Occupational health testing method, system, electronic equipment and storage medium

Abstract

The present application provides an occupational health detection method, system, electronic device and storage medium, which relates to the field of occupational health detection technology. The method includes: obtaining the operation type of the target to be detected, and determining the working environment detection scheme and the occupational disease detection scheme according to the operation type; detecting the target to be detected according to the working environment detection scheme to obtain working environment detection data; detecting the target to be detected according to the working environment detection scheme to obtain occupational disease detection data; determining the working environment detection threshold according to the working environment detection data, and determining the work abnormality detection data exceeding the work environment detection threshold in the work environment detection data according to the working environment detection data and the working environment detection threshold; performing detection and analysis according to the work abnormality detection data and the occupational disease detection data to obtain a detection report. The above method improves the accuracy of occupational health detection.

Description

Technical Field

[0001] The present application relates to the technical field of occupational health detection, and in particular to an occupational health detection method, system, electronic device and storage medium. Background Art

[0002] With the acceleration of industrialization, the problem of occupational diseases has become increasingly prominent. In order to protect the physical and mental health of workers and to promptly discover and control occupational hazards, it is necessary to carry out occupational health testing. At present, occupational health testing mainly adopts the method of regular on-site testing. Testing personnel from professional institutions carry testing equipment to the enterprise site to sample and analyze occupational hazard factors in the working environment, and conduct occupational health examinations on workers exposed to occupational hazards. According to the test results, it is determined whether the working environment of the enterprise meets the hygiene standards and whether the workers have occupational contraindications or suspected occupational diseases. However, traditional occupational health testing methods have certain limitations. The formulation of the testing plan is highly dependent on the experience of the testing personnel and lacks quantitative analysis support, resulting in low accuracy of occupational health testing. Summary of the invention

[0003] The present application provides an occupational health testing method, system, electronic device and storage medium to improve the accuracy of occupational health testing.

[0004] In a first aspect, the present application provides an occupational health detection method, the method comprising: Obtain the job type of the target to be tested, and determine the work environment testing plan and occupational disease testing plan based on the job type; According to the working environment testing plan, the target to be tested is tested to obtain working environment testing data; Test the target according to the working environment testing plan to obtain occupational disease testing data; Determine a working environment detection threshold value according to the working environment detection data, and determine working abnormality detection data exceeding the working environment detection threshold value in the working environment detection data according to the working environment detection data and the working environment detection threshold value; Detection and analysis are performed based on the work abnormality detection data and occupational disease detection data to obtain a detection report.

[0005] In the above technical solution, the occupational health detection method proposed in this application first obtains the job type of the target to be detected, and determines the work environment detection plan and occupational disease detection plan according to the job type. By fully considering the characteristics of different job types, the detection plan is formulated in a targeted manner, thereby improving the pertinence and effectiveness of the detection.

[0006] After the testing plan is determined, the target to be tested is tested according to the working environment testing plan to obtain working environment testing data; at the same time, the target to be tested is tested according to the occupational disease testing plan to obtain occupational disease testing data. By comprehensively collecting data on both working environment and occupational diseases, a data foundation is laid for subsequent correlation analysis.

[0007] After obtaining the work environment detection data, this application further determines the work environment detection threshold based on the detection data, and determines the abnormal data in the detection data that exceeds the threshold. By determining a scientific and reasonable threshold through quantitative analysis, it is possible to more accurately and objectively determine whether there is an abnormality in the work environment, providing a basis for occupational disease warning.

[0008] Finally, the selected work abnormality detection data and occupational disease detection data are correlated and analyzed to obtain a detection report. By exploring the intrinsic connection between abnormal working environment and the occurrence of occupational diseases, the risk of occupational diseases caused by environmental factors can be discovered in a timely manner, providing quantitative analysis support for early warning and timely intervention of occupational diseases.

[0009] In a second aspect of the present application, an occupational health detection system is provided, the system comprising: The data acquisition module is used to obtain the job type of the target to be tested, and determine the working environment detection plan and occupational disease detection plan according to the job type; A working environment detection module is used to detect the target to be detected according to the working environment detection plan to obtain working environment detection data; An occupational disease detection module is used to detect the target to be detected according to the working environment detection plan to obtain occupational disease detection data; An abnormal data detection module is used to determine a working environment detection threshold according to the working environment detection data, and determine working abnormal detection data exceeding the working environment detection threshold in the working environment detection data according to the working environment detection data and the working environment detection threshold; The detection and analysis module is used to perform detection and analysis based on work abnormality detection data and occupational disease detection data to obtain a detection report.

[0010] In a third aspect of the present application, a computer storage medium is provided, wherein the computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the above method steps.

[0011] In the fourth aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the above method.

[0012] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. The occupational health detection method proposed in this application first obtains the job type of the target to be detected, and determines the work environment detection plan and occupational disease detection plan based on the job type. By fully considering the characteristics of different job types, the detection plan is formulated in a targeted manner, thereby improving the pertinence and effectiveness of the detection.

[0013] 2. After determining the testing plan, this application tests the target to be tested according to the working environment testing plan to obtain working environment testing data; at the same time, the target to be tested is tested according to the occupational disease testing plan to obtain occupational disease testing data. By comprehensively collecting data on both the working environment and occupational diseases, a data foundation is laid for subsequent correlation analysis.

[0014] 3. After obtaining the working environment detection data, this application further determines the working environment detection threshold based on the detection data, and judges the abnormal data in the detection data that exceeds the threshold. By determining a scientific and reasonable threshold through quantitative analysis, it is possible to more accurately and objectively judge whether there is an abnormality in the working environment, providing a basis for occupational disease warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic diagram of a process flow of an occupational health detection method provided in an embodiment of the present application; Figure 2 An architecture diagram of an occupational health detection system provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of an electronic device provided in this application. DETAILED DESCRIPTION

[0016] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0017] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0018] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0019] In order to facilitate understanding of the method and system provided by the embodiments of the present application, before introducing the embodiments of the present application, the background of the embodiments of the present application is first introduced.

[0020] With the continuous advancement of industrialization, occupational diseases have become increasingly prominent and have become a major hidden danger threatening the physical and mental health of workers. In order to effectively prevent and control occupational hazards and effectively safeguard the legitimate rights and interests of workers, carrying out systematic and standardized occupational health testing has become a top priority for corporate occupational health management.

[0021] At present, occupational health testing mainly adopts the mode of regular on-site testing. Professional institutions send certified testing personnel to the production line of enterprises with sophisticated testing instruments and equipment to systematically sample and accurately analyze various occupational disease hazards in the working environment, such as dust, noise, chemical poisons, etc. At the same time, special occupational health inspections are carried out for workers exposed to occupational hazards. Through the comprehensive judgment of environmental testing results and personal physical examination reports, it is clear whether the enterprise's workplace meets the national occupational health standards, whether the workers have occupational taboos or early signs of occupational diseases, and provide scientific decision-making basis for the prevention and control of occupational diseases in enterprises.

[0022] However, years of practice have shown that traditional occupational health testing methods still have certain shortcomings. The design and implementation of the testing plan is highly dependent on the personal experience and professional quality of the testers, and lacks scientific and quantitative analysis methods and intelligent auxiliary means. When different testers face the same enterprise and the same position, the testing methods, testing frequency, focus, etc. adopted may vary greatly, making it difficult to ensure the consistency and continuity of the testing process. The highly subjective testing plan not only affects the testing efficiency, but also makes it difficult to ensure the accuracy and reliability of the test results, and cannot truly play the "sentinel" role of occupational health testing in the prevention and control of occupational diseases.

[0023] After the background introduction of the above content, those skilled in the art can understand the problems existing in the prior art. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments.

[0024] Based on the above background technology, please refer to Figure 1 , Figure 1 A flowchart of an occupational health detection method provided in an embodiment of the present application. The system can be implemented by a computer program or can be run as an independent tool application. Specifically, in an embodiment of the present application, the method can be applied on a server, but can also be applied to electronic devices such as servers. An occupational health detection method includes the following steps: S101, obtaining the job type of the target to be tested, and determining a work environment testing plan and an occupational disease testing plan according to the job type; Specifically, we can collect comprehensive information on the company's production process, raw and auxiliary materials, job settings, etc. through on-site inspections, reviewing company information, interviewing management personnel, etc., and accurately identify each job type. In practice, the national economic industry classification and occupational classification standards are usually used to standardize the classification of job types.

[0025] After clarifying the type of work, the work environment detection plan and occupational disease detection plan can be determined accordingly. The work environment detection plan needs to clearly identify the occupational disease hazards that need to be focused on in the environment, and reasonably set the detection indicators, sampling points, sampling frequency, etc. to ensure that the detection is comprehensive, standardized, and comparable. The occupational disease detection plan should determine the occupational health examination items and evaluation standards in a targeted manner according to the types of occupational diseases that may be contracted by different types of work. For example, for medical staff who are exposed to radioactive substances, peripheral blood and bone marrow examinations can be included in the scope of routine physical examinations.

[0026] By obtaining the type of work and determining the detection plan accordingly, the accuracy and effectiveness of the detection can be maximized. On the one hand, a highly targeted detection plan can focus on key occupational disease hazard factors, improve the sensitivity of abnormal detection, and reduce the risk of missed detection. On the other hand, a standardized and unified detection plan is conducive to the horizontal comparison and vertical tracking of detection data, laying a good foundation for systematically evaluating occupational disease hazard trends and conducting occupational disease epidemiological research.

[0027] Based on the above embodiment, as an optional embodiment, according to the type of operation, a working environment detection scheme and an occupational disease detection scheme are determined, including: S201, identifying occupational disease hazard factors according to the job type, and obtaining target occupational disease hazard factors; Specifically, in the process of intelligent occupational health testing, determining the work environment testing plan and occupational disease testing plan according to the type of operation is a key step. To achieve this goal, the first task is to identify the occupational disease hazard factors related to the operation type, and then determine the key objects of the test, that is, the target occupational disease hazard factors. This is because the occupational disease risks faced by different types of operations vary greatly. Only by prescribing the right medicine and implementing precise policies can we achieve twice the result with half the effort in the prevention and control of occupational diseases.

[0028] During the specific implementation, occupational health professionals need to comprehensively collect information on the company's production process, raw and auxiliary material composition, occupational health archives, etc., and identify the physical, chemical, biological and other hazards that may be generated in each process one by one by comparing them with the classification catalog of occupational disease hazards issued by the state. Taking pesticide production enterprises as an example, in the synthesis of highly toxic raw materials, workers are mainly exposed to highly toxic pesticides such as organophosphorus and carbamates; in the processing of auxiliary agents, workers may be exposed to organic solvents such as benzene and toluene. Through on-site investigation and data analysis, the target occupational disease hazard factors of the company's pesticide production operations can be obtained.

[0029] When identifying occupational disease hazard factors, we should make full use of knowledge from disciplines such as occupational hygiene, labor hygiene, and environmental medicine to conduct assessments from two dimensions: the possibility of the hazard occurring and the degree of the hazard. Hazard factors with high probability and serious consequences should be included in the key monitoring category; for factors with low probability and low hazard, the detection methods can be relatively simplified. In addition, when determining the target occupational disease hazard factors, we should also pay attention to the synergy between different hazard factors and comprehensively consider the compound effects of multiple hazards.

[0030] By accurately identifying the target occupational hazard factors, a solid foundation can be laid for the subsequent development of targeted work environment testing plans and occupational disease testing plans. On the one hand, by focusing on the target hazard factors, the sampling plan, testing indicators, analysis methods, etc. can be designed in a targeted manner, which can greatly improve the scientificity and accuracy of the work environment evaluation. On the other hand, for the specific occupational diseases that may be caused by the target hazard factors, the occupational health examination items and diagnostic standards can be determined in a targeted manner, which can significantly improve the efficiency of early screening and diagnosis of occupational diseases.

[0031] S202, determining the test objects that need to be tested in the workplace according to the target occupational disease hazard factors; Specifically, after clarifying the target occupational disease hazard factors corresponding to the job type, the intelligent occupational health detection system needs to further determine the objects that need to be detected in the workplace based on these hazard factors. This step aims to focus on the key links of occupational disease hazards, optimize the allocation of detection resources, and effectively improve the pertinence and effectiveness of work environment evaluation.

[0032] During the specific implementation, occupational health professionals should go deep into the production line, check the target occupational disease hazard factors, and comprehensively check the areas, equipment, positions, etc. that may be hazardous in the workplace, so as to determine the type and scope of the detection object. Taking welding operations as an example, since welding smoke is listed as the primary target occupational disease hazard factor, the detection objects should cover the air, ventilation facilities, dust removal devices, etc. in the welding workshop and its surrounding areas, with a focus on welding positions where the smoke concentration exceeds the standard.

[0033] When identifying the test object, in addition to relying on experience, we should also make full use of relevant theories of occupational hygiene to quantitatively evaluate the spatial distribution characteristics of hazardous substances. For example, we can use fluid mechanics models to simulate the airflow field in the workshop to determine the direction and distance of dust migration and diffusion; we can use chemical reaction kinetic models to predict the chemical transformation process of toxic gases and estimate the trend of their concentration over time. Based on theoretical analysis and combined with field surveys, we can more accurately and comprehensively determine the key places and facilities that need to be tested.

[0034] S203, planning a working environment testing plan according to the test object; Specifically, after defining the test objects in the workplace, the intelligent occupational health testing system needs to plan a complete work environment testing plan based on this. This step aims to clarify the specific elements such as test indicators, test frequency, sampling methods, and analysis methods around the test objects, making the test process more standardized and the test results more accurate, thereby providing a scientific basis for occupational disease hazard assessment.

[0035] During the specific implementation, occupational health professionals should comprehensively sort out the list of test objects and formulate personalized test strategies for different types of test objects. Taking underground coal mine operations as an example, since miners are mainly exposed to complex occupational disease hazards such as coal dust, noise, and high temperature, the test objects include both working areas such as mining faces and transportation tunnels, as well as key equipment such as ventilators and air compressors. On this basis, customized work environment test plans can be planned around test objects such as air, equipment, and personnel.

[0036] For the detection of air in the working area, factors such as the ventilation conditions of the mine and the distribution of dust-generating points should be comprehensively considered, sampling points should be set scientifically, and the sampling time and frequency should be reasonably determined. At the same time, based on the special dusty and high-humidity environment underground in coal mines, the explosion-proof and moisture-proof performance of sampling equipment should also be evaluated when selecting it. In terms of detection indicators, in addition to the conventional coal dust concentration, the analysis of key toxic components such as free silica should also be included.

[0037] In terms of equipment testing, the detection of physical hazards such as noise and vibration is particularly critical. High-precision and highly sensitive noise meters and vibration measuring instruments should be used to conduct all-round measurements of different types of ventilators, air compressors, etc., focusing on the sound level distribution at different distances from the noise source. The frequency of testing should cover various operating conditions such as equipment startup, operation, and shutdown to grasp the characteristics of noise at all times.

[0038] S204: Determine the target occupational disease type based on the target occupational disease hazard factors, and plan an occupational testing program based on the target occupational disease type.

[0039] Specifically, on the basis of clarifying the target occupational disease hazard factors, the intelligent occupational health detection system needs to further determine the corresponding target occupational disease types and plan the occupational disease detection plan accordingly. The fundamental purpose of this step is to clarify the occupational health damage consequences that may be caused by the hazard factors, so as to carry out occupational disease screening and diagnosis in a targeted manner, and achieve early detection, early intervention, and early treatment.

[0040] When implementing the measures, occupational health professionals should systematically sort out the current classification and catalog of occupational diseases in my country, and clarify the corresponding relationship between different occupational disease hazards and specific occupational disease types. Taking lead and its compounds as an example, according to the catalog of occupational diseases, occupational diseases caused by lead and its compounds mainly include lead poisoning, organ function damage, etc. Therefore, when facing high-risk industries such as lead smelting and lead-acid battery manufacturing, occupational disease detection of relevant practitioners should focus on the target organ functions such as the nervous system, hematopoietic system, and digestive system.

[0041] After clarifying the target occupational disease type, the occupational disease detection program should be planned in a targeted manner based on the pathogenesis and clinical characteristics of the occupational disease. Taking noise-induced occupational deafness as an example, since hearing loss usually has an insidious onset and progresses slowly, occupational disease detection should cover all employees, seize the opportunity of screening high-risk groups and dynamic follow-up, and include sensitive indicators such as high-frequency hearing and otoacoustic emissions.

[0042] S102, testing the target to be tested according to the working environment testing plan to obtain working environment testing data; Specifically, after determining the work environment testing plan, the next step is to conduct actual testing on the target to be tested according to the plan to obtain detailed and reliable work environment testing data. The work environment testing data is the direct basis for evaluating the occupational disease hazard status of the enterprise and is the basic work for carrying out occupational disease prevention and control.

[0043] S103, testing the target to be tested according to the working environment testing plan to obtain occupational disease testing data; Specifically, in addition to obtaining work environment testing data, it is also a crucial step to test the target according to the occupational disease testing plan to obtain occupational disease testing data. Occupational disease testing data directly reflects the occupational health status of workers and is an objective basis for judging whether they have occupational diseases or early occupational disease injuries. Only by combining occupational disease testing data with work environment testing data can we comprehensively assess the enterprise's occupational disease hazard risks and find out the root causes of the hazards.

[0044] S104, determining a working environment detection threshold according to the working environment detection data, and determining working abnormality detection data exceeding the working environment detection threshold in the working environment detection data according to the working environment detection data and the working environment detection threshold; Specifically, after obtaining sufficient work environment detection data, the intelligent occupational health detection system needs to further determine the work environment detection threshold based on this data, and screen out abnormal work detection data that exceeds the threshold. Setting a reasonable detection threshold will help to quickly and accurately identify occupational disease hazards in the work environment, and provide a decision-making basis for timely eliminating hazards and improving environmental quality.

[0045] In specific implementation, we can comprehensively consider national occupational health standards, industry norms, local regulations, etc., and set scientific detection thresholds for various occupational disease hazards. Taking noise as an example, my country's "Industrial Enterprise Design Hygiene Standards" stipulate that the equivalent continuous A sound level in the workshop shall not exceed 85 decibels. Combining this standard value and referring to the international occupational noise exposure limit, we can set the noise working environment detection threshold.

[0046] After the detection threshold is determined, the system automatically compares the collected massive work environment monitoring data with the threshold and quickly identifies abnormal data that exceeds the standard. For example, the 24-hour continuous noise monitoring data in the workshop is imported into the system, and through big data analysis technology, abnormal monitoring points that exceed the 85-decibel threshold at any time during the day are marked to form a work abnormality detection data set.

[0047] The work abnormality detection data directly reflects the distribution and excess of occupational disease hazard factors in the workplace, and is an important starting point for carrying out occupational health management. According to the time, region, degree and other characteristics reflected in the abnormal data, the law of hazard generation can be judged, the key links of high incidence of occupational diseases can be found, and targeted rectification plans can be formulated. For example, if it is found that the noise exceeds the standard more during the night shift, the night operation process should be checked; if it is found that the time of exhaust gas exceeding the standard coincides with the failure of negative pressure ventilation, the maintenance of environmental protection facilities should be included in the rectification priority.

[0048] Based on the above embodiment, as an optional embodiment, determining the working environment detection threshold according to the working environment detection scheme includes: S301, sorting out key indicator information and detection point information data in the working environment detection plan, and determining the detection indicator limit value of each detection point according to the key indicator information; Specifically, after the work environment testing plan is formulated, the intelligent occupational health testing system needs to further clarify the threshold standards for work environment testing. This step aims to clarify the boundaries of different testing objects and different testing points, provide an objective basis for determining whether the work environment is qualified, and lay the foundation for the management of occupational hazards.

[0049] When implementing the plan, the first task is to comprehensively sort out the key information and data in the work environment testing plan. Occupational health professionals need to carefully review the text of the testing plan, extract key information such as the test object, test indicators, sampling points, and systematically organize and classify them. Taking the benzene workplace of a chemical enterprise as an example, by sorting out the testing plan, it can be made clear that this test focuses on characteristic poisons such as benzene, toluene, and xylene, and covers dozens of sampling points such as production workshops and tank areas.

[0050] After understanding the basic situation of the detection plan, we should base ourselves on occupational health standards and specifications, and combine the characteristics of the production process to determine the key indicator limits of each detection point in a targeted manner. Specifically, we should consult the occupational exposure limit standards for harmful factors in the workplace formulated by the state, and extract the quantitative limit indicators related to this test. For example, for benzene workplaces, it can be clearly stated that the short-term contact permissible concentrations of benzene, toluene, and xylene are 10mg / m³, 100mg / m³, and 100mg / m³, respectively. On this basis, we should also fully consider the differences in exposure risks at different detection points, and adjust the strictness of the limit standards as appropriate. For example, for places with high hazard risks such as benzene storage tanks, the limit standards can be tightened from the permissible concentration to 50% of the short-term contact permissible concentration to achieve precise control of key hazards.

[0051] S302: adjusting the detection index limit of each detection point according to the detection point information data to obtain a working environment detection threshold.

[0052] Specifically, after initially determining the detection index limit values ​​of each detection point, the intelligent occupational health detection system needs to dynamically adjust the limit values ​​according to the actual conditions of the detection point, and finally form a practical working environment detection threshold. The key to this step is to make full use of the detection point information data, revise the limit values ​​according to local conditions, and ensure that the detection threshold is both scientific and reasonable and operational.

[0053] When implementing the work, occupational health professionals should go to the front line and collect background information data of each detection point through on-site investigation, file review, expert consultation, etc. Taking high-temperature work in metal smelting enterprises as an example, the key factors affecting the degree of heat hazard, such as ambient temperature in different workplaces, labor intensity of workers, ventilation effect, etc., should be paid attention to.

[0054] On the basis of mastering the background information of the detection point, the theoretical knowledge of occupational health and practical experience should be used to analyze the impact of various factors on the occupational disease hazard limit standards. Taking high-temperature workplaces as an example, when the ambient temperature is high and the labor intensity is high, the balance between human heat production and heat dissipation is more likely to be broken, and the risk of thermal hazards is greatly increased. Therefore, for places with high heat loads such as blast furnaces and foundries, the limit standards of environmental thermal parameters should be appropriately lowered, such as adjusting the temperature limit from 33°C to 28°C. On the contrary, for environmentally friendly places such as lounges, the thermal parameter limits can be moderately relaxed.

[0055] When determining the adjustment range of the detection point limit, in addition to following the principles of occupational health, the cost-benefit of different adjustment plans should also be fully considered. Blindly tightening standards is certainly beneficial to protecting the health of workers, but it may also increase the governance burden of enterprises. Occupational health professionals should base themselves on cost-benefit analysis and, on the premise of ensuring occupational health, adjust the detection limit within a reasonable range that the enterprise can bear. Taking high-temperature work as an example, the heat hazard control effect and the required input cost under different temperature threshold schemes can be evaluated, and the limit adjustment range that takes into account both occupational health protection and the enterprise's tolerance can be selected.

[0056] Based on the above embodiment, as an optional embodiment, the detection index limit of each detection point is adjusted according to the detection point information data to obtain the working environment detection threshold, including: S401, sorting out the detection point information data to obtain detection point key data, and performing heterogeneity analysis based on the detection point key data to obtain heterogeneous data between various detection points; Specifically, after the preliminary collection of information data from the detection points, the intelligent occupational health detection system needs to further sort out and analyze the data to lay the foundation for the precise adjustment of the detection index limit. The core of this step is to reveal the differences in the degree of occupational disease hazards between different detection points through heterogeneity analysis, and then provide a quantitative basis for the limit adjustment.

[0057] When implementing it, the collected information data of the detection points should be systematically sorted out first. Occupational health professionals need to carefully review the background information of each detection point, such as environmental conditions, production processes, and protective facilities, and extract key information data that have a decisive impact on the degree of occupational disease hazards. Taking the organic solvent workplace as an example, by sorting out the data of each detection point, key parameters such as the type of organic solvent used, daily usage, operation method, and ventilation times can be obtained.

[0058] After clarifying the key data of the detection points, the heterogeneity analysis method should be used to systematically evaluate the differences in the level of occupational hazard between different detection points. The basic idea of ​​heterogeneity analysis is to judge the degree of occupational hazard by comparing the similarities and differences of key parameters of different detection points. Taking organic solvent operations as an example, when the type of solvent is the same, the greater the daily usage, the more closed the operation method, and the fewer ventilation times, the higher the degree of occupational hazard. On the contrary, the risk of occupational disease at detection points with small daily usage, open operation, and good ventilation is relatively low.

[0059] There are many methods for heterogeneity analysis, which can be done by qualitative logical reasoning or quantitative mathematical models. In qualitative analysis, experienced occupational health experts can be invited to conduct brainstorming discussions on the heterogeneity characteristics of detection points around key influencing factors to draw qualitative judgment conclusions. In quantitative analysis, mathematical tools such as hierarchical analysis method and fuzzy comprehensive evaluation can be used to calculate the relative weights of the hazard levels of different detection points, and cluster analysis can be carried out based on this to divide the detection points into different hazard levels of high, medium and low. Of course, when applying heterogeneity analysis methods, attention should also be paid to the characteristics of different industries and different occupational disease hazard factors, and practical analysis paths and models should be flexibly selected.

[0060] S402, adjusting the detection index limit of each detection point according to the heterogeneous data to obtain a working environment detection threshold.

[0061] Specifically, after obtaining the heterogeneous data of the detection points, the intelligent occupational health detection system can make differentiated adjustments to the detection index limits of each detection point, and finally determine the detection threshold of the working environment that is appropriate to local conditions. This step aims to make full use of the results of heterogeneous analysis and ensure that the detection standards are highly consistent with the actual occupational hazards through the threshold setting method of "one point, one policy".

[0062] In specific implementation, the basic principle of "strict standards for high hazards and wide standards for low hazards" should be followed, and the adjustment direction and adjustment range of the detection index limit should be determined according to the high and low levels of hazards reflected by the heterogeneous data. For detection points that are judged to have a high hazard level in the heterogeneous analysis, the limit standards should be strictly adjusted. Taking dust operations as an example, for crushing workshops and screening workshops with high hazard levels, the dust concentration limit can be lowered from the original 10mg / m³ to 5mg / m³ to minimize the risk of occupational diseases. On the contrary, for detection points with low hazard levels and complete protective measures, the limit standards can be moderately relaxed, such as appropriately increasing the dust concentration limit.

[0063] When adjusting the limits of detection indicators, in addition to grasping the direction of adjustment, attention should also be paid to controlling the quantitative range of adjustment. The determination of the adjustment range requires comprehensive consideration of occupational health needs and the company's tolerance. On the one hand, the adjustment range should be sufficient to cover the difference in hazard levels at the detection points, so that the limit standards of high and low hazard detection points are sufficiently different. On the other hand, the adjustment range should not be too large, so as not to increase the burden of corporate governance. In practice, experts in the fields of occupational health and production management can be invited to conduct a comprehensive evaluation and demonstration of different adjustment range plans, and select the optimal plan to adjust the detection limit within a reasonable range.

[0064] It is worth noting that the differentiated adjustment of detection limits should be based on the limits specified in national standards and carried out within their allowable range. For high-hazard detection points, the adjusted limits can be lower than the national standard values ​​to achieve stricter occupational health management. However, for low-hazard detection points, the adjusted limits should not exceed the upper limit set by the national standard to avoid violating mandatory regulations. At the same time, for individual special detection points, such as chemical leak emergency disposal areas, their detection limits should not be adjusted, but should always be implemented in accordance with national standards to deal with emergencies.

[0065] S105, performing detection and analysis based on the work abnormality detection data and the occupational disease detection data to obtain a detection report.

[0066] Specifically, after identifying the abnormal work detection data, the intelligent occupational health detection system needs to further correlate it with the occupational disease detection data to obtain a comprehensive detection report. This step aims to deeply explore the inherent connection between occupational disease hazards in the work environment and occupational health injuries of workers, reveal the causes and laws of occupational diseases, and provide a practical basis for the effective prevention and control of occupational diseases.

[0067] In specific implementation, the system uses technologies such as big data mining and machine learning to intelligently match and cross-validate work anomaly detection data and occupational disease detection data. On the one hand, based on each worker's work number, name, position and other information, their occupational health files are accurately linked to the detection records of occupational disease hazard factors in the corresponding workplace to explore the quantitative relationship between specific hazard factors and the occurrence of occupational diseases. On the other hand, statistical methods such as correlation analysis and regression analysis are used to reveal the differences in occupational disease prevalence rates in different types of work, different environments, and different exposure levels at the group level, and to identify susceptible populations and high-risk links.

[0068] For example, after a comprehensive analysis of the test data of a smelting enterprise, the system found that the concentration of free silica in the smelting workshop exceeded the standard all year round. At the same time, the incidence of pneumoconiosis among workers in this workshop was significantly higher than that in other positions. Through data modeling and analysis, the quantitative relationship between the concentration of free silica and the risk of pneumoconiosis was further determined, and based on this, it was predicted that if effective protective measures were not taken in time, the number of pneumoconiosis patients in this workshop would continue to increase, seriously threatening the physical and mental health of employees.

[0069] After completing the intelligent analysis of the test data, the system automatically generates a structured test report. The report uses pictures and texts to intuitively present key information such as the main occupational disease hazards in the working environment, the occupational health status of workers, the scope of high-risk positions, and the trend of occupational disease incidence. At the same time, from the perspective of medicine and engineering technology, the report analyzes the causes of occupational diseases, evaluates the effectiveness of existing protective facilities, and proposes practical prevention and control measures, providing quantitative reference for corporate occupational disease prevention and control decisions.

[0070] Based on the above embodiment, as an optional embodiment, detection and analysis are performed based on the work abnormality detection data and the occupational disease detection data to obtain a detection report, including: S501, classifying the work abnormality detection data to obtain work abnormality detection classification data; Specifically, after completing the work environment detection and occupational disease screening, the intelligent occupational health detection system needs to conduct in-depth analysis of the massive heterogeneous data collected to form an intuitive, comprehensive, and targeted detection report. The primary task of report generation is to scientifically classify the abnormal work detection data and merge similar abnormal problems to lay the foundation for subsequent analysis.

[0071] In the specific implementation, we should base on the characteristics of occupational hazards in the workplace and carry out multi-dimensional classification of work abnormality detection data. First, it should be classified according to the source of the abnormality. Taking metal smelting enterprises as an example, abnormal data can be divided into abnormal problems caused by different hazard factors such as high temperature, dust, noise, chemicals, etc. Secondly, it should be classified according to the type of abnormality. For each hazard factor, there may be different types of problems such as environmental abnormalities, behavioral abnormalities, and protection abnormalities. Thirdly, it can also be classified according to the severity of the abnormality, distinguishing between mild, moderate, and severe abnormalities.

[0072] After determining the classification dimensions, appropriate data analysis methods should be used to achieve accurate classification of work anomaly detection data. Common classification methods include rule-based classification and model-based classification. Rule-based classification means that occupational health experts pre-set abnormal classification rules, such as determining that an ambient temperature exceeding 35°C is a high temperature abnormality. When classifying data, the system strictly classifies them one by one according to the rules. Model-based classification is more intelligent. The system uses algorithms such as machine learning to autonomously learn abnormal features, form a classification discrimination model, and then use the model to automatically classify data. Compared with rule-based methods, this method can autonomously mine the inherent classification features of the data and has higher classification accuracy. Of course, in practice, it is often necessary to combine the two classification methods, both to give play to expert experience and to rely on machine intelligence to achieve comprehensive and accurate classification of abnormal data.

[0073] S502, analyzing the correlation between the work abnormality detection classification data and the occupational disease detection data to obtain correlation data; Specifically, after obtaining the classification data of work abnormality detection, the intelligent occupational health detection system needs to further analyze the correlation between the data and the occupational disease detection data to reveal the intrinsic connection between work environment problems and employee health status. The core purpose of correlation analysis is to find out the key work abnormality factors that lead to occupational diseases through data association mining, and then lay the foundation for the formulation of targeted prevention and control measures.

[0074] When implementing it, the scope of the object of correlation analysis should be clarified first. Occupational disease detection data usually include employees' occupational disease diagnosis results, occupational pathology examination indicators and other contents. When conducting correlation analysis, the focus should be on specific occupational diseases and occupational pathological changes corresponding to the types of work abnormalities. Taking metal smelting enterprises as an example, the focus should be on analyzing the correlation between abnormal high temperature and heat diseases such as heat stroke and heat cramps, and the correlation between abnormal dust and pneumoconiosis and abnormal lung function.

[0075] After clarifying the analysis object, it is necessary to use scientific association analysis methods to deeply explore the internal connection between the two types of data. Commonly used methods include statistical association analysis and data mining association analysis. In statistical analysis, methods such as chi-square test and correlation analysis can be used to examine the correlation between the exposure level of abnormal factors and the incidence of occupational diseases. For example, the difference in the incidence of febrile diseases between employees in high-temperature workshops and normal-temperature workshops can be statistically analyzed, and the correlation coefficient can be calculated to preliminarily determine the strength of the association between abnormal high temperature and febrile diseases. On the basis of statistical analysis, data mining algorithms such as association rule mining and time series pattern mining can also be used to further explore the complex association patterns between abnormal factors and occupational disease results. For example, the Apriori algorithm can be used to mine the association rule of "abnormal high temperature + sharp increase in labor intensity → heat stroke", revealing the combined effect of high temperature and high-intensity labor.

[0076] By comprehensively applying statistics and data mining techniques, correlation analysis can fully reveal the intrinsic connection between abnormal work factors and occupational disease outcomes, and form objective and quantitative correlation data. Taking dust abnormality as an example, correlation analysis can clarify the differences in the incidence of pneumoconiosis under different dust concentrations, dust types, and years of exposure, and determine the contribution of dust abnormality to the occurrence of occupational diseases. For another example, noise abnormality, correlation data can reveal the corresponding relationship between noise spectrum, intensity, exposure time and different degrees of noise deafness.

[0077] The significance of correlation data lies in that it extracts the key influencing factors of occupational diseases from the complex test data and clarifies the causal logic between abnormal work and occupational diseases. Relying on correlation data, occupational health managers can "prescribe the right medicine" and formulate targeted abnormal rectification and occupational disease prevention and control plans. For example, in view of the high correlation between noise abnormality and noise-induced deafness, the focus should be on strengthening the sound source control and individual protection of high-noise positions. For another example, in view of the dose-effect relationship between dust concentration and the incidence of pneumoconiosis, the target concentration of dust control can be determined according to local conditions.

[0078] Of course, the relationship between work abnormalities and occupational diseases is somewhat complex. Some abnormal factors may lead to occupational diseases after a long incubation period, and the occurrence of some occupational diseases may be the result of the combined action of multiple abnormal factors. Therefore, when conducting correlation analysis, attention should also be paid to incorporating the time dimension, examining the lag effect of abnormal factors, and comprehensively evaluating the interactive effects of multiple abnormalities, striving to fully and accurately reveal the correlation rules. Only by continuously optimizing the iterative correlation analysis method can the correlation data better guide the practice of occupational disease prevention and control.

[0079] Based on the above embodiment, as an optional embodiment, the correlation between the work abnormality detection classification data and the occupational disease detection data is analyzed to obtain correlation data, including: S601, matching the work abnormality detection classification data with the occupational disease detection data to obtain an abnormality type-occupational disease type matrix; Specifically, when conducting the correlation analysis between work abnormalities and occupational diseases, the first task is to systematically match the work abnormality detection classification data with the occupational disease detection data to form an abnormality type-occupational disease type matrix. The core purpose of constructing a matching matrix is ​​to clarify the correspondence between different abnormality types and various occupational diseases, laying the foundation for subsequent in-depth investigation of the relationship between the two.

[0080] When implementing it, we should base ourselves on professional knowledge of occupational health, and design a scientific abnormality-occupational disease matching path based on theoretical and practical experience. First of all, we should refer to the theory of occupational disease event tree, and link various abnormal factors with occupational disease results according to the pathogenic mechanism. Taking metal smelting enterprises as an example, high temperature abnormalities should be matched with febrile diseases such as heat stroke and heat cramps, and dust abnormalities should be matched with respiratory diseases such as pneumoconiosis. When linking the mechanism, we should also explore the combined effects of abnormal factors. For example, high temperature abnormalities plus heavy physical labor can lead to a significant increase in the risk of febrile diseases.

[0081] On the basis of theoretical links, we should also make full use of past occupational disease detection data to verify and optimize the preliminary abnormality-occupational disease matching matrix. For example, we should conduct a retrospective analysis of the detection data of a certain enterprise in the past five years, examine the frequency of simultaneous occurrence of various abnormalities and corresponding occupational disease types, calculate the abnormality-occupational disease Lift value and other correlation indicators, and screen out the matching items with high actual correlation, and eliminate the redundant matching items with low correlation. In this way, we can continuously correct the matching matrix to make it closer to the objective law of occupational disease occurrence.

[0082] Through system matching analysis, a highly structured abnormality type-occupational disease type matrix can be obtained. Taking metal smelting enterprises as an example, the matrix may include the following main matching items: abnormal high temperature-heatstroke, abnormal high temperature-heat cramps, abnormal dust-pneumoconiosis, abnormal dust-pulmonary function, abnormal noise-noise deafness, abnormal toxic substances-acute and chronic poisoning, etc. The matching matrix intuitively presents the hypotheses of the association between various work abnormalities and occupational disease outcomes, making the complex occupational disease hazard factors organized and systematized, thus creating conditions for further quantitative investigation of the association between the two.

[0083] S602, performing correlation analysis based on the abnormality type-occupational disease type matrix to obtain correlation data.

[0084] Specifically, after constructing the abnormality type-occupational disease type matrix, the intelligent occupational health detection system needs to further conduct in-depth correlation analysis based on the matrix, quantitatively examine the correlation strength and correlation pattern between various types of work abnormalities and occupational disease results, and finally form correlation data that reflects the internal connection between the two. The core purpose of correlation analysis is to characterize the impact of work environment problems on occupational health from both macro and micro dimensions, and to reveal the complex mechanism of occupational disease occurrence with rigorous analysis and quantitative data, so as to provide a precise grasp for the subsequent formulation of targeted prevention and control measures.

[0085] When implementing it, we should first focus on each matching item in the abnormality type-occupational disease type matrix, and examine the correlation characteristics between a single abnormality type and the corresponding occupational disease results. Taking the high temperature abnormality-heat stroke matching item as an example, a regression model can be used to analyze the odds ratio (OR value) of heat stroke at different temperature levels, and the percentage of heat stroke risk increase for every 1°C increase in temperature. For another example, for the dust abnormality-pneumoconiosis matching item, a multivariate Cox survival analysis model can be used to calculate the effects of different dust concentrations, dust types, and dust exposure years on the onset time of pneumoconiosis, revealing the multifactorial effect of dust on the disease. Similarly, other matching items such as noise abnormalities and toxic substance abnormalities should also carry out targeted association analysis to quantitatively characterize the dose-response relationship, multifactor interaction and other internal connections between various abnormal factors and the corresponding occupational disease results.

[0086] Univariate association analysis can reveal the occupational hazard effects of various abnormalities, but the occurrence of occupational diseases is often the result of the combined action of multiple hazard factors. Therefore, it is necessary to comprehensively examine the composite correlation characteristics of multiple abnormal types and multiple occupational disease results on the basis of univariate analysis. Taking metal smelting enterprises as an example, multiple abnormal factors such as high temperature, dust, noise, and toxic substances usually coexist, and multiple occupational diseases such as febrile diseases, occupational respiratory diseases, and occupational poisoning may also occur at the same time. Advanced statistical methods such as structural equation modeling (SEM) should be used to comprehensively analyze the direct and indirect effects of multiple abnormal paths on the occurrence of occupational diseases, revealing the networked association mechanism between work environment hazards and the occurrence of occupational diseases. At the same time, for key occupational disease types, a multivariate logistic regression model can be established to examine the joint impact of combined exposure of multiple abnormal factors on the risk of the disease. For example, the impact of the interaction term of high temperature abnormality and dust abnormality on the OR value of pneumoconiosis incidence is analyzed to reveal the synergistic pathogenic effect of the two types of abnormalities.

[0087] By systematically conducting the above correlation analysis, a series of correlation data that quantitatively reflect the intrinsic connection between work abnormalities and occupational diseases can be obtained. These data cover the occupational hazard effect parameters of a single abnormal type (such as the OR value of logistic regression and the risk ratio HR value of Cox regression), as well as the composite correlation effect parameters of multiple abnormal types and multiple occupational disease outcomes (such as the path coefficient of the structural equation model and the regression coefficient of the interaction term). The correlation data whiteboxes the black-box relationship between work environment problems and the occurrence of occupational diseases, and uses rigorous and meticulous quantitative analysis to reveal the complex correlation mechanism between the two. The data results intuitively show the weight differences of various abnormal factors in the occurrence of occupational diseases, depict the dose-response relationship between different levels of abnormal exposure and the risk of occupational diseases, and reveal the interactive pathogenic effects between abnormal factors, laying a solid foundation for the subsequent targeted formulation of prevention and control strategies and programs.

[0088] Based on the above embodiment, as an optional embodiment, correlation analysis is performed based on the abnormality type-occupational disease type matrix to obtain correlation data, including: S701, calculating the frequency of each cell in the abnormality type-occupational disease type matrix to generate a frequency matrix; Specifically, when conducting the correlation analysis between work abnormalities and occupational diseases, the first task is to calculate the frequency of each cell in the abnormality type-occupational disease type matrix and generate a frequency matrix. The core purpose of frequency calculation is to quantitatively characterize the absolute number of times each type of abnormality and each occupational disease occur at the same time, grasp the co-occurrence law of the two from a holistic perspective, and lay the foundation for further investigation of the strength of the association.

[0089] In the specific implementation, the enterprise's occupational health detection data should be used as a basis, and the database SQL statement should be used to count the frequency of each cross cell of the abnormality type-occupational disease type matrix. Taking metal smelting enterprises as an example, the occupational disease diagnosis results and corresponding work abnormality detection records of each employee in the historical data should be extracted, and the principle of cross-positioning of matrix rows and columns should be used to count and accumulate the simultaneous occurrences of each abnormality type-occupational disease type combination. For example, the simultaneous occurrence of high temperature abnormality and heat stroke diagnosis is counted as 1 time, and the simultaneous occurrence of high temperature abnormality and pneumoconiosis diagnosis is also counted as 1 time. Finally, the total frequency of simultaneous occurrence of high temperature abnormality-heatstroke cell and high temperature abnormality-pneumoconiosis cell can be obtained. Similarly, the frequency of other abnormal types such as noise abnormality, dust abnormality, toxic substance abnormality and corresponding occupational disease types can also be obtained through this cross-positioning accumulation method.

[0090] During the frequency calculation process, some key details should be focused on. First, the analysis unit of frequency statistics should be clarified. Usually, each employee should be used as an independent observation unit, and the abnormal records and occupational disease results at the individual level should be paired and accumulated. For example, if an employee has 3 abnormal high temperature records in 5 years and is diagnosed with heat stroke, the frequency of the abnormal high temperature-heat stroke cell will be increased by 3. Second, it is necessary to distinguish between simultaneous and non-simultaneous situations. If a certain abnormal type and a certain occupational disease type appear separately, but the two do not appear at the same time in the test records of the same individual, the corresponding cell frequencies cannot be accumulated. If an employee has a record of abnormal high temperature but is not diagnosed with heat stroke, the frequency of the abnormal high temperature-heat stroke cell will not be increased by 1. Third, for chronic occupational diseases, a certain abnormal exposure-disease occurrence time window should be set. If you want to analyze the frequency of dust abnormalities and pneumoconiosis, the situation where the employee's dust abnormality record is within 10 years of the diagnosis of pneumoconiosis can be defined as simultaneous occurrence.

[0091] By systematically carrying out the above frequency calculations, a frequency matrix that comprehensively reflects the co-occurrence rules of various abnormalities and various occupational diseases can be obtained. Taking metal smelting enterprises as an example, the frequency of the high temperature abnormality-heatstroke cell of the matrix may be 300, indicating that there are 300 cases of both high temperature abnormality records and diagnosis of heatstroke among all employees; the frequency of the dust abnormality-pneumoconiosis cell may be 150, indicating that there are 150 cases of both dust abnormality records and pneumoconiosis diagnosis within 10 years. The frequency matrix intuitively presents the frequency of simultaneous occurrence of each type of abnormality and the corresponding occupational disease results, and is an important data basis for further examining the strength of the correlation between the two. Generally speaking, the higher the frequency, the more common the co-occurrence of a certain abnormality and a certain occupational disease, the greater the correlation may be, and it should be paid special attention to.

[0092] S702, extracting the correlation coefficient between the detection index classification value and the occupational disease incidence rate in the abnormal type-occupational disease type matrix; Specifically, after generating the frequency matrix of abnormal type-occupational disease type matrix, the intelligent occupational health detection system needs to further extract the correlation coefficient between the detection index classification value and the occupational disease incidence rate in the matrix. The core purpose of correlation coefficient extraction is to quantitatively examine the correlation strength between the different classifications of each type of abnormal detection index and the corresponding occupational disease incidence rate, thereby revealing the inherent connection between the increased degree of abnormality and the increased risk of occupational diseases.

[0093] In specific implementation, each row of the frequency matrix should be focused on, and the correlation between the different graded values ​​of each detection index in the abnormal type corresponding to the row and the incidence rate of the corresponding occupational disease on the column side should be examined. Taking the high temperature abnormality-heatstroke matrix row as an example, the Spearman rank correlation coefficient between the employee dust concentration detection value (such as level 4: <0.5mg / m³, 0.5-1mg / m³, 1-2mg / m³, ≥2mg / m³) and the incidence rate of heatstroke can be extracted to quantitatively judge the same direction change trend of dust concentration and heatstroke risk; the Gamma correlation coefficient between the noise detection value (such as level 3: <80 decibels, 80-90 decibels, ≥90 decibels) and the incidence rate of heatstroke can also be calculated to examine the impact of increased noise levels on the risk of heatstroke. Similarly, for other rows of the matrix such as dust abnormality, noise abnormality, and toxic substance abnormality, different graded values ​​of the corresponding detection indicators should also be selected in a targeted manner to examine their equal-interval Pearson correlation, graded Spearman rank correlation or Gamma correlation with the incidence rate of occupational diseases on the column side.

[0094] During the extraction process, attention should be paid to the following key issues. First, it is necessary to properly classify the continuous values ​​of the detection indicators. Actual detection data are usually continuous variables, which need to be converted into ordered categorical variables before they can be included in the matrix calculation. The classification standard should be formulated under the guidance of occupational health professional knowledge, and strive to reflect the qualitative differences of different abnormal levels, but it should not be too fine to result in insufficient sample size. Second, it is necessary to choose the appropriate type of correlation coefficient. Pearson correlation is applicable to situations where row and column variables are linearly related and close to normal distribution. Spearman rank correlation and Gamma correlation do not need to meet these prerequisites, and are more suitable for situations where variables are ordered classifications and have fewer ranks. It should be carefully selected according to the nature and distribution characteristics of the data. Third, it is necessary to distinguish between unidirectional correlation and reverse correlation. A positive correlation coefficient indicates that the increased degree of abnormality is positively correlated with the increased risk of occupational diseases, and a negative correlation indicates a negative correlation. Abnormal negative correlations should be interpreted with caution to control the influence of confounding factors.

[0095] By systematically extracting the above correlations, a series of correlation coefficients reflecting the intrinsic connection between the classification of abnormal detection indicators and the incidence of occupational diseases can be obtained. Taking metal smelting enterprises as an example, the Spearman rank correlation coefficient between the 4-level classification of high temperature detection values ​​and the incidence of heat stroke may reach 0.8, indicating that the risk of heat stroke increases significantly with the ambient temperature from <28℃ to ≥35℃; the Gamma correlation coefficient between the 3-level classification of noise detection values ​​and the incidence of heat stroke may be 0.6, indicating that the risk of heat stroke increases synchronously to a certain extent when the noise increases from <80 decibels to ≥90 decibels. The correlation coefficient matrix makes the dose-response relationship between the classification of detection indicators and the incidence of occupational diseases clear at a glance. Which abnormal levels are increased and the risk of occupational diseases increases sharply, and which abnormalities are aggravated and have no obvious correlation with occupational diseases. This can be determined by comparing the positive and negative and size of the correlation coefficient. This provides an important basis for making targeted prevention and control measures.

[0096] S703, performing a chi-square test comparison based on the correlation coefficient and the frequency moment to obtain a correlation coefficient matrix of the correlation strength between abnormalities and occupational diseases; Specifically, after extracting the correlation coefficient between the classification value of the detection index and the incidence rate of occupational diseases, the intelligent occupational health detection system needs to perform a chi-square test comparison based on the obtained correlation coefficient and frequency matrix, and finally obtain the correlation coefficient matrix of the correlation strength between abnormalities and occupational diseases. The core purpose of conducting a chi-square test comparison is to further determine whether the correlation coefficient reflects the strength of the correlation between abnormalities and occupational diseases. It excludes purely accidental false correlations and ensures that subsequent management and control decisions are based on reliable correlations.

[0097] In the specific implementation, for each cell of the correlation coefficient matrix, it should be examined whether the co-occurrence frequency of the abnormal type and the occupational disease type corresponding to the cell in the frequency matrix significantly deviates from the random distribution. Taking the high temperature abnormality-heatstroke correlation coefficient as an example, if the Spearman rank correlation coefficient between the high temperature detection grade value and the heat stroke incidence rate is as high as 0.8, it is necessary to determine whether the co-occurrence frequency 300 in the frequency matrix of the two is significantly higher than the expected frequency under random distribution. The specific approach is to use the total frequency of high temperature abnormality, the total frequency of heatstroke, and the total number of employees as marginal degrees, calculate the expected co-occurrence frequency of the two under independent conditions, and then substitute the difference between the actual frequency 300 and the expected frequency into the chi-square formula to test the significance of the association. If the chi-square value is larger and the P value is smaller, it means that the actual co-occurrence frequency is significantly higher than the random distribution, and the correlation coefficient reflects a real dose-response relationship, which deserves special attention; on the contrary, if the chi-square value is small and the P value is large, it indicates that the co-occurrence frequency does not deviate significantly from the random distribution, and the correlation reflected by the correlation coefficient may be due to chance, and it needs to be treated with caution. Similarly, similar chi-square tests are needed to compare other abnormality types such as noise abnormality, dust abnormality and related occupational disease types such as noise-induced deafness and pneumoconiosis to systematically identify the statistical significance of the correlation coefficient.

[0098] In the comparison process, the following key aspects should be emphasized. First, the random distribution should be accurately defined. The total frequency of occurrence of a certain abnormality type and a certain occupational disease type is determined. The key is to reasonably estimate the expected probability of the two occurring at the same time under independent conditions based on the total number of employees. This expected probability is often very low, and multiplying it by the total number of employees is the expected co-occurrence frequency. Second, it is necessary to select an appropriate form of chi-square test. When both abnormalities and occupational diseases are binary variables, a four-cell chi-square test should be used; when at least one of the two is a multi-classified ordered variable, a linear trend chi-square test should be used to examine the significance of the overall linear association. Third, the professional significance of the association should be clarified. The professional significance of statistically significant associations must also withstand clinical and epidemiological verification. In the case where the statistical test results are inconsistent with previous cognition, the reasons should be carefully analyzed, and prospective cohort studies should be conducted to provide evidence when necessary.

[0099] By systematically carrying out the above chi-square test comparison, a correlation coefficient matrix that comprehensively reflects the statistical significance of the correlation strength between various abnormalities and various occupational diseases can be obtained. Taking metal smelting enterprises as an example, the chi-square value corresponding to the high temperature abnormality-heatstroke correlation coefficient of 0.8 may reach 78.5, and the P value is much less than 0.001, indicating that the correlation between the two is indeed not accidental. For every step increase in the degree of abnormality, the risk of heatstroke will increase significantly by an order of magnitude; the chi-square value corresponding to the noise abnormality-heatstroke correlation coefficient of 0.6 may be only 8.3, and the P value is 0.07, indicating that although the association between noise and heatstroke cannot be ignored, the statistical significance is not sufficient, and more epidemiological evidence is needed to support it. The correlation coefficient matrix of the strength of the association between abnormalities and occupational diseases extracts a dose-response relationship with clear statistical significance from the massive abnormal detection data and occupational disease result records, providing a reliable quantitative basis for the priority sorting of limited prevention and control resources.

[0100] S704, performing fusion data analysis based on the correlation coefficient matrix and the frequency matrix to obtain correlation data.

[0101] Specifically, after obtaining the correlation coefficient matrix of the strength of association between abnormalities and occupational diseases, the intelligent occupational health detection system must further perform fusion data analysis based on the correlation coefficient matrix and the aforementioned frequency matrix, and finally obtain correlation data that fully reflects the law of association between abnormalities and occupational diseases. The core purpose of conducting fusion analysis is to make a comprehensive judgment on the intrinsic connection between abnormalities and occupational diseases from multiple dimensions, avoid the one-sidedness of a single perspective, and panoramically depict the correlation trajectory between the two from occurrence to development, so as to provide a three-dimensional dynamic decision-making basis for subsequent graded warning and hierarchical control.

[0102] In specific implementation, the information on the strength of association provided by the correlation coefficient matrix and the information on the distribution law reflected by the frequency matrix should be fully utilized to conduct an overall investigation of the evolution of various abnormalities and occupational diseases in terms of both time and space. Taking high temperature abnormality as an example, in terms of time dimension, the trend of the correlation coefficient from small to large and the dynamic distribution of frequency in each grade can be combined to depict which occupational disease risks are more closely associated with high temperature abnormality from the early stage to the late stage and more serious; in terms of space dimension, the regional differences in correlation coefficients and the regional distribution of frequencies can be combined to analyze whether there are significant differences in the association patterns between high temperature abnormality and corresponding occupational diseases in different places and workshops. On the basis of systematically comparing the spatiotemporal differentiation characteristics of various indicators, further interactive impact analysis can be carried out to examine the common evolution of the correlation coefficients and frequencies of high temperature abnormality and other abnormal types in time and space, and to depict the dynamic changes of the spectrum of occupational diseases under different combinations. Similarly, other matrix rows such as dust abnormality and noise abnormality also need to carry out multi-dimensional fusion analysis that runs through time and space and interacts with cause and effect, so as to form a global understanding of the association between various abnormalities and occupational diseases.

[0103] During the analysis process, the following key issues should be emphasized. First, the time scale should be clarified. Reasonable observation periods should be set around the short, medium and long term to reflect the dynamic changes in the association between abnormalities and occupational diseases in each period, and to reveal the cumulative effect and time lag effect. Second, the spatial scale should be clarified. Different areas should be reasonably divided according to the actual situation of the enterprise site, the difference in the association between abnormalities and occupational diseases in various places and workshops should be revealed, and the spatial correlation and related hot spots should be found. The third is the interactive impact analysis. For abnormal combinations that may have interactions, the dynamic evolution of their association with occupational diseases should be systematically examined under the dual coordinates of time and space to reveal the etiology network.

[0104] By systematically conducting the above fusion data analysis, we can finally obtain a set of correlation data that comprehensively reflects the temporal and spatial correlation between various anomalies and various occupational diseases. Taking metal smelting enterprises as an example, in the time dimension, the correlation coefficient between high temperature anomalies and heat stroke may jump from 0.4 in the first year to 0.8 in the third year, and the frequency also changes from the sporadic stage to the frequent stage, indicating that the two are accelerating over time. Deterioration; in the spatial dimension, the correlation coefficient and frequency of the smelting workshop may be significantly higher than those of the raw material workshop, indicating that high temperature anomalies pose a greater threat to the health of employees in this area; high temperature anomalies may also have a significant interactive effect with the noise anomaly in the smelting workshop, and the correlation coefficient jumps from 0.6 when acting alone to 0.9 when acting in combination, and the frequency also shows a synergistic and frequent trend, indicating that the combination of the two types of anomalies will further worsen the risk of heat stroke. The correlation data dynamically presents the entire process of the spatiotemporal evolution of anomalies and occupational diseases from nothing to something, from light to heavy, and from sporadic to frequent from a multi-dimensional perspective, revealing the combination of abnormal types that should be focused on prevention and control in different places and at different times, and providing a targeted reference for precise policy implementation.

[0105] S503, performing detection analysis based on the correlation data to obtain a detection report.

[0106] Specifically, after revealing the intrinsic correlation between abnormal work factors and occupational disease results, the intelligent occupational health detection system needs to further conduct in-depth analysis of the correlation data to form an intuitive, complete, and readable detection report. The core purpose of this link is to transform the results of the correlation analysis into a decision-making basis and action guide for occupational disease prevention and control, and effectively guide enterprises to optimize the working environment and protect occupational health.

[0107] When implementing it, we should start from the actual needs of occupational health management and conduct a multi-angle and three-dimensional analysis of the correlation data. First, we should evaluate the contribution of abnormal work factors to the occurrence of occupational diseases in general. We can count the incidence rates of various abnormal occupational diseases, and calculate the percentage of abnormal population attributable risk (PAR%) based on this, and quantitatively evaluate the weight of different abnormal factors in the occurrence of occupational diseases. This analysis can clarify the key links of occupational disease prevention and control in enterprises and provide a macro decision-making basis for formulating rectification plans.

[0108] On the basis of macro analysis, the influencing characteristics of key abnormal factors should also be analyzed in depth from a local perspective. Taking high temperature abnormality as an example, we can further analyze the differences in the occurrence of febrile diseases under different temperature gradients, different exposure times, different labor intensities, etc., form a multi-dimensional cross-analysis matrix, and reveal the multi-factor effects of high temperature on disease. For example, dust abnormality can further analyze the differences in the risk of pneumoconiosis caused by different types of dust, different particle size distributions, and different work processes, and explore the key influencing links of dust hazards. These local analyses can provide detailed micro-level grasps for the targeted formulation of prevention and control measures.

[0109] On the other hand, the present application also provides an occupational health detection system, such as Figure 2 , the system comprises: Data acquisition module 1 is used to obtain the job type of the target to be tested, and determine the working environment detection plan and occupational disease detection plan according to the job type; Working environment detection module 2, used to detect the target to be detected according to the working environment detection scheme, and obtain working environment detection data; Occupational disease detection module 3, used to detect the target to be detected according to the working environment detection plan to obtain occupational disease detection data; The abnormal data detection module 4 is used to determine the working environment detection threshold according to the working environment detection data, and determine the working abnormal detection data exceeding the working environment detection threshold in the working environment detection data according to the working environment detection data and the working environment detection threshold; The detection and analysis module 5 is used to perform detection and analysis based on the work abnormality detection data and the occupational disease detection data to obtain a detection report.

[0110] Please refer to Figure 3 The application also discloses an electronic device. Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0111] The communication bus 302 is used to realize the connection and communication between these components.

[0112] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0113] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0114] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field~Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0115] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read~Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally be at least one storage system located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program of an occupational health detection method.

[0116] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program storing the road assessment method in the memory 305. When executed by one or more processors 301, the electronic device 300 executes one or more methods in the above-mentioned embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application. In the above embodiments, the description of each embodiment has its own emphasis. For the parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0117] In the several implementations provided in this application, it should be understood that the disclosed system can be implemented in other ways. For example, the system embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of the system or unit can be electrical or other forms.

[0118] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0119] The present application also provides a computer storage medium that can store multiple instructions, which are suitable for being loaded and executed by a processor as described above. Figure 1 The road assessment method of the embodiment shown in the figure can be found in the specific implementation process. Figure 1 The specific description of the illustrated embodiment will not be repeated here.

[0120] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0121] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0122] The above are only exemplary embodiments of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0123] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. An occupational health detection method, characterized in that: The method comprises: Obtaining the job type of the target to be tested, and determining a work environment testing plan and an occupational disease testing plan based on the job type; Detect the target to be detected according to the working environment detection scheme to obtain working environment detection data; Detecting the target to be detected according to the working environment detection scheme to obtain occupational disease detection data; Determine a working environment detection threshold according to the working environment detection data, and determine working abnormality detection data in the working environment detection data that exceeds the working environment detection threshold according to the working environment detection data and the working environment detection threshold; Detection and analysis are performed based on the work abnormality detection data and the occupational disease detection data to obtain a detection report.

2. The method according to claim 1, characterized in that: Determining a work environment detection plan and an occupational disease detection plan based on the type of operation includes: Identify occupational disease hazard factors according to the job type to obtain target occupational disease hazard factors; Determine the objects that need to be tested in the workplace according to the target occupational disease hazard factors; Planning the working environment detection scheme according to the detection object; According to the target occupational disease hazard factors, the target occupational disease type is determined, and the occupational detection program is planned according to the target occupational disease type.

3. The method according to claim 1, characterized in that Determining the working environment detection threshold according to the working environment detection scheme includes: Sorting out the key indicator information and detection point information data in the working environment detection plan, and determining the detection indicator limit value of each detection point according to the key indicator information; The detection index limit value of each detection point is adjusted according to the detection point information data to obtain the working environment detection threshold value.

4. The method according to claim 3, characterized in that The step of adjusting the detection index limit of each detection point according to the detection point information data to obtain the working environment detection threshold comprises: Sorting out the detection point information data to obtain detection point key data, and performing heterogeneity analysis based on the detection point key data to obtain heterogeneous data between various detection points; The detection index limit of each detection point is adjusted according to the heterogeneity data to obtain the working environment detection threshold.

5. The method according to claim 1, characterized in that The detection and analysis is performed based on the work abnormality detection data and the occupational disease detection data to obtain a detection report, including: Classifying the work abnormality detection data to obtain work abnormality detection classification data; Analyzing the correlation between the work abnormality detection classification data and the occupational disease detection data to obtain correlation data; Detection analysis is performed based on the correlation data to obtain the detection report.

6. The method according to claim 5, characterized in that The analyzing the correlation between the work abnormality detection classification data and the occupational disease detection data to obtain correlation data includes: Matching the work abnormality detection classification data with the occupational disease detection data to obtain an abnormality type-occupational disease type matrix; A correlation analysis is performed based on the abnormality type-occupational disease type matrix to obtain the correlation data.

7. The method according to claim 6, characterized in that The correlation analysis is performed based on the abnormality type-occupational disease type matrix to obtain the correlation data, including: Calculating the frequency of each cell in the abnormality type-occupational disease type matrix to generate a frequency matrix; Extracting the correlation coefficient between the detection index classification value and the occupational disease incidence rate in the abnormal type-occupational disease type matrix; Perform a chi-square test comparison based on the correlation coefficient and the frequency moment to obtain a correlation coefficient matrix of the strength of association between abnormalities and occupational diseases; The correlation data is obtained by performing fusion data analysis based on the correlation coefficient matrix and the frequency matrix.

8. An occupational health detection system, characterized in that: The system comprises: A data acquisition module is used to obtain the operation type of the target to be tested, and determine the working environment detection plan and the occupational disease detection plan according to the operation type; A working environment detection module, used to detect the target to be detected according to the working environment detection scheme to obtain working environment detection data; An occupational disease detection module, used to detect the target to be detected according to the working environment detection scheme to obtain occupational disease detection data; an abnormal data detection module, used to determine a working environment detection threshold according to the working environment detection data, and determine working abnormal detection data exceeding the working environment detection threshold in the working environment detection data according to the working environment detection data and the working environment detection threshold; The detection and analysis module is used to perform detection and analysis based on the work abnormality detection data and the occupational disease detection data to obtain a detection report.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes a processor, a memory and a transceiver, the memory is used to store instructions, the transceiver is used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method according to any one of claims 1 to 7.

Images