A data processing method and system for detecting environmental components in occupational health

Abstract

The application discloses a kind of environmental component detection data processing method and system in occupational health, belong to environmental data processing technical field, it includes obtaining the original detection data of multiple-source detection equipment and obtaining the real-time position information of staff and matching, generate structured monitoring matrix and calculate dynamic risk value, generate real-time risk vector, identify complex pollution scene and calculate enhancement effect, generate superimposed risk index and compare with occupational exposure limit standard, generate risk classification signal and carry out short-term exposure trend analysis, predict future risk level change, generate early warning decision instruction containing current risk level and predicted risk level and execute double-path intervention strategy, generate device control signal driving physical device action.The application dynamically associates multiple-source monitoring data with personnel position, and carries out multidimensional risk calculation, trend prediction and closed-loop control, and can realize accurate dynamic evaluation and forward-looking early warning intervention on individual risk.

Description

Technical Field

[0001] This invention relates to the field of environmental data processing technology, and in particular to a method and system for processing environmental component detection data in occupational health. Background Technology

[0002] Occupational health aims to protect the health and safety of workers by identifying, assessing, and controlling various hazardous factors in the work environment. With the development of information technology, automating the processing of environmental monitoring data using computer systems has become a key technological means to improve occupational health management. Data processing systems collect and analyze data from various sensors to support risk assessment and safety decision-making, forming the cornerstone of intelligent and refined occupational health management.

[0003] In existing technologies, occupational health monitoring typically involves deploying detection equipment at fixed locations within the workplace to measure the concentration of specific environmental components, such as harmful gases or dust. After this data is transmitted to a central computer system, the data processing primarily involves comparing real-time concentration values ​​with occupational exposure limits set by national or industry standards. When the system detects that a monitored value exceeds a preset static threshold, it triggers an alarm signal to alert management.

[0004] However, the data processing is region-based, failing to effectively correlate environmental data with on-site moving workers, leading to distorted assessments of individual actual exposure levels. Secondly, the data processing is relatively simplistic, typically relying solely on instantaneous concentration as the sole criterion, failing to comprehensively address complex factors such as the cumulative effect of exposure time and the combined toxicity effects of multiple pollutants present simultaneously, resulting in incomplete and unscientific risk assessments. Finally, the entire data processing and response mechanism is reactive, only issuing alerts after a hazard has occurred, lacking the ability to analyze and predict risk development trends, making proactive preventative intervention difficult. Summary of the Invention

[0005] To address the aforementioned issues, this invention provides a method and system for processing environmental component detection data in occupational health. It employs a technical solution that dynamically correlates multi-source monitoring data with personnel location and performs multi-dimensional risk calculation, trend prediction, and closed-loop control. This enables precise dynamic assessment of individual risks and proactive early warning intervention, significantly enhancing the scientific rigor and initiative of occupational health management.

[0006] The above objectives can be achieved through the following approach:

[0007] A method for processing environmental component detection data in occupational health includes: acquiring raw detection data from multi-source detection devices and adding device location tags and timestamps to the raw detection data to generate an initial dataset, wherein the raw detection data includes pollutant type and pollutant concentration data; acquiring real-time location information of workers and matching the real-time location information with the device location tags in the initial dataset to generate a structured monitoring matrix dynamically associated with worker IDs; calculating dynamic risk values ​​based on the structured monitoring matrix and according to preset toxicity coefficients and preset exposure duration correction factors to generate a real-time risk vector; identifying compound pollution scenarios and calculating enhancement effects based on the real-time risk vector to generate a superimposed risk index; comparing the superimposed risk index with preset occupational exposure limit standards and generating a risk grading signal based on the comparison results; performing short-term exposure trend analysis on the risk grading signal to predict future risk level changes and generating an early warning decision instruction containing the current risk level and the predicted risk level; and executing a dual-path intervention strategy based on the current risk level and the predicted risk level in the early warning decision instruction to generate device control signals that drive the physical equipment.

[0008] Optionally, generating a structured monitoring matrix dynamically associated with staff ID numbers includes: obtaining coordinate data containing staff ID numbers through positioning devices worn by staff to obtain real-time location information; matching the coordinate data in the real-time location information with device location tags in an initial dataset to determine the target detection device; obtaining the original detection data, device location tags, and timestamps of the target detection device based on the initial dataset, and binding them with the staff IDs corresponding to the coordinate data, arranging them in chronological order to generate a structured monitoring matrix containing four-dimensional data fields.

[0009] Optionally, the step of calculating a dynamic risk value and generating a real-time risk vector based on the structured monitoring matrix and according to a preset toxicity coefficient and a preset exposure duration correction factor includes: extracting the pollutant type and corresponding current pollutant concentration data bound to the worker's ID from the structured monitoring matrix; obtaining the corresponding toxicity intensity parameter from a preset toxicity coefficient library based on the bound pollutant type; calculating a basic hazard value using the toxicity intensity parameter and the current pollutant concentration data; obtaining the worker's exposure duration data based on the structured monitoring matrix, and generating an exposure duration correction factor based on the exposure duration data; calculating the dynamic risk value of the corresponding pollutant using the exposure duration correction factor and the basic hazard value; and integrating the worker's ID, the bound pollutant type, and the dynamic risk value of the corresponding pollutant to generate a real-time risk vector.

[0010] Optionally, the step of identifying compound pollution scenarios and calculating enhancement effects based on the real-time risk vector to generate a superimposed risk index includes: obtaining combinations of different pollutant types based on the real-time risk vector to obtain a pollutant combination dataset; obtaining a synergistic enhancement coefficient of the pollutant combination using a preset compound hazard database and the pollutant combination dataset; correcting the dynamic risk value of the corresponding pollutant using the synergistic enhancement coefficient to obtain a compound risk value; extracting the corresponding equipment location tag from the real-time risk vector, and integrating the staff number, the corresponding equipment location tag, and the compound risk value to obtain a superimposed risk index.

[0011] Optionally, the step of comparing the superimposed risk index with a preset occupational exposure limit standard includes: obtaining the individual sensitivity parameters of the staff, which are generated based on the staff's historical physical examination data or allergy history records; and using the individual sensitivity parameters to make personalized corrections to the composite risk value in the superimposed risk index.

[0012] Optionally, comparing the superimposed risk index with a preset occupational exposure limit standard and generating a risk classification signal based on the comparison result includes: obtaining the concentration safety threshold of each pollutant from the preset occupational exposure limit standard based on the superimposed risk index; calculating the average of the ratios of the corrected composite risk value of each pollutant to the corresponding concentration safety threshold to obtain a risk score; generating a risk-free label when the risk score is less than a preset first threshold; generating a level-one risk label when the risk score is greater than or equal to the first threshold and less than a preset second threshold; generating a level-two risk label when the risk score is greater than or equal to the second threshold; and obtaining a risk classification signal based on the worker number, the corresponding equipment location label, and the generated risk label in the superimposed risk index; wherein the generated risk label includes the risk-free label, the level-one risk label, and the level-two risk label.

[0013] Optionally, the step of performing short-term exposure trend analysis on the risk grading signal, predicting future risk level changes, and generating an early warning decision instruction containing the current risk level and the predicted risk level includes: extracting the current risk level based on the risk label generated from the risk grading signal, and converting it into a numerical form using a preset risk level mapping table to obtain the current risk level value; obtaining the historical risk level value and historical time series of the corresponding equipment location label; establishing a risk mapping function to characterize the historical risk level value using the historical time series; calculating the risk level value at a preset time point based on the current risk level value and the risk mapping function to obtain the predicted risk level value; obtaining the predicted risk level based on the predicted risk level value and the risk level mapping table; and integrating the staff number, the corresponding equipment location label, the current risk level, and the predicted risk level to generate an early warning decision instruction.

[0014] Optionally, the step of executing a dual-path intervention strategy based on the current risk level and the predicted risk level in the early warning decision instruction to generate equipment control signals to drive physical equipment includes: generating a first control signal to activate the on-site audible and visual alarm device when the current risk level in the early warning decision instruction triggers a preset instant alarm threshold; and generating a second control signal to start the ventilation and purification system or increase the operating power of the ventilation and purification system when the predicted risk level in the early warning decision instruction is greater than or equal to the current risk level; wherein the equipment control signal includes the first control signal and the second control signal.

[0015] Optionally, the method further includes: acquiring status data fed back by the device based on the device control signal; acquiring the real-time risk level at the preset time point; performing correlation analysis on the predicted risk level at the preset time point, the real-time risk level at the preset time point, and the status data to generate an intervention effect evaluation report.

[0016] Based on the same inventive concept, this invention also provides a data processing system for environmental component detection in occupational health. The system includes: an equipment data acquisition module for acquiring raw detection data from multi-source detection equipment and attaching equipment location tags and timestamps to the raw detection data to generate an initial dataset; the raw detection data includes pollutant type and pollutant concentration data; an environmental monitoring module for acquiring real-time location information of workers and matching the real-time location information with the equipment location tags in the initial dataset to generate a structured monitoring matrix dynamically associated with worker IDs; and an initial risk calculation module for calculating risks based on the structured monitoring matrix and according to a preset toxicity coefficient and a preset exposure duration correction factor. The system includes: a dynamic risk value calculation module to generate a real-time risk vector; a composite risk calculation module to identify composite pollution scenarios and calculate the enhancement effect based on the real-time risk vector, generating a superimposed risk index; a risk level confirmation module to compare the superimposed risk index with a preset occupational exposure limit standard, and generate a risk classification signal based on the comparison result; a risk warning module to perform short-term exposure trend analysis on the risk classification signal, predict future risk level changes, and generate a warning decision instruction containing the current risk level and the predicted risk level; and a decision execution module to execute a dual-path intervention strategy based on the current risk level and the predicted risk level in the warning decision instruction, generating equipment control signals that drive the physical equipment to move.

[0017] Compared with the prior art, the present invention has the following advantages:

[0018] 1. This invention realizes the transformation from traditional regional and static environmental monitoring to individualized and dynamic occupational health risk assessment by constructing an environmental monitoring data processing flow that dynamically links the location of workers. The method accurately matches the pollutant concentration data of environmental sensors with the real-time location information of workers, generating a unique exposure data stream for each worker. This enables accurate quantification of the real risks faced by individuals at specific times and locations, greatly improving the pertinence and accuracy of risk assessment.

[0019] 2. This invention proposes a multi-dimensional and scientific risk quantification model. Its risk calculation no longer relies solely on the concentration of a single pollutant, but comprehensively considers the inherent toxicity of pollutants, the cumulative exposure time of workers, the synergistic enhancement effect when multiple pollutants coexist, and even individual differences in physiological sensitivity. This comprehensive calculation method makes the risk assessment results closer to the actual physiological health impact, and can identify hidden and complex risks that may be overlooked under traditional standards, thus providing a more profound and comprehensive basis for occupational health management decisions.

[0020] 3. This invention introduces a risk prediction mechanism based on historical data trend analysis, and designs a dual-path intervention strategy that takes into account both the present and the future, upgrading occupational health management from passive response to proactive prevention. The system can not only provide real-time audible and visual alarms for risks that have already exceeded limits, but also activate or adjust environmental intervention equipment such as ventilation and purification in advance by predicting the development trend of risks, effectively curbing the deterioration of risks. This forward-looking closed-loop management model closely integrates data processing, risk assessment, early warning decision-making and physical intervention, significantly improving the initiative and efficiency of risk control.

[0021] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures pointed out in the description, claims and drawings. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart illustrating a method for processing environmental component detection data in occupational health according to an embodiment of the present invention.

[0024] Figure 2 This is a schematic diagram of the structure of an occupational health environmental component detection data processing system according to an embodiment of the present invention.

[0025] Figure 3 This is a schematic diagram illustrating the change of toluene and benzene concentrations over time according to an embodiment of the present invention. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] Reference Figure 1One embodiment of the present invention proposes a method for processing environmental component detection data in occupational health. The method adopts a technical solution that dynamically correlates multi-source monitoring data with personnel location and performs multi-dimensional risk calculation, trend prediction and closed-loop control. This can achieve accurate dynamic assessment of individual risks and proactive early warning intervention, significantly improving the scientific nature and initiative of occupational health management.

[0028] The method described in this embodiment specifically includes:

[0029] Acquire raw detection data from multi-source detection devices, and attach device location tags and timestamps to the raw detection data to generate an initial dataset. The raw detection data includes pollutant type and pollutant concentration data.

[0030] Specifically, environmental data is first collected using multi-source detection devices deployed at various locations within the workplace. These devices are specialized sensors for specific pollutants, such as carbon monoxide detectors or volatile organic compound (VOC) sensors. Each device continuously measures the concentration of its monitored pollutant type in the air during its operating cycle, generating raw detection data containing these two core pieces of information. These distributed devices transmit the collected raw detection data to a central data processing server in real-time or periodically via built-in wireless or wired communication modules. When the central server receives a data packet from any detection device, it immediately performs data enrichment and structuring processing. First, the server precisely appends a timestamp to each received data packet, recording the exact moment the data was received and processed by the server, ensuring consistency and comparability of all data across time. Simultaneously, the server queries a pre-configured device asset database using the unique device identifier contained in the data packet. This database stores static information for each detection device, most importantly its precise physical installation coordinates, i.e., device location tags. The server then appends the retrieved device location tags to the corresponding raw detection data. After the two crucial steps of adding timestamps and device location tags, the originally fragmented raw detection data, lacking spatiotemporal context, is transformed into structurally complete data records. These records are continuously aggregated, eventually forming a dynamically updated initial dataset, providing a standardized data source containing both temporal and spatial dimensions for subsequent risk analysis.

[0031] The real-time location information of the staff is obtained, and the real-time location information is matched with the device location tags in the initial dataset to generate a structured monitoring matrix that is dynamically associated with the staff ID.

[0032] Based on the structured monitoring matrix and according to the preset toxicity coefficient and the preset exposure duration correction factor, the dynamic risk value is calculated and a real-time risk vector is generated.

[0033] Based on the real-time risk vector, composite pollution scenarios are identified and the enhancement effect is calculated to generate superimposed risk indicators.

[0034] The superimposed risk index is compared with the preset occupational exposure limit standard, and a risk classification signal is generated based on the comparison result.

[0035] The risk classification signal is subjected to short-term exposure trend analysis to predict future changes in risk level and generate early warning decision instructions that include the current risk level and the predicted risk level.

[0036] Based on the current risk level and the predicted risk level in the early warning decision instruction, a dual-path intervention strategy is executed to generate equipment control signals that drive the physical equipment to move.

[0037] This invention establishes a standardized initial dataset by attaching spatiotemporal labels to multi-source environmental monitoring data. Next, this environmental data is dynamically matched with the real-time location information of personnel, transforming macro-level environmental monitoring data into an individual-centric exposure information stream. Based on this, a basic dynamic risk value is calculated by combining the inherent toxicity of pollutants with exposure duration. Then, complex scenarios with multiple pollutants coexisting are identified, and a synergistic enhancement effect is introduced to generate a more realistic superimposed risk indicator. Subsequently, this quantified risk is compared with legal standards for classification, and time series analysis is introduced to predict the changing trend of the risk level. Finally, based on the current and predicted risk levels, a dual-path decision engine is activated to generate control signals that can directly drive physical intervention equipment, achieving automated risk management and control.

[0038] Optionally, generating a structured monitoring matrix dynamically associated with staff ID numbers includes:

[0039] Real-time location information is obtained by acquiring coordinate data containing staff identification numbers through positioning devices worn by staff.

[0040] The coordinate data in the real-time location information is matched with the device location labels in the initial dataset to determine the target detection device;

[0041] Based on the initial dataset, the original detection data, device location tags, and timestamps of the target detection device are obtained and bound to the staff numbers of the corresponding coordinate data. The data are then arranged in chronological order to generate a structured monitoring matrix containing four-dimensional data fields.

[0042] Specifically, the core of this method lies in constructing a data structure—a structured monitoring matrix—that dynamically associates environmental monitoring data with specific staff members. This process first obtains the real-time location information of each staff member using a personal positioning device. This information includes a unique staff member number and their real-time coordinates within the workplace. Simultaneously, the system has pre-built an initial dataset containing information on various pollutant monitoring devices, where each device has a fixed location label—the coordinates of its installation location. Next, a crucial matching operation is performed to determine the target monitoring device most relevant to the staff member's current location. This matching operation is achieved by calculating the spatial distance between the staff member's coordinates and the location labels of each device in the initial dataset. The spatial distance between the staff member and the monitoring device is calculated. ,have:

[0043] ,

[0044] in, Real-time coordinate data obtained from positioning devices worn by staff; These are the fixed coordinates represented by the device location labels of the detection devices obtained from the initial dataset. When the calculated spatial distance... When the effective monitoring radius is less than a preset limit, the detection device is identified as the target detection device. Once the target detection device is identified, a complete set of information related to the device is extracted from the initial dataset, including the raw detection data it monitored, i.e., the specific pollutant type and concentration data, as well as the device location tag and timestamp that recorded the data. Subsequently, this information is bound to the worker ID that triggered the matching, forming a complete data record. These records are continuously generated and arranged in chronological order according to their timestamps, thus compiling a dynamically updated structured monitoring matrix. Each entry in this matrix contains four core data fields: worker ID, timestamp, device location tag, and raw detection data, comprehensively describing the environmental conditions encountered by a specific worker at a specific time and location. By constructing a structured monitoring matrix dynamically associated with the real-time location of workers, and combining toxicity coefficients, exposure duration, compound pollution enhancement effects, and individual sensitivity parameters, a shift from static, regional environmental monitoring to dynamic, individualized occupational health risk assessment is achieved. This significantly improves the accuracy, foresight, and proactivity of occupational health management, thereby more effectively protecting the health and safety of workers and optimizing the allocation of safety resources.

[0045] It should be noted that after acquiring the raw detection data from multi-source detection devices and the real-time location information of personnel, the system first performs data preprocessing and verification steps to ensure the accuracy of subsequent analysis and the robustness of the system. Specifically, for the raw detection data collected by sensors, validity verification is performed. For example, it checks whether the data is within a reasonable physical range, identifies and marks outliers such as persistent flat lines or extreme jumps caused by sensor malfunctions, and uses the 3σ principle or the isolated forest algorithm to remove or correct them. For the real-time location information acquired by the positioning devices worn by personnel, since signal fluctuations may cause noise or drift in the coordinate data, algorithms such as Kalman filtering are used to smooth and denoise the data, resulting in a more stable and accurate position trajectory, ensuring the quality of the data input into subsequent processes.

[0046] Optionally, the step of calculating a dynamic risk value and generating a real-time risk vector based on the structured monitoring matrix and according to a preset toxicity coefficient and a preset exposure duration correction factor includes:

[0047] Extract the pollutant type and corresponding current pollutant concentration data associated with the staff member's ID from the structured monitoring matrix;

[0048] Based on the type of pollutant, the corresponding toxicity intensity parameter is obtained from a preset toxicity coefficient library;

[0049] The basic hazard value is calculated using the aforementioned toxicity intensity parameter and the current pollutant concentration data;

[0050] Based on the structured monitoring matrix, the exposure duration data of the staff is obtained, and an exposure duration correction factor is generated based on the exposure duration data.

[0051] Using the exposure duration correction factor and the baseline hazard value, the dynamic risk value of the corresponding pollutant is calculated;

[0052] By integrating staff numbers, associated pollutant types, and corresponding dynamic risk values ​​of pollutants, a real-time risk vector is generated.

[0053] Specifically, firstly, from the dynamically generated structured monitoring matrix, for each worker's ID, the type of pollutant and its corresponding current concentration in their current environment are precisely extracted. Next, using the extracted pollutant type as an index, a search and matching process is performed in a pre-defined toxicity coefficient database. This database is based on toxicological data published by authoritative institutions, normalizing the occupational exposure limits (OELs) of different pollutants to 0-2 to obtain dimensionless toxicity intensity parameters to characterize their relative hazard levels. Following this, the basic hazard value calculation stage begins. By combining the current pollutant concentration data with the toxicity intensity parameter, a preliminary risk measure, i.e., the basic hazard value, is generated. ,have:

[0054] ,

[0055] in, The current pollutant concentration data obtained from the structured monitoring matrix are direct physical measurements. This represents the toxicity intensity parameter obtained from the toxicity coefficient database. It has been standardized and is a dimensionless coefficient whose value is determined by the toxicity of the substance itself. After calculating the basic hazard value, a time dimension is further introduced to make the risk assessment dynamic. The structured monitoring matrix is ​​accessed again to obtain the exposure duration data associated with the worker's ID number. This data records the duration from the worker's entry into the monitored area. Based on this exposure duration data, an exposure duration correction factor is generated. This correction factor is also a dimensionless adjustment coefficient used to quantify the cumulative effect of risk. Its generation can be based on a pre-defined nonlinear function, such as a logarithmic function. Where T is the exposure duration (in hours). This is an adjustment factor. It reflects the pattern of rapid risk growth in the initial exposure phase, followed by a gradual slowdown. Finally, this adjustment factor is used to adjust the previously calculated baseline hazard value to calculate the final dynamic risk value. For the dynamic risk value... ,have:

[0056] ,

[0057] in, This represents an exposure duration correction factor generated based on exposure duration data. Through this multiplication operation, three key factors—the inherent toxicity of the pollutant, its current concentration, and the duration of exposure—are integrated to obtain a comprehensive dynamic risk indicator. Finally, the system integrates the worker's ID, the type of pollutant they were exposed to, and the calculated dynamic risk value of the corresponding pollutant to construct a real-time risk vector, which serves as input for subsequent composite risk analysis. This elevates static, isolated pollutant concentration monitoring to a dynamic, personalized risk assessment mechanism. By introducing a toxicity intensity parameter, this method can distinguish the inherent hazards of different pollutants, avoiding the one-sidedness of treating all substances equally. By combining the exposure duration correction factor, it accurately reflects the objective law that occupational health risks increase with the cumulative exposure time. This makes the risk assessment result no longer an instantaneous snapshot, but a dynamic indicator that reflects the cumulative effect, thus providing a more profound, accurate, and forward-looking decision-making basis for occupational health management, significantly improving the accuracy and timeliness of risk identification.

[0058] Optionally, the step of identifying compound pollution scenarios and calculating enhancement effects based on the real-time risk vector to generate superimposed risk indicators includes:

[0059] Based on the real-time risk vector, combinations of different pollutant types are obtained to generate a pollutant combination dataset.

[0060] Using a pre-defined composite hazard database and the pollutant combination dataset, the synergistic enhancement coefficient of the pollutant combination is obtained;

[0061] The dynamic risk value of the corresponding pollutant is corrected using the synergistic enhancement coefficient to obtain the composite risk value;

[0062] The corresponding equipment location tags are extracted from the real-time risk vector, and the staff number, the corresponding equipment location tags, and the composite risk value are integrated to obtain the superimposed risk index.

[0063] Specifically, this method aims to address complex pollution scenarios where multiple pollutants coexist in the workplace. By calculating the synergistic enhancement effect, it generates a more accurate cumulative risk index. This process begins with the analysis of real-time risk vectors. First, based on the real-time risk vectors, all types of pollutants that a specific worker is exposed to at the same time and place are identified. These coexisting pollutant types are then combined to form a pollutant combination dataset, which forms the basis for identifying complex pollution scenarios. Subsequently, a pre-defined complex hazard database, established based on toxicological studies, is used, where the synergistic enhancement coefficient is determined according to the interaction relationships between pollutants. For example, for a simple additive effect, the synergistic enhancement coefficient is 1; for known synergistic enhancement effects (such as certain solvent mixtures), the synergistic enhancement coefficient is greater than 1, and its specific value can be determined by experimental data or professional literature. Using a specific combination from the pollutant combination dataset as the query condition, the corresponding synergistic enhancement coefficient is retrieved from this database. The synergistic enhancement coefficient is a key dimensionless parameter used to quantify the degree of enhancement of the total hazard relative to the individual hazard of each pollutant when different pollutants coexist. After obtaining this coefficient, it is used to correct the original dynamic risk values ​​of all individual pollutants in the pollutant combination, thus obtaining the composite risk value of the corresponding pollutants. For example, the synergistic enhancement coefficient of the first combination containing pollutant A is... The synergistic enhancement coefficient of the second combination containing pollutant A is For the composite risk value of pollutant A Then we have:

[0064] ,

[0065] in, The dynamic risk value of pollutant A is represented by this formula. These dynamic risk values ​​are obtained from the real-time risk vector generated in the previous steps and are themselves dimensionless values ​​that have undergone standardization, so they can be directly added together. This formula objectively reflects the true hazard of individual pollutants in compound pollution by multiplying independent risks by synergistic enhancement effects. Finally, the corresponding equipment location tags are extracted from the real-time risk vector, and the workers are numbered. These equipment location tags are integrated with the calculated compound risk values ​​to generate a structured superimposed risk index. By introducing the key concept of synergistic enhancement effects, the true health risks in compound pollution scenarios can be assessed more scientifically and accurately. By identifying pollutant combinations and quantifying their enhancement effects using a compound hazard database, this method can reveal potentially high-risk situations where the concentration of individual pollutants is within limits, but the combination may produce serious hazards. This greatly improves the sensitivity and accuracy of risk assessment, enabling occupational health management to identify and address previously overlooked hidden risks, providing solid data support for developing more targeted protective measures and intervention strategies, thereby more effectively protecting the health and safety of workers in complex chemical environments.

[0066] Optionally, the method further includes:

[0067] Obtain individual sensitivity parameters for staff members, which are generated based on staff members' historical physical examination data or allergy history records;

[0068] The composite risk value in the superimposed risk index is personalized by using the individual sensitivity parameter.

[0069] Specifically, individual sensitivity parameters characterizing individual health differences among staff members were introduced and applied. This process first requires obtaining the individual sensitivity parameters for each staff member. These parameters are generated based on in-depth analysis of individual health records, primarily using historical medical examination data and allergy records. The generation of individual sensitivity parameters can be achieved through a weighted model. For example, key physiological indicators (such as ALT values ​​in liver function) from historical medical examination data are compared with standard values, combined with allergy records (such as allergies to a certain type of dust), and weighted differently to calculate a comprehensive, standardized correction coefficient. This parameter serves as a correction coefficient with a baseline value of 1, representing the average sensitivity under standard health conditions. A value greater than 1 indicates that the staff member is relatively sensitive to a specific hazard, while a value less than 1 indicates relatively strong tolerance. After obtaining the individual sensitivity parameters, these parameters are used to individually correct the superimposed risk indicators calculated in the previous steps. The specific target of the correction is the composite risk value contained in the superimposed risk indicators. The correction process can be achieved by multiplying the individual sensitivity parameter by the composite risk value. After the calculation is completed, this new personalized composite risk value replaces the original composite risk value in the superimposed risk indicator, thereby generating a personalized superimposed risk indicator. This corrected indicator is then used in subsequent risk classification and early warning decision-making processes.

[0070] Optionally, comparing the superimposed risk index with a preset occupational exposure limit standard and generating a risk classification signal based on the comparison result includes:

[0071] Based on the superimposed risk indicators, the concentration safety thresholds of each pollutant are obtained from the preset occupational exposure limit standards.

[0072] The risk score is obtained by averaging the ratios of the corrected composite risk value for each pollutant to the corresponding concentration safety threshold.

[0073] When the risk score is less than a preset first threshold, a risk-free label is generated;

[0074] When the risk score is greater than or equal to the first threshold and less than the preset second threshold, a level 1 risk label is generated;

[0075] When the risk score is greater than or equal to the second threshold, a secondary risk label is generated;

[0076] Based on the staff number, the corresponding equipment location tag, and the generated risk tag in the superimposed risk index, a risk classification signal is obtained;

[0077] The generated risk labels include the risk-free label, the primary risk label, and the secondary risk label.

[0078] Specifically, the process begins with inputting a worker-specific overlay risk indicator, which includes the worker's ID, equipment location tag, and a personalized composite risk value. Based on the pollutant type corresponding to the personalized composite risk value within this overlay risk indicator, the system retrieves the concentration safety threshold for each pollutant from a pre-defined occupational exposure limit database. These thresholds represent legally mandated or industry-recommended safe exposure limits. After obtaining the benchmark, the ratio of the corrected composite risk value for all pollutants faced by the worker to their respective concentration safety thresholds is calculated. The average of these ratios is then calculated to obtain a risk score. This ratio calculation normalizes different pollutants for easier comparison. When the risk score is less than the first threshold, the current situation is considered safe, and a "no risk" label is generated. When the risk score is greater than or equal to the first threshold but less than the second threshold, risk exposure is identified, and a Level 1 risk label is generated, representing a localized or single source exceeding the limit. In more severe composite pollution scenarios, when the risk score is greater than or equal to the second threshold, a comprehensive high-risk exposure state is identified, and a Level 2 risk label is generated. Finally, the staff ID and corresponding equipment location tag carried in the superimposed risk indicators are integrated with the newly generated risk tag—either a no-risk tag, a level-one risk tag, or a level-two risk tag—to form a structured risk grading signal. This signal not only clearly defines the severity of the current risk but also precisely identifies the personnel and locations associated with the risk, providing direct and crucial input information for subsequent risk trend prediction and early warning decisions.

[0079] Optionally, the step of performing short-term exposure trend analysis on the risk grading signal, predicting future changes in risk level, and generating an early warning decision instruction that includes the current risk level and the predicted risk level includes:

[0080] Based on the risk label generated from the risk classification signal, the current risk level is extracted and converted into a numerical form using a preset risk level mapping table to obtain the current risk level value.

[0081] Obtain the historical risk level values ​​and historical time series of the corresponding device location tags;

[0082] By utilizing historical time series data, a risk mapping function is established to characterize historical risk level values.

[0083] Based on the current risk level value and the risk mapping function, the risk level value at a preset time point is calculated to obtain the predicted risk level value;

[0084] Based on the predicted risk level value and the risk level mapping table, the predicted risk level is obtained;

[0085] By integrating staff numbers, corresponding equipment location tags, current risk levels, and predicted risk levels, early warning decision instructions are generated.

[0086] Specifically, the analysis of the risk grading signal generated in the previous stage first involves extracting the generated risk labels, such as the Level 1 risk label, from the signal and directly identifying it as the current risk level. To facilitate mathematical calculations and trend analysis, a preset risk level mapping table is used to convert the textual current risk level into a dimensionless numerical form, i.e., the current risk level value. For example, no risk, Level 1 risk, and Level 2 risk are mapped to the values ​​0, 1, and 2, respectively, as shown in Table 1.

[0087] Table 1 Risk Level Mapping Table

[0088] Current risk level value Risk level Predicted risk level value 0 Risk-free 0-0.9 1 Level 1 1-1.9 2 Level 2 ≥2

[0089] Next, to build a predictive model, the system needs to acquire historical data. Based on the equipment location tags in the risk grading signal, the system queries the historical database to retrieve a series of historical risk level values ​​associated with that specific location and their corresponding timestamps, i.e., the historical time series. Using this historical time series data, the system establishes a risk mapping function to characterize the evolution of the historical risk level values ​​at that location. This function is a time series model that can capture and quantify the trend of risk changes over time, such as the growth rate or fluctuation pattern. After obtaining the current risk level value and the risk mapping function, based on the current risk level value and the rate of risk change revealed by the risk mapping function, the system calculates the risk level value after a preset time point to obtain the predicted risk level value. For the risk mapping function, we have:

[0090] ,

[0091] in, To predict the risk level value, This is the current risk level value that has been obtained. It is the time difference from the current moment to the preset time point. This represents the rate of change of risk level calculated by the risk mapping function, with its dimension being the change in risk value per unit time. This formula ensures the physical consistency of all quantities involved in the calculation. After calculating the predicted risk level value, the risk level mapping table is used again to convert it back into text form of the predicted risk level. Finally, the system integrates four key pieces of information—worker number, corresponding equipment location label, current risk level, and predicted risk level—to generate a well-structured early warning decision instruction, providing a basis for subsequent intervention measures. By introducing short-term exposure trend analysis, occupational health management is elevated from a passive response to the current situation to a proactive prevention of future risks. This forward-looking risk assessment capability makes it possible to take preventative measures before the risk truly reaches a dangerous level, thereby significantly enhancing the initiative and effectiveness of occupational health and safety protection and achieving a more intelligent and efficient closed-loop risk management system.

[0092] Optionally, the step of executing a dual-path intervention strategy based on the current risk level and the predicted risk level in the early warning decision instruction to generate equipment control signals that drive the physical equipment includes:

[0093] When the current risk level in the early warning decision instruction triggers a preset instant alarm threshold, a first control signal is generated to activate the on-site audible and visual alarm device.

[0094] When the predicted risk level in the early warning decision instruction is greater than or equal to the current risk level, a second control signal is generated to start the ventilation and purification system or increase the operating power of the ventilation and purification system.

[0095] The device control signal includes the first control signal and the second control signal.

[0096] Specifically, the system inputs the early warning decision instruction generated in the previous stage. This instruction contains the current risk level and the predicted risk level for a specific worker. Based on this instruction, two independent logical paths are evaluated in parallel to determine the control signals that need to be generated. The first path is the immediate response path, which focuses on addressing the existing high-risk situation. It compares the current risk level in the early warning decision instruction with a preset immediate alarm threshold. This threshold is predefined and typically corresponds to a risk level that may lead to acute health damage, such as a level 2 risk label. When the system determines that the current risk level has triggered or exceeded this threshold, it immediately generates the first control signal. This signal is a clear instruction sent to the audible and visual alarm devices at the work site to activate the alarm and warn workers in the hazardous area to evacuate immediately or take protective measures. The second path is the proactive prevention path, which aims to curb the worsening trend of the risk. It compares the predicted risk level in the early warning decision instruction with the current risk level. When the predicted risk level is found to be greater than or equal to the current risk level, it indicates that the risk is escalating. Under this condition, a second control signal is generated. This signal is sent to environmental control equipment, such as ventilation and purification systems. It can be a command to start the system, or, for systems already in operation, a command to increase their operating power, such as increasing fan speed. Ultimately, the output device control signal is a combination of signals generated from these two paths, ensuring a comprehensive response to immediate hazards and potential risks.

[0097] Optionally, the method further includes:

[0098] Based on the device control signals, obtain the status data fed back by the device;

[0099] Obtain the real-time risk level at the preset time point;

[0100] The predicted risk level at the preset time point, the real-time risk level at the preset time point, and the status data are correlated and analyzed to generate an intervention effect evaluation report.

[0101] Specifically, two key types of feedback information need to be obtained first. The first is to actively query the controlled physical equipment based on previously issued equipment control signals and obtain its status data. This status data represents the actual operating parameters of the equipment after executing commands, such as the actual operating power reported by a ventilation system or the timestamp confirming the activation of an audible and visual alarm device. The second is to obtain the real-time risk level at the same preset time point. To achieve this, the complete risk assessment process needs to be re-executed at that time point, starting with the collection of the latest environmental data, through a series of steps including individual correlation, risk calculation, and risk classification, ultimately generating a real-time risk level representing the actual situation at that time. Afterward, the core correlation analysis stage begins. Three sets of data are integrated and compared: the original predicted risk level obtained from the early warning decision command, the newly obtained real-time risk level, and the status data fed back by the equipment. To conduct a quantitative effect evaluation, an intervention effectiveness difference can be calculated. :

[0102] ,

[0103] in, It is a dimensionless value obtained after the predicted risk level is converted through a risk level mapping table. This is a dimensionless value obtained after the real-time risk level has also been transformed using a mapping table. A positive intervention efficacy difference indicates that the actual risk is lower than the predicted risk, meaning that the intervention measures are effective. Finally, the system systematically organizes and integrates information such as the predicted risk level, the real-time risk level, the status data fed back by the equipment, and the calculated intervention efficacy difference to generate a structured intervention effect evaluation report.

[0104] Based on the same inventive concept, such as Figure 2 As shown, the present invention also provides a data processing system for the detection of environmental components in occupational health, the system comprising:

[0105] The equipment data acquisition module is used to acquire the raw detection data of the multi-source detection equipment, and to add equipment location tags and timestamps to the raw detection data to generate an initial dataset. The raw detection data includes pollutant type and pollutant concentration data.

[0106] The environmental monitoring module is used to acquire the real-time location information of the staff, match the real-time location information with the equipment location tags in the initial dataset, and generate a structured monitoring matrix that is dynamically associated with the staff number.

[0107] The initial risk calculation module is used to calculate the dynamic risk value and generate a real-time risk vector based on the structured monitoring matrix and according to the preset toxicity coefficient and the preset exposure duration correction factor.

[0108] The composite risk calculation module is used to identify composite pollution scenarios and calculate the enhancement effect based on the real-time risk vector, and generate superimposed risk indicators.

[0109] The risk level confirmation module is used to compare the superimposed risk indicators with preset occupational exposure limit standards, and generate a risk classification signal based on the comparison results.

[0110] The risk warning module is used to perform short-term exposure trend analysis on the risk classification signal, predict future risk level changes, and generate warning decision instructions that include the current risk level and the predicted risk level.

[0111] The decision execution module is used to execute a dual-path intervention strategy based on the current risk level and the predicted risk level in the early warning decision instruction, and generate equipment control signals that drive the physical equipment to move.

[0112] To verify the feasibility of this invention in practice, it was applied to the toluene and xylene mixed solvent production workshop of a large chemical enterprise. Due to the production process, this workshop continuously contains varying concentrations of volatile organic compounds such as toluene and xylene in the environment, and some areas may also pose a risk of release of more toxic pollutants such as benzene. Traditional occupational health management relies on manual sampling at fixed points and times, followed by laboratory analysis, which suffers from problems such as delayed response, inability to assess real-time individual exposure risks, and difficulty in addressing the synergistic effects of combined pollution. This chemical enterprise hopes to use the method and system of this invention to achieve real-time, dynamic, accurate assessment and intelligent intervention of individual exposure risks for workshop workers.

[0113] In this embodiment, the company deployed 15 all-in-one gas detection devices (device numbers S-01 to S-15) at key workstations, passageways, and potential leak points in the workshop. These devices, acting as data acquisition modules, can monitor the concentrations of toluene and benzene in real time, and the collected data changes over time as follows: Figure 3 As shown. Meanwhile, 20 workers in the workshop (employee numbers W-001 to W-020) were equipped with name tags featuring UWB (Ultra-Wideband) positioning capabilities. The entire system processes data and makes decisions through a central server.

[0114] After the system starts up, the equipment data acquisition module begins to work. For example, at 10:05:30 AM on November 8, 2024, the S-03 detection device located at the feed inlet of Area A collected a set of raw detection data: {Contaminant type: [Toluene, Benzene], Contaminant concentration: [45 mg / m³]} 3 5mg / m 3The system immediately appended the device location tag "S-03 (Area A Feed Port)" and the timestamp "2024-11-08 10:05:30" to the data, generating a record in the initial dataset. Simultaneously, the environmental monitoring module obtained the real-time location information of worker W-007, whose coordinates successfully matched the location tag of device S-03 (the spatial distance was less than the preset 2-meter effective monitoring radius). The system then generated a dynamically linked record and stored it in the structured monitoring matrix in chronological order: {Worker ID: W-007, Timestamp: 10:05:30, Device Location Tag: S-03, Original Detection Data: {Toluene: 45mg / m³}} 3 Benzene: 5mg / m³ 3}}.

[0115] Based on the aforementioned matrix, the initial risk calculation module calculates the dynamic risk value for worker W-007. First, it retrieves the toxicity intensity parameters for toluene and benzene from a pre-set toxicity coefficient library, which are 0.8 and 1.5 respectively. Then, it calculates the basic hazard value; the basic hazard value for toluene is 45 * 0.8 = 36 mg / m³. 3 The basic hazard value for benzene is 5 * 1.5 = 7.5 mg / m³. 3 W-007 has been operating continuously in the area for 1 hour. Based on the exposure duration data, the system generated an exposure duration correction factor Ft=1.2. The dynamic risk value for toluene was calculated to be 36*1.2=43.2 mg / m³. 3 The dynamic risk value for benzene is 7.5 * 1.2 = 9.0 mg / m³. 3 At this point, a real-time risk vector is generated: {W-007, [toluene, benzene], [43.2 mg / m 3 9.0 mg / m 3 ]}.

[0116] Next, the composite risk calculation module identified the combined pollution scenario of toluene and benzene. From the pre-set composite hazard database, the synergistic enhancement coefficient for this combination was found to be 1.4. The system used this coefficient to correct the dynamic risk value, obtaining a composite risk value of toluene of 43.2 * 1.4 = 60.48 mg / m³. 3 The combined risk value of benzene is 9 * 1.4 = 12.6 mg / m³. 3 In addition, the system also obtained an individual sensitivity parameter of 1.1 for employee W-007 (based on a record of weak liver function indicators in their annual physical examination). The final personalized composite risk value for toluene was 60.48 * 1.1 = 66.528 mg / m³. 3 The personalized adjusted composite risk value for benzene is 12.6 * 1.1 = 13.86 mg / m³. 3The system generates the following superimposed risk indicators: {W-007, S-03, [66.528mg / m³] 3 13.86 mg / m³ 3 ]}.

[0117] The risk level confirmation module compares the superimposed risk index with the preset occupational exposure limit standard, where the safe concentration threshold for toluene is 50 mg / m³. 3 The safe concentration threshold for benzene is 6 mg / m³. 3 Therefore, the risk score is (66.528 / 50 + 13.86 / 6) / 2 = 1.82028, which is greater than the second threshold of 1.5. The system determines that the risk has reached a severe level and generates a "Level 2 Risk Label" for staff member W-007, forming a risk classification signal. The risk warning module receives this signal and extracts the current risk level as "Level 2". At the same time, the module analyzes the risk data of location S-03 over the past half hour and constructs a risk mapping function. Based on the risk mapping function, it predicts that the risk value will reach 2.8 in the next 10 minutes, still at Level 2 risk. Therefore, the system generates a warning decision instruction containing the current risk level "Level 2" and the predicted risk level "Level 2 (increasing trend)".

[0118] The decision execution module implements a dual-path intervention strategy based on the early warning decision command. Since the current risk level "Level 2" triggered the immediate alarm threshold, the system immediately generates a first control signal, activating the audible and visual alarm device located at the material feeding port in Zone A, and alerting worker W-007 to evacuate immediately via badge vibration. Predicting an escalating risk trend, the system simultaneously generates a second control signal, instructing the activation of the high-power ventilation and purification system in Zone A to enhance local ventilation.

[0119] Ten minutes after the intervention was implemented, the system obtained equipment feedback status data (ventilation system power had increased to 90%) and the real-time risk level at the preset time point (due to ventilation and personnel evacuation, the pollutant concentration at location S-03 decreased, and the recalculated real-time risk value dropped to 0). The system performed correlation analysis on the predicted risk value of 2.8, the real-time risk value of 0, and the equipment status data to generate an intervention effectiveness evaluation report, concluding that: "The intervention was effective and successfully prevented a serious overexposure event."

[0120] To verify the beneficial effects of the present invention, the company selected 20 experimental group members who applied the present invention and another 20 control group members who adopted traditional management methods, and conducted a comparative test for 6 months.

[0121] Table 2 Comparison of High-Risk Exposure Events for Staff

[0122] month Number of high-risk exposure events in the experimental group (times) Number of high-risk exposure events in the control group (times) January 3 11 February 2 14 March 2 12 April 1 15 May 0 13 June 1 11

[0123] Table 3 Comparison of Risk Event Response and Handling Time

[0124] Evaluation Project Experimental group (using this invention) Control group (traditional method) Average time for risk identification <1 minute Approximately 4-8 hours (depending on sampling and analysis) Average time for issuing warnings Within 1 minute 8-24 hours Average time to intervention 1.5 minutes (automated) 2-4 hours (human intervention) Average response time for personnel evacuation 2 minutes N / A (No real-time evacuation order)

[0125] Table 4 Comparison of Energy Consumption of Workshop Ventilation Systems

[0126] Evaluation Project Experimental group (using this invention) Control group (traditional method) Ventilation system operation strategy Predictive, on-demand startup / enhancement Specified time period / constant power throughout the day Average monthly energy consumption (kWh) 3500 4800 Energy saving rate - Approximately 27%

[0127] As can be seen from the data in Tables 2-4 above, the experimental group experienced significant improvement after applying this invention. This invention constructs a complete closed-loop occupational health risk management system through multi-source data collection, dynamic individual correlation, composite risk quantification, risk trend prediction, and dual-path intelligent intervention. It successfully transforms static, lagging regional monitoring into dynamic, precise, and individualized risk management, greatly improving the timeliness of risk identification, the accuracy of risk assessment, and the effectiveness of intervention measures, providing strong technical support for ensuring the health and safety of workers in complex working environments.

[0128] It should be noted that the formulas described above, through the principle of dimensional consistency and mathematical standardization methods (such as normalization, dimensionless parameter conversion, or unit system unification), can translate physical quantities with different properties into unitless standard values ​​or parameters that can be superimposed in the same dimension. This eliminates the interference of different dimensions on the computational logic, allowing the formulas to retain the original data distribution characteristics while possessing mathematical rationality and adaptability to objective laws. These are conventional technical methods and will not be elaborated upon here. The electrical connections between the various units described above do not necessarily represent direct or indirect connections; any indirect connection method is applicable to the embodiments of this invention as long as it achieves the purpose of this invention. The above descriptions are merely exemplary embodiments of this invention and should not be construed as limiting the scope of this invention.

[0129] All equivalent changes and modifications made in accordance with the teachings of this invention are still within the scope of this invention. Those skilled in the art will readily conceive of other embodiments of this invention upon considering the specification and the disclosure of practical truth. This application is intended to cover any variations, uses, or adaptations of this invention that follow the general principles of this invention and include common knowledge or conventional techniques in the art not described herein.

Claims

1. A method for processing environmental component detection data in occupational health, characterized in that, The method includes: Acquire raw detection data from multi-source detection devices, and attach device location tags and timestamps to the raw detection data to generate an initial dataset. The raw detection data includes pollutant type and pollutant concentration data. The real-time location information of the staff is obtained, and the real-time location information is matched with the device location tags in the initial dataset to generate a structured monitoring matrix that is dynamically associated with the staff ID. Based on the structured monitoring matrix and according to the preset toxicity coefficient and the preset exposure duration correction factor, the dynamic risk value is calculated and a real-time risk vector is generated. Based on the real-time risk vector, composite pollution scenarios are identified and the enhancement effect is calculated to generate superimposed risk indicators. The superimposed risk index is compared with the preset occupational exposure limit standard, and a risk classification signal is generated based on the comparison result. The risk classification signal is subjected to short-term exposure trend analysis to predict future changes in risk level and generate early warning decision instructions that include the current risk level and the predicted risk level. Based on the current risk level and the predicted risk level in the early warning decision instruction, a dual-path intervention strategy is executed to generate equipment control signals that drive the physical equipment to move.

2. The method for processing environmental component detection data in occupational health according to claim 1, characterized in that, The generated structured monitoring matrix, which dynamically associates staff numbers, includes: Real-time location information is obtained by acquiring coordinate data containing staff identification numbers through positioning devices worn by staff. The coordinate data in the real-time location information is matched with the device location labels in the initial dataset to determine the target detection device; Based on the initial dataset, the original detection data, device location tags, and timestamps of the target detection device are obtained and bound to the staff numbers of the corresponding coordinate data. The data are then arranged in chronological order to generate a structured monitoring matrix containing four-dimensional data fields.

3. The method for processing environmental component detection data in occupational health according to claim 2, characterized in that, The process of calculating dynamic risk values ​​and generating real-time risk vectors based on the structured monitoring matrix and according to preset toxicity coefficients and preset exposure duration correction factors includes: Extract the pollutant type and corresponding current pollutant concentration data associated with the staff member's ID from the structured monitoring matrix; Based on the type of pollutant, the corresponding toxicity intensity parameter is obtained from a preset toxicity coefficient library; The basic hazard value is calculated using the aforementioned toxicity intensity parameter and the current pollutant concentration data; Based on the structured monitoring matrix, the exposure duration data of the staff is obtained, and an exposure duration correction factor is generated based on the exposure duration data. Using the exposure duration correction factor and the baseline hazard value, the dynamic risk value of the corresponding pollutant is calculated; By integrating staff numbers, associated pollutant types, and corresponding dynamic risk values ​​of pollutants, a real-time risk vector is generated.

4. The method for processing environmental component detection data in occupational health according to claim 3, characterized in that, The process of identifying compound pollution scenarios and calculating enhancement effects based on the real-time risk vector, and generating superimposed risk indicators, includes: Based on the real-time risk vector, combinations of different pollutant types are obtained to generate a pollutant combination dataset. Using a pre-defined composite hazard database and the pollutant combination dataset, the synergistic enhancement coefficient of the pollutant combination is obtained; The dynamic risk value of the corresponding pollutant is corrected using the synergistic enhancement coefficient to obtain the composite risk value; The corresponding equipment location tags are extracted from the real-time risk vector, and the staff number, the corresponding equipment location tags, and the composite risk value are integrated to obtain the superimposed risk index.

5. The method for processing environmental component detection data in occupational health according to claim 4, characterized in that, The step of comparing the superimposed risk index with the preset occupational exposure limit standard includes: Obtain individual sensitivity parameters for staff members, which are generated based on staff members' historical physical examination data or allergy history records; The composite risk value in the superimposed risk index is personalized by using the individual sensitivity parameter.

6. The method for processing environmental component detection data in occupational health according to claim 5, characterized in that, The step of comparing the superimposed risk index with a preset occupational exposure limit standard and generating a risk classification signal based on the comparison result includes: Based on the superimposed risk indicators, the concentration safety thresholds of each pollutant are obtained from the preset occupational exposure limit standards. The risk score is obtained by averaging the ratios of the corrected composite risk value for each pollutant to the corresponding concentration safety threshold. When the risk score is less than a preset first threshold, a risk-free label is generated; When the risk score is greater than or equal to the first threshold and less than the preset second threshold, a level 1 risk label is generated; When the risk score is greater than or equal to the second threshold, a secondary risk label is generated; Based on the staff number, the corresponding equipment location tag, and the generated risk tag in the superimposed risk index, a risk classification signal is obtained; The generated risk labels include the risk-free label, the primary risk label, and the secondary risk label.

7. The method for processing environmental component detection data in occupational health according to claim 6, characterized in that, The step of performing short-term exposure trend analysis on the risk grading signal, predicting future changes in risk level, and generating early warning decision instructions that include the current risk level and the predicted risk level includes: Based on the risk label generated from the risk classification signal, the current risk level is extracted and converted into a numerical form using a preset risk level mapping table to obtain the current risk level value. Obtain the historical risk level values ​​and historical time series of the corresponding device location tags; By utilizing historical time series data, a risk mapping function is established to characterize historical risk level values. Based on the current risk level value and the risk mapping function, the risk level value at a preset time point is calculated to obtain the predicted risk level value; Based on the predicted risk level value and the risk level mapping table, the predicted risk level is obtained; By integrating staff numbers, corresponding equipment location tags, current risk levels, and predicted risk levels, early warning decision instructions are generated.

8. The method for processing environmental component detection data in occupational health according to claim 7, characterized in that, The step of executing a dual-path intervention strategy based on the current risk level and the predicted risk level in the early warning decision instruction, and generating equipment control signals to drive the physical equipment to operate, includes: When the current risk level in the early warning decision instruction triggers a preset instant alarm threshold, a first control signal is generated to activate the on-site audible and visual alarm device. When the predicted risk level in the early warning decision instruction is greater than or equal to the current risk level, a second control signal is generated to start the ventilation and purification system or increase the operating power of the ventilation and purification system. The device control signal includes the first control signal and the second control signal.

9. A method for processing environmental component detection data in occupational health according to claim 8, characterized in that, The method further includes: Based on the device control signals, obtain the status data fed back by the device; Obtain the real-time risk level at the preset time point; The predicted risk level at the preset time point, the real-time risk level at the preset time point, and the status data are correlated and analyzed to generate an intervention effect evaluation report.

10. A data processing system for environmental component detection in occupational health, applied to the data processing method for environmental component detection in occupational health as described in any one of claims 1-9, characterized in that, The system includes: The equipment data acquisition module is used to acquire the raw detection data of the multi-source detection equipment, and to add equipment location tags and timestamps to the raw detection data to generate an initial dataset. The raw detection data includes pollutant type and pollutant concentration data. The environmental monitoring module is used to acquire the real-time location information of the staff, match the real-time location information with the equipment location tags in the initial dataset, and generate a structured monitoring matrix that is dynamically associated with the staff number. The initial risk calculation module is used to calculate the dynamic risk value and generate a real-time risk vector based on the structured monitoring matrix and according to the preset toxicity coefficient and the preset exposure duration correction factor. The composite risk calculation module is used to identify composite pollution scenarios and calculate the enhancement effect based on the real-time risk vector, and generate superimposed risk indicators. The risk level confirmation module is used to compare the superimposed risk indicators with preset occupational exposure limit standards, and generate a risk classification signal based on the comparison results. The risk warning module is used to perform short-term exposure trend analysis on the risk classification signal, predict future risk level changes, and generate warning decision instructions that include the current risk level and the predicted risk level. The decision execution module is used to execute a dual-path intervention strategy based on the current risk level and the predicted risk level in the early warning decision instruction, and generate equipment control signals that drive the physical equipment to move.

Images