Health condition monitoring method, system, device, electronic device and storage medium

Abstract

This application provides a health status monitoring method, system, device, electronic device, and storage medium, applied in the field of occupational safety and health monitoring technology. The method includes acquiring the fused data to be detected and physiological data observations of a target individual; inputting the fused data to be detected into a time series prediction model to obtain the predicted physiological data values ​​of the target individual, the time series prediction model being constructed based on a long short-term memory network; determining the health risk score of the target individual based on the predicted physiological data values ​​and the observed physiological data values; and issuing an alarm and protection measure if the health risk score exceeds a maximum score threshold. This application refines the process to the individual level, utilizing deep learning algorithms to accurately predict the health status of a target individual based on their physiological data and fused data, quantitatively assessing the individual's health risk, promptly detecting health abnormalities, and taking corresponding early warning and protection measures to reduce the occurrence of heat-related diseases and accidents in high-temperature environments, thus ensuring personnel safety.

Description

Technical Field

[0001] This application relates to the field of occupational safety and health monitoring technology, and in particular to a health status monitoring method, system, device, electronic device, and storage medium. Background Technology

[0002] In high-temperature working environments such as factory workshops, high-temperature equipment workshops, and outdoor work in summer, high temperatures can easily cause health damage to workers. Studies have found that high-temperature work can lead to various health problems for workers, including acute heat-related illnesses (such as heatstroke, heat rash, and prickly heat) and chronic heat-related illnesses (such as chronic heat exhaustion, myocardial damage, digestive system diseases, and kidney stones). Among these, heatstroke is the most common and poses the greatest health hazard. Heatstroke refers to an acute systemic illness caused by heat balance and / or water-electrolyte metabolism disorders, as well as a reduction in effective circulating blood volume, resulting in elevated body temperature, central nervous system dysfunction, and cardiovascular dysfunction. Therefore, effective protective measures must be taken when working in high-temperature environments to reduce the risk of occupational health damage.

[0003] In related technologies, high-temperature prevention and control is achieved by monitoring the average temperature within the workplace. However, this method cannot detect abnormal conditions in individuals in a timely manner, leading to a lack of timely intervention. Summary of the Invention

[0004] This application provides a health status monitoring method, system, device, electronic device, and storage medium to achieve the effect of timely detection of abnormal conditions in an individual's body and timely intervention.

[0005] In a first aspect, embodiments of this application provide a health status monitoring method applied to a central monitoring system, comprising:

[0006] Acquire the target individual's fusion data and physiological data observations;

[0007] The fused data to be detected is input into the time series prediction model to obtain the predicted values ​​of the physiological data of the target individual. The time series prediction model is constructed based on the long short-term memory network.

[0008] Based on the predicted values ​​and observed values ​​of physiological data, the health risk score of the target individual is determined;

[0009] An alert will be triggered when the health risk score exceeds the highest score threshold.

[0010] In one possible implementation, an alarm is triggered when the health risk score exceeds a maximum score threshold, including:

[0011] If the health risk score is greater than or equal to the warning threshold and less than the emergency threshold, then Level 1 cooling measures will be activated. Level 1 cooling measures include activating ventilation facilities and activating cooling equipment.

[0012] If the health risk score is greater than or equal to the emergency threshold, Level 2 cooling measures will be activated and an evacuation alert will be sent.

[0013] In one possible implementation, a health risk score for the target individual is determined based on predicted and observed physiological data, including:

[0014] The health risk score of the target individual is determined based on the mean square error of the predicted values ​​and observed values ​​of physiological data.

[0015] In one possible implementation, the health monitoring method further includes:

[0016] Obtain the wet-bulb black-bulb temperature index of the target individual in the target work area; when the wet-bulb black-bulb temperature index is detected to be greater than or equal to the standard contact index, send the first warning information to the management server;

[0017] And / or, obtain the time information of the target individual's exposure to the high temperature environment; based on the time information, when the duration of the target individual's exposure to the high temperature environment is detected to be greater than or equal to the maximum working time threshold, send a second warning message to the management personnel server;

[0018] And / or, when the health risk score exceeds the highest score threshold, send a third warning message to the administrator's server.

[0019] In one possible implementation, the health monitoring method further includes:

[0020] Anomaly reports are sent to the administrator's server. These reports include multi-dimensional time-series charts, first warning information, second warning information, and third warning information.

[0021] Secondly, this application provides a health monitoring method applied to a wearable device, comprising:

[0022] Acquire physiological data of the target individual and temperature data of the environment in which it is located; the temperature data reflects the wet-bulb spherical temperature index.

[0023] Temperature data and physiological data are fused to obtain fused data;

[0024] The fused data is preprocessed to obtain the fused data to be detected;

[0025] Send the fusion data to be tested to the central monitoring system.

[0026] In one possible implementation, the health monitoring method further includes:

[0027] Obtain the wet-bulb sphere temperature index of the target individual in the target work area; send the wet-bulb sphere temperature index to the central monitoring system;

[0028] And / or, obtain information on the time when a target individual was exposed to a temperature greater than or equal to a standard high temperature; send the time information to the central monitoring system.

[0029] Thirdly, this application provides a health status monitoring method, applied to a server-side administrator, comprising:

[0030] Obtain health risk scores for multiple individuals within the target group, which are obtained through health status monitoring methods as described in the first aspect.

[0031] Based on the health risk score, determine the population health risk trend score for the target group;

[0032] When the population health risk trend score is greater than or equal to the population alert score threshold, the rotation frequency of the target population should be increased.

[0033] Fourthly, this application provides a health status monitoring device for use in a central monitoring system, comprising:

[0034] The acquisition module is used to acquire the fusion data to be detected and the physiological data observations of the target individual;

[0035] The input module is used to input the fused data to be detected into the time series prediction model to obtain the predicted values ​​of the physiological data of the target individual. The time series prediction model is built based on the long short-term memory network.

[0036] The determination module is used to determine the health risk score of a target individual based on predicted values ​​and observed values ​​of physiological data.

[0037] The alarm protection module is used to provide alarm protection when the health risk score exceeds the highest score threshold.

[0038] In one possible implementation, the alarm protection module is specifically used to: activate a first-level cooling measure if the health risk score is greater than or equal to the warning threshold and less than the emergency threshold, the first-level cooling measure including activating ventilation facilities and activating cooling equipment; and activate a second-level cooling measure and send an evacuation alarm if the health risk score is greater than or equal to the emergency threshold.

[0039] In one possible implementation, the determining module is specifically used to: determine the health risk score of the target individual based on the mean square error of the predicted values ​​of physiological data and the observed values ​​of physiological data.

[0040] In one possible implementation, the alarm protection module is further configured to: acquire the wet-bulb black bulb temperature index of the target individual in the target work area; and send a first warning message to the management server when the wet-bulb black bulb temperature index is detected to be greater than or equal to the standard contact index.

[0041] And / or, obtain the time information of the target individual's exposure to the high temperature environment; based on the time information, when the duration of the target individual's exposure to the high temperature environment is detected to be greater than or equal to the maximum working time threshold, send a second warning message to the management personnel server;

[0042] And / or, when the health risk score exceeds the highest score threshold, send a third warning message to the administrator's server.

[0043] In one possible implementation, the alarm protection module is also used to: send an anomaly report to the administrator's server, the anomaly report including a multi-dimensional time series chart, a first warning message, a second warning message and a third warning message.

[0044] Fifthly, this application provides a health monitoring device for wearable devices, comprising:

[0045] The acquisition module is used to acquire the physiological data of the target individual and the temperature data of its environment. The temperature data reflects the wet-bulb spherical temperature index.

[0046] The fusion module is used to fuse temperature data and physiological data to obtain fused data;

[0047] The preprocessing module is used to preprocess the fused data to obtain the fused data to be detected;

[0048] The sending module is used to send the fused data to be detected to the central monitoring system.

[0049] In one possible implementation, the sending module is further configured to: acquire the wet-bulb black-bulb temperature index of the target individual in contact with the target work area; and send the wet-bulb black-bulb temperature index to the central monitoring system.

[0050] And / or, obtain information on the time when a target individual was exposed to a temperature greater than or equal to a standard high temperature; send the time information to the central monitoring system.

[0051] Sixthly, this application provides a health status monitoring device, applied to a server-side administrator, comprising:

[0052] The acquisition module is used to acquire the health risk scores of multiple individuals within the target group. The health risk scores are obtained through the health status monitoring method described in the first aspect.

[0053] The determination module is used to determine the population health risk trend score for the target group based on the health risk score;

[0054] The adjustment module is used to increase the rotation frequency of the target group when the group health risk trend score is greater than or equal to the group alert score threshold.

[0055] Seventhly, this application provides a health status monitoring system, comprising:

[0056] The wet-bulb sphere temperature index meter is used to collect temperature data of the environment in which a target individual is located;

[0057] Wearable devices for performing any of the health monitoring methods in the second aspect;

[0058] A central monitoring system for implementing any of the health monitoring methods in the first aspect;

[0059] The administrator server is used to execute third-party health monitoring methods.

[0060] Eighthly, this application provides an electronic device, including: a memory and a processor;

[0061] The memory stores instructions that the computer executes;

[0062] The processor executes computer execution instructions stored in memory, causing the processor to perform any of the health monitoring methods described in the first, second, or third aspects above.

[0063] Ninthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed, are used to implement a health monitoring method as described in any one of the first, second, or third aspects.

[0064] In a tenth aspect, this application provides a computer program product, including a computer program that, when executed, implements a health monitoring method as described in any one of the first, second, or third aspects.

[0065] The health status monitoring method, system, device, electronic equipment, and storage medium provided in this application are applied to a central monitoring system. The health status monitoring method includes: acquiring the fusion data to be detected and the physiological data observation values ​​of a target individual; inputting the fusion data to be detected into a time series prediction model to obtain the physiological data prediction values ​​of the target individual, the time series prediction model being constructed based on a long short-term memory network; determining the health risk score of the target individual based on the physiological data prediction values ​​and the physiological data observation values; and issuing an alarm and protection when the health risk score exceeds a maximum score threshold. This application utilizes deep learning algorithms, refined to the individual level, to accurately predict the health status of the target individual based on their physiological data and multi-dimensional fusion data, and to quantitatively assess the individual's health risk, promptly detecting individual health abnormalities and taking corresponding early warning and protection measures. This helps reduce the occurrence of heat-related diseases and workplace accidents in high-temperature environments, ensuring personnel safety. Attached Figure Description

[0066] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0067] Figure 1 A schematic diagram of a scenario for a health monitoring method provided in an embodiment of this application;

[0068] Figure 2 Flowchart of the health monitoring method provided in the embodiments of this application Figure 1 ;

[0069] Figure 3 Flowchart of the health monitoring method provided in the embodiments of this application Figure 2 ;

[0070] Figure 4 Flowchart of the health monitoring method provided in the embodiments of this application Figure 3 ;

[0071] Figure 5 Flowchart of the health monitoring method provided in the embodiments of this application Figure 4 ;

[0072] Figure 6 Schematic diagram of the health monitoring system provided in the embodiments of this application Figure 1 ;

[0073] Figure 7 Schematic diagram of the health monitoring system provided in the embodiments of this application Figure 2 ;

[0074] Figure 8 Schematic diagram of the health status monitoring device provided in the embodiments of this application Figure 1 ;

[0075] Figure 9 Schematic diagram of the health status monitoring device provided in the embodiments of this application Figure 2 ;

[0076] Figure 10 Schematic diagram of the health status monitoring device provided in the embodiments of this application Figure 3 ;

[0077] Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0078] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0079] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0080] Studies have found that working in high temperatures can lead to various health problems for workers, with heatstroke being the most common and posing the greatest health hazard. Heatstroke can be divided into three types: heat cramps, heat exhaustion, and heatstroke. Heat cramps are caused by excessive sweating and loss of sodium and potassium, mainly manifested as significant muscle spasms accompanied by contraction pain, most commonly affecting the limbs and abdominal muscles, which are frequently used. Heat exhaustion is caused by insufficient blood volume, generally with a rapid onset, and may present with excessive sweating, significantly increased heart rate, low blood pressure, slightly elevated body temperature, dizziness, headache, and may also be accompanied by vertigo and fainting. Heatstroke is caused by obstructed heat dissipation pathways and dysfunction of the body's thermoregulation mechanism, mainly manifested as a significant increase in body temperature to above 40°C, accompanied by altered consciousness and coma, with a high mortality rate. Therefore, effective protective measures must be taken when working in high-temperature environments to reduce the risk of occupational health damage.

[0081] In related technologies, high-temperature prevention and control only involves broadly calculating the average temperature in the workplace, without monitoring and protecting the health status of individual individuals in high-temperature environments. Therefore, it often fails to detect abnormal physical conditions in a timely manner.

[0082] To address the aforementioned technical problems, this application provides a health status monitoring method, system, device, electronic device, and storage medium. By monitoring the temperature data of an individual's environment and individual physiological data in a high-temperature environment, deep learning algorithms are used to predict the individual's health status in advance and quantify and assess the individual's health risks. This ensures the timely detection and intervention of abnormal physical conditions of workers, helps reduce the occurrence of heat-related diseases and work accidents in high-temperature environments, and protects personnel safety.

[0083] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0084] Figure 1 This is a schematic diagram illustrating a scenario of a health monitoring method provided in an embodiment of this application. Figure 1 As shown, this application scenario includes a wet-bulb thermometer 11, a central monitoring system 12, a management server 13, and a wearable device 14. The wet-bulb thermometer 11 is installed in a high-temperature workplace to collect real-time temperature data from the high-temperature environment. The wet-bulb thermometer 11 can wirelessly communicate with the wearable device 14 and the central monitoring system 12, sending the collected temperature data to both. The wearable device 14 can monitor individual physiological data, such as heart rate, blood pressure, and body temperature. The wearable device 14 can wirelessly communicate with the central monitoring system 12, sending the collected data to the central monitoring system 12. The central monitoring system 12 analyzes and processes the received data, assesses individual health risks, and triggers corresponding alarms and protective measures. The central monitoring system 12 also communicates with the management server 13, sending relevant alarm and protective information to the management server 13, facilitating relevant management personnel to monitor the health status of the employee group and take protective measures.

[0085] It should be noted that the individual wears a wearable device 14 with monitoring data function. The wearable device 14 is equipped with various sensors to collect the individual's physiological data. The wearable device 14 can be, for example, a smart bracelet, smart clothing, smart ring, smart earphone, etc. The central monitoring system 12 and the management server 13 can be deployed on a server, server cluster, or virtual resource, etc. This application does not limit this, nor does it limit the number of servers. There is no limit to the number of wet bulb thermometers 11. Wireless communication is not limited to Bluetooth or Wi-Fi.

[0086] The following is combined Figure 1 Application scenarios, refer to Figure 2 This application describes a health monitoring method provided in one embodiment. The health monitoring method is implemented using a wet-bulb spherical temperature index meter 11, a central monitoring system 12, a management server 13, and a wearable device 14. It should be noted that the above application scenarios are shown only to facilitate understanding of the spirit and principles of this application, and the implementation of this application is not limited to... Figure 1 The limitations of the application scenarios shown.

[0087] Figure 2 Flowchart of the health monitoring method provided in the embodiments of this application Figure 1 , refer to Figure 2 As shown in the embodiment of this application, the health status monitoring method is applied to the central monitoring system 12. The health status monitoring method includes:

[0088] S201. Obtain the fusion data to be detected and the physiological data observations of the target individual.

[0089] The fusion data to be detected is generated based on the physiological data of the target individual and the temperature data of the high-temperature environment, and can be understood as historical data. The physiological data observations can be understood as current data.

[0090] In one implementation, the central monitoring system 12 obtains the fusion data to be detected and the physiological data observation values ​​from the wearable device 14 via wireless communication. For example, the central monitoring system 12 and the wearable device 14 establish signal interaction, and the wearable device 14 periodically sends the fusion data to be detected to the central monitoring system 12 and sends the physiological data observation values ​​in real time.

[0091] In another implementation, the central monitoring system 12 obtains the fusion data to be detected from other storage servers. These storage servers also have a certain computing power. The storage servers obtain physiological data of the target individual from the wearable device 14 and temperature data of the high-temperature environment from the wet-bulb sphere temperature index meter 11. The physiological data and the temperature data of the high-temperature environment are fused and calculated to obtain the fusion data to be detected.

[0092] If the central monitoring system 12 acquires the fused data to be detected from the wearable device 14, then in some embodiments, the health status monitoring method is applied to the wearable device 14, such as... Figure 3 Flowchart of the health monitoring method provided in the embodiments of this application Figure 2 As shown, health status monitoring methods include:

[0093] S301. Obtain physiological data of the target individual and temperature data of the environment in which it is located. The temperature data reflects the wet-bulb spherical temperature index.

[0094] The temperature data of the environment is collected by a wet-bulb black-sphere temperature index (WBGT) meter installed in the high-temperature workplace. The WBGT meter then transmits the temperature data to a wearable device via wireless communication, thus enabling the wearable device to acquire the temperature data of the target individual's environment. In this application, the temperature data can also be referred to as the wet-bulb black-sphere temperature index or the WBGT index. Let's assume the temperature data for the j-th time period is represented as WBGT. j .

[0095] The physiological data of the target individual includes heart rate data, blood pressure data (including systolic and diastolic blood pressure data), and body temperature data. For example, the physiological data of the target individual is collected by wearing a wearable device. This wearable device is heat-resistant, such as a wristwatch, and is equipped with sensors, including a heart rate monitoring sensor, a body surface temperature monitoring sensor, a blood pressure index sensor, a position sensor, and a main processor. The main processor can acquire the target individual's heart rate data from the heart rate monitoring sensor, blood pressure data from the blood pressure index sensor, and body temperature data from the body surface temperature monitoring sensor.

[0096] Furthermore, the physiological data collected by the wearable device for the target individual specifically includes (assuming the i-th individual is the target individual): collecting the physiological data of the i-th individual in the j-th time period, including heart rate data H. i,j And systolic blood pressure data SP i,j DP and diastolic blood pressure data i,j and body surface temperature data ST i,j .

[0097] S302. The temperature data and physiological data are fused to obtain fused data.

[0098] For example, based on the fusion algorithm, the main processor combines the physiological data of the i-th individual in the j-th time period with the temperature data WBGT in the j-th time period. j The data is fused to obtain a multi-dimensional fused dataset F. i,j .

[0099] S303. Preprocess the fused data to obtain the fused data to be detected.

[0100] For example, the main processor processes the fused dataset F i,j Outlier removal and normalization are performed to obtain the fused data to be detected.

[0101] This application combines the physiological data of the target individual with the WBGT index of their work environment, providing a more comprehensive dataset for assessing the individual's physiological response and heat stress risk in high-temperature environments, thus improving the accuracy of time series prediction models. By removing outliers, the impact of erroneous data on the analysis results is reduced. Normalization processing allows data from different sources and with different dimensions to be compared and analyzed on the same scale, which helps improve the accuracy of data analysis and provides standardized input for subsequent time series prediction models, thereby improving the reliability of time series prediction models.

[0102] S202. Input the fused data to be detected into the time series prediction model to obtain the predicted values ​​of the physiological data of the target individual. The time series prediction model is constructed based on the long short-term memory network.

[0103] The time series prediction model is built upon a Long Short-Term Memory (LSTM) network. LSTM is a special type of recurrent neural network specifically designed to process and predict long-term dependencies in sequential data, i.e., to predict future trends and changes. Therefore, the time series prediction model can predict the physiological data of a target individual at a future target time in the short term, as these data change over time.

[0104] When constructing a time series prediction model, the model structure of the Long Short-Term Memory Network is first set. This model structure includes setting an input layer, an LSTM layer, and a fully connected layer. Using the Long Short-Term Memory Network is a conventional technique, and this will not be described in detail in the embodiments of this application.

[0105] Based on the prediction function of the time series prediction model, the fused data to be detected can be input into the time series prediction model to obtain the predicted values ​​of the physiological data of the target individual.

[0106] For example, input the fusion data to be detected {F i,j-n ,…F i,j-1 ,F i,j The fused data to be detected represents historical data from the past n time periods, and the predicted physiological data values ​​{S} for the next m time periods are obtained. i,j+1 ,S i,j+2 ,…S i,j+m}, where i, j, and m are all integers greater than or equal to 1, and n is an integer greater than or equal to 0.

[0107] S203. Determine the health risk score of the target individual based on the predicted values ​​and observed values ​​of physiological data.

[0108] Wearable devices monitor and collect physiological data of target individuals in real time and send it to a central monitoring system. For any time period within the next m time intervals, the predicted physiological data value for that time interval is compared with the actual observed physiological data value for that time interval. The error between the predicted and observed physiological data values ​​is calculated, such as a simple difference calculation or a more complex error measure (e.g., mean squared error, absolute error, etc.). The error result is used as the health risk score for the target individual. Optionally, data features, such as the mean, standard deviation, maximum, and minimum values ​​of the error, can be extracted from the error result. Machine learning algorithms (e.g., decision trees, random forests, support vector machines, etc.) or statistical models (e.g., logistic regression) can then be used to convert the extracted features into a health risk score.

[0109] S204. When the health risk score is greater than the highest score threshold, an alarm protection will be activated.

[0110] The higher the health risk score of a target individual, the greater the probability of abnormal health conditions.

[0111] For example, the central monitoring system has a preset maximum score threshold. When the health risk score is detected to be greater than the maximum score threshold, an alarm protection mechanism is triggered. For example, the system may remind the target individual to rest in time through wearable devices, or control and adjust the environmental parameters of the target individual's work environment, or prompt relevant managers to take relevant protective measures, etc.

[0112] It is understandable that the central monitoring system issues alerts and protections based on health risk scores, which is an early warning of physiological data at future time points, allowing for corresponding measures to be taken in advance.

[0113] Optionally, health risk scores can be mapped to specific risk levels, and corresponding health advice and interventions can be provided based on different risk levels.

[0114] This application embodiment utilizes multi-dimensional fused data generated from the physiological data of a target individual and the temperature data of a high-temperature environment, and employs an LSTM network algorithm for time series prediction to accurately predict the physiological data of the target individual in a high-temperature environment. Based on the predicted and observed physiological data, the health risks of the target individual are precisely assessed, enabling accurate prediction of any abnormal physical conditions. This provides real-time health monitoring and early warning for individuals in high-temperature environments, facilitating timely preventative measures, reducing heat-related illnesses and accidents, and ensuring operational safety. Furthermore, the assessment of individual health status allows for more rational work and rest scheduling, improving work efficiency.

[0115] In some embodiments, an alarm is triggered when the health risk score exceeds a maximum score threshold, including the following possible implementations:

[0116] In one implementation, if the health risk score is greater than or equal to the warning threshold and less than the emergency threshold, then a Level 1 cooling measure is initiated. The Level 1 cooling measure includes activating ventilation facilities and activating cooling equipment.

[0117] It is understandable that the central monitoring system has preset warning thresholds, emergency thresholds, and maximum score thresholds. The maximum score threshold is lower than the warning threshold, and the warning threshold is lower than the emergency threshold.

[0118] For example, the specific risk level can be determined based on the health risk score. If the health risk score is greater than the highest score threshold but less than the warning threshold, the risk level is low. In this case, cooling measures may not be initiated, and the target individual may only be advised to rest. If the health risk score is greater than or equal to the warning threshold but less than the emergency threshold, the risk level is medium. In this case, level one cooling measures are initiated. If the health risk score is greater than or equal to the emergency threshold, the risk level is high. In this case, level two cooling measures are initiated.

[0119] In another implementation, if the health risk score is greater than or equal to the emergency threshold, a level-two cooling measure is initiated and an evacuation alert is sent.

[0120] Among them, the secondary cooling measure is a more rapid response operation compared to the primary cooling measure.

[0121] For example, secondary cooling measures include not only activating ventilation facilities and cooling equipment, but also opening ventilation ducts and shutting down heat-generating equipment. Opening ventilation ducts involves opening the main ventilation windows and doors in the workshop or factory walls to quickly ventilate and cool the interior. Shutting down heat-generating equipment includes shutting down some non-critical equipment that generates significant heat, lighting systems, and other equipment.

[0122] In addition, evacuation alerts are sent, such as sound alarms, visual alarms, notifications sent via mobile applications or broadcast systems.

[0123] It should be noted that the central monitoring system can either send alarm protection commands to the management personnel's server, which then executes corresponding alarm protection measures. For example, the management personnel's server might instruct manual execution of Level 1 or Level 2 cooling measures. Alternatively, the management personnel's server could connect to an IoT system to automatically control the cooling and ventilation equipment within the IoT system. The central monitoring system can also directly send alarm protection commands to the IoT system, meaning the central monitoring system connects to the IoT system and directly controls the cooling and ventilation equipment within the IoT system. This application does not impose any limitations on this aspect.

[0124] In this embodiment of the application, by using pre-set warning thresholds, emergency thresholds, and maximum score thresholds, the central monitoring system can automatically adopt a graded early warning mechanism based on the health risk score and initiate corresponding cooling measures. The graded early warning mechanism makes the response measures more refined and can take appropriate measures according to the actual situation to avoid overreaction or underreaction.

[0125] In some embodiments, determining a target individual's health risk score based on predicted and observed physiological data includes determining the target individual's health risk score based on the mean squared error of the predicted and observed physiological data.

[0126] For example, the predicted value of physiological data is represented as S. i,j+k k = 1, 2, ..., m, and the actual physiological data observations are represented as O i,j+k The health risk score of target individual i is represented as R. i,j That is, mean square error R i,j satisfy:

[0127]

[0128] Where i represents the index of an individual, for example, i=1 represents the first individual (the first worker individual); j represents the index of a time period, which usually refers to a specific point in time or time period, for example, j=1 represents the data of the first time period; k represents the offset of the future time period, which is usually used to predict the future time period, for example, j+k represents the kth time period after time period j.

[0129] In this embodiment, the mean squared error of the predicted and observed physiological data is used as the health risk score for the target individual, providing a quantitative assessment of the individual's health status and algorithmic support for early warning and intervention mechanisms. In addition, the higher the mean squared error, the greater the deviation between the predicted and actual physiological states, and the greater the potential health risk. By continuously monitoring the changes in the mean squared error, the deterioration trend of health status can be identified in a timely manner, thereby issuing early warnings and intervening promptly.

[0130] In some embodiments, the health status monitoring method further includes: obtaining the wet-bulb black-bulb temperature index of the target individual in the target work area; and sending a first warning message to the management personnel server when the wet-bulb black-bulb temperature index is detected to be greater than or equal to the standard contact index.

[0131] In occupational disease prevention and control, exposure level is used to assess the potential health risks of hazardous substances in the workplace. Exposure level reflects, to some extent, the intensity of the high temperatures that workers are exposed to within a specific timeframe. In this application, exposure level can also be expressed using the Wet Bulb Black Sphere Temperature Index (WBGT), which is an indicator used to evaluate the intensity of high-temperature workshops. It provides a basic parameter to assess the heat load on the human body exposed to the work environment.

[0132] The central monitoring system can obtain the wet-bulb temperature index of the target individual in the target work area from wearable devices.

[0133] For example, the target individual wears a wearable device, and the main processor in the wearable device records in real time the individual's dwell time at the work location, as well as the corresponding WBGT index encountered during the dwell time at the current work location. Correspondingly, in some embodiments, the health status monitoring method is applied to the wearable device, specifically including: acquiring the wet-bulb sphere temperature index encountered by the target individual in the target work area, and sending the wet-bulb sphere temperature index to a central monitoring system.

[0134] The WBGT index is obtained by measuring the temperature data of the high-temperature environment in real time using a wet-bulb black-bulb temperature index (WBGT index) measuring instrument installed in a high-temperature workplace. The WBGT index measuring instrument then sends the temperature data of the high-temperature environment to a wearable device worn by the target individual.

[0135] In other words, the wearable device obtains the wet-bulb black bulb temperature index of the target individual in the target work area from the WBGT index meter and then sends it to the central monitoring system.

[0136] Wearable devices not only collect an individual's heart rate, blood pressure, and body temperature data, but also record the individual's activity range and work location through position sensors, as well as the time spent at specific locations and their corresponding WBGT index. This multi-parameter data fusion provides more comprehensive information on the work environment and individual physiological state.

[0137] It should be noted that the temperature data of the high-temperature environment measured by the WBGT index meter can be sent to the wearable device on the individual being sensed, so that the data information can be uploaded to the central monitoring system through the wearable device within the sensing range; it should also be noted that even when the WBGT index meter does not sense the terminal device (i.e., the wearable device), the WBGT index meter can still directly upload the temperature data of the high-temperature environment to the central monitoring system online.

[0138] It is understandable that WBGT index measuring instruments or wearable devices transmit the collected data to the central monitoring system via wireless communication, enabling remote and real-time data transmission, which facilitates subsequent centralized data analysis by the central monitoring system with higher computing power.

[0139] Accordingly, the central monitoring system receives real-time records of the individual's dwell time at the work location and simultaneously records the corresponding WBGT index encountered during the dwell time at the current work location, and accumulates the corresponding WBGT index encountered during the dwell time at the current work location; if the corresponding WBGT index encountered during the dwell time at the current work location exceeds the standard contact index, an alarm command is triggered, sending a first warning message to the management server. Further, the first warning message may include the wearable device ID of the current (target) individual and the accumulated corresponding WBGT index encountered during the dwell time at the current work location (target work area).

[0140] This application embodiment achieves real-time monitoring of both the high-temperature environment and individual physiological state by acquiring temperature data and individual physiological data. This real-time monitoring helps to promptly detect abnormal changes in both the environment and individual physiology. Furthermore, real-time monitoring and timely alerts help reduce workplace accidents in high-temperature environments and improve worker safety. Simultaneously, assessing individual health conditions facilitates the rational arrangement of work and rest, improving work efficiency.

[0141] In some embodiments, the health status monitoring method further includes: acquiring time information of the target individual's exposure to a high-temperature environment; and based on the time information, sending a second warning message to the management server when the duration of the target individual's exposure to a high-temperature environment is detected to be greater than or equal to the maximum working time threshold.

[0142] The central monitoring system can obtain information on the duration of a target individual's exposure to high-temperature environments from wearable devices.

[0143] For example, an individual wears a wearable device. The main processor in the wearable device collects position change data from the individual's position sensors to calculate the individual's activity range and current working position, and simultaneously collects the number of times the individual was exposed to temperatures exceeding the standard high temperature value. Correspondingly, in some embodiments, the health status monitoring method applied to the wearable device further includes: acquiring information on the time the individual was exposed to temperatures greater than or equal to the standard high temperature value, and sending the time information to a central monitoring system.

[0144] The central monitoring system receives time information from wearable devices and calculates the current duration of exposure to temperatures exceeding the standard high temperature. If the current duration exceeds the maximum working time threshold, an alarm command is triggered, sending a second warning message. The second warning message includes the wearable device ID of the target individual and the current duration.

[0145] It is understandable that the above-mentioned second warning information refers to the need to monitor the duration of an individual's exposure to high temperatures even if the corresponding WBGT index during the stay period does not exceed the standard exposure index, and use this as an indicator for duration monitoring; that is, long-term exposure to high-temperature environments is prone to physical abnormalities, so even if there are no physical abnormalities, the maximum working hours threshold should be used to limit it.

[0146] In this embodiment, when the duration of exposure of a target individual to a high-temperature environment is greater than or equal to the maximum working time threshold, a second early warning message is sent to the management personnel server to promptly remind the management personnel to take necessary protective measures to prevent the occurrence of heat-related diseases.

[0147] In some embodiments, the health status monitoring method further includes sending a third early warning message to the administrator server when the health risk score is greater than the highest score threshold.

[0148] For example, the third warning information may include the wearable device ID of the target individual and the target individual's health risk score.

[0149] Based on the above embodiments, in some embodiments, the health status monitoring method may further include: sending an abnormal situation report to the management personnel server, the abnormal situation report including a multi-dimensional time series chart, a first warning information, a second warning information and a third warning information.

[0150] For example, multi-dimensional time series charts can show the trends of key indicators and data related to anomalies over time. To ensure that the charts are clear and easy to understand, data can be displayed in the form of line charts, bar charts, or heatmaps.

[0151] In this embodiment of the application, by sending anomaly reports to the management personnel's server, detailed data analysis and decision support are provided to the management personnel's server, enabling the management personnel to understand the on-site situation in a timely manner, make rapid responses, and improve management efficiency and response speed.

[0152] Based on the above embodiments, such as Figure 4 Flowchart of the health monitoring method provided in the embodiments of this application Figure 3 As shown, the health status monitoring method can also be applied to the server side for administrators, including:

[0153] S401. Obtain health risk scores for multiple individuals within the target group.

[0154] For example, the administrator server obtains health risk scores for multiple individuals within a target group from a central monitoring system.

[0155] S402. Based on the health risk score, determine the population health risk trend score for the target group.

[0156] For example, calculate the average health risk score R for all individuals over a consecutive t-day period. t , Where N is the total number of individuals, R i,t R is the health risk score of the i-th individual over a continuous period of t days. t It is also recorded as the population health risk trend score of the target group.

[0157] It should be noted that wearable devices are used to collect physiological data of the i-th individual during the j-th time period, and then the health risk score R of the i-th individual during the j-th time period is obtained through S201 to S203. i,j Finally, the health risk score R for the t-day period can be calculated. i,t .

[0158] S403. When the population health risk trend score is greater than or equal to the population alert score threshold, increase the rotation frequency of the target population.

[0159] A preset rotation frequency is defined, based on the average health risk score R within a consecutive rotation cycle. t When the group alert score threshold is exceeded, the rotation frequency within the current (target) group is adjusted and increased.

[0160] In this embodiment, the health risk trend score of the group is calculated by the administrator server, and the rotation frequency within the current group is adjusted and increased according to the health risk trend score. This intelligent adjustment helps to reasonably arrange the working hours of the staff, reduce the impact of high temperature on individual health, improve work efficiency, and help improve the safety of individuals in high temperature environments, and reduce health problems and work accidents caused by high temperature.

[0161] The health status monitoring method provided in this application will be described next through a specific embodiment. Figure 5 Flowchart of the health monitoring method provided in the embodiments of this application Figure 4 .like Figure 5 As shown, health status monitoring methods include:

[0162] S501. Install a wet-bulb black-bulb temperature index meter in high-temperature workplaces to measure temperature data of the high-temperature environment in real time.

[0163] The WBGT index is used as the basic parameter for evaluating the heat load of human exposure in the work environment in this application. The WBGT index provides calculation methods for measuring the WBGT index of different parts of the human body and the weighted WBGT index for different exposure times. Specifically, a WBGT index measuring instrument is used to measure the temperature data of the head, abdomen, and ankle height of the human body.

[0164] The WBGT index measuring instrument has a measurement range of 21℃ to 49℃ and can be used for direct measurement. It includes a dry-bulb thermometer (measurement range 10℃ to 60℃), a wet-bulb thermometer (measurement range 5℃ to 40℃), and a black bulb thermometer (150mm or 50mm diameter black bulb, measurement range 20℃ to 120℃). The WBGT index measuring instrument measures these three temperatures respectively, and the WBGT index is calculated using the following formula.

[0165] For outdoor conditions: WBGT = wet bulb temperature (°C) × 0.7 + black bulb temperature (°C) × 0.2 + dry bulb temperature (°C) × 0.1.

[0166] For indoor conditions: WBGT = wet-bulb temperature (°C) × 0.7 + black bulb temperature (°C) × 0.3.

[0167] The measurement method of the WBGT index measuring instrument includes the preparation stage and the selection of measuring points.

[0168] Preparation stage: Before measurement, the instrument should be calibrated according to the instruction manual. Ensure the water tank of the wet-bulb thermometer is filled with distilled water, and that the cotton wick is clean and fully moistened; do not add tap water. During startup, if the displayed battery voltage is low, replace the battery or recharge it. A stabilization period of 10 minutes is required before measurement or after adding water.

[0169] The selection of measurement points includes the number and location of measurement points. Number of measurement points: For workplaces without productive heat sources, select 3 measurement points and take the average value; for workplaces with productive heat sources, select 3-5 measurement points and take the average value; for workplaces isolated into different thermal or ventilation environments, set up 2 measurement points in each area and take the average value. Measurement point location: Measurement points should include the work locations with the highest temperature and the worst ventilation. Since workers are mobile, measurements should be taken at relatively fixed work locations within the mobile area to calculate the time-weighted WBGT index. Measurement height: 1.5m for standing work; 1.1m for sitting work. When the actual heat exposure of workers is uneven, the head, abdomen, and ankle should be measured separately: 1.7m, 1.1m, and 0.1m for standing work; 1.1m, 0.6m, and 0.1m for sitting work.

[0170] The average value of the WBGT index satisfies formula (2):

[0171]

[0172] Wherein, WBGT is the average of the WBGT exponent; WBGT 头 To measure the WBGT index of the head; WBGT 腹 To measure the abdominal WBGT index; WBGT 踝 To measure the WBGT index of the ankle.

[0173] Optionally, WBGT can also be used for auxiliary reference calculation by contacting different time-weighted WBGT indices, and the calculation of the time-weighted average WBGT index satisfies formula (3);

[0174]

[0175] in, The time-weighted average WBGT exponent; t1+t2+…+t n The actual time a worker spends at the 1st, 2nd, ..., nth work location; WBGT1, WBGT2, ..., WBGT n Let time be t1, t2…t n The average value of the WBGT index at that time.

[0176] Temperature data from high-temperature environments are sent to wearable devices worn by individuals and / or a central monitoring system.

[0177] S502. Wearable devices are worn on individuals to collect data on the number of times an individual is exposed to temperatures exceeding standard high temperatures, the corresponding WBGT index during the time spent at the current work location, and the individual's physiological data.

[0178] The wearable device is a high-temperature resistant device. It is a wristwatch-style wearable device equipped with sensors, including a heart rate monitoring sensor, a body surface temperature monitoring sensor, a blood pressure index sensor, a position sensor, and a main processor.

[0179] The main processor collects position change data from the individual's position sensors to calculate the individual's activity range and current working position, and simultaneously collects the number of times the individual is exposed to temperatures exceeding the standard high temperature. The main processor also records the individual's dwell time at the current working position in real time and synchronously records the corresponding WBGT index during the dwell time at the current working position. The main processor also obtains the individual's heart rate data from the heart rate monitoring sensor, the blood pressure data from the blood pressure index sensor, and the body temperature data from the body surface temperature monitoring sensor.

[0180] The main processor fuses the physiological data obtained from monitoring with the temperature data acquired from the WBGT index meter to obtain the fused data to be detected. See S301 to S303 for details, which will not be repeated here.

[0181] S503. The collected data is transmitted to the central monitoring system using a wireless communication module.

[0182] Wearable devices communicate wirelessly with the central monitoring system, such as via Wi-Fi or Bluetooth, to transmit the observed values ​​of the fused data and physiological data to the central monitoring system.

[0183] The main processor in the wearable device records the time an individual spends at the work location in real time, and simultaneously records the corresponding WBGT index encountered during the time spent at the work location, and sends the recorded data to the central monitoring system.

[0184] In wearable devices, the main processor collects position change data from the individual's position sensors to calculate the individual's activity range and current working position. It also collects the number of times the individual is exposed to temperatures exceeding standard high temperatures and sends this data to the central monitoring system.

[0185] S504 The central monitoring system analyzes and processes the received data and outputs the analysis results.

[0186] A time series prediction model is deployed on the central monitoring system (see S202). The fused data to be detected is regarded as historical data and represented as matrix X. The physiological data prediction values ​​S for the next m time periods are predicted by the time series prediction model.

[0187]

[0188] It can be understood that inputting matrix X into a time series prediction model yields an output S; if we denote the output of the time series prediction model as Y, then Y = LSTM(X), thus obtaining the predicted physiological data value S. i,j+k , k=1,2,…m.

[0189] For example, for a given individual (i=1), historical data is input into a time series forecasting model to predict physiological data S for the next 5 time periods. 1,j+1 To S 1,j+5 The mean squared error between predicted physiological data and actual observed physiological data (e.g., physiological data measured during subsequent training) is calculated to derive the individual's health risk score R. 1,j .

[0190] S505. Assess individual health risks based on the analysis results.

[0191] Based on the mean squared error of the predicted values ​​and observed values ​​of physiological data, a health risk score is determined for the target individual to assess individual health risk.

[0192] S506. When an abnormal amount of contact or prolonged exposure to high temperatures is detected, or when the physiological data of the individual being tested is abnormal, an alarm mechanism is triggered.

[0193] Among them, an alarm mechanism is triggered when abnormal contact is detected. Specifically, when the wet-bulb black bulb temperature index of the target individual in the target work area is greater than or equal to the standard contact index, the first warning information is sent to the management server.

[0194] An alarm mechanism is triggered when prolonged exposure to high temperatures is detected. Specifically, when the duration of exposure of a target individual to a high-temperature environment is greater than or equal to the maximum working time threshold, a second warning message is sent to the management server.

[0195] An alarm mechanism is triggered when an individual's physiological data is detected to be abnormal. Specifically, when the health risk score of a target individual exceeds the highest score threshold, a third-level warning message is sent to the administrator's server, and alarm protection is implemented. Specifically, as described in the above embodiment, a tiered warning mechanism is automatically adopted based on the health risk score, and corresponding cooling measures are initiated, such as initiating a level one cooling measure or a level two cooling measure.

[0196] In summary, this application has at least the following advantages:

[0197] First, wearable devices not only collect an individual's heart rate and blood pressure data, but also record the individual's activity range and work location through location sensors, as well as the time spent at specific locations and their corresponding WBGT index. This multi-parameter data fusion provides more comprehensive information on the work environment and individual physiological state.

[0198] Second, the LSTM network algorithm is used for time series prediction to accurately predict the physiological data of target individuals in high-temperature environments. Based on the predicted and observed physiological data, the health risks of target individuals are accurately assessed, enabling accurate prediction of abnormal physical conditions. This provides real-time health monitoring and early warning for individuals in high-temperature environments, facilitating timely preventive measures, reducing the occurrence of heat-related diseases and accidents, and ensuring operational safety.

[0199] Third, by installing WBGT index measuring instruments and wearable devices worn by individuals in high-temperature workplaces, real-time monitoring of ambient temperature and individual physiological states (such as heart rate, blood pressure, and body temperature) can be achieved. This monitoring helps to promptly detect abnormal changes in the environment and individual physiology.

[0200] Fourth, an automatic tiered early warning mechanism is adopted based on health risk scores. When the health risk score exceeds the threshold of different levels, the system will activate different levels of cooling measures to mitigate the impact of high temperatures on individuals. This tiered early warning mechanism allows for more refined response measures, enabling appropriate actions to be taken based on the actual situation, avoiding overreaction or underreaction.

[0201] Fifth, the central monitoring system sends abnormal situation reports to the management server, enabling managers to understand the on-site situation in a timely manner, make rapid responses, and improve management efficiency and response speed. In addition, the management server calculates the group health risk trend score and adjusts the rotation frequency within the current group according to the group health risk trend score. This intelligent adjustment helps to reasonably arrange employees' working hours, reduce the impact of high temperature on individual health, and improve work efficiency.

[0202] Figure 6 Schematic diagram of the health monitoring system provided in the embodiments of this application Figure 1 ,like Figure 6 As shown, the health status monitoring system 60 provided in this application includes: a wet-bulb thermometer 11, a wearable device 14, a central monitoring system 12, and a management server 13. Wherein:

[0203] The wet-bulb black-bulb temperature index meter 11 is used to collect temperature data of the environment in which the target individual is located.

[0204] Wearable device 14 is used to perform the following: acquiring physiological data of the target individual and temperature data of the environment, the temperature data reflecting the wet-bulb spherical temperature index; fusing the temperature data and physiological data to obtain fused data; and preprocessing the fused data to obtain fused data to be detected.

[0205] In one possible implementation, the wearable device 14 is also used to perform: acquiring the wet-bulb black-bulb temperature index of the target individual in contact with the target work area, and sending the wet-bulb black-bulb temperature index to the central monitoring system; and / or acquiring the time information of the target individual being exposed to a high temperature value greater than or equal to the standard temperature value, and sending the time information to the central monitoring system.

[0206] The central monitoring system 12 is used to perform the following: acquiring the fusion data to be detected and the physiological data observation values ​​of the target individual; inputting the fusion data to be detected into the time series prediction model to obtain the physiological data prediction value of the target individual, the time series prediction model being constructed based on a long short-term memory network; determining the health risk score of the target individual based on the physiological data prediction value and the physiological data observation value; and issuing an alarm protection when the health risk score is greater than the highest score threshold.

[0207] In one possible implementation, the central monitoring system 12 is also configured to: activate Level 1 cooling measures if the health risk score is greater than or equal to the warning threshold and less than the emergency threshold, the Level 1 cooling measures including activating ventilation facilities and activating cooling equipment; and activate Level 2 cooling measures and send an evacuation alarm if the health risk score is greater than or equal to the emergency threshold.

[0208] In one possible implementation, the central monitoring system 12 is also used to perform: determining a health risk score for a target individual based on the mean square error of the predicted values ​​of physiological data and the observed values ​​of physiological data.

[0209] In one possible implementation, the central monitoring system 12 is further configured to: acquire the wet-bulb black-bulb temperature index (WBI) of the target individual in contact with the target work area; send a first warning message to the management server when the WBI is detected to be greater than or equal to the standard exposure index; and / or acquire the time information of the target individual's exposure to the high-temperature environment; based on the time information, send a second warning message to the management server when the duration of the target individual's exposure to the high-temperature environment is detected to be greater than or equal to the maximum working time threshold; and / or send a third warning message to the management server when the health risk score is greater than the highest score threshold.

[0210] In one possible implementation, the central monitoring system 12 is also used to perform: sending an anomaly report to the management personnel server, the anomaly report including a multi-dimensional time series chart, a first warning message, a second warning message and a third warning message.

[0211] The administrator server 13 is used to perform the following actions: obtain the health risk scores of multiple individuals within the target group; determine the group health risk trend score for the target group based on the health risk scores; and increase the rotation frequency of the target group when the group health risk trend score is greater than or equal to the group alert score threshold.

[0212] This application embodiment provides a comprehensive health monitoring and risk assessment system for individuals in high-temperature environments by integrating environmental monitoring, physiological monitoring, data analysis, and alarm systems, which helps to improve the safety of the working environment and the health protection of individuals.

[0213] Figure 7 Schematic diagram of the health monitoring system provided in the embodiments of this application Figure 2 ,like Figure 7 As shown, the health status monitoring system 60 includes a wet-bulb sphere temperature index meter 11, a central monitoring system 12, a management server 13, a wearable device 14, and a wireless communication module 15.

[0214] The wet-bulb black-bulb temperature index measuring instrument 11 is also equipped with a positioning sensor 111, which communicates with the wearable device 14 to achieve a handshake.

[0215] Wearable device 14 is a wristwatch-style wearable device equipped with sensors, including a heart rate monitoring sensor 141, a blood pressure index sensor 142, a position sensor 143, a body surface temperature monitoring sensor 144, and a main processor 145. Wearable device 14 can monitor an individual's vital signs in real time, continuously, and for extended periods, achieving comprehensive health monitoring across the entire population and throughout the entire life cycle. Position sensor 143 establishes a communication connection with positioning sensor 111. The main processor 145 is used to collect position change data from the individual's position sensor 143 to calculate the individual's activity range and current working position, and simultaneously collect the number of times the individual was exposed to temperatures exceeding standard high temperatures. The main processor 145 is also used to record the individual's dwell time at the current working position in real time and simultaneously record the corresponding WBGT index encountered during the dwell time at the current working position. The main processor 145 is also used to obtain the individual's heart rate data from the heart rate monitoring sensor 141, the individual's blood pressure data from the blood pressure index sensor 142, and the individual's body temperature data from the body surface temperature monitoring sensor 144. The collected data is transmitted to the central monitoring system 12 using the wireless communication module 15, such as via Wi-Fi or Bluetooth.

[0216] The central monitoring system 12 is used to analyze and process the received data and output analysis results. Individual health risks are assessed based on the analysis results. An alarm mechanism is triggered when abnormal exposure levels (i.e., cumulative total exposure levels), prolonged exposure to high temperatures, or abnormal physiological data of an individual are detected.

[0217] The health status monitoring system 60 enables comprehensive and real-time monitoring of individual exposure in high-temperature environments, improving the accuracy and reliability of data collection. It also achieves effective fusion and in-depth analysis of multi-source data, providing a quantitative assessment of individual health risks. Wearable devices are used to collect individual physiological data and exposure levels, and data fusion algorithms are used to integrate data from different sources, improving data quality and completeness. Individual activity models are constructed to predict short-term activity trends and implement individual health risk assessments. Predictive indicators for future time periods are used to quantify individual health status, providing algorithmic support for the final early warning and intervention mechanisms.

[0218] The Health Status Monitoring System 60, through the comprehensive application of multiple sensor technologies, data analysis techniques, and modeling technologies, achieves precise monitoring of individual exposure levels and effective management of health risks in high-temperature environments. It not only improves the accuracy of data collection and analysis but also provides strong support for management decisions, helping to reduce health problems among workers in high-temperature environments and improve workplace safety.

[0219] In summary, this application combines multi-source data acquisition, advanced data processing algorithms, and an early warning mechanism to provide a comprehensive and effective solution for addressing the issue of individual health monitoring in high-temperature environments. Through real-time monitoring and risk assessment, this method has the potential to significantly improve safety management in high-temperature working environments and make a significant contribution to the technological development of related fields.

[0220] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0221] Figure 8 Schematic diagram of the health status monitoring device provided in the embodiments of this application Figure 1 ,like Figure 8 As shown, the health status monitoring device 80 is used in a central monitoring system and includes: an acquisition module 81, an input module 82, a determination module 83, and an alarm protection module 84. Wherein:

[0222] The acquisition module 81 is used to acquire the fusion data to be detected and the physiological data observations of the target individual;

[0223] Input module 82 is used to input the fused data to be detected into the time series prediction model to obtain the physiological data prediction value of the target individual. The time series prediction model is constructed based on the long short-term memory network.

[0224] Module 83 is used to determine the health risk score of the target individual based on the predicted values ​​and observed values ​​of physiological data.

[0225] Alarm protection module 84 is used to provide alarm protection when the health risk score is greater than the highest score threshold.

[0226] In one possible implementation, the alarm protection module 84 is specifically used to: activate a first-level cooling measure if the health risk score is greater than or equal to the warning threshold and less than the emergency threshold, the first-level cooling measure including activating ventilation facilities and activating cooling equipment; and activate a second-level cooling measure and send an evacuation alarm if the health risk score is greater than or equal to the emergency threshold.

[0227] In one possible implementation, the determining module 83 is specifically used to: determine the health risk score of the target individual based on the mean square error of the predicted physiological data value and the observed physiological data value.

[0228] In one possible implementation, the alarm protection module 84 is further configured to: acquire the wet-bulb black-bulb temperature index of the target individual in the target work area; and send a first warning message to the management server when the wet-bulb black-bulb temperature index is detected to be greater than or equal to the standard contact index.

[0229] And / or, obtain the time information of the target individual's exposure to the high temperature environment; based on the time information, when the duration of the target individual's exposure to the high temperature environment is detected to be greater than or equal to the maximum working time threshold, send a second warning message to the management personnel server;

[0230] And / or, when the health risk score exceeds the highest score threshold, send a third warning message to the administrator's server.

[0231] In one possible implementation, the alarm protection module 84 is further configured to: send an anomaly report to the administrator server, the anomaly report including a multi-dimensional time series chart, a first warning message, a second warning message, and a third warning message.

[0232] The health status monitoring device provided in this application embodiment can execute the technical solution shown in the above-described health status monitoring method embodiment applied to the central monitoring system. Its implementation principle and beneficial effects are similar, and will not be repeated here.

[0233] Figure 9 Schematic diagram of the health status monitoring device provided in the embodiments of this application Figure 2 ,like Figure 9 As shown, the health status monitoring device 90 is applied to a wearable device and includes: an acquisition module 91, a fusion module 92, a preprocessing module 93, and a transmission module 94. Wherein:

[0234] The acquisition module 91 is used to acquire the physiological data of the target individual and the temperature data of the environment in which it is located. The temperature data reflects the wet-bulb spherical temperature index.

[0235] The fusion module 92 is used to fuse temperature data and physiological data to obtain fused data;

[0236] Preprocessing module 93 is used to preprocess the fused data to obtain the fused data to be detected;

[0237] The sending module 94 is used to send the fused data to be detected to the central monitoring system.

[0238] In one possible implementation, the sending module 94 is further configured to: acquire the wet-bulb black-bulb temperature index of the target individual in contact with the target work area; send the wet-bulb black-bulb temperature index to the central monitoring system; and / or acquire the time information of the target individual being exposed to a temperature greater than or equal to the standard high temperature value; and send the time information to the central monitoring system.

[0239] The health monitoring device provided in this application embodiment can execute the technical solution shown in the above-described health monitoring method embodiment applied to wearable devices. Its implementation principle and beneficial effects are similar, and will not be repeated here.

[0240] Figure 10 Schematic diagram of the health status monitoring device provided in the embodiments of this application Figure 3 ,like Figure 10 As shown, the health status monitoring device 100 is applied to the management server and includes: an acquisition module 101, a determination module 102, and an adjustment module 103. Wherein:

[0241] Module 101 is used to acquire health risk scores of multiple individuals within the target group;

[0242] Module 102 is used to determine a population health risk trend score for a target group based on the health risk score.

[0243] Adjustment module 103 is used to increase the rotation frequency of the target group when the group health risk trend score is greater than or equal to the group alert score threshold.

[0244] The health status monitoring device provided in this application embodiment can execute the technical solution shown in the above-described embodiment of the health status monitoring method applied to the administrator server. Its implementation principle and beneficial effects are similar, and will not be repeated here.

[0245] Figure 11 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application, such as... Figure 11 As shown, the electronic device 110 provided in this embodiment includes at least one processor 1101 and a memory 1102. Optionally, the electronic device 110 further includes a communication component 1103. The processor 1101, the memory 1102, and the communication component 1103 are connected via a bus 1104.

[0246] In a specific implementation, at least one processor 1101 executes computer execution instructions stored in memory 1102, causing at least one processor 1101 to perform the above-described method.

[0247] The specific implementation process of processor 1101 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0248] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0249] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0250] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0251] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0252] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0253] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0254] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0255] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0256] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0257] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0258] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0259] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0260] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A health condition monitoring method characterized by, Applications in central monitoring systems include: Acquire the target individual's fusion data and physiological data observations; The fused data to be detected is input into a time series prediction model to obtain the predicted physiological data of the target individual. The time series prediction model is constructed based on a long short-term memory network. The health risk score of the target individual is determined based on the predicted values ​​of the physiological data and the observed values ​​of the physiological data. An alarm will be triggered when the health risk score exceeds the highest score threshold.

2. The health condition monitoring method of claim 1, wherein, The alarm protection when the health risk score is greater than the highest score threshold includes: If the health risk score is greater than or equal to the warning threshold and the health risk score is less than the emergency threshold, then a Level 1 cooling measure is initiated, which includes activating ventilation facilities and activating cooling equipment. If the health risk score is greater than or equal to the emergency threshold, then Level 2 cooling measures are initiated and an evacuation alert is sent.

3. The health condition monitoring method of claim 1, wherein, The step of determining the health risk score of the target individual based on the predicted values ​​and observed values ​​of the physiological data includes: The health risk score of the target individual is determined based on the mean square error of the predicted values ​​of the physiological data and the observed values ​​of the physiological data.

4. The health condition monitoring method according to any one of claims 1 to 3, characterized by, Also includes: The wet-bulb black-bulb temperature index of the target individual in contact with the target work area is obtained; when the wet-bulb black-bulb temperature index is detected to be greater than or equal to the standard contact index, a first warning message is sent to the management server. And / or, obtain information on the time the target individual was exposed to the high-temperature environment; Based on the time information, when the duration of exposure of the target individual to a high-temperature environment is detected to be greater than or equal to the maximum working time threshold, a second early warning message is sent to the management personnel server. And / or, when the health risk score is greater than the highest score threshold, a third early warning message is sent to the administrator's server.

5. The health condition monitoring method of claim 4, wherein, Also includes: An anomaly report is sent to the management personnel server. The anomaly report includes a multi-dimensional time series chart, the first warning information, the second warning information, and the third warning information.

6. A health condition monitoring method characterized by, Applications in wearable devices, including: Acquire physiological data of the target individual and temperature data of the environment in which it is located, wherein the temperature data reflects the wet-bulb spheroid temperature index; The temperature data and the physiological data are fused to obtain fused data; The fused data is preprocessed to obtain the fused data to be detected; The data to be detected and fused is sent to the central monitoring system.

7. The health condition monitoring method of claim 6, wherein, Also includes: Obtain the wet-bulb sphere temperature index of the target individual in contact with the target work area; send the wet-bulb sphere temperature index to the central monitoring system; And / or, obtain the time information of the target individual being exposed to a high temperature value greater than or equal to the standard high temperature value; send the time information to the central monitoring system.

8. A health condition monitoring method characterized by, For administration server-side use, including: Obtain health risk scores for multiple individuals within a target group, wherein the health risk scores are obtained using the health status monitoring method as described in any one of claims 1 to 5; Based on the health risk score, a population health risk trend score is determined for the target group; When the health risk trend score of the target group is greater than or equal to the group alert score threshold, the rotation frequency of the target group is increased.

9. A health condition monitoring apparatus characterized by, Applications in central monitoring systems include: The acquisition module is used to acquire the fusion data to be detected and the physiological data observations of the target individual; The input module is used to input the fused data to be detected into the time series prediction model to obtain the physiological data prediction value of the target individual. The time series prediction model is constructed based on the long short-term memory network. The determination module is used to determine the health risk score of the target individual based on the predicted values ​​of the physiological data and the observed values ​​of the physiological data; An alarm protection module is used to provide alarm protection when the health risk score is greater than the highest score threshold.

10. A health condition monitoring apparatus characterized by, Applications in wearable devices, including: The acquisition module is used to acquire the physiological data of the target individual and the temperature data of the environment in which it is located, wherein the temperature data reflects the wet-bulb spheroid temperature index; The fusion module is used to fuse the temperature data and the physiological data to obtain fused data; The preprocessing module is used to preprocess the fused data to obtain the fused data to be detected; The sending module is used to send the fused data to be detected to the central monitoring system.

11. A health condition monitoring apparatus characterized by, For administration server-side use, including: An acquisition module is used to acquire health risk scores of multiple individuals within a target group, wherein the health risk scores are obtained by the health status monitoring method as described in any one of claims 1 to 5; The determination module is used to determine a population health risk trend score for the target group based on the health risk score. An adjustment module is used to increase the rotation frequency of the target group when the group health risk trend score is greater than or equal to the group alert score threshold.

12. A health condition monitoring system characterized by, include: The wet-bulb sphere temperature index meter is used to collect temperature data of the environment in which a target individual is located; Wearable device for performing the health monitoring method as described in claim 6 or 7; A central monitoring system for performing the health monitoring method as described in any one of claims 1 to 5; The administrator server is used to execute the health status monitoring method as described in claim 8.

13. An electronic device, comprising: include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the health monitoring method as described in any one of claims 1 to 8.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed, are used to implement the method as described in any one of claims 1 to 8.

15. A computer program product, characterised in that, Includes a computer program, which, when executed, implements the method as described in any one of claims 1 to 8.

Images