S of the residents in the target community, and at the same time, detect the non-fatigue value of the residents in the target community and buffer the non-fatigue value relative to the fatigue value.

[0064] Since the residents in the target community are mainly office workers, only a small number of elderly groups and student groups are not taken into account, and most of the going-out is for work.

[0065] Through this technical solution, by evaluating the average going-out time of the residents in the target community, there will be differences due to different ways of entering and leaving the community by the residents in the target community. At the same time, the means of transportation used for going out will also affect the fatigue degree of the residents. That is, under the condition of the same going-out distance, when the user goes out using different means of transportation, the fatigue values are different, and the corresponding medical and health conditions will also be different.

[0066] In some preferred embodiments, the analyzing the fatigue value of the residents in the target community based on the average going-out efficiency S of the residents in the target community includes:

[0067] Step S201: Obtain the situation of the residents passing through the monitoring area through the monitor, including real-time monitoring, historical data query, and fatigue value monitoring model switching;

[0068] Among them, the fatigue value monitoring model includes data processing and storage, processes the image and video data of the residents passing through the monitoring range, and the image and video data are used to identify the eye characteristics of the residents passing through the monitoring area. In the fatigue value detection model, the first eye characteristics of the residents leaving the monitoring range are compared with the second eye characteristics of the residents entering the monitoring range;

[0069] Step S202: Obtain the fatigue value change influence factor Q corresponding to the absolute value of the difference between the first eye characteristics and the second eye characteristics in the historical data query, then the fatigue value Z of the residents in the target community = QS.

[0070] Through this technical solution, it has excellent environmental adaptability and model generalization ability, ensuring high recognition accuracy under diverse environmental conditions; at the same time, it provides a favorable foundation for the platform to have powerful data processing capabilities and efficient storage mechanisms, which is related to the real-time nature of identifying fatigue values and the management and health query efficiency of long-term data, reduces the operation difficulty of monitoring the fatigue value of the residents in the target community, has a reasonable function layout, quickly allows users to access the living status they need, and improves the detection accuracy of the medical and health big data management platform.

[0071] In some preferred embodiments, the detecting the non-fatigue value of the residents in the target community and buffering the non-fatigue value relative to the fatigue value includes:

[0072] Step S211: Obtain the bright light situation within the target community area through the lighting system installed in the target community. Herein, the target community area includes the street lamps within the community and the lighting range of households, and the target community area does not include the lighting range of external roads.

[0073] Step S212: If it is detected that the proportion of the time period of the selected range from the current time node to the time node of leaving the community moving within the time curve exceeds 10%, record it as a change time node. The change time node includes the time period moving forward within the time curve and the time period moving backward within the time curve. The time period moving forward within the time curve corresponds to a non-fatigue value, indicating that the household has obtained more sleep time and the health value has increased; the time period moving backward within the time curve corresponds to a fatigue value, indicating that the household has obtained less sleep time and the health value has decreased. The main health problems within the community are mainly affected by the irregular daily routines of the households themselves.

[0074] Step S213: According to the change time node, adjust the fatigue value with the non-fatigue value in a preset model to obtain the actual fatigue value of the household.

[0075] In a preferred embodiment, the time period moving forward within the time curve corresponds to a fatigue value, indicating that the household has a high work intensity, so more sleep time is needed and the health value decreases. The time period moving backward within the time curve corresponds to a non-fatigue value, indicating that the household has a high work intensity, so more sleep time is needed and the health value decreases. In this case, it is inclined to solve the current fatigue problem of the household. The main health problems within the community are mainly affected by work. By detecting the non-fatigue value of the households in the target community and buffering the non-fatigue value relative to the fatigue value, it can help the households better obtain sleep time and improve the average health level.

[0076] In some preferred embodiments, the obtaining of the bright light situation within the target community area includes:

[0077] Step S2111: Detect the brightness value within the target community area based on the lighting system, evaluate the number of light rays directly irradiating the unit area according to the brightness value of the unit area within the target community area, and corresponding to the number of light rays, screen out the number of street lamps in the unit area according to a preset lighting irradiation brightness model to obtain the number of households in the unit area that have not turned off the lights.

[0078] Step S2112: Sequentially record the number of households with lights not turned off in each unit area within the multiple target community areas and sequentially sum them up to obtain the total number of households with lights not turned off in the target community area. Every day, when the preset value of the total number of households with lights not turned off is detected to be lower than the threshold value for the first time, record the current time node and select the time period from the current time node to the time node of leaving the community.

[0079] In some preferred embodiments, detecting the actual fatigue value of the households in the target community and conducting an examination includes:

[0080] Step S31: Further, after obtaining the authorization of the household, conduct a physiological index detection on the household, and obtain the medical and health value of the household in the target community according to the inspection of the physiological index, including:

[0081] Heart Rate index, including:

[0082] After a household has carried out a day of high-intensity work, as muscle contraction increases, the cardiovascular load also increases. The heart needs to transport more blood to the whole body, the amount of blood flowing to the muscles gradually increases, and the heart's output needs to be increased. The heart cannot instantaneously increase its stroke volume per beat, so it increases the heart rate to improve blood transportation;

[0083] Step S32: Classify the HR based on the response of the body's workload severity to the HR;

[0084] In a preferred embodiment, classifying the heart rate index includes: light work, HR - 90 beats / min; moderate-intensity work, HR - 90 - 110 beats / min; heavy work, HR - 110 - 130 beats / min; very heavy work, HR - 130 - 150 beats / min; extremely heavy work, HR - 150 - 170 beats / min. Similarly, some researchers also classify the fatigue level according to the percentage of cardiovascular load, such as CVL(%) = (HRwork - HRrest) / (HRmax - HRrest) x 100. Based on the CVL value, fatigue is classified into the following levels: CVL below 30%, no fatigue; CVL between 30% and 60%, it is recommended to take a break; CVL between 60% and 80% and 80% and 100%, shorten the working time and have a good rest; CVL exceeding 100%, work should be completely stopped;

[0085] Step S33: Combine the heart rate index with other physiological parameters to improve the prediction ability of the fatigue level, including;

[0086] Body temperature (TEMP) metrics, including: monitoring skin temperature and related temperature regulation changes during the development of fatigue through an infrared temperature sensor;

[0087] The temperature of the skin is affected by potential muscle activity, skin blood flow, and sweating patterns in certain parts of the body, including the cheeks, ears, forehead, and temples. During work, the core body temperature increases, and there is a body temperature regulation system inside the body that maintains the core body temperature within the normal physiological range. In particular, the skin plays a key role in core body temperature regulation. The temperature regulation patterns of specific body parts, including the cheeks, ears, forehead, and temples, have great application potential in detecting fatigue;

[0088] Electromyogram (EMG) metrics, including: local muscle body fatigue can be detected by analyzing changes in the median frequency or root mean square amplitude of surface electromyogram signals;

[0089] Due to its non-invasiveness and ease of application, surface electromyogram has been widely used in muscle fatigue detection;

[0090] By placing two bipolar surface electrodes on the target muscle, the corresponding electromyogram signals can be measured to estimate muscle activity;

[0091] In EMG analysis, including the root mean square, median, and mean power frequency of EMG signals, etc., can be used to evaluate the degree of muscle fatigue. In particular, the root mean square amplitude of surface EMG signals. Since fatigued muscles need to activate more muscle fibers to maintain the required force, the root mean square amplitude of surface EMG signals of fatigued muscles is significantly higher than that of non-fatigued muscles. On the contrary, when the muscle contracts, the median frequency and mean power frequency of the EMG signals of fatigued muscles are significantly lower than those of non-fatigued muscle EMG signals;

[0092] Jerk metric, including: applying a wearable IMU motion capture system integrated with a magnetometer, accelerometer, and gyroscope, which can be used to detect the speed, acceleration, and body orientation of the occupant's fatigue jerk.

[0093] Sampling motion data at a high frequency makes it possible to evaluate fatigue using the jerk metric. Since fatigue may lead to poor motion control and motion quality after the occupant returns home from work, the increased jerk value after work may infer physical fatigue.

[0094] Based on the same concept as the above embodiments, the embodiments of the present invention also provide a management system based on medical and health big data, including:

[0095] An analysis module, which is used to statistically analyze the time node data of the residents in the target community when entering and leaving the community usually, evaluate the average going-out time of the residents in the target community based on the time node data of entering and leaving the community, obtain the average going-out efficiency of the residents in the target community and analyze it. The average going-out efficiency is used to monitor the energy required for the residents to go out;

[0096] A medical detection module, which is used to analyze the actual fatigue value of the residents in the target community based on the average going-out efficiency of the residents in the target community, detect the medical health condition corresponding to the actual fatigue value of the residents in the target community and conduct an inspection. If the medical health value corresponding to the detected actual fatigue value of the residents in the target community is lower than the threshold value, medical assistance will be provided to the residents in the target community regularly.

[0097] In this embodiment, the analysis module includes:

[0098] A first analysis module, which is used to set a monitor at the entrance and exit of the community. The monitor is used to obtain the time node and passing time of the residents entering and leaving the community. Subtracting the time node of leaving the community from the time node of entering the community to get the going-out time T of the residents. The average going-out time of the residents in the target community n is the number of going-out time samples of the residents obtained by the monitor, T i is the multiple going-out times of the residents obtained by the monitor; within the monitoring range of the monitor, the passing time of the residents is obtained as t, and the straight-line distance within the monitoring range of the monitor is L, where L is a variable value. Then the going-out efficiency of the residents where φ1 is the influence coefficient preset for the average going-out time of the residents in the target community, φ2 is the influence coefficient preset for the passing time of the residents obtained, and ε is the unit conversion parameter;

[0099] A second analysis module, which is used to analyze the fatigue value of the residents in the target cell based on the average going-out efficiency S of the residents in the target cell, and at the same time detect the non-fatigue value of the residents in the target cell and buffer the non-fatigue value relative to the fatigue value; obtain the situation of the residents passing through the monitoring area through the monitor, including real-time monitoring, historical data query, and fatigue value monitoring model switching; wherein, the fatigue value monitoring model includes data processing and storage, processes the image and video data of the residents passing through the monitoring range, and the image and video data are used to identify the eye characteristics of the residents passing through the monitoring area. In the fatigue value detection model, the first eye characteristic of the resident leaving the monitoring range is compared with the second eye characteristic of the resident entering the monitoring range, and the fatigue value change influence factor Q corresponding to the absolute value of the difference between the first eye characteristic and the second eye characteristic is obtained through the historical data query, then the fatigue value Z of the residents in the target cell = QS.

[0100] In this embodiment, the medical detection module includes:

[0101] A first medical detection module, which is used to obtain the bright light situation in the target cell area through the lighting system set in the target cell. Among them, the target cell area includes the street lights and the resident lighting range in the cell, and the target cell area does not include the external road lighting range; if it is detected that the proportion of the moving time period of the selected time period from the current time node to the time node of leaving the cell in the time curve exceeds 10%, it is recorded as a change time node. The change time node includes the moving time period moving forward in the time curve and the moving time period moving backward in the time curve. The moving time period moving forward in the time curve corresponds to the non-fatigue value, and the moving time period moving backward in the time curve corresponds to the fatigue value;

[0102] According to the change time node, adjust the fatigue value with the non-fatigue value in a preset model to obtain the actual fatigue value of the resident.

[0103] The second medical detection module, which is used to detect the brightness value in the target community area based on the lighting system, evaluate the number of light rays directly irradiating the unit area in the target community area according to the brightness value of the unit area, and corresponding to the number of light rays, screen and remove the number of street lamps in the unit area according to the preset lighting irradiation brightness model, and obtain the number of households with lights on in the unit area; record the number of households with lights on in multiple unit areas in the target community area in sequence and stack them in sequence to obtain the total number of households with lights on in the target community area. When it is detected for the first time that the preset value of the total number of households with lights on is lower than the threshold value every day, record the current time node and frame the time period from the current time node to the time node of leaving the community.

[0104] In this embodiment, the medical detection module further includes:

[0105] An output module, which is used to further detect the physiological indicators of the household after obtaining the authorization of the household, and obtain the medical health value of the household in the target community according to the inspection of the physiological indicators, including:

[0106] Heart Rate indicator, including:

[0107] After a household has carried out a day of high-intensity work, as muscle contraction increases, the cardiovascular load also increases. The heart needs to pump more blood to the whole body, the amount of blood flowing to the muscles gradually increases, and the heart's output needs to be increased. The heart cannot instantaneously increase its stroke volume, so it increases the heart rate to improve blood transportation;

[0108] Classify HR based on the reaction of HR to the severity of physical work load;

[0109] Combine the heart rate indicator with other physiological parameters to improve the prediction ability of fatigue level, including;

[0110] Temperature (TEMP) indicator, including: monitoring skin temperature and related temperature regulation changes during the development of fatigue through an infrared temperature sensor;

[0111] Electromyogram (EMG) indicator, including: Local muscle physical fatigue can be detected by analyzing the changes in the median frequency or root mean square amplitude of the surface electromyogram signal;

[0112] By placing two bipolar surface electrodes on the target muscle, the corresponding electromyogram signal can be measured to estimate muscle activity;

[0113] Jerk metric, including: applying a wearable IMU motion capture system integrated with a magnetometer, an accelerometer, and a gyroscope, which can be used to detect the speed, acceleration, and body orientation of the jerk of the household fatigue.

[0114] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "including", "comprising", or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article, or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article, or device.

[0115] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A management platform based on medical and health big data, characterized in that: Including: Statistical analysis is performed on the time node data of the target community residents' usual entry and exit from the community. Based on the time node data of entering and exiting the community, the average going-out time of the target community residents is evaluated. The average going-out efficiency of the target community residents is obtained and analyzed. The average going-out efficiency is used to monitor the energy required for residents to go out. Based on the average going-out efficiency of the target community residents, the actual fatigue value of the target community residents is analyzed. The medical and health conditions corresponding to the actual fatigue value of the target community residents are detected and examined. If the medical and health value corresponding to the actual fatigue value of the target community residents is lower than the threshold value, medical assistance is provided to the target community residents regularly.

2. The management platform based on medical and health big data according to claim 1, characterized in that: The statistical analysis of the time node data of the target community residents' usual entry and exit from the community, the evaluation of the average going-out time of the target community residents based on the time node data of entering and exiting the community, and the obtaining and analysis of the average going-out efficiency of the target community residents include: A monitor is set at the entrance and exit of the community. The monitor is used to obtain the time nodes and passing times when residents enter and leave the community. The time node of entering the community is subtracted from the time node of leaving the community to obtain the residents' going-out time T, which is the average going-out time of the residents in the target community 1≤i≤n, where n is the number of samples of the residents' going-out times obtained by the monitor, and T i is the going-out times of multiple residents obtained by the monitor; Within the monitoring range of the monitor, the passing time of the household is obtained as t, and the straight-line distance within the monitoring range of the monitor is L, where L is a variable value. Then the going-out efficiency of the household where φ1 is the influence coefficient preset for the average going-out time of the households in the target community, φ2 is the influence coefficient preset for the passing time of the obtained household, and ε is the unit conversion parameter; Based on the average going-out efficiency S of the target community residents, the fatigue value of the target community residents is analyzed. At the same time, the non-fatigue value of the target community residents is detected and the non-fatigue value is buffered relative to the fatigue value.

3. The management platform based on medical and health big data according to claim 2, characterized in that: The analysis of the fatigue value of the target community residents based on the average going-out efficiency S of the target community residents includes: The situation of residents passing through the monitoring area is obtained through the monitor, including real-time monitoring, historical data query, and fatigue value monitoring model switching. Among them, the fatigue value monitoring model includes data processing and storage. The image and video data of residents passing through the monitoring range are processed. The image and video data are used to identify the eye movement characteristics of residents passing through the monitoring area. In the fatigue value detection model, the first eye movement characteristics of the residents leaving the monitoring range are compared with the second eye movement characteristics of the residents entering the monitoring range. And the fatigue value change influence factor Q corresponding to the absolute value of the difference between the first eye movement characteristics and the second eye movement characteristics is obtained through historical data query. Then the fatigue value Z of the target community residents = QS.

4. A management platform based on medical and health big data according to claim 2, characterized in that: The detection of the non-fatigue value of the target community residents and the buffering of the non-fatigue value relative to the fatigue value include: Through the lighting system set in the target community, the bright light situation in the target community area is obtained. Among them, the target community area includes the street lights in the community and the lighting range of residents' houses, and the target community area does not include the lighting range of external roads. If it is detected that the proportion of the moving time period of the selected time period from the current time node to the time node of leaving the community in the time curve exceeds 10%, it is recorded as a changed time node. The changed time node includes the moving time period moving forward in the time curve and the moving time period moving backward in the time curve. The moving time period moving forward in the time curve corresponds to the non-fatigue value, and the moving time period moving backward in the time curve corresponds to the fatigue value. According to the changed time node, the non-fatigue value is adjusted to the fatigue value in a preset model to obtain the actual fatigue value of the resident.

5. A management platform based on medical and health big data according to claim 4, characterized in that: The obtaining of the bright light situation in the target community area includes: Detect the brightness value within the target community area based on the lighting system, evaluate the number of light rays directly hitting the unit area within the target community area according to the brightness value of the unit area, and corresponding to the number of light rays, filter out the number of street lights in the unit area according to the preset lighting brightness model, and obtain the number of households with lights on in the unit area; Record the number of households with lights on in the unit areas of multiple target community areas in sequence and stack them up in sequence to obtain the total number of households with lights on in the target community area. When it is detected for the first time that the preset value of the total number of households with lights on is lower than the threshold value every day, record the current time node and select the time period from the current time node to the time node of leaving the community.

6. The management platform based on medical and health big data according to claim 1, characterized in that: Detect and test the actual fatigue value corresponding to the medical and health conditions of the households in the target community, including: After further obtaining the authorization of the household, conduct physiological index detection on the household, and obtain the medical and health value of the household in the target community according to the test of the physiological index, including: Heart Rate index, including: After a household has carried out a day of high-intensity work, as muscle contraction increases, the cardiovascular load also increases. The heart needs to transport more blood to the whole body, the amount of blood flowing to the muscles gradually increases, and the heart's output needs to be increased. The heart cannot instantaneously increase its stroke volume, so it increases the heart rate to improve blood transportation; Classify HR based on the reaction of HR to the severity of physical workload; Combine the heart rate index with other physiological parameters to improve the prediction ability of fatigue level, including; Temperature (TEMP) index, including: monitoring skin temperature and related temperature regulation changes during the development of fatigue through an infrared temperature sensor; Electromyogram (EMG) index, including: local muscle physical fatigue can be detected by analyzing the changes in the median frequency or root mean square amplitude of the surface electromyogram signal; By placing two bipolar surface electrodes on the target muscle, the corresponding electromyogram signal can be measured to estimate muscle activity; Jerk metric, including: applying a wearable IMU motion capture system integrated with a magnetometer, an accelerometer, and a gyroscope, which can be used to detect the speed, acceleration, and body orientation of the household's fatigue jerk; 7. A management system based on medical and health big data, characterized in that: including: An analysis module, which is used to statistically analyze the time node data of the target community households' usual entry and exit from the community, evaluate the average time away from home of the target community households based on the entry and exit time node data, obtain the average exit efficiency of the target community households and conduct analysis, and the average exit efficiency is used to monitor the energy required for the household to go out; A medical detection module, which is used to analyze the actual fatigue value of the target community households based on the average exit efficiency of the target community households, detect and test the medical and health conditions corresponding to the actual fatigue value of the target community households. If the medical and health value corresponding to the actual fatigue value of the target community households is lower than the threshold value, provide medical assistance to the target community households regularly.

8. A management platform based on medical and health big data according to claim 7, characterized in that: The analysis module includes: The first analysis module is used to set up monitors at the entrance and exit of the community. The monitors are used to obtain the time nodes and passing time of residents entering and leaving the community. The time node of entering the community minus the time node of leaving the community is used to obtain the resident’s outgoing time T. The average outgoing time of the residents in the target community is 1≤i≤n, n is the number of samples of residents’ going-out time acquired by the monitor, T i is the outgoing time of multiple residents obtained by the monitor; within the monitoring range of the monitor, the passing time of the residents is t, and the straight-line distance within the monitoring range of the monitor is L, where L is a variable value, then the outgoing efficiency of the residents Among them, φ1 is the preset influence coefficient of the average out-of-town time of the residents in the target community, φ2 is the preset influence coefficient of the passing time of the acquired residents, and ε is the unit conversion parameter; A second analysis module, which is used to analyze the fatigue value of the residents in the target community based on the average going-out efficiency S of the residents in the target community, and at the same time detect the non-fatigue value of the residents in the target community and buffer the non-fatigue value relative to the fatigue value; obtain the situation of the residents passing through the monitoring area through the monitor, including real-time monitoring, historical data query, and fatigue value monitoring model switching; among them, the fatigue value monitoring model includes data processing and storage, processes the image and video data of the residents passing through the monitoring range, and the image and video data are used to identify the eye characteristics of the residents passing through the monitoring area for identification. In the fatigue value detection model, the first eye characteristic of the resident leaving the monitoring range is compared with the second eye characteristic of the resident entering the monitoring range, and the fatigue value change influence factor Q corresponding to the absolute value of the difference between the first eye characteristic and the second eye characteristic is obtained through historical data query. Then, the fatigue value Z of the residents in the target community is Z = QS.

9. A management platform based on medical and health big data according to claim 8, characterized in that: The medical detection module includes: A first medical detection module, which is used to obtain the bright light situation in the target community area through the lighting system set in the target community. Among them, the target community area includes the street lights and the residential light range in the community, and the target community area does not include the external road light range; if it is detected that the proportion of the moving time period of the selected time period from the current time node to the time node of leaving the community in the time curve exceeds 10%, it is recorded as a change time node. The change time node includes the moving time period moving forward in the time curve and the moving time period moving backward in the time curve. The moving time period moving forward in the time curve corresponds to the non-fatigue value, and the moving time period moving backward in the time curve corresponds to the fatigue value; According to the change time node, adjust the fatigue value with the non-fatigue value in a preset model to obtain the actual fatigue value of the resident; A second medical detection module, which is used to detect the brightness value in the target community area based on the lighting system, evaluate the number of light rays directly hitting the unit area according to the brightness value of the unit area in the target community area, and corresponding to the number of light rays, screen and remove the number of street lights in the unit area according to the preset lighting illumination brightness model, and obtain the number of residents whose lights are not turned off in the unit area; record the number of residents whose lights are not turned off in multiple unit areas in the target community area in sequence and add them up in sequence to obtain the total number of residents whose lights are not turned off in the target community area. When it is detected for the first time that the preset value of the total number of residents whose lights are not turned off is lower than the limit value every day, record the current time node and select the time period from the current time node to the time node of leaving the community.

10. A management platform based on medical and health big data according to claim 9, characterized in that: The medical detection module further includes: An output module, which is used to further detect the physiological indicators of the resident after obtaining the authorization of the resident, and obtain the medical health value of the resident in the target community according to the physiological indicator test, including: Heart Rate indicator, including: After a household has carried out a day of high-intensity work, as muscle contraction increases, the cardiovascular load also increases. The heart needs to pump more blood to the whole body, and the amount of blood flowing to the muscles gradually increases. The heart needs to increase its output. The heart cannot instantaneously increase its stroke volume, so it increases the heart rate to improve blood transportation. Classify HR based on its response to the severity of the body's workload. Combine the heart rate indicator with other physiological parameters to improve the ability to predict fatigue levels, including: Temperature (TEMP) indicator, including: monitoring skin temperature and related thermoregulatory changes during the development of fatigue through an infrared temperature sensor. Electromyogram (EMG) indicator, including: local muscle body fatigue can be detected by analyzing changes in the median frequency or root mean square amplitude of the surface electromyogram signal. By placing two bipolar surface electrodes on the target muscle, the corresponding electromyogram signal can be measured to estimate muscle activity. Jerk metric, including: applying a wearable IMU motion capture system, integrated with a magnetometer, accelerometer, and gyroscope, which can be used to detect the speed, acceleration, and body orientation of the jerk of the household's fatigue.

Images