Method and system for barrack health monitoring based on multi-parameter sensing

Abstract

The application relates to a barrack health monitoring method and system based on multi-parameter sensing. The method comprises the following steps: acquiring fluctuation monitoring data, gas monitoring data and barrack structure data of a target barrack; extracting features of the fluctuation monitoring data and the gas monitoring data to obtain fluctuation feature data and gas feature data; performing object hazard analysis according to the fluctuation feature data and the gas feature data to obtain health hazard data of the target barrack; performing hazard protection simulation according to the barrack structure data and the health hazard data to obtain hazard protection data of the target barrack; and adjusting the health hazard data according to the hazard protection data to obtain actual health data of the target barrack. The method can accurately obtain specific health data in the barrack and effectively maintain the health of the barrack.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a barrack health monitoring method and system based on multi-parameter sensing. BACKGROUND

[0002] In the traditional technology, the radiation dose monitored by the radiation sensor or / and the concentration of pollutants such as PM2.5, CO2 and formaldehyde monitored by the air quality sensor is recorded in real time and compared with the preset safety standard. When the data exceeds the set safety threshold, the system will automatically issue an alarm. However, the traditional technology only alarms and records data for radiation dose or / and air pollution, and does not assess the health of the barrack environment for radiation dose or / and air pollution in the barrack, resulting in the inability to accurately obtain specific health data in the barrack and the difficulty in achieving effective barrack health maintenance. SUMMARY

[0003] Therefore, it is necessary to provide a barrack health monitoring method and system based on multi-parameter sensing which can accurately obtain specific health data in the barrack and achieve effective barrack health maintenance.

[0004] In a first aspect, the present application provides a barrack health monitoring method based on multi-parameter sensing, comprising:

[0005] obtaining fluctuation monitoring data, gas monitoring data and barrack structure data of a target barrack;

[0006] extracting features from the fluctuation monitoring data and the gas monitoring data to obtain fluctuation feature data and gas feature data;

[0007] performing object hazard analysis according to the fluctuation feature data and the gas feature data to obtain health hazard data of the target barrack;

[0008] performing hazard protection simulation according to the barrack structure data and the health hazard data to obtain hazard protection data of the target barrack;

[0009] adjusting the health hazard data according to the hazard protection data to obtain actual health data of the target barrack.

[0010] In a second aspect, the present application further provides a barrack health monitoring system based on multi-parameter sensing, comprising a computer device and a data monitoring terminal; the computer device comprises a barrack data acquisition module, a hazard data extraction module, a hazard data analysis module, a barrack protection simulation module and a barrack health analysis module;

[0011] The barrack data acquisition module is configured to acquire fluctuation monitoring data, gas monitoring data and barrack structure data of a target barrack.

[0012] The hazard data extraction module is configured to extract features from the fluctuation monitoring data and the gas monitoring data to obtain fluctuation feature data and gas feature data.

[0013] The hazard data analysis module is configured to analyze object hazards according to the fluctuation feature data and the gas feature data to obtain health hazard data of the target barrack.

[0014] The barrack protection simulation module is configured to simulate hazard protection according to the barrack structure data and the health hazard data to obtain hazard protection data of the target barrack.

[0015] The barrack health analysis module is configured to adjust the health hazard data according to the hazard protection data to obtain actual health data of the target barrack.

[0016] The barrack health monitoring method and system based on multi-parameter sensing can accurately extract fluctuation feature data and gas feature data by acquiring fluctuation monitoring data, gas monitoring data and barrack structure data of a target barrack, combining data analysis and feature extraction technology, and providing a reliable foundation for subsequent object hazard analysis. Further, by analyzing the potential impact of fluctuation sources and gas on the health of personnel in the barrack, detailed health hazard data is obtained, hazard protection simulation is performed according to the specific structural characteristics of the barrack and the health hazard data, the impact of different protection measures on health risks can be predicted, and the optimal protection scheme is generated. Finally, the health hazard data is adjusted according to the hazard protection data obtained by simulation, and accurate health risk assessment is achieved. The specific health data in the barrack can be accurately obtained, effective barrack health maintenance can be achieved, and further more scientific and personalized protection schemes can be provided in complex environments to reduce potential health hazards and improve the survival and work quality of personnel in special environments. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the embodiments or related art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0018] Figure 1 An application environment diagram of a barrack health monitoring method based on multi-parameter sensing in an embodiment;

[0019] Figure 2 Flowchart of a barracks health monitoring method based on multi-parameter sensing in an embodiment;

[0020] Figure 3 Flowchart of a health hazard data obtaining method in an embodiment;

[0021] Figure 4 Flowchart of a target multi-source data analysis algorithm obtaining method in an embodiment;

[0022] Figure 5 Flowchart of a target multi-source data analysis algorithm obtaining method in another embodiment;

[0023] Figure 6 Flowchart of a hazard protection data obtaining method in an embodiment;

[0024] Figure 7 Flowchart of a hazard handling simulation data obtaining method in an embodiment;

[0025] Figure 8 Flowchart of a biofeedback monitoring simulation data obtaining method in an embodiment;

[0026] Figure 9 Structural block diagram of an apparatus of a computer device part in a barracks health monitoring system based on multi-parameter sensing in an embodiment;

[0027] Figure 10 Internal structural diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0028] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application.

[0029] The barracks health monitoring method based on multi-parameter sensing provided by the embodiments of the present application can be applied in an application environment as shown in Figure 1 . In the application environment, a terminal 102 communicates with a server 104 through a network. A data storage system can store data required to be processed by the server 104. The data storage system can be integrated on the server 104, or placed on a cloud or other network server. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0030] In an exemplary embodiment, as shown in Figure 2 , a barracks health monitoring method based on multi-parameter sensing is provided. The method is applied in Figure 1The server in the system is taken as an example for illustration, including the following steps 202 to 210. Among them:

[0031] Step 202, obtaining fluctuation monitoring data, gas monitoring data and barrack structure data of the target barrack.

[0032] Among them, the target barrack can be a specific building or facility that needs to be evaluated for health hazards and simulated for protection. It can be a military barrack, a scientific research laboratory, a medical facility, etc., usually located in a specific working environment, facing potential hazards such as radiation or harmful gases.

[0033] Among them, the fluctuation monitoring data can be data information about the target barrack with fluctuation properties collected by special detection equipment (such as detectors, radiation instruments, etc.). These data include but are not limited to radiation, water quality and earthquakes, etc. Radiation includes radiation types (such as α, β, γ rays), radiation intensity, radiation source location, radiation dose rate, etc.; water quality includes pH value, conductivity, dissolved oxygen (DO), turbidity, heavy metal content (such as lead Pb, mercury Hg), organic pollutants (such as COD, BOD), pathogenic microorganism content, ammonia nitrogen (NH4-N), etc.; earthquakes include earthquake magnitude (expressed in Richter magnitude or moment magnitude Mw), focal depth (km), epicenter location (latitude and longitude), seismic wave propagation speed, stress accumulation before the earthquake, aftershock activity, historical earthquake data, etc. Among them, the gas monitoring data can be data related to gas propagation in the barrack obtained by video monitoring equipment or sensors, including but not limited to toxic gases, viruses, etc. Toxic gases include the types, concentration, diffusion range of toxic gases in the air, etc. For example, common toxic gas monitoring data involves the real-time concentration (ppm or mg / m³) of harmful gases such as carbon monoxide, sulfur dioxide, ammonia, chlorine, etc., and the location of the gas leakage source; viruses include virus types, transmission speed, air or water virus concentration, etc.

[0034] Among them, it is worth noting that in order to illustrate the data processing relationship between fluctuation monitoring data and gas detection data, therefore in the subsequent embodiments, the fluctuation monitoring data is mainly introduced as radiation, and the same method is used for processing other data with fluctuation properties (such as earthquakes and water).

[0035] Among them, the barrack structure data can be information related to the structure of the target barrack building, such as barrack structure, wall material, building thickness, window size, ventilation system layout, etc.

[0036] Specifically, by deploying radiation monitoring instruments and gas detection equipment within the target barrack, real-time collection of radiation intensity and harmful gas concentration data in the environment is performed to obtain fluctuation monitoring data and gas monitoring data of the target barrack. Meanwhile, structural drawings of the building and sensor data are identified to obtain structural information of the barrack, and barrack structure data of the target barrack, such as wall thickness, window size, ventilation system, etc.

[0037] Step 204, feature extraction is performed on the fluctuation monitoring data and the gas monitoring data to obtain fluctuation feature data and gas feature data.

[0038] The fluctuation feature data can be key features extracted from the fluctuation monitoring data, typically including radiation types (alpha, beta, gamma rays), radiation intensity, dose rate, radiation source distribution, temporal and spatial changes, etc.

[0039] The gas feature data can be important information extracted from the gas monitoring data, typically including gas types (such as CO2, ammonia), concentration fluctuations, maximum concentration values, average concentration values, concentration change trends, etc.

[0040] Specifically, the collected fluctuation monitoring data and gas monitoring data are preprocessed to remove noise and outliers, obtaining preprocessed fluctuation monitoring data and preprocessed gas monitoring data, and then using feature extraction algorithms to convert the preprocessed fluctuation monitoring data and preprocessed gas monitoring data into representative information. For example, for the processed fluctuation monitoring data, the radiation intensity, radiation wavelength and ray type (such as alpha, beta, gamma rays, etc.) in different time periods are extracted, and the distribution and change trend of radiation dose are calculated; while for the preprocessed gas monitoring data, the concentration changes of different gas types (such as CO2, ammonia, etc.) can be analyzed, and features such as gas concentration peak value, average value, maximum fluctuation range, etc. are extracted. In addition, time series analysis methods can be used to mine periodic and sudden changes in the data, further identifying potential danger points. After feature extraction, the fluctuation feature data and the gas feature data are obtained.

[0041] Step 206, object hazard analysis is performed according to the fluctuation feature data and the gas feature data to obtain health hazard data of the target barrack.

[0042] The object hazard analysis can be a quantitative analysis process combining fluctuation feature data and gas feature data, simulating the health impact of radiation and harmful gases on people and animals in the target barrack, and analyzing possible health hazards (such as radiation damage, respiratory diseases, etc.) under different exposure conditions.

[0043] The health hazard data can be potential risk information about personnel health based on the object hazard analysis.

[0044] Specifically, by using the wave characteristic data, combined with the type, intensity and duration of radiation, the potential harm of different radiation sources to humans and animals is evaluated, such as the damage of radiation to cells, the risk of inducing cancer, etc. For gas characteristic data, by analyzing the concentration, type and exposure time of the gas, the harm of harmful gases (such as carbon monoxide, ammonia, etc.) to the respiratory system, nervous system, etc. of humans and animals is evaluated. At the same time, considering that the radiation and gas concentration may be different at different positions in the barrack, the exposure degree of humans and animals is analyzed, and the health impact under different exposure conditions is simulated through a human body model. Combined with the specific impact data of radiation and gas on health obtained above, the health hazard data is finally obtained, including the occurrence probability, severity and potential health problems of each hazard.

[0045] Step 208, according to the barrack structure data and the health hazard data, hazard protection simulation is carried out to obtain the hazard protection data of the target barrack.

[0046] Among them, the hazard protection simulation can be to simulate the inhibition effect of different protection measures (such as radiation shielding materials, gas purification devices, ventilation optimization, etc.) on health hazards by establishing a protection model.

[0047] Among them, the hazard protection data can be the result of hazard protection simulation, which usually includes the change of radiation intensity and gas concentration in the barrack after the implementation of protection measures, and the inhibition effect of these changes on health hazards.

[0048] Specifically, combined with the barrack structure data of the target barrack (such as wall material, window layout, ventilation system, pipe gallery structure, etc.), its protection performance and shielding effect on radiation and gas are calculated. For example, thick walls may have good shielding effect on radiation, and windows with poor sealing may increase the leakage of harmful gas. Then combined with the health hazard data, the inhibition or hindering effect of different protection measures on these hazards is simulated, or the weakening of these hazards in different places of the target barrack is simulated through the barrack structure data. The protection measures include radiation shielding materials, starting air purification devices, optimizing ventilation systems or planning safe evacuation channels, etc. Through simulation calculation, the change of radiation intensity and gas concentration in the barrack is predicted to change the health risk of humans and animals, and detailed hazard protection data is obtained.

[0049] Step 210, according to the hazard protection data, the health hazard data is adjusted to obtain the actual health data of the target barrack.

[0050] Among them, the actual health data can be the health hazard data adjusted after the hazard protection simulation, reflecting the actual health status of humans and animals in the barrack after the protection measures.

[0051] Specifically, according to the hazard protection data obtained after simulation, the radiation dose and gas concentration under the simulated actual protection condition are adjusted to new values, and the health risk of the personnel is re-evaluated. Specifically, if the hazard protection data indicates that the protection measures effectively reduce the concentration of radiation or harmful gas, the risk value in the health hazard data will be reduced accordingly, and vice versa; in addition, the side effects or other factors that the protection measures may bring, such as limited air circulation, movement of radiation source, etc., need to be considered, and finally the actual health data of the target barrack is obtained.

[0052] In the above-mentioned barrack health monitoring method based on multi-parameter sensing, by obtaining the fluctuation monitoring data, gas monitoring data and barrack structure data of the target barrack, combining data analysis and feature extraction technology, the fluctuation feature data and gas feature data can be accurately extracted, providing a reliable foundation for subsequent object hazard analysis; further by analyzing the potential influence of fluctuation source and gas on the health of personnel in the barrack, detailed health hazard data is obtained, and according to the specific structural characteristics of the barrack and the health hazard data, hazard protection simulation is carried out, which can predict the influence of different protection measures on health risk and generate the optimal protection scheme; finally, according to the hazard protection data obtained by simulation, the health hazard data is adjusted to realize accurate health risk evaluation. The specific health data in the barrack can be accurately obtained, and effective barrack health maintenance can be realized, and further more scientific and personalized protection schemes can be provided in complex environments to reduce the occurrence of potential health hazards and improve the survival and work quality of personnel in special environments.

[0053] In one exemplary embodiment, as shown in Figure 3 According to the fluctuation feature data and the gas feature data, the object hazard analysis is carried out to obtain the health hazard data of the target barrack, including steps 302 to 306. Among them:

[0054] Step 302, analyze the correlation between the fluctuation feature data and the gas feature data to obtain multi-source hazard correlation information.

[0055] Among them, the multi-source hazard correlation information can be the relationship and influence between different potential hazard factors obtained by analyzing the mutual relationship between the fluctuation feature data and the gas feature data.

[0056] Specifically, the fluctuation feature data and the gas feature data are preprocessed to remove noise and perform standardization processing, and then statistical analysis methods such as correlation analysis, regression analysis or joint distribution analysis are used to analyze the potential relationship between the fluctuation feature data and the gas feature data, for example, their common fluctuations at the same time or in the same location. Through correlation analysis, regression analysis or joint distribution analysis, it is identified whether there is a synergistic effect or a superimposed effect between the fluctuation feature data and the gas feature data, and how they jointly affect the health risk, to obtain multi-source hazard correlation information.

[0057] Step 304, according to the multi-source hazard correlation information, setting the parameters of the initial multi-source data analysis algorithm of the target barracks, obtaining the target multi-source data analysis algorithm.

[0058] Wherein, the initial multi-source data analysis algorithm can be a preliminary algorithm model designed according to the multi-source hazard correlation information, used to process the fluctuation feature data and the gas feature data. The core purpose of this algorithm is to integrate data from different sources and comprehensively analyze them through the algorithm to evaluate the impact of each hazard factor on health risk.

[0059] Wherein, the target multi-source data analysis algorithm can be the final algorithm after optimization and adjustment, used for comprehensive analysis of radiation and gas data in the target barracks environment.

[0060] Specifically, according to the multi-source hazard correlation information between the fluctuation feature data and the gas feature data, the key factors affecting health risk assessment are determined, such as radiation intensity, gas concentration, exposure time, etc., and appropriate weight values are assigned to these factors. Combined with historical data and research data in related fields, the initial parameters of the initial multi-source data analysis algorithm are set, including the weight coefficient of the data, the convergence speed of the algorithm, the error tolerance, etc., to ensure that the initial multi-source data analysis algorithm can reasonably handle the interaction effects of different types of data. Using the Pareto frontier optimization algorithm, the parameters of the initial multi-source data analysis algorithm are multi-objective optimized, so that the algorithm can more accurately handle the complex relationship between radiation and gas data, and obtain the target multi-source data analysis algorithm.

[0061] Step 306, inputting the fluctuation feature data and the gas feature data into the target multi-source data analysis algorithm to obtain health hazard data.

[0062] Specifically, the fluctuation feature data and the gas feature data are input into the target multi-source data analysis algorithm constructed in the previous step. The algorithm will consider the interaction between the fluctuation feature data and the gas feature data, assess the potential health hazards that people and animals in the target barrack may face through calculation and model prediction, and output health hazard data, including but not limited to potential health risk levels, different types of health hazards (such as radiation sickness, respiratory diseases, etc.), and the probability and severity of their occurrence, etc.

[0063] In this embodiment, by analyzing the correlation between the fluctuation feature data and the gas feature data, multi-source hazard correlation information can be obtained, which provides a comprehensive hazard background for further analysis. According to these correlation information, the parameters of the initial multi-source data analysis algorithm are set, so that the multi-source data analysis algorithm of the target barrack can accurately adapt to the specific hazard environment. After inputting the fluctuation and gas feature data into the algorithm, accurate calculation and prediction of health hazard data can be realized, so as to comprehensively evaluate the combined hazards of fluctuation sources and gases in the target barrack. Ultimately, it can provide a basis for formulating more scientific and effective health risk management measures, and ensure the pertinence and effectiveness of hazard protection measures.

[0064] In one exemplary embodiment, as shown in Figure 4 If the multi-source hazard correlation information is less than the preset hazard correlation threshold, the parameters of the initial multi-source data analysis algorithm of the target barrack are set according to the multi-source hazard correlation information to obtain the target multi-source data analysis algorithm, including steps 402 to 408.

[0065] Step 402, according to the multi-source hazard correlation information, constructing the initial fluctuation hazard analysis item and the initial gas hazard analysis item of the initial multi-source data analysis algorithm.

[0066] The initial fluctuation hazard analysis item can be an initial radiation hazard assessment module constructed based on the fluctuation feature data (such as radiation type, intensity, time distribution, etc.) when constructing the multi-source data analysis algorithm. It mainly focuses on the potential impact of radiation sources on human health, and analyzes key factors such as exposure dose, dose rate, and exposure time.

[0067] The initial gas hazard analysis item can be an initial gas hazard assessment module constructed based on the gas feature data (such as gas type, concentration, exposure time, etc.) when constructing the multi-source data analysis algorithm. It mainly analyzes the potential threat of different gases to health at a specific concentration, especially the impact on the respiratory system and other physiological functions.

[0068] Specifically, in the case where the multi-source hazard correlation information is less than the preset hazard correlation threshold, according to the multi-source hazard correlation information between the fluctuation feature data and the gas feature data, for example, the radiation intensity and the gas concentration may have certain interaction, or in some cases, the concentration change of a certain gas will exacerbate the harm of radiation, the initial analysis items are constructed for the radiation harm and the gas harm respectively, and the initial fluctuation harm analysis item and the initial gas harm analysis item of the initial multi-source data analysis algorithm are obtained. The fluctuation harm analysis item will focus on the type, intensity, exposure time and other factors of radiation, and consider the potential harm to human health; and the gas harm analysis item focuses on the type, concentration, exposure duration and other factors of the gas, and analyzes the influence on the respiratory system or other physiological systems.

[0069] In step 404, according to the fluctuation feature data, the parameters of the initial fluctuation harm analysis item are set, and a target fluctuation harm analysis item is obtained.

[0070] The target fluctuation harm analysis item can be an analysis module that is optimized and adjusted on the basis of the initial fluctuation harm analysis item in combination with the specific target barracks environment and the fluctuation feature data (such as radiation intensity, exposure time, etc.).

[0071] Specifically, the fluctuation feature data, including radiation intensity, radiation type (such as alpha, beta, gamma rays), radiation source distribution, and time and space characteristics of radiation exposure, are analyzed. According to the analysis data, the threshold and weighting coefficient of radiation exposure in the initial fluctuation harm analysis item are set to ensure that the initial fluctuation harm analysis item can reasonably reflect the influence on health under different radiation sources and different exposure conditions. For example, for high-intensity radiation sources, a higher harm weight may need to be set; and for long-term low-dose radiation, the potential impact of cumulative dose on health may need to be calculated. In addition, the radiation protection standards and human physiological response models need to be combined to adjust the parameters in the initial fluctuation harm analysis item to ensure that the health risks under different radiation conditions can be accurately evaluated, and finally the target fluctuation harm analysis item is constructed.

[0072] In step 406, according to the gas feature data, the parameters of the initial gas harm analysis item are set, and a target gas harm analysis item is obtained.

[0073] The target gas harm analysis item can be an analysis module that is optimized and adjusted on the basis of the initial gas harm analysis item by optimizing and adjusting the gas feature data (such as gas concentration, type, space-time change, etc.).

[0074] Specifically, detailed analysis is conducted on the gas characteristic data, including the type of gas (such as carbon monoxide, ammonia, methane, etc.), concentration level, exposure time, fluctuation trend, and other factors. According to the data of the above analysis, the harm weighting coefficient of each gas is determined, and the influence weight of the human body health under different concentrations is set. For example, for high concentration of carbon monoxide, a higher harm weight may need to be set because it is more harmful to the respiratory and nervous systems; for lower concentration of gas, it may need to be adjusted in combination with exposure time and dose effect. At the same time, the combined effect of gas and radiation needs to be considered, especially when the concentration of some gases reaches a certain threshold, they may increase the potential threat of radiation to health, ensuring that the target gas hazard analysis item can accurately reflect the health risks under different gas exposure conditions in the target barracks.

[0075] Step 408, fuse the target fluctuation hazard analysis item and the target gas hazard analysis item to obtain the target multi-source data analysis algorithm.

[0076] Specifically, the parameters in the target fluctuation hazard analysis item and the target gas hazard analysis item are weighted and integrated to ensure that each hazard factor (such as radiation intensity, gas concentration, etc.) is appropriately allocated according to its actual risk level and interaction. During the fusion process, techniques such as multiple regression, weighted average, or machine learning models may be used to combine the influence factors of both to reflect the combined effect of radiation and gas hazards in the same environment. Secondly, during the fusion process, the potential synergistic effect between radiation and gas needs to be considered, such as the concentration of some gases may increase the health risk in a high radiation environment, this interaction effect needs to be quantified through the model, and the target multi-source data analysis algorithm is obtained.

[0077] In this embodiment, by constructing the fluctuation hazard analysis item and the gas hazard analysis item of the initial multi-source data analysis algorithm according to the multi-source hazard correlation information, and setting the parameters according to the fluctuation characteristic data and the gas characteristic data respectively, the harm of the fluctuation source and the gas to the target barracks can be accurately identified and quantified. By fusing these two target hazard analysis items, a comprehensive multi-source data analysis algorithm is formed, which not only can comprehensively evaluate the independent harm of the fluctuation source and the gas, but also can consider the interaction effect of the two, and improve the prediction accuracy of the comprehensive harm and the effectiveness of the coping strategy. Finally, more accurate and comprehensive health risk assessment can be provided for the target barracks, and reliable basis can be provided for formulating effective protection measures and emergency response schemes.

[0078] In one exemplary embodiment, as shown in Figure 5 if the multi-source hazard correlation information is greater than the preset hazard correlation threshold, the parameters of the initial multi-source data analysis algorithm of the target barracks are set according to the multi-source hazard correlation information, and the target multi-source data analysis algorithm is obtained, including steps 502 to 510. Among them:

[0079] At step 502, an initial hazard analysis weighting term and an initial hazard analysis correlation term of an initial multi-source data analysis algorithm are constructed according to multi-source hazard correlation information.

[0080] The initial hazard analysis weighting term can be a relative influence weight of each hazard source on health risk, which is set according to characteristics of radiation and gas hazard sources when the multi-source data analysis algorithm is constructed.

[0081] The initial hazard analysis correlation term can be a correlation term constructed based on mutual relationships between different hazard sources such as radiation and gas data in multi-source data analysis.

[0082] Specifically, in a case where the multi-source hazard correlation information is greater than a preset hazard correlation threshold, the multi-source hazard correlation information obtained through correlation analysis of the fluctuation characteristic data and the gas characteristic data, such as radiation intensity and gas concentration, can have certain interaction, or in some cases, concentration changes of a certain gas can aggravate radiation hazards. Analysis terms of the initial multi-source data analysis algorithm are constructed for radiation hazards and gas hazards respectively. The fluctuation hazard analysis term will focus on the type, intensity, exposure time and other factors of radiation, and consider the potential harm to human health; the gas hazard analysis term focuses on the type, concentration, exposure duration and other factors of gas, and analyzes the impact on the respiratory system or other physiological systems.

[0083] At step 504, multi-dimensional nonlinear transformation is performed on the fluctuation characteristic data and the gas characteristic data respectively to obtain a fluctuation nonlinear matrix and a gas nonlinear matrix.

[0084] The multi-dimensional nonlinear transformation can be a nonlinear mapping method for converting radiation and gas characteristic data into a higher dimensional representation, thereby revealing the potential nonlinear relationship in the data.

[0085] The fluctuation nonlinear matrix can be a fluctuation characteristic data matrix after multi-dimensional nonlinear transformation, reflecting the potential nonlinear relationship and complex pattern in the radiation data.

[0086] The gas nonlinear matrix can be a gas characteristic data matrix after multi-dimensional nonlinear transformation, reflecting the nonlinear pattern of gas concentration, type and its impact on health.

[0087] Specifically, since the fluctuation feature data and the gas feature data themselves usually have complex nonlinear relationships, simple linear analysis methods can not fully reveal the potential patterns and interactions therein, and therefore multi-dimensional nonlinear transformation techniques such as principal component analysis (PCA), support vector machine (SVM), or neural network methods are adopted to respectively map the original fluctuation feature data and the gas feature data to a high-dimensional space, to extract nonlinear features in the data, eliminate possible complex dependency relationships between variables, and make the data better reflect the implicit interaction effects between different hazard factors, so as to obtain a fluctuation nonlinear matrix and a gas nonlinear matrix, to capture deep features in the data that are not identified by linear models.

[0088] Step 506, setting an initial hazard analysis weighting term according to the fluctuation nonlinear matrix and the gas nonlinear matrix, to obtain a target hazard analysis weighting term.

[0089] Among them, the target hazard analysis weighting term can be a weighting term obtained by optimization and adjustment on the basis of the initial hazard analysis weighting term, in combination with the fluctuation nonlinear matrix and the gas nonlinear matrix.

[0090] Specifically, since the fluctuation nonlinear matrix and the gas nonlinear matrix respectively contain complex features extracted by nonlinear transformation, they reflect deep information of nonlinear relationships in radiation and gas hazard data, and therefore analysis data obtained by statistical analysis, correlation analysis, etc. on the data in the fluctuation nonlinear matrix and the gas nonlinear matrix, in combination with multi-source hazard correlation information, can accurately adjust the initial hazard analysis weighting term to make it more consistent with actual risks. For example, some nonlinear relationships can indicate that the combined effect of radiation and gas can produce more significant health hazards at a certain concentration or dose, and therefore higher weights need to be assigned to such high-risk combinations. In addition, information in the nonlinear matrix can help reveal possible complex interaction effects between radiation and gas data, thereby better guiding the weighting setting, and the target hazard analysis weighting term obtained after weighting can more accurately reflect the relative contribution of different radiation and gas features to health risks.

[0091] Step 508, setting a multi-source data correlation matrix of an initial hazard analysis correlation term according to multi-source hazard correlation information, to obtain a target hazard analysis correlation term.

[0092] Among them, the multi-source data correlation matrix is a mathematical tool for describing the mutual relationship between multiple variables, which calculates the correlation between multiple data sources (such as radiation, gas, etc. hazard data) to establish a matrix form representation, each element of the matrix representing the correlation coefficient between two variables, and is usually used to measure the strength and direction of linear relationship between variables.

[0093] The target hazard analysis correlation item can be a data correlation matrix optimized on the basis of the initial hazard analysis correlation item in combination with the multi-source hazard correlation matrix, and indicates the interaction between different hazard sources (such as radiation and gas). After optimization, the relationship between these data sources can be more accurately reflected.

[0094] Specifically, since the role of the initial hazard analysis correlation item is to indicate the mutual relationship and interaction effect between different hazard sources (such as radiation and gas), the construction of these correlation items depends on multi-source hazard correlation information, which reveals the potential correlation between different data sources such as radiation and gas. Therefore, the correlation analysis, synergistic effect analysis or interaction modeling of the multi-source hazard correlation information is performed, and a multi-source data correlation matrix is set to accurately quantify and represent the interaction between these data sources. For example, the multi-source hazard correlation information indicates that some gases may exacerbate the harm of radiation at high concentrations, or different types of radiation have different responses to gas exposure, and these factors need to be captured and quantified through the correlation matrix. By adjusting and optimizing the correlation matrix, the target hazard analysis correlation item can better handle the complex interaction of multi-source hazard data.

[0095] Step 510, constructing a nonlinear fusion of the target hazard analysis weighted item and the target hazard analysis correlation item to obtain a target multi-source data analysis algorithm.

[0096] The nonlinear fusion can be a combination of multiple hazard analysis weighted items and correlation items through a nonlinear method (such as neural network, deep learning, etc.) to form a comprehensive multi-source data analysis algorithm.

[0097] Specifically, through nonlinear fusion technology (such as neural network, nonlinear regression, etc.), the complex interaction relationship between the weighted item and the correlation item is integrated, so that the model can simultaneously process the nonlinear characteristics of radiation and gas data and their interaction. Finally, the target multi-source data analysis algorithm is obtained.

[0098] The expression of the target multi-source data analysis algorithm is

[0099]

[0100] wherein, H is health hazard data; is a fusion function for mapping each part of the feature data to the health hazard assessment space corresponding to the health hazard data; is a time-varying weighting coefficient of the fluctuation feature data; is a time-varying weighting coefficient of the gas feature data; is a fluctuation nonlinear matrix; is a gas nonlinear matrix; is fluctuation feature data; is gas feature data; is time-varying correlation weight coefficient; is multi-source data correlation matrix; is nonlinear fusion; T is feature dimension number; M and N are respectively the number of rows and the number of columns of the multi-source data correlation matrix; S is barrack structure data; is structure data mapping function; is barrack structure influence weight; is index variable of nonlinear transformation channel. is initial hazard analysis correlation item; is initial hazard analysis weighted item.

[0101] In this embodiment, by constructing the initial hazard analysis weighted item and the hazard analysis correlation item according to the multi-source hazard correlation information, and performing multi-dimensional nonlinear transformation on the fluctuation feature data and the gas feature data, the nonlinear relationship between complex environmental hazards and biological reactions can be effectively captured. The generation and application of these nonlinear matrices make the hazard analysis of the target barrack more accurate, and can carefully consider the complex interaction of fluctuation data and gas. By adjusting the initial weighted item and the correlation item, the target hazard analysis weighted item and the correlation item are obtained, thereby providing high-quality data support for subsequent nonlinear fusion. The finally constructed target multi-source data analysis algorithm not only improves the analysis ability of the comprehensive hazards of fluctuations and gas, but also enhances the accuracy of its prediction and protection measures, which is helpful for formulating more effective health protection strategies and emergency response schemes.

[0102] In one exemplary embodiment, as shown in Figure 6 , hazard protection simulation is performed according to the barrack structure data and the health hazard data to obtain hazard protection data of the target barrack, including steps 602 to 608. Among them:

[0103] Step 602, hazard processing simulation is performed according to the barrack structure data and the health hazard data to obtain hazard processing simulation data.

[0104] Among them, the hazard processing simulation can be a process of simulating the influence of hazard sources (such as radiation, gas leakage, etc.) on personnel or organisms in the barrack under different environmental conditions by comprehensively considering the structure data and health hazard data of the barrack.

[0105] Among them, the hazard processing simulation data can be the output result obtained by the hazard processing simulation process, which specifically embodies the potential health impact of hazard sources on personnel in the barrack under different structures and protection measures. These data include information such as the intensity of the hazard source, the propagation range, and the protection effect.

[0106] Specifically, the barrack structure data provides the physical characteristics of the building, such as wall material, door and window design, etc., which affect the propagation path and intensity of hazards such as radiation, gas leakage, etc. At the same time, the health hazard data reflects the potential impact of different hazard sources (such as radiation, gas, etc.) on human health. By inputting this information into the simulation system, the propagation of hazards under different structural conditions and the degree of impact on organisms are simulated, and hazard handling simulation data is generated to provide a preliminary assessment of the effectiveness of hazard control in different environments.

[0107] Step 604, according to the hazard handling simulation data, biological feedback monitoring is performed on each simulated organism in the target barrack, and biological feedback monitoring simulation data is obtained.

[0108] Among them, biological feedback monitoring can be through monitoring the physiological response of simulated organisms (such as simulated human groups, experimental animals, etc.) in the barrack, to evaluate their health status when facing specific hazard sources. This monitoring usually involves real-time detection of physiological indicators (such as heart rate, body temperature, blood pressure, respiratory rate, etc.) of simulated organisms, to help evaluate the specific impact of hazard sources (such as radiation or toxic gas) on biological health.

[0109] Among them, biological feedback monitoring simulation data can be output data obtained by monitoring the health response of simulated organisms in the hazard handling simulation environment. These data include physiological changes and health indicators of simulated organisms (such as abnormal reactions, health damage or fluctuations in physiological indicators of organisms).

[0110] Specifically, according to the hazard handling simulation data, the biological response of different organisms (such as staff, residents, animals, plants, etc.) in the barrack under the environment is simulated, and their physical condition under different hazard conditions is monitored. For example, by simulating the health status of simulated organisms (such as physiological impact on organisms after radiation exposure), and monitoring biological health indicators (such as heart rate, respiratory rate, etc.) according to simulation data, biological feedback monitoring simulation data can be generated to evaluate the effectiveness of current hazard protection measures.

[0111] Step 606, in the case that any simulated organism has physical abnormalities represented by the biological feedback monitoring simulation data, the simulation parameters of the hazard handling simulation are adjusted.

[0112] Among them, the simulation parameters can be parameters used to adjust and set the protection variables in the simulation environment during the hazard handling simulation process.

[0113] Specifically, if the biofeedback monitoring simulation data indicates that the simulated organisms exhibit physical abnormalities (such as excessive radiation dose or high gas concentration leading to abnormal physical indicators of the organisms), adjustments need to be made to the hazard handling simulation. Specifically, based on the health responses of the biofeedback monitoring simulation data (such as symptoms of radiation poisoning, difficulty breathing, etc.), the hazard protection parameters in the simulation can be adjusted, which may include increasing the strength of protective barriers, adjusting air flow channels, optimizing the operation of air purification equipment, etc., to reduce the impact of hazards on the organisms. The adjusted simulation parameters will be used for the next round of hazard handling simulation to optimize the protection measures.

[0114] Step 608, using the new simulation parameters, return to the step of performing hazard handling simulation based on barrack structure data and health hazard data to obtain hazard handling simulation data until each simulated organism does not have physical abnormalities or the simulation parameters trigger the hazard handling constraint rules to obtain hazard protection data.

[0115] Among them, the hazard handling constraint rules can be conditions and restrictions set during the hazard handling simulation to ensure that the simulation results meet safety standards and actual needs. For example, it may be set that the radiation dose cannot exceed a certain safety threshold, the gas concentration cannot exceed the standard, or the cost and implementability of the protection measures cannot exceed a certain range.

[0116] Specifically, after adjusting the simulation parameters, the hazard handling simulation is performed again using the new simulation parameters to evaluate whether the adjusted protection measures effectively reduce the impact of hazards on the organisms. If the health status of the simulated organisms returns to normal or meets the set protection standards (such as radiation dose, gas concentration reaching a safe level) after adjustment, the final hazard protection data is generated. If there are still abnormal reactions, the simulation parameters continue to be adjusted and simulated until the health status of all simulated organisms meets the requirements or reaches the hazard handling constraint rules (such as the maximum allowable range of protection measures), and the final hazard protection data is obtained.

[0117] In this embodiment, by performing hazard handling simulation based on barrack structure data and health hazard data, and conducting biofeedback monitoring on simulated organisms, the effectiveness of hazard handling measures can be dynamically evaluated, and health abnormalities of organisms can be identified in a timely manner. When physical abnormalities of simulated organisms are detected, iterative optimization is performed by adjusting simulation parameters to ensure that the hazard handling scheme can more accurately respond to various health threats. Repeated adjustment until the health status of the simulated organisms returns to normal or the constraint rules are triggered, and the precise hazard protection data is finally obtained, which can realize real-time optimization of hazard protection measures, ensure the effectiveness of the protection scheme in the target barrack under different hazard conditions, and provide more scientific basis for decision-makers, thereby effectively reducing health risks and improving protection effect.

[0118] In one exemplary embodiment, as shown in Figure 7 The hazard treatment simulation according to the barrack structure data and the health hazard data to obtain hazard treatment simulation data includes steps 702 to 710. Among them:

[0119] Step 702, according to the barrack structure data and the health hazard data, the hazard treatment air duct of the target barrack is simulated, and the hazard treatment ventilation data is obtained.

[0120] Among them, the hazard treatment air duct can be a temporary air duct designed or simulated in the barrack for treating hazards, which is specially used to deal with specific hazard sources such as toxic gas leakage, fire smoke or radiation diffusion.

[0121] Among them, the hazard treatment ventilation data can be the output data after simulating the hazard treatment air duct, reflecting the concentration distribution, flow path and ventilation effect of harmful substances (such as gas, smoke, etc.) in the barrack using the above air duct, which also includes the information of the current air duct.

[0122] Specifically, since the structure data of the barrack provides basic information of the ventilation system, such as the air outlet in the room, the air duct arrangement, the wall permeability, etc., and the health hazard data reflects the potential threat of different hazard sources (such as radiation, gas concentration, etc.) to human body. Through these information, the hazard treatment air duct of the target barrack can be simulated to treat the harmful substances by air exhaust, and the influence of different air duct combinations on air flow and concentration change of harmful substances can be simulated to evaluate the best air duct combination of the ventilation system, and finally obtain the hazard treatment ventilation data.

[0123] Step 704, adjusting the health hazard data according to the hazard treatment ventilation data to obtain the ventilation adjusted hazard data.

[0124] Among them, the ventilation adjusted hazard data can be the adjustment result based on the hazard treatment ventilation data. These adjustments reflect how the ventilation system affects the health hazard data in actual operation, especially the changes of gas concentration, radiation intensity and other factors.

[0125] Specifically, based on the hazard treatment ventilation data, the health hazard data is further adjusted. For example, the hazard treatment ventilation data represents that the ventilation effect may cause the decrease of gas concentration or the weakening of radiation intensity, so the original health hazard data is adjusted according to these data to ensure that the actual effect of ventilation measures is accurately reflected, and the ventilation adjusted hazard data is obtained.

[0126] Step 706, in the case that the ventilation adjusted hazard data is not empty, according to the barrack structure data and the ventilation adjusted hazard data, the spray data of the target barrack is simulated to obtain the hazard treatment spray data.

[0127] The spray data can be data obtained by simulating the effect of the spray system on the hazard source (such as fire or toxic gas leakage). The spray system reduces the concentration of harmful substances in the air or the temperature by releasing water mist or liquid, thereby reducing the threat of the hazard source to personnel. The spray data usually includes information such as spray range, spray volume, spray pressure, etc., to evaluate the control ability of the spray system on harmful substances under certain conditions.

[0128] Specifically, in the case that the ventilation adjustment hazard data is not empty, it indicates that the target barrack still has factors that pose a danger to the biological existence. Since the concentration of harmful substances is reduced or overheated areas are cooled by releasing water mist or liquid, according to the ventilation adjustment hazard data, combined with the structure data of the barrack (such as the position of the sprinkler, the spray range, the spray pressure, etc.), simulation is performed. The goal is to evaluate the protection effect of the spray system under certain conditions and determine whether it can effectively reduce the intensity of the hazard source or reduce the diffusion of harmful substances. For example, the spray system can further reduce the health risk to personnel by reducing the concentration of harmful gases, suppressing the spread of fire, or adsorbing toxic substances. The final simulation obtains hazard treatment spray data.

[0129] Step 708: Adjust the ventilation adjustment hazard data according to the hazard treatment spray data to obtain spray adjustment hazard data.

[0130] The spray adjustment hazard data can be the result of adjustment based on the spray data, reflecting the actual impact of the spray system on the health hazard data when dealing with the hazard source. Through the action of the spray system, the gas concentration, radiation intensity, etc. may be further reduced. The adjusted hazard data shows the effect of the spray system in slowing down the diffusion of harmful substances and reducing health hazards.

[0131] Specifically, based on the hazard treatment spray data, the ventilation adjustment hazard data is adjusted again. For example, the introduction of the spray system can further reduce the concentration or impact of certain hazard sources, thereby further improving the ventilation adjustment hazard data. Therefore, the impact of the hazard source is re-evaluated in combination with the spray data to obtain updated hazard data, i.e. spray adjustment hazard data, to ensure that the effect of the spray measure is accurately reflected in the adjusted health hazard data, and to optimize the comprehensive protection effect.

[0132] Step 710: In the case that the spray adjustment hazard data is not empty, according to the structure data of the barrack and the distribution of the spray adjustment hazard data, the evacuation channel information of each simulated biological is constructed as hazard treatment simulation data.

[0133] The evacuation path information can simulate how the living beings (such as personnel) safely evacuate through the escape path inside the barracks when the hazard occurs. This information is constructed according to the structure data of the barracks (such as the positions of doors and windows, the layout of corridors, the number of exits, etc.) and the distribution of the hazard source (such as the distribution of toxic gas or fire hot zone).

[0134] Specifically, in the case that the spray adjustment hazard data is not empty, it indicates that the target barracks still has factors that endanger the living beings, and analyzing the structure data of the barracks, such as the positions of doors and windows, the layout of corridors, the number of exits and their positions, etc., and analyzing the distribution of the spray adjustment hazard data will lead to a decrease in gas concentration or heat in certain areas, and also lead to chemical reactions in certain areas that result in unpredictable situations, so these changes need to be considered to affect the evacuation route of the living beings. For example, the effect of the spray system can make some exit areas safer, while other areas can become dangerous due to wet and slippery or too high water mist concentration. Based on these safe and unsafe factors, the system simulates how the living beings choose a path to avoid the hazard source according to the current environmental conditions. For example, if an exit is not safe due to high gas concentration, the simulated living beings will choose other safer channels. By considering different biological reactions, risk avoidance decisions and environmental factors, the best evacuation route for each simulated living being is constructed as the evacuation path information to ensure that it can avoid the hazard and safely evacuate to a safe area in the shortest time. This process is realized through a simulation algorithm to accurately evaluate the evacuation efficiency and safety when the hazard occurs.

[0135] In this embodiment, by simulating the hazard treatment air duct according to the barracks structure data and health hazard data, the ventilation system can be effectively optimized to reduce the accumulation of harmful substances and reduce health hazards. After adjusting the ventilation system, the spray simulation is performed again according to the updated hazard data to further enhance the hazard treatment effect and reduce the impact of the hazard source. The data after each adjustment can be optimized in the case that it is not empty, so as to accurately adjust the hazard treatment scheme and ensure the effectiveness of the protective measures. In addition, by analyzing the hazard data after the spray adjustment and constructing the evacuation path information, more reasonable risk avoidance paths can be provided for the simulated living beings to ensure timely evacuation in emergency situations and minimize personnel harm. Ultimately, comprehensive and effective hazard protection data can be provided to provide a scientific basis for actual emergency response and health risk management.

[0136] In one exemplary embodiment, as shown in Figure 8 According to the hazard treatment simulation data, biological feedback monitoring is performed on each simulated living being in the target barracks to obtain biological feedback monitoring simulation data, including steps 802 to 810. Among them:

[0137] At step 802, biological feedback data of each simulation organism in the target barrack is monitored according to the hazard treatment simulation data, and biological monitoring feature data of each simulation organism is obtained.

[0138] The biological feedback data can be data obtained by monitoring physiological responses of the simulation organism in a specific environment or condition. It usually includes heart rate, body temperature, blood oxygen level, respiratory rate and other indicators, reflecting the immediate physiological response of the organism to external hazards or environmental changes.

[0139] The biological monitoring feature data can be physiological feature data of the organism within a certain time after feature extraction of the biological feedback data.

[0140] Specifically, based on the hazard treatment simulation data of the target barrack, the biological feedback monitoring of each simulation organism (such as personnel or other organisms) in the target barrack is simulated, and the simulation organism feedback data such as heart rate, body temperature, respiratory rate, blood oxygen saturation, etc. is collected in real time to reflect its physiological response in the current hazardous environment, and further feature extraction is performed on the biological feedback data to obtain the biological monitoring feature data of each simulation organism.

[0141] At step 804, for any simulation organism, a physiological state development model of the simulation organism is constructed according to the biological monitoring feature data and the hazard treatment simulation data.

[0142] The physiological state development model can be a model for describing the physiological state change of the organism in a specific hazardous environment. The model is based on biological principles, combined with biological monitoring data and environmental hazard data, and predicts the evolution of the physiological state of the organism over time when exposed to different hazard sources (such as toxic gases, radiation, etc.) through mathematical equations and algorithms.

[0143] Specifically, for any simulated organism, the collected biological monitoring data (such as heart rate, body temperature, respiratory rate, etc.) and environmental hazard data (such as gas concentration, temperature, etc.) are taken as input variables to construct a multi-dimensional dataset. Then, regression analysis methods (such as linear regression, nonlinear regression, etc.) are used to model the relationship between the physiological response of the organism and the environmental hazards, and mathematical equations are established to describe the response pattern of the organism under different hazard conditions. Or use machine learning methods (such as random forest, support vector machine, neural network, etc.), combined with a large amount of historical data to train the model, so that it can learn the physiological change law of the organism under different environments. For more complex physiological changes, physiological models based on biological principles (such as dynamic models based on physiological systems) can be used to model the internal physiological processes of the organism, simulate the adaptation and response of the organism under different hazard conditions. Any of the above methods can combine biological monitoring data and hazard processing simulation data to form a physiological state development model that can predict the physiological state changes of the organism.

[0144] Step 806, according to the physiological state development model, the current physical condition of the simulated organism is evaluated, and the current physical state data of the organism is obtained.

[0145] Among them, the current physical state data of the organism can be the health data of the organism at a specific time obtained through real-time simulation monitoring. These data include heart rate, body temperature, blood oxygen level, respiratory rate, etc. physiological parameters, reflecting the immediate physiological response of the organism under the current hazardous environment.

[0146] Specifically, using the physiological state development model, combining the current biological monitoring feature data and hazard processing simulation data, the current health status of the simulated organism is calculated, such as whether there is excessive fatigue, toxicity poisoning, heat stress, etc. physiological abnormalities. The model will quantify the physiological response caused by different hazard sources and give the evaluation results, such as whether the organism is within the normal healthy range, whether emergency measures or adjustment of protection strategies need to be taken, and the current physical state data of the organism is obtained.

[0147] Step 808, according to the physiological state development model, the future physical condition of the simulated organism is evaluated, and the future physical change data of the organism is obtained.

[0148] Among them, the future physical change data of the organism can be predicted by the physiological state development model, describing the health change trend of the organism in the future period of time. These data are calculated according to the current physiological condition, environmental hazards and physiological adaptability, indicating the possible physiological changes of the organism under continuous exposure to a specific hazardous environment, such as health deterioration, recovery or adaptation, etc.

[0149] Specifically, the physiological state development model combines the current biomonitoring feature data with the hazard handling simulation data to analyze and predict the possible overt physical changes in the future, such as the cumulative effect of continuous exposure to harmful gases or radiation on the organism, or the stress response of the organism to long-term exposure to high temperature, high humidity, and other environmental conditions. Then input the just obtained overt physical changes (such as gas concentration changes or temperature fluctuations in the future few hours), the physiological state development model simulates the evolution of the physiological state of the simulated organism, evaluates the possible future health risks such as toxicity accumulation, physical exhaustion, and immune system damage, and obtains the future physical change data of the organism.

[0150] Step 810, fuse the current physical state data of the organism and the future physical change data of the organism to obtain the feedback monitoring simulation data of the organism.

[0151] Specifically, the current physical state data reflects the immediate health condition of the organism, while the future physical change data of the organism provides an early warning of future health risks. By combining these two parts of data according to certain weights. In practice, the current physical state data is usually considered to have a higher weight because it directly reflects the immediate health condition of the organism under the harmful environment and can provide the most timely and accurate risk information. While the future physical change data of the organism considers the long-term impact, although important, it usually has a certain uncertainty due to its model-based prediction, so the weight is relatively low. The specific value of the weight can be evaluated by regression analysis of the correlation between the current physical state data and the future physical change data of the organism and the health outcome, so as to assign a suitable weight to each type of data. Finally, the overall health risk of the organism under the current environmental hazard is calculated, and a complete evaluation result is generated to obtain the feedback monitoring simulation data of the organism.

[0152] In this embodiment, by monitoring the biological feedback data of the simulated organism and combining the hazard handling simulation data, the biological monitoring feature data of each simulated organism can be accurately obtained, thereby providing a scientific basis for its physiological state. Based on these data, a physiological state development model can be constructed to evaluate the current physical condition of the simulated organism in real time and predict possible future physiological changes. By fusing the current physical state and future physical change data, the health status of the organism in a specific harmful environment can be comprehensively reflected, providing a more accurate reference for health risk assessment. Ultimately, it provides a practical basis for formulating effective protective measures and emergency response strategies, which helps to improve the health protection of the simulated organism in the target barrack and optimize the hazard response strategy.

[0153] Based on the same inventive concept, the embodiment of the present application also provides a barracks health monitoring system based on multi-parameter sensing for implementing the barracks health monitoring method based on multi-parameter sensing. The system comprises a computer device and a data monitoring terminal. Figure 9 As shown in the figure, the computer device comprises a barracks data acquisition module 902, a hazard data extraction module 904, a hazard data analysis module 906, a barracks protection simulation module 908, and a barracks health analysis module 910. Further, the computer device can be a server, and its internal structure diagram can be as shown in the figure. Figure 10 As shown in the figure, the computer device comprises a barracks data acquisition module 902, a hazard data extraction module 904, a hazard data analysis module 906, a barracks protection simulation module 908, and a barracks health analysis module 910. Further, the computer device can be a server, and its internal structure diagram can be as shown in the figure.

[0154] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0155] The technical features of the above embodiments can be combined in any way. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combinations of the technical features do not exist contradictory, they should be considered as the scope of the present application.

[0156] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be noted that for ordinary skilled in the art, without departing from the concept of the present application, some modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for monitoring the health of barracks based on multi-parameter sensing, characterized in that, The method includes: Acquire fluctuation monitoring data, gas monitoring data, and structural data of the target barracks; the fluctuation monitoring data includes radiation data and / or seismic data corresponding to the target barracks; Feature extraction is performed on the wave monitoring data and the gas monitoring data to obtain wave feature data and gas feature data; By analyzing the correlation between the wave characteristic data and the gas characteristic data, multi-source hazard correlation information is obtained; Based on the multi-source hazard association information, the parameters of the initial multi-source data analysis algorithm for the target barracks are set to obtain the target multi-source data analysis algorithm; wherein, the expression of the target multi-source data analysis algorithm is, in, H Data on health hazards; This is the fusion function; These are the time-varying weighting coefficients for the fluctuation characteristic data; These are the time-varying weighting coefficients for gas characteristic data; It is a wave nonlinear matrix; For gas nonlinearity; This is data exhibiting fluctuation characteristics; For gas characteristic data; Time-varying correlation weight coefficients; A multi-source data association matrix; Nonlinear fusion; T The number of feature dimensions; M and N These represent the number of rows and columns in the multi-source data association matrix, respectively. S For barracks structure data; For structured data mapping functions; The weighting of the influence of barracks structure; This is the index variable for the nonlinear transformation channel; The fluctuation characteristic data and the gas characteristic data are input into the target multi-source data analysis algorithm to obtain the health hazard data; there is a synergistic effect or superposition effect between the fluctuation characteristic data and the gas characteristic data; Based on the barracks structure data and the health hazard data, a hazard protection simulation is performed to obtain the hazard protection data for the target barracks; The health hazard data is adjusted based on the hazard protection data to obtain the actual health data of the target barracks.

2. The method according to claim 1, characterized in that, When the multi-source hazard association information is less than a preset hazard association threshold, the step of setting the parameters of the initial multi-source data analysis algorithm for the target barracks based on the multi-source hazard association information to obtain the target multi-source data analysis algorithm includes: Based on the multi-source hazard association information, the initial fluctuation hazard analysis item and the initial gas hazard analysis item of the initial multi-source data analysis algorithm are constructed. Based on the fluctuation characteristic data, the parameters of the initial fluctuation hazard analysis item are set to obtain the target fluctuation hazard analysis item; Based on the gas characteristic data, the parameters of the initial gas hazard analysis item are set to obtain the target gas hazard analysis item; The target fluctuation hazard analysis item and the target gas hazard analysis item are combined to obtain the target multi-source data analysis algorithm.

3. The method according to claim 1, characterized in that, When the multi-source hazard association information is greater than a preset hazard association threshold, the step of setting the parameters of the initial multi-source data analysis algorithm for the target barracks based on the multi-source hazard association information to obtain the target multi-source data analysis algorithm includes: Based on the multi-source hazard association information, the initial hazard analysis weighting term and the initial hazard analysis association term of the initial multi-source data analysis algorithm are constructed. Multidimensional nonlinear transformations are performed on the wave characteristic data and the gas characteristic data respectively to obtain the wave nonlinear matrix and the gas nonlinear matrix. Based on the wave nonlinear matrix and the gas nonlinear matrix, the initial hazard analysis weighting term is set to obtain the target hazard analysis weighting term; Based on the multi-source hazard association information, the multi-source data association matrix of the initial hazard analysis association items is set to obtain the target hazard analysis association items; The nonlinear fusion of the target hazard analysis weighting term and the target hazard analysis correlation term is constructed to obtain the target multi-source data analysis algorithm.

4. The method according to claim 1, characterized in that, The step of performing hazard protection simulation based on the barracks structure data and the health hazard data to obtain hazard protection data for the target barracks includes: Based on the barracks structure data and the health hazard data, a hazard treatment simulation was performed to obtain hazard treatment simulation data. Based on the hazard treatment simulation data, biofeedback monitoring was performed on each simulated organism in the target barracks to obtain biofeedback monitoring simulation data. If the biofeedback monitoring simulation data indicates that any of the simulated organisms has a physical abnormality, the simulation parameters of the hazard treatment simulation are adjusted. Using the new simulation parameters, return to the step of performing hazard treatment simulation based on the barracks structure data and the health hazard data to obtain hazard treatment simulation data, until none of the simulated organisms have any physical abnormalities or the simulation parameters trigger hazard treatment constraint rules, and obtain the hazard protection data.

5. The method according to claim 4, characterized in that, The step of performing hazard treatment simulation based on the barracks structure data and the health hazard data to obtain hazard treatment simulation data includes: Based on the barracks structure data and the health hazard data, the hazard treatment ventilation duct of the target barracks is simulated to obtain hazard treatment ventilation data; The health hazard data is adjusted based on the hazard treatment ventilation data to obtain ventilation-adjusted hazard data; If the ventilation adjustment hazard data is not empty, the spray data of the target barracks is simulated based on the barracks structure data and the ventilation adjustment hazard data to obtain hazard treatment spray data; Based on the hazard treatment spray data, the ventilation adjustment hazard data is adjusted to obtain the spray adjustment hazard data; If the sprinkler adjustment hazard data is not null, the evacuation channel information of each of the simulated organisms is constructed as the hazard treatment simulation data based on the barracks structure data and the distribution of the sprinkler adjustment hazard data.

6. The method according to claim 4, characterized in that, The step of conducting biofeedback monitoring on each simulated organism in the target barracks based on the hazard treatment simulation data to obtain biofeedback monitoring simulation data includes: Based on the hazard treatment simulation data, biofeedback data of each simulated organism in the target barracks is monitored to obtain biomonitoring characteristic data of each simulated organism. For any of the simulated organisms, a physiological state development model of the simulated organism is constructed based on the biological monitoring characteristic data and the hazard treatment simulation data; The current physical condition of the simulated organism is assessed based on the physiological state development model to obtain the organism's current physical condition data; Furthermore, the future physical condition of the simulated organism is assessed based on the physiological state development model to obtain data on future physical changes in the organism; By integrating the current physical state data of the organism and the future physical change data of the organism, the biological feedback monitoring simulation data is obtained.

7. A barracks health monitoring system based on multi-parameter sensing, characterized in that, The system includes: computer equipment and data monitoring terminal; the computer equipment includes a barracks data acquisition module, a hazard data extraction module, a hazard data analysis module, a barracks protection simulation module, and a barracks health analysis module; The barracks data acquisition module is used to acquire fluctuation monitoring data, gas monitoring data, and barracks structural data of the target barracks; the fluctuation monitoring data includes radiation data and / or earthquake data corresponding to the target barracks. The hazard data extraction module is used to extract features from the fluctuation monitoring data and the gas monitoring data to obtain fluctuation feature data and gas feature data. The hazard data analysis module is used to analyze the correlation between the fluctuation characteristic data and the gas characteristic data to obtain multi-source hazard correlation information; Based on the multi-source hazard association information, the parameters of the initial multi-source data analysis algorithm for the target barracks are set to obtain the target multi-source data analysis algorithm; wherein, the expression of the target multi-source data analysis algorithm is, in, H Data on health hazards; This is the fusion function; These are the time-varying weighting coefficients for the fluctuation characteristic data; These are the time-varying weighting coefficients for gas characteristic data; It is a wave nonlinear matrix; For gas nonlinearity; This is data exhibiting fluctuation characteristics; For gas characteristic data; Time-varying correlation weight coefficients; A multi-source data association matrix; Nonlinear fusion; T The number of feature dimensions; M and N These represent the number of rows and columns in the multi-source data association matrix, respectively. S For barracks structure data; For structured data mapping functions; The weighting of the influence of barracks structure; This is the index variable for the nonlinear transformation channel; The fluctuation characteristic data and the gas characteristic data are input into the target multi-source data analysis algorithm to obtain the health hazard data; there is a synergistic effect or superposition effect between the fluctuation characteristic data and the gas characteristic data; The barracks protection simulation module is used to perform hazard protection simulation based on the barracks structure data and the health hazard data to obtain the hazard protection data of the target barracks. The barracks health analysis module is used to adjust the health hazard data based on the hazard protection data to obtain the actual health data of the target barracks.

8. The system according to claim 7, characterized in that, The computer device further includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method according to any one of claims 1 to 6.

Images