Worker health condition assessment method based on AI recognition

Abstract

The application relates to the technical field of engineering construction, and provides a worker health condition evaluation method based on AI recognition, which comprises the following steps: obtaining worker health data in engineering construction, and building a health record; importing the health record into a pre-configured exposure factor identification network, identifying exposure factors in engineering construction, and building an attribution risk degree function of different exposure factors; determining the attribution risk degree values of different exposure factors relative to the workers according to the attribution risk degree function, and generating a worker health condition evaluation report. The application not only provides strong support for engineering safety management, but also exhibits remarkable effects in solving practical problems. The method realizes accurate quantitative evaluation of the risk degree by in-depth analysis of the sources, influence degrees and occurrence probabilities of various potential risk factors in the engineering construction process. According to the evaluation results, corresponding risk prevention and control measures are formulated, the possibility of accidents is effectively reduced, and the safe and stable progress of the engineering construction is ensured.

Description

Technical Field

[0001] This invention relates to the field of risk calculation and control in engineering construction, and in particular to a method for assessing worker health status based on AI recognition. Background Technology

[0002] With the development of science and technology and people's increasing attention to health, the health of construction workers during engineering projects has become a key focus of the country. Attribution risk calculation methods, as a core area of ​​this field, have brought tremendous changes and convenience to people's lives.

[0003] Because construction workers often live far from home and in rudimentary accommodations, their work hours are long, typically exceeding 12 hours a day, from 6 AM to 6 or 8 PM. Illegal long working hours have become the norm, and their health is easily affected by the prolonged labor. Many workers suffer from various occupational diseases due to the high workload, such as asthma and bronchitis. Some workers have even become physically weak or faced life-threatening situations due to the long hours, requiring conventional treatment.

[0004] For example: 1. Physical examination, 2. Occupational disease detection, 3. Screening for common diseases, 4. Mental health assessment, 5. Nutritional examination, 6. Inspection of personal protective equipment, etc.

[0005] However, conventional methods can lead to missed opportunities for optimal treatment due to untimely or improper testing, resulting in sudden death incidents caused by underlying medical conditions among the construction workers.

[0006] Therefore, existing detection methods and early warning measures cannot adequately analyze the health status of construction personnel. Summary of the Invention

[0007] This invention proposes an AI-based method for assessing the health status of workers, addressing the limitations of existing detection methods and early warning measures in comprehensively analyzing the health status of construction workers.

[0008] This invention proposes an AI-based method for assessing worker health status, comprising:

[0009] Acquire worker health data during construction projects and establish health records;

[0010] Import health records into a pre-configured exposure factor identification network to identify exposure factors in engineering construction and build attribution hazard functions for different exposure factors;

[0011] Based on the attribution hazard function, the attribution hazard values ​​of different exposure factors relative to workers are determined, and a worker health status assessment report is generated.

[0012] Furthermore, the health record includes personal records and project records, wherein:

[0013] Personal files are used to obtain workers' physiological and biochemical data, lifestyle data, personal health history data, and family health history data;

[0014] The project archives are used to obtain environmental exposure data during project construction. This environmental exposure data includes: noise data, air pollution data, building safety data, equipment safety risk data, water pollution data, and body temperature status data.

[0015] Furthermore, the acquisition process for the exposure environment data also includes:

[0016] Acquire environmental exposure data from historical engineering construction projects to determine the characteristics of environmental and ecological factors;

[0017] Based on the characteristics of environmental and ecological factors, determine the time points of occurrence of environmental and ecological factors in different environmental ecosystems;

[0018] Based on the time points of occurrence of environmental and ecological factors, construct an environmental and ecological statistical matrix;

[0019] Based on the statistical matrix of environmental ecology, the attribute intervals of different environmental ecological factors are determined; among them, the attribute intervals include time intervals and intensity intervals.

[0020] Based on the attribute range, the distribution patterns of different environmental and ecological factors are determined, and distribution markers for different environmental and ecological factors are set; among them, the distribution patterns include regional distribution, intensity distribution and time distribution.

[0021] Furthermore, the health record is also equipped with a classification and filling mechanism, wherein:

[0022] Configure similar configuration patterns for various health data attributes, including:

[0023] In the similar configuration mode, the health record has multiple sets of fill positions, and the data attributes of each fill position in the multiple sets of fill positions match the target phrase attributes; each fill position in the multiple sets of fill positions is configured with displacement fill rules;

[0024] When worker health data responds to any target phrase attribute, the worker health data and the corresponding phrase's fill position are categorized and traversed.

[0025] When the data meets the filling rules for any filling position after traversing the categories, health data filling is performed.

[0026] Furthermore, the process of importing health records into a pre-configured exposure factor identification network to identify exposure factors during engineering construction includes:

[0027] Based on the exposure factor identification network, environmental and ecological data in health records are identified one by one to determine environmental and ecological characteristics;

[0028] Determine the strong correlation between different environmental and ecological characteristics and workers' health status, and construct a strong correlation network, in which:

[0029] In a strongly correlated network, different environmental and ecological characteristics and worker health statuses each have a unique connected component.

[0030] Based on strong correlation networks, the positive and negative impacts of different environmental and ecological characteristics on workers' health status were determined;

[0031] Based on the negative impacts, the corresponding target environmental ecological characteristics are determined and labeled as exposure factors.

[0032] Furthermore, the construction of the attribution hazard function for different exposure factors includes:

[0033] Based on the exposure factors, the risk levels of different exposure factors are predefined, and the corresponding exposure behaviors are collected. Based on the exposure behaviors, the statistical risk rates of different exposure behaviors are determined, where the statistical risk rate is the incidence rate of different exposure behaviors among workers;

[0034] Calculate the population attributable risk percentage based on the statistical risk rate;

[0035] Calculate the relative risk of different exposure behaviors based on the population attribution percentage;

[0036] Based on the relative risk, attribution risk functions for different exposure factors are constructed.

[0037] Furthermore, the specific formula for the attribution hazard function is as follows:

[0038] CRF=C*RT*SI*IP+C*MD*P(CI0-CI1)

[0039] in:

[0040] C = Risk factor, with a value range of [0, 6].

[0041] RT = Risk Transfer Rate, with a value range of [0,1] dimensionless.

[0042] MD = rate of change, ranging from [-1, 1] dimensionless.

[0043] P = the probability of potential risk, with a value in the range [0,1] dimensionless.

[0044] CI0 = Safety index before the change, with a value range of [0,1] dimensionless.

[0045] CI1 = The revised safety index, with a value range of [0,1] dimensionless.

[0046] SI = Safety Index, with a value range of [0,1] dimensionless.

[0047] IP = Implementation Plan, value range [0,1] dimensionless.

[0048] Where C = Cy + Ck + Cj + Ct + Cs + Cp

[0049] Cy is the noise pollution hazard coefficient; Ck is the air pollution hazard coefficient; Cj is the building hazard coefficient; Ct is the equipment hazard coefficient; Cs is the water resource hazard coefficient; Cp is the water resource hazard coefficient.

[0050] Furthermore, determining the attribution hazard value of different exposure factors relative to the worker based on the attribution hazard function includes:

[0051] Based on the attribution hazard function, the first simulation evolution is performed sequentially for different exposure factors; the simulation calculation includes the initial exposure time and the end time of exposure for different exposure factors;

[0052] Based on simulation calculations, the original calculation times for multiple different exposure factors are determined sequentially, and their adjustment times are determined, where adjacent adjustment times have a proportional coefficient;

[0053] Based on the adjustment time, a second simulation evolution was conducted for different exposure factors, and the results of the first and second simulation evolutions were compared.

[0054] If the second simulation evolution result is greater than the first simulation evolution result, the target and attribution hazard values ​​of the second simulation evolution result will be adjusted.

[0055] If the second simulation evolution result is greater than the first simulation evolution result, the first simulation evolution result or the first simulation evolution result shall be used as the target attribution risk value.

[0056] When the second simulation evolution result is less than the first simulation evolution result, the first simulation evolution result is used as the target attribution risk value;

[0057] Furthermore, the generation of the worker health status assessment report includes:

[0058] Configure assessment maps for different exposure factors;

[0059] Based on the assessment map, the workers' health status is divided into multiple assessment display pages according to different exposure factors, and each assessment display page corresponds to a display page for different exposure factors;

[0060] Based on the display page, at least one type of health risk is identified for different exposure factors. The different assessment contents on the display page are then linked using the health risk types to generate a visual assessment report.

[0061] Furthermore, the generation of the worker health status assessment report also includes:

[0062] The visualization evaluation report displays at least one visualization area and sets a trigger command; the trigger command is used to trigger the corresponding evaluation process.

[0063] When the assessment process is triggered, the corresponding attribution mapping map is configured based on the worker's physical risk data;

[0064] Based on the attribution mapping map, the user's exposure distribution status in the project construction is determined, and an exposure factor distribution table for the project construction is generated based on the exposure distribution status.

[0065] The beneficial effects of this invention are as follows:

[0066] This invention utilizes AI technology to deeply analyze workers' health data, enabling more accurate identification of individual health conditions and providing more personalized health management recommendations. Continuous monitoring and analysis of health records allows for the timely detection of early signs of worker health problems, facilitating preventative measures and preventing their deterioration. By constructing an attribution hazard function, the impact of different exposure factors on workers' health can be quantified. Identifying the attribution hazard of different exposure factors allows for the targeted allocation of safety protection resources and health interventions. Automated data processing and assessment report generation significantly improve the efficiency of health management and reduce the workload of managers. Systematic health assessments help improve the working environment, reduce the incidence of occupational diseases, and safeguard workers' health and safety.

[0067] Other features and advantages of the invention will be set forth in the following description, 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 particularly pointed out in the written description and the accompanying drawings.

[0068] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0069] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0070] Figure 1This is a flowchart of a worker health status assessment method based on AI recognition, as described in an embodiment of the present invention.

[0071] Figure 2 This is a flowchart illustrating the process of obtaining the distribution identifiers of environmental and ecological factors in an embodiment of the present invention.

[0072] Figure 3 This describes the process of obtaining the exposure factor distribution table in this embodiment of the invention. Detailed Implementation

[0073] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0074] This invention relates to construction engineering, and fully considers various parameters, including noise pollution hazard coefficient, air pollution hazard system, building safety risk hazard coefficient, equipment safety risk hazard coefficient, water resource pollution hazard coefficient, and body temperature hazard coefficient; based on the aforementioned noise pollution hazard coefficient, air pollution system, building safety risk hazard coefficient, equipment safety risk hazard coefficient, and water resource pollution hazard coefficient, it establishes an artificial intelligence-based formula for calculating the attribution hazard of engineering construction.

[0075] Attribution hazard calculation methods offer numerous advantages over traditional health monitoring approaches. First, they are highly real-time, allowing for the monitoring and analysis of individual physiological indicators anytime, anywhere, enabling timely detection and intervention of problems. Second, they are personalized, providing tailored health recommendations based on user needs and characteristics, facilitating precise health management. Furthermore, attribution hazard calculation methods integrate technologies such as cloud computing and big data analytics.

[0076] like Figure 1 As shown, this embodiment provides a worker health status assessment method based on AI recognition, including:

[0077] Acquire worker health data during construction projects and establish health records;

[0078] Import health records into a pre-configured exposure factor identification network to identify exposure factors in engineering construction and build attribution hazard functions for different exposure factors;

[0079] Based on the attribution hazard function, the attribution hazard values ​​of different exposure factors relative to workers are determined, and a worker health status assessment report is generated.

[0080] The principle behind the above technical solution is as follows:

[0081] In practice, worker health data is acquired during construction, and health records are established. Worker health data is collected through various methods, such as employee health management systems, physical examination records, or medical records. After collection, the worker health data is imported into a pre-defined worker health database and stored and managed using the corresponding software interface of this invention.

[0082] Health records are established during the process of disease screening and prevention, enabling the early detection of many diseases, such as hypertension and diabetes. Health records collect information on an individual's physiological and biochemical data, lifestyle, and personal or family health history. This information is used to assess an individual's attributable risk (AR), which is the difference between the incidence rate in the exposed group and the non-exposed group, reflecting the degree to which the disease is attributed to the exposure factor.

[0083] Health records are imported into a pre-configured exposure factor identification network. This network identifies factors that may impact worker health based on different environments and conditions, classifying them into various exposure factors. These exposure factors include, but are not limited to, noise, vibration, radiation, high / low temperature, and chemical contamination. Within the network, each exposure factor has a corresponding weight and parameters to characterize the potential impact of that factor on worker health.

[0084] Based on the output of the exposure factor identification network, the attributable hazard values ​​of different exposure factors relative to workers are determined. The attributable hazard value reflects the degree of impact of the corresponding factor on worker health, assessing the health risks of workers in a specific environment. The calculation of the attributable hazard value involves a comprehensive assessment and weighted average calculation of multiple factors.

[0085] Attribution hazard functions include:

[0086] The attributable risk percentage (AR%) is the percentage of illnesses caused by the exposed factor among all illnesses in an exposed population. Personal health information recorded in health records can be used to calculate an individual's AR%, thereby assessing the extent to which a particular health behavior or condition affects an individual's health.

[0087] Population attributable risk percentage (PAR%) refers to the proportion of illnesses caused by an exposure in the total population. By analyzing the health records of large populations, the distribution of a specific exposure factor in the population can be estimated, and PAR% can be calculated. This helps public health policymakers understand the potential health benefits of controlling specific exposure factors.

[0088] Based on the generated worker health status assessment report, relevant health recommendations and interventions are provided. The worker health status assessment report includes a description of the exposure factors, the worker's health status assessment results, and corresponding health recommendations and interventions. Based on the recommendations, corresponding improvement strategies or measures are generated, including improving the working environment, enhancing personal protective equipment, increasing rest time, etc. These recommendations and measures can help workers reduce health risks and prevent the occurrence and worsening of diseases.

[0089] In practice, by establishing health records, disseminating health knowledge, and changing unhealthy behaviors and lifestyle habits, attributable risk can be reduced. Health records help users conduct comprehensive self-health assessments based on their records, effectively control their health status, and prevent the occurrence and development of diseases.

[0090] Health records can quickly reveal the trends in a patient's health indicators and potential risk factors, thereby enabling a comprehensive assessment of the condition and the implementation of accurate and effective treatment measures. This is closely related to the assessment and management of attributable risk.

[0091] The technical benefits of the above solution are as follows: In-depth analysis of workers' health data using AI technology enables more accurate identification of individual health conditions, providing workers with more personalized health management recommendations. Continuous monitoring and analysis of health records allows for the timely detection of early signs of worker health problems, enabling timely preventative measures to avoid their deterioration. The construction of attribution hazard functions quantifies the impact of different exposure factors on workers' health. Identifying the attribution hazard of different exposure factors allows for the targeted allocation of safety protection resources and health interventions. Automated data processing and assessment report generation significantly improve the efficiency of health management and reduce the workload of managers. Systematic health assessments help improve the working environment, reduce the incidence of occupational diseases, and protect workers' health and safety.

[0092] As one embodiment of the present invention: the health record includes a personal record and an engineering record, wherein:

[0093] Personal files are used to obtain workers' physiological and biochemical data, lifestyle data, personal health history data, and family health history data;

[0094] The project archives are used to obtain environmental exposure data during project construction. This environmental exposure data includes: noise data, air pollution data, building safety data, equipment safety risk data, water pollution data, and body temperature status data.

[0095] The principle behind the above technical solution is as follows:

[0096] In practice, health-related information about workers is collected by establishing personal and project files. Personal files include physiological and biochemical data (such as blood pressure, blood sugar, and blood lipids), lifestyle data (such as smoking, drinking, and exercise habits), personal health history data, and family health history data. Project files focus on environmental exposure data during construction, such as noise, air pollution, building safety, equipment safety risks, water pollution, and body temperature status.

[0097] Artificial intelligence technologies, such as machine learning algorithms, are used to process and analyze this data. AI can identify patterns and correlations in the data, thereby assessing workers' health status and potential health risks.

[0098] Based on AI analysis, workers' health status is assessed, including risk prediction for specific diseases and attribution risk assessment for workplace exposures.

[0099] As one embodiment of the present invention: the process of acquiring the exposure environment data further includes:

[0100] Acquire environmental exposure data from historical engineering construction projects to determine the characteristics of environmental and ecological factors;

[0101] Based on the characteristics of environmental and ecological factors, determine the time points of occurrence of environmental and ecological factors in different environmental ecosystems;

[0102] Based on the time points of occurrence of environmental and ecological factors, construct an environmental and ecological statistical matrix;

[0103] Based on the statistical matrix of environmental ecology, the attribute intervals of different environmental ecological factors are determined; among them, the attribute intervals include time intervals and intensity intervals.

[0104] Based on the attribute range, the distribution patterns of different environmental and ecological factors are determined, and distribution markers for different environmental and ecological factors are set; among them, the distribution patterns include regional distribution, intensity distribution and time distribution.

[0105] The principle behind the above technical solution is as follows:

[0106] like Figure 2 As shown, in actual implementation, the data of historical engineering construction is first analyzed to identify historical data that may pose a threat to employee health. This analysis involves collecting exposure data from historical engineering construction projects while simultaneously acquiring current exposure data, in order to determine the changing trends and characteristics of environmental and ecological factors over time.

[0107] Identifying the characteristics of environmental and ecological factors involves analyzing historical and current data to determine the nature and characteristics of these factors that affect worker health, such as noise and air pollution. Determining the time point involves identifying the point in time when different environmental and ecological factors begin to affect worker health.

[0108] Then, based on the time points of occurrence of different environmental and ecological factors, a statistical matrix is ​​constructed to record and analyze the data of these factors at different time points. Finally, based on the statistical results of the statistical matrix, the attribute parameters of different environmental and ecological factors after assignment are divided, thereby determining the distribution patterns and distribution indicators of specific environmental and ecological factors and quantifying different environmental and ecological factors.

[0109] As one embodiment of the present invention: the health record is further configured with a classification filling mechanism, wherein:

[0110] Configure similar configuration patterns for various health data attributes, including:

[0111] In the similar configuration mode, the health record has multiple sets of fill positions, and the data attributes of each fill position in the multiple sets of fill positions match the target phrase attributes; each fill position in the multiple sets of fill positions is configured with displacement fill rules;

[0112] When worker health data responds to any target phrase attribute, the worker health data and the corresponding phrase's fill position are categorized and traversed.

[0113] When the data meets the filling rules for any filling position after traversing the categories, health data filling is performed.

[0114] The principle behind the above technical solution is as follows:

[0115] In practical implementation, the classification and filling mechanism of this invention enables health records to be classified and filled according to different data attributes by configuring multiple similar data attribute configuration modes for health data. In actual operation, the similar data attribute configuration mode fills multiple sets of filling positions in the health record with specific data attributes, matching the data attribute filling with the attributes of the target phrase (i.e., keywords or phrases related to health data).

[0116] Then, through the displacement fill rules, each fill position can be configured with a specific displacement fill rule, which defines how data is filled into the corresponding position.

[0117] Then, by setting response target phrase attributes, worker health data is correlated with a specific target phrase attribute through a categorized traversal process. The worker's health data is categorized and traversed according to the target phrase's fill position, checking whether the data conforms to the fill rule for any fill position. If it does, health data filling is performed, that is, the data is placed in the corresponding position.

[0118] As one embodiment of the present invention: the step of importing health records into a pre-configured exposure factor identification network to identify exposure factors in engineering construction includes:

[0119] Based on the exposure factor identification network, environmental and ecological data in health records are identified one by one to determine environmental and ecological characteristics;

[0120] Determine the strong correlation between different environmental and ecological characteristics and workers' health status, and construct a strong correlation network, in which:

[0121] In a strongly correlated network, different environmental and ecological characteristics and worker resistance conditions each possess a unique connected component.

[0122] Based on strong correlation networks, the positive and negative impacts of different environmental and ecological characteristics on workers' health status were determined;

[0123] Based on the negative impacts, the corresponding target environmental ecological characteristics are determined and labeled as exposure factors.

[0124] The principle behind the above technical solution is as follows:

[0125] In practical implementation, the exposure factor identification network is a pre-configured AI network of this invention, specifically used to identify and evaluate environmental and ecological data in engineering construction and determine exposure factors that may affect workers' health.

[0126] Then, based on environmental and ecological data identification, the environmental and ecological data from health records are input into an exposure factor identification network. The network identifies each data point individually to determine environmental and ecological characteristics. A strong correlation network is constructed by identifying the strong correlations between different environmental and ecological characteristics and workers' health status. In this process, the nature of the impact is determined by the unique connected component between each environmental and ecological characteristic and the worker's health status, meaning the relationship between them is explicit and direct. Furthermore, the strong correlation network is used to assess the positive and negative impacts of different environmental and ecological characteristics on workers' health status.

[0127] Then, by labeling exposure factors, that is, based on negative impacts, we identify environmental and ecological characteristics that have a negative impact on workers' health and label them as exposure factors.

[0128] As one embodiment of the present invention: the construction of the attribution hazard function for different exposure factors includes:

[0129] Based on the exposure factors, the risk level of different exposure factors is predefined, and the exposure behaviors of the corresponding exposure factors are collected.

[0130] Based on the exposure behaviors, the statistical risk rates for different exposure behaviors are determined, where the statistical risk rate is the incidence rate of different exposure behaviors among workers;

[0131] Calculate the population attributable risk percentage based on the statistical risk rate;

[0132] Calculate the relative risk of different exposure behaviors based on the population attribution percentage;

[0133] Based on the relative risk, attribution risk functions for different exposure factors are constructed.

[0134] The principle behind the above technical solution is as follows:

[0135] In the actual implementation of this invention, the risk level of different exposure factors is predefined. Based on different exposure factors, their respective risks are predefined, and the risks are determined based on existing epidemiological studies and data.

[0136] Next, exposure behaviors are collected, followed by worker exposure behavior data related to these exposure factors, including worker activities in specific environments and exposure times.

[0137] The statistical hazard rate is then determined by analyzing exposure behavior data to identify the statistical hazard rate for different exposure behaviors, i.e., the incidence rate of these behaviors among workers. The population attributable hazard percentage (PAF) is calculated using the statistical hazard rate; this represents the expected reduction in disease incidence in a specific population if a particular exposure factor were eliminated. The relative risk (RR) is calculated based on the population attributable hazard percentage; this is the ratio of the risk of disease occurrence in the exposed group to that in the unexposed group.

[0138] Finally, attribution hazard functions are constructed. In this process, attribution hazard functions for different exposure factors are built based on relative risk, and the specific impact of a particular exposure factor on the health status of workers is assessed through the attribution hazard functions.

[0139] As one embodiment of the present invention: the specific formula of the attribution hazard function is:

[0140] CRF=C*RT*SI*IP+C*MD*P(CI0-CI1)

[0141] in:

[0142] C = Risk factor, with a value range of [0, 6].

[0143] RT = Risk Transfer Rate, with a value range of [0,1] dimensionless.

[0144] MD = rate of change, ranging from [-1, 1] dimensionless.

[0145] P = the probability of potential risk, with a value in the range [0,1] dimensionless.

[0146] CI0 = Safety index before the change, with a value range of [0,1] dimensionless.

[0147] CI1 = The revised safety index, with a value range of [0,1] dimensionless.

[0148] SI = Safety Index, with a value range of [0,1] dimensionless.

[0149] IP = Implementation Plan, value range [0,1] dimensionless.

[0150] Where C = Cy + Ck + Cj + Ct + Cs + Cp

[0151] Cy is the noise pollution hazard coefficient; Ck is the air pollution hazard coefficient; Cj is the building hazard coefficient; Ct is the equipment hazard coefficient; Cs is the water resource hazard coefficient; Cp is the water resource hazard coefficient.

[0152] In practice, a second attribution hazard function is also included to determine the attribution probability of different exposure factors:

[0153]

[0154] Where x represents the combined coefficient of the exposure factor, risk intensity, and level; y represents the duration of the exposure factor in the exposure environment; D(X) represents the relative hazard under exposure factor x; P x Indicates the proportion of the population exposed to exposure factor x; I x This represents the risk coefficient under exposure factor x; N represents the total number of workers.

[0155] As one embodiment of the present invention: determining the attribution hazard value of different exposure factors relative to the worker based on the attribution hazard function includes:

[0156] Based on the attribution hazard function, the first simulation evolution is performed sequentially for different exposure factors; the simulation calculation includes the initial exposure time and the end time of exposure for different exposure factors;

[0157] Based on simulation calculations, the original calculation times for multiple different exposure factors are determined sequentially, and their adjustment times are determined, where adjacent adjustment times have a proportional coefficient;

[0158] Based on the adjustment time, a second simulation evolution was conducted for different exposure factors, and the results of the first and second simulation evolutions were compared.

[0159] If the second simulation evolution result is greater than the first simulation evolution result, the target and attribution hazard values ​​of the second simulation evolution result will be adjusted.

[0160] If the second simulation evolution result is greater than the first simulation evolution result, the first simulation evolution result or the first simulation evolution result shall be used as the target attribution risk value.

[0161] If the second simulation evolution result is less than the first simulation evolution result, the first simulation evolution result is used as the target attribution risk value.

[0162] The principle behind the above technical solution is as follows:

[0163] In the actual implementation process, during the first simulation evolution, different exposure factors are simulated and evolved based on the attribution hazard function. During this process, the simulation calculations consider the initial exposure time and exposure end time of each exposure factor, simulating the impact of the exposure factor on worker health.

[0164] Then, based on the results of the first simulation evolution, the original calculation times for multiple different exposure factors were adjusted using a determined adjustment time. The determination of the adjustment time took into account the proportional coefficient between adjacent adjustment times, thus more accurately simulating the dynamic changes in exposure time.

[0165] A second simulation evolution is then performed using adjusted time. This second simulation evolution aims to verify the accuracy and stability of the first simulation results. Finally, the results are compared between the first and second simulation evolutions to determine which result more accurately reflects the attributable risk of the exposure factor to worker health. The target attributable risk value is determined by selecting the more reliable simulation evolution result as the target attributable risk value based on the comparison results. If the second simulation evolution result is superior to the first, the second result is adopted; otherwise, the first result is retained.

[0166] As one embodiment of the present invention: the generation of the worker health status assessment report includes:

[0167] Configure assessment maps for different exposure factors;

[0168] Based on the assessment map, the workers' health status is divided into multiple assessment display pages according to different exposure factors, and each assessment display page corresponds to a display page for different exposure factors;

[0169] Based on the display page, at least one type of health risk is identified for different exposure factors. The different assessment contents on the display page are then linked using the health risk types to generate a visual assessment report.

[0170] The principle behind the above scheme is as follows:

[0171] In actual implementation, in order to achieve accurate assessment and issue assessment reports, it is necessary to configure assessment maps. First, assessment maps are configured according to different exposure factors. The assessment maps are based on a pre-set framework or template to organize and display health risk assessment information related to each exposure factor.

[0172] By dividing the assessment display pages, based on the assessment map, workers' health status is divided into multiple assessment display pages according to different exposure factors. Each display page is specifically for a particular exposure factor, showing the related health risk assessment results.

[0173] Finally, the health risk type is determined based on each displayed page, such as respiratory diseases, skin diseases, hearing loss, etc.

[0174] Based on the assessment content, and utilizing the identified health risk types, the different assessment contents on the display page are linked to ensure that the information in each part is associated with a specific health risk. A visual assessment report is generated by integrating all the information from the display pages, making the assessment results intuitive and easy to understand.

[0175] As one embodiment of the present invention: the generation of the worker health status assessment report further includes:

[0176] The visualization evaluation report displays at least one visualization area and sets a trigger command; the trigger command is used to trigger the corresponding evaluation process.

[0177] When the assessment process is triggered, the corresponding attribution mapping map is configured based on the worker's physical risk data;

[0178] Based on the attribution mapping map, the user's exposure distribution status in the project construction is determined, and an exposure factor distribution table for the project construction is generated based on the exposure distribution status.

[0179] The principle behind the above technical solution is as follows:

[0180] like Figure 3As shown, in the specific implementation process, the visual assessment report includes at least one visual area equipped with trigger instructions. These trigger instructions can be clicking a button, selecting a drop-down menu, or other interactive elements to activate a specific assessment process. Configuring the attribution mapping map involves configuring the corresponding attribution mapping map based on the worker's health risk data when the user activates the assessment process via the trigger instruction. An attribution mapping map is a chart or model that associates worker health risks with specific exposure factors. Then, the exposure distribution is determined. This process, based on the attribution mapping map, identifies the user's exposure distribution during the construction project—that is, which workers or work areas were affected by which exposure factors, and the degree and extent of these effects.

[0181] Finally, an exposure factor distribution table is generated. In this process, based on the exposure distribution status, an exposure factor distribution table for the project construction is generated. The exposure factor distribution table records in detail the distribution and impact of each exposure factor in the project.

[0182] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for assessing worker health status based on AI recognition, characterized in that, include: Acquire worker health data during construction projects and establish health records; Import health records into a pre-configured exposure factor identification network to identify exposure factors in engineering construction and build attribution hazard functions for different exposure factors; Based on the attribution hazard function, the attribution hazard values ​​of different exposure factors relative to workers are determined, and a worker health status assessment report is generated. The construction of the attribution hazard function for different exposure factors includes: Based on the exposure factors, the risk level of different exposure factors is predefined, and the exposure behaviors corresponding to the exposure factors are collected; Based on the exposure behaviors, the statistical risk rates for different exposure behaviors are determined, where the statistical risk rate is the incidence rate of different exposure behaviors among workers; Calculate the population attributable risk percentage based on the statistical risk rate; Calculate the relative risk of different exposure behaviors based on the population attribution percentage; Based on the relative risk, construct the attribution risk function for different exposure factors; The specific formula for the attribution hazard function is as follows: CRF=C*RT*SI*IP+C*MD*P(CI0-CI1) in: C = Risk factor, with a value range of [0, 6]. RT = Risk Transfer Rate, with a value range of [0,1] and is dimensionless. MD = rate of change, range [-1, 1] dimensionless P = the probability of potential risk, with a value in the range [0,1] dimensionless. CI0 = Safety index before the change, with a value range of [0,1] dimensionless. CI1 = The revised safety index, with a value range of [0,1] dimensionless. SI = Safety Index, with a value range of [0,1] dimensionless. IP = Implementation Plan, value range [0,1] dimensionless. Where C = Cy + Ck + Cj + Ct + Cs + Cp Cy is the noise pollution hazard coefficient; Ck is the air pollution hazard coefficient; Cj is the building hazard coefficient; Ct is the equipment hazard coefficient; Cs is the water resource hazard coefficient; Cp is the water resource hazard coefficient.

2. The worker health status assessment method based on AI recognition as described in claim 1, characterized in that, The health records include personal records and project records, wherein: Personal files are used to obtain workers' physiological and biochemical data, lifestyle data, personal health history data, and family health history data; The project archives are used to obtain environmental exposure data during project construction. This environmental exposure data includes: noise data, air pollution data, building safety data, equipment safety risk data, water pollution data, and body temperature status data.

3. The worker health status assessment method based on AI recognition as described in claim 2, characterized in that, The process of acquiring the exposure environment data also includes: Acquire environmental exposure data from historical engineering construction projects to determine the characteristics of environmental and ecological factors; Based on the characteristics of environmental and ecological factors, determine the time points of occurrence of environmental and ecological factors in different environmental ecosystems; Based on the time points of occurrence of environmental and ecological factors, construct an environmental and ecological statistical matrix; Based on the statistical matrix of environmental ecology, the attribute intervals of different environmental ecological factors are determined; among them, the attribute intervals include time intervals and intensity intervals. Based on the attribute range, the distribution patterns of different environmental and ecological factors are determined, and distribution markers for different environmental and ecological factors are set; among them, the distribution patterns include regional distribution, intensity distribution and time distribution.

4. The worker health status assessment method based on AI recognition as described in claim 2, characterized in that, The health record is also equipped with a classification and filling mechanism, in which: Configure similar configuration patterns for various health data attributes, including: In the similar configuration mode, the health record has multiple sets of fill positions, and the data attributes of each fill position in the multiple sets of fill positions match the target phrase attributes; each fill position in the multiple sets of fill positions is configured with displacement fill rules; When worker health data responds to any target phrase attribute, the worker health data and the corresponding phrase's fill position are categorized and traversed. When the data meets the filling rules for any filling position after traversing the categories, health data filling is performed.

5. The worker health status assessment method based on AI recognition as described in claim 1, characterized in that, The process of importing health records into a pre-configured exposure factor identification network to identify exposure factors during engineering construction includes: Based on the exposure factor identification network, environmental and ecological data in health records are identified one by one to determine environmental and ecological characteristics; Determine the strong correlation between different environmental and ecological characteristics and workers' health status, and construct a strong correlation network, in which: In a strongly correlated network, different environmental and ecological characteristics and worker health statuses each have a unique connected component. Based on strong correlation networks, the positive and negative impacts of different environmental and ecological characteristics on workers' health status were determined; Based on the negative impacts, the corresponding target environmental ecological characteristics are determined and labeled as exposure factors.

6. The worker health status assessment method based on AI recognition as described in claim 1, characterized in that, The step of determining the attribution hazard value of different exposure factors relative to workers based on the attribution hazard function includes: Based on the attribution hazard function, the first simulation evolution is performed sequentially for different exposure factors; the simulation calculation includes the initial exposure time and the end time of exposure for different exposure factors; Based on simulation calculations, the original calculation times for multiple different exposure factors are determined sequentially, and their adjustment times are determined, where adjacent adjustment times have a proportional coefficient; Based on the adjustment time, a second simulation evolution was conducted for different exposure factors, and the results of the first and second simulation evolutions were compared. If the second simulation evolution result is greater than the first simulation evolution result, the target and attribution hazard values ​​of the second simulation evolution result will be adjusted. If the second simulation evolution result is greater than the first simulation evolution result, the first simulation evolution result or the first simulation evolution result shall be used as the target attribution risk value. If the second simulation evolution result is less than the first simulation evolution result, the first simulation evolution result is used as the target attribution risk value.

7. The worker health status assessment method based on AI recognition as described in claim 1, characterized in that, The generated worker health status assessment report includes: Configure assessment maps for different exposure factors; Based on the assessment map, the workers' health status is divided into multiple assessment display pages according to different exposure factors, and each assessment display page corresponds to a display page for different exposure factors; Based on the display page, at least one type of health risk is identified for different exposure factors. The different assessment contents on the display page are then linked using the health risk types to generate a visual assessment report.

8. The worker health status assessment method based on AI recognition as described in claim 1, characterized in that, The generation of the worker health status assessment report also includes: The visualization evaluation report displays at least one visualization area and sets a trigger command; the trigger command is used to trigger the corresponding evaluation process. When the assessment process is triggered, the corresponding attribution mapping map is configured based on the worker's physical risk data; Based on the attribution mapping map, the user's exposure distribution status in the project construction is determined, and an exposure factor distribution table for the project construction is generated based on the exposure distribution status.

Images