A method and system for industrial health and safety risk data assessment

Abstract

This invention discloses an industrial data security risk assessment method and system, relating to the technical field of industrial risk. By classifying sick leave reasons and constructing a set of disease types, and combining attendance data, a contagious disease risk index (Cfxs) is generated. This index helps enterprises quickly assess the potential risks of employee sick leave and infectious diseases, providing a basis for targeted preventative measures. Time series analysis is used to further evaluate the impact of different sick leave types on the contagious disease risk index, obtaining a correlation coefficient (Gxxs). Preliminary health screening using this correlation coefficient enables dynamic monitoring of employee health status within the industrial park and early identification of potential health abnormalities. When abnormalities occur, a timely regional restriction order is issued.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial risks, and in particular to a method and system for industrial health and safety risk data assessment. Background Art

[0002] Although the current health and safety monitoring of industrial parks has relied on data analysis for preliminary management, there are still obvious shortcomings and deficiencies. Existing methods usually rely too much on the monitoring of a single health indicator and lack a detailed analysis of the reasons for sick leave and the type of disease, resulting in a lag and inaccuracy in the judgment of infectious disease risks. This method may cause the spread of the disease to expand without preventive measures, especially when there is frequent movement between multiple departments or regions, and the potential risk of cross-infection is difficult to control. In addition, when infectious diseases are discovered, the monitoring system often lacks an effective emergency response mechanism, such as the precise division of regional control and protective measures. Therefore, it is difficult for traditional means to accurately assess the risk of the spread of infectious diseases in the early stages, resulting in potential safety hazards that are difficult to discover in time and take corresponding prevention and control measures. Summary of the invention

[0003] In view of the deficiencies in the prior art, the present invention provides a method and system for industrial health and safety risk data assessment, which solves the problems in the above-mentioned background technology.

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: A method for industrial health and safety risk data assessment, comprising the following steps:

[0005] S1. According to the attendance information of each employee in the industrial park provided by the human resources department, relevant attendance data information is obtained, and based on the relevant attendance data information, the reasons for employees taking leave are tracked, and the relevant reason difference data information is obtained. After dimensionless processing, a personnel statistical data set is generated;

[0006] S2. Extract the relevant sick leave reasons according to the relevant reason difference data information in the personnel statistical data set, and classify the relevant sick leave reasons to obtain the disease type set, and combine with the relevant attendance data information to construct the infection risk index Cfxs;

[0007] S3. Use the time series analysis method to analyze the impact of the corresponding type of sick leave on the infectious risk index Cfxs to obtain the correlation coefficient Gxxs, and perform preliminary health screening operations based on the correlation coefficient Gxxs value. If abnormal results are found, issue an area reduction instruction;

[0008] S4, after receiving the regional reduction instruction, randomly set n groups of cluster centers, and combine with the correlation coefficient Gxxs obtained in S3, after iterative operation, to determine the number of departments in each cluster center, and according to the number of departments in each cluster center, re-determine the overall correlation coefficient Gxx of the corresponding abnormal disease in each cluster center;

[0009] S5. Based on the overall correlation coefficient Gxx of the corresponding abnormal diseases in each cluster center obtained in S4, the entire industrial park is divided into safety areas, and corresponding prevention and control measures are taken according to the division results.

[0010] Preferably, S1 specifically includes:

[0011] S11. Collect relevant attendance data information of all employees in the industrial park from the human resources department in advance, wherein the relevant attendance data information includes the attendance times, lateness times, early departure times and leave times of each employee in the industrial park, and is accompanied by the employee ID, name, position and department of each employee; use statistical algorithms to obtain the total number of leave requests Zs;

[0012] S12. Based on the relevant attendance data information collected in S11, the reasons for the employees taking leave are tracked and recorded to obtain the difference data information of the relevant reasons for the employees taking leave, wherein the difference data information of the relevant reasons includes the reasons for the leave of different employees taking leave; using statistical algorithms, the number of people taking leave Qs under different types of disease states, the incidence of different types of disease states and the number of people who requested sick leave, Bqi;

[0013] S13. Pre-process the relevant attendance data information and relevant cause difference data information to generate a personnel statistical data set, and use dimensionless technology to convert data of different dimensions in the personnel statistical data set to the same scale range.

[0014] Preferably, S2 specifically includes:

[0015] S21. Extracting relevant sick leave reasons according to relevant reason difference data information in the personnel statistical data set, and classifying the relevant sick leave reasons to obtain a disease type set, wherein the disease type set includes different types of diseases;

[0016] S22. According to the disease type set, calculate the ratio of the number of people who take leave due to different types of diseases to the total number of people who take leave, Jqs, which can be obtained by: ;

[0017] S23. During the operation of the industrial park, the working status of employees is monitored in real time, and relevant work data is obtained, wherein the relevant work data includes the number of contacts between each employee Jccs and the duration of each contact Jsc; based on the relevant work data, a contact factor Jcyz is obtained, wherein the contact factor Jcyz is obtained by the following formula:

[0018] ;

[0019] In the formula, m represents the total number of employees, i=1, 2, 3, ..., m, It is represented as the number of contacts of the ith employee, and T is the monitoring period.

[0020] Preferably, S2 also includes:

[0021] S24. Based on S22 and S23, construct the infection risk index Cfxs under different types of disease states, which can be obtained in the following way:

[0022] ;

[0023] In the formula, It is expressed as the ratio of the number of people who take leave due to the j-th type of disease to the total number of people who take leave. It is represented by the incidence rate of the j-th type of disease, and Bqi is represented by the number of people who take sick leave.

[0024] Preferably, S3 specifically includes:

[0025] S31. Use the time series analysis method to analyze the influence of the corresponding type of sick leave on the infection risk index Cfxs, so as to obtain the correlation coefficient Gxxs under the corresponding type of sick leave state, which is obtained in the following way:

[0026] ;

[0027] In the formula, It is expressed as the ratio of the number of people taking sick leave of the corresponding type in the k-th analysis time series to the number of people taking sick leave. It is expressed as the infection risk index of the corresponding disease state in the k-th analysis time series, It is expressed as the standard deviation of the proportion of the number of people taking sick leave under the corresponding type of sick leave to the number of people taking sick leave. It is expressed as the standard deviation of the infection risk index under the corresponding type of disease state, Expressed as and The covariance of

[0028] S32. Preset a safety threshold W, and compare the correlation coefficient Gxxs under the corresponding type of sick leave status with the safety threshold W to perform a preliminary health screening operation to determine whether there is a risk of transmission of the corresponding disease in the current industrial park. The specific determination content is as follows:

[0029] If the correlation coefficient Gxxs exceeds the safety threshold W, it will be judged that there is a risk of the spread of the corresponding disease in the current industrial park, and an area reduction instruction will be issued to the outside, and the corresponding disease will be marked as an abnormal disease;

[0030] If the correlation coefficient Gxxs does not exceed the safety threshold W, it will be judged that there is no risk of transmission of the corresponding disease in the current industrial park.

[0031] Preferably, S4 specifically includes:

[0032] S41. Randomly set n groups of cluster centers, and combine with the abnormal diseases obtained in S32 to perform correlation analysis on the abnormal diseases in various departments in the industrial park, and calculate the correlation coefficient Gxxs corresponding to the corresponding abnormal diseases in each department according to the method of obtaining the correlation coefficient Gxxs under the corresponding type of sick leave status; and preliminarily distribute the correlation coefficient Gxxs corresponding to the corresponding abnormal diseases in each department to each group of cluster centers to calculate the distance from the correlation coefficient Gxxs corresponding to the corresponding abnormal diseases in each department to all cluster centers, wherein each group of cluster centers is represented by the average correlation coefficient corresponding to the corresponding abnormal diseases in each cluster, and the average correlation coefficient corresponding to the corresponding abnormal diseases in each cluster is preliminarily randomly set;

[0033] S42. Use the Euclidean distance algorithm to calculate the distance from the correlation coefficient Gxxs corresponding to the abnormal disease in each department to the center of all clusters, and record it as the distance Jz, which is specifically obtained by the following method:

[0034] ;

[0035] In the formula, Expressed as The correlation coefficient corresponding to the g-th abnormal disease in a department, It is expressed as the correlation coefficient corresponding to the g-th abnormal disease in the center of the R-th cluster.

[0036] Preferably, S4 also includes:

[0037] S43. According to the calculated distances from the correlation coefficients Gxxs corresponding to the corresponding abnormal diseases in each department to all cluster centers, the correlation coefficients Gxxs corresponding to the corresponding abnormal diseases in each department are assigned to the nearest cluster center to calculate the mean value of the correlation coefficients Gxxs corresponding to the corresponding abnormal diseases in all departments in each cluster, and the mean value of the correlation coefficients Gxxs corresponding to the corresponding abnormal diseases in all departments in each cluster currently calculated is used as the new cluster center.

[0038] S44, repeating steps S41, S42 and S43 until the preset n groups of cluster centers no longer change, stopping the repetitive operation, obtaining the final cluster center, and finally determining the corresponding departments and the number of departments in each cluster center.

[0039] Preferably, S4 also includes:

[0040] S45. According to the corresponding departments and the number of departments in each cluster center, the overall correlation coefficient Gxx of the corresponding abnormal diseases in each cluster center is re-determined. The specific acquisition method is as follows:

[0041] ;

[0042] Where P represents the number of departments in each cluster center, c=1, 2, 3, ..., P, It is expressed as the correlation coefficient corresponding to the corresponding abnormal disease in the cth department in each cluster center.

[0043] Preferably, S5 specifically includes:

[0044] S51, comparing the overall correlation coefficients Gxx of the corresponding abnormal diseases in each cluster center, to screen out the value with the largest value again from the overall correlation coefficients Gxx of the corresponding abnormal diseases in the n groups of cluster centers, and regard the cluster center corresponding to the overall correlation coefficient Gxx with the largest value as a dangerous area, so as to divide the entire industrial park into safety areas;

[0045] S52. Take corresponding prevention and control measures for dangerous areas. The specific prevention and control measures are: immediately require employees to wear personal protective equipment, including masks and gloves, and replace them regularly. Give priority to vaccinating employees in dangerous areas to establish a herd immunity barrier. At the same time, carry out disinfection tasks regularly, and adopt staggered get off work and rest hours for dangerous areas.

[0046] A system for industrial health and safety risk data assessment, including a data acquisition module, a transmission risk analysis module, an impact module, a regional property analysis module and a management module;

[0047] The data collection module is used to obtain relevant attendance data information based on the attendance status of each employee in the industrial park provided by the human resources department, and based on the relevant attendance data information, track the reasons for employees taking leave, and obtain relevant reason difference data information, and generate a personnel statistical data set after dimensionless processing;

[0048] The transmission risk analysis module is used to extract relevant sick leave reasons based on the relevant reason difference data information in the personnel statistical data set, and classify the relevant sick leave reasons to obtain a disease type set, and combine the relevant attendance data information to construct a transmission risk index Cfxs;

[0049] The impact module is used to analyze the impact of the corresponding type of sick leave on the infectious risk index Cfxs by using a time series analysis method to obtain a correlation coefficient Gxxs, and based on the value of the correlation coefficient Gxxs, perform a preliminary health screening operation. If an abnormal result is screened out, an area reduction instruction is issued;

[0050] The regional property analysis module is used to randomly set n groups of cluster centers after receiving the regional reduction instruction, and combine the correlation coefficient Gxxs obtained in S3 to determine the number of departments in each cluster center after iterative operation, and re-determine the overall correlation coefficient Gxx of the corresponding abnormal disease in each cluster center according to the number of departments in each cluster center;

[0051] The management module is used to divide the entire industrial park into safety areas according to the overall correlation coefficient Gxx of the corresponding abnormal diseases in each cluster center, and take corresponding prevention and control measures according to the division results.

[0052] The present invention provides a method and system for industrial health and safety risk data assessment, which has the following beneficial effects:

[0053] (1) By collecting attendance information and sick leave reasons from S1 and performing dimensionless processing on these data, a set of personnel statistics data was generated. This step can not only help with salary calculations but also prepare for the analysis of potential high-risk diseases. In S2, by classifying sick leave reasons and constructing a set of disease types, the infectious risk index Cfxs was generated in combination with attendance data. The construction of this index helps companies quickly assess the potential risks of employee sick leave and infectious diseases, and provides companies with a decision-making basis for targeted preventive measures. By using time series analysis methods, the impact of different types of sick leave on the infectious risk index is further evaluated to obtain the correlation coefficient Gxxs. Through the preliminary health screening of the correlation coefficient, the health status of employees in the park can be dynamically monitored and potential health abnormalities can be identified early. When abnormal conditions occur, regional restrictions are issued in a timely manner to reduce the further spread of the disease. In S4, by randomly setting the cluster center, combining the iterative algorithm to determine the cluster structure within the department, and recalculating the overall correlation coefficient Gxx of abnormal diseases in each cluster center, this model based on cluster analysis can effectively divide areas with infectious risks and provide customized prevention and control suggestions for the risk levels of different departments to ensure that prevention and control measures are more accurate. In step S5, by dividing the industrial park into safety areas based on the overall correlation coefficient Gxx, high-risk areas can be quickly divided, providing enterprises with flexible prevention and control measures. This method can further enhance the emergency response capabilities of the industrial park to infectious diseases and reduce potential losses. Overall, this method shows a high degree of scientificity and pertinence in disease monitoring and risk assessment, effectively improves the health and safety management capabilities of the industrial park, and provides enterprises with a more intelligent and automated risk prevention system.

[0054] (2) S21 forms a set of disease types to deeply analyze the distribution of various diseases in the industrial park and the potential for disease transmission. This refined data processing enables enterprises to timely determine the prevalence of certain diseases. S22 further calculates the proportion of the number of people taking leave under different disease conditions to the total number of people taking leave Jqs, and accurately analyzes the distribution of different diseases among employees. This classification and proportion calculation method helps managers of industrial parks to clearly understand the distribution of various diseases in the park and quickly adjust disease prevention and control strategies based on this information. S23 dynamically evaluates the frequency and intensity of contact between employees through the contact factor Jcyz. This real-time monitoring method enables enterprises to understand the interaction between employees, especially during the peak period of epidemics, and can accurately identify employee groups with high contact risks, providing an important basis for the prevention and control of infectious diseases.

[0055] (3) S31 uses the time series analysis method to analyze the impact of the corresponding type of sick leave on the infectious risk index Cfxs, and extracts the correlation coefficient Gxxs under the corresponding type of sick leave. This method establishes a dynamic risk assessment system by considering factors such as the proportion of sick leave in the time series, the infectious risk index and its covariance. This enables the park management to monitor the changing trend of infectious disease risks in real time and effectively prevent potential risks from spreading rapidly in the park. And through the value of the correlation coefficient Gxxs, it can quickly determine whether there is a risk of transmission of the corresponding disease in the park. This intelligent health screening mechanism can automatically issue a regional reduction instruction and mark abnormal diseases when the infectious risk exceeds the threshold, which maximizes the level of health management automation in the park and reduces the possibility of human judgment errors.

[0056] (4) According to the Euclidean distance algorithm, the correlation coefficient Gxxs of the corresponding abnormal diseases in each department and the distance Jz between the cluster center are calculated, so that the disease risks of each department can be reasonably allocated to the nearest cluster center. This analysis method can help the park more accurately determine the correlation between the disease transmission risks of different departments, so as to formulate more targeted risk prevention and control measures. Through continuous iterative calculations, until the correlation coefficient of the cluster center no longer changes, the departments and their numbers in each cluster center are finally determined. This iterative clustering process ensures that the regional division of disease transmission risks is more accurate and ensures the stability and rationality of the risk area. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 A schematic diagram of a method flow for industrial health and safety risk data assessment according to the present invention;

[0058] Figure 2 The present invention is a system block diagram for industrial health and safety risk data assessment. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] Example 1

[0061] See also Figure 1 The present invention provides a method for industrial health and safety risk data assessment, comprising the following steps:

[0062] S1. According to the attendance information of each employee in the industrial park provided by the human resources department, relevant attendance data information is obtained, and based on the relevant attendance data information, the reasons for employees taking leave are tracked, and the relevant reason difference data information is obtained. After dimensionless processing, a personnel statistical data set is generated;

[0063] S2. Extract the relevant sick leave reasons according to the relevant reason difference data information in the personnel statistical data set, and classify the relevant sick leave reasons to obtain the disease type set, and combine with the relevant attendance data information to construct the infection risk index Cfxs;

[0064] S3. Use the time series analysis method to analyze the impact of the corresponding type of sick leave on the infectious risk index Cfxs to obtain the correlation coefficient Gxxs, and perform preliminary health screening operations based on the correlation coefficient Gxxs value. If abnormal results are found, issue an area reduction instruction;

[0065] S4, after receiving the regional reduction instruction, randomly set n groups of cluster centers, and combine with the correlation coefficient Gxxs obtained in S3, after iterative operation, to determine the number of departments in each cluster center, and according to the number of departments in each cluster center, re-determine the overall correlation coefficient Gxx of the corresponding abnormal disease in each cluster center;

[0066] S5. Based on the overall correlation coefficient Gxx of the corresponding abnormal diseases in each cluster center obtained in S4, the entire industrial park is divided into safety areas, and corresponding prevention and control measures are taken according to the division results.

[0067] In this embodiment, in step S1, the employee attendance data provided by the human resources department is combined with the data processing of the reasons for leave and the differences in the reasons, which can not only realize the multi-faceted grasp of attendance information, but also standardize the data through the dimensionless processing method to generate a universal set of personnel statistical data. This process is likely to improve the accuracy and adaptability of data analysis, and can provide reliable data support for subsequent risk assessment. The classification of sick leave reasons and the construction of the infectious risk index Cfxs in step S2 enable risk assessment to be refined based on specific sick leave types and disease characteristics. This not only quantifies the potential risks of infectious diseases, but also divides risks according to specific disease categories, which helps prevent the spread of highly contagious diseases in the park. The time series analysis method is used to evaluate the impact of sick leave types on the infectious risk index Cfxs. By calculating the correlation coefficient Gxxs, the infectious risk can be dynamically tracked and predicted. This operation can detect abnormal health conditions in advance, and by issuing regional reduction instructions, quickly respond to the potential risks of infectious disease outbreaks, and improve the timeliness and accuracy of health monitoring. Step S4 accurately divides disease risks among multiple departments through the setting of cluster centers and iterative optimization of the correlation coefficient Gxx, ensuring that prevention and control measures can be accurately implemented. The abnormal disease correlation coefficient in each cluster center helps to identify high-risk areas and adjust the department size and layout accordingly, further avoiding the interference of a single prevention and control measure on the entire park and improving the stability of park operations. Finally, step S5 divides the park's safety areas based on the aforementioned overall correlation coefficient Gxx, making the prevention and control measures in different areas more targeted. This division method optimizes resource allocation and management models, minimizes the risk of infectious disease transmission, and ensures production efficiency and employee health and safety.

[0068] Example 2

[0069] Please refer to Figure 1 , specifically: S1 specifically includes:

[0070] S11. Collect relevant attendance data information of all employees in the industrial park from the human resources department in advance, wherein the relevant attendance data information includes the attendance times, lateness times, early departure times and leave times of each employee in the industrial park, and is accompanied by the employee ID, name, position and department of each employee; use statistical algorithms to obtain the total number of leave requests Zs;

[0071] S12. Based on the relevant attendance data information collected in S11, the reasons for the employees who take leave are tracked and recorded to obtain the relevant reasons for the employees who take leave. The relevant reasons for the difference data information include the reasons for the leave of different employees who take leave; the reasons for the leave include but are not limited to sick leave, personal leave and absence without reason; using statistical algorithms, obtain the number of leavers Qs under different types of disease conditions, the incidence of different types of disease conditions and the number of people who requested sick leave, Bqi;

[0072] S13. Pre-process the relevant attendance data information and relevant cause difference data information to generate a personnel statistical data set, and use dimensionless technology to convert data of different dimensions in the personnel statistical data set to the same scale range.

[0073] In this embodiment, a multi-dimensional data foundation is established by combining the detailed data collected in advance by S11 with the personal information of employees. This operation ensures that the attendance of each employee can be effectively monitored, especially the tracking of the number of leave requests, which can further help managers to fully grasp the leave status of employees and improve the accuracy and coverage of data. Step S12 not only tracks all employees who take leave, but also carefully classifies the reasons for leave, covering multiple dimensions such as sick leave, personal leave and absence without reason. The number of leave requests, the incidence of different diseases and the number of sick leave obtained by statistical algorithms further deepen the monitoring of employee health status. By analyzing the number of leave requests and the incidence of different types of diseases, managers can quickly find out whether there are potential health risks in the park, further improving the effectiveness of early detection and prevention of diseases. In S13, the attendance data and the difference data of the reasons are dimensionlessly processed, and the data of different dimensions can be normalized and converted into data sets of the same scale range. This processing method eliminates the influence between different data dimensions, making subsequent data analysis more scientific and accurate. At the same time, the pre-processed personnel statistics data set provides a high-quality data foundation for subsequent risk assessment, effectively improving the efficiency and accuracy of data processing. Through the synergy of the above steps, the attendance and leave of employees in the industrial park can be monitored in a multi-faceted and detailed manner, especially in the analysis of sick leave reasons and disease types, which can provide an earlier and more accurate early warning mechanism for disease transmission risks, helping enterprises to take timely response measures to reduce the risk of infectious disease transmission.

[0074] Example 3

[0075] Please refer to Figure 1 , specifically: S2 specifically includes:

[0076] S21. Extracting relevant sick leave reasons according to relevant reason difference data information in the personnel statistical data set, and classifying the relevant sick leave reasons to obtain a disease type set, wherein the disease type set includes different types of diseases;

[0077] S22. According to the disease type set, calculate the ratio of the number of people who take leave due to different types of diseases to the total number of people who take leave, Jqs, which can be obtained by: ;

[0078] S23. During the operation of the industrial park, the working status of employees is monitored in real time, and relevant work data is obtained, wherein the relevant work data includes the number of contacts between each employee Jccs and the duration of each contact Jsc; based on the relevant work data, a contact factor Jcyz is obtained, wherein the contact factor Jcyz is obtained by the following formula:

[0079] ;

[0080] In the formula, m represents the total number of employees, i=1, 2, 3, ..., m, It is represented as the number of contacts of the ith employee, and T is the monitoring period.

[0081] S2 also includes:

[0082] S24. Based on S22 and S23, construct the infection risk index Cfxs under different types of disease states, which can be obtained in the following way:

[0083] ;

[0084] In the formula, It is expressed as the ratio of the number of people who take leave due to the j-th type of disease to the total number of people who take leave. It is represented by the incidence rate of the jth type of disease, Bqi is represented by the number of people who take sick leave, A healthy proportion.

[0085] The incidence of the different types of disease states mentioned above Refers to the proportion of people taking leave due to different types of illness to the total number of working employees;

[0086] In this embodiment, the reasons for sick leave are classified through step S21, and different types of diseases are extracted to form a set of disease types. The implementation of this step enables the enterprise to analyze the prevalence of each disease in detail; S22 further calculates the proportion of the number of people taking leave for different types of diseases to the total number of people taking leave, ensuring the accurate quantification of the impact of various diseases. By analyzing the proportion of each disease, the enterprise can clearly understand the impact of each disease on employee health and the operation of the industrial park, and then take targeted prevention and control measures for different diseases. In step S23, the working status of employees in the industrial park is monitored in real time, and the contact factor Jcyz is calculated. This real-time monitoring and calculation step effectively improves the dynamic assessment capability of the infection risk in the park; the introduction of the contact factor Jcyz can reflect the interaction of employees in the work environment, and then provide a basis for analyzing the potential pathways of disease transmission. This step can more intuitively assess the risk of disease transmission between employees and identify possible high-risk areas or groups in a timely manner. In step S24, based on key parameters such as the leave ratio Jqs of disease type, the incidence of sick leave and contact factors, the infectious risk index Cfxs is constructed. This infectious risk index takes into account multiple factors such as the incidence of the disease, the proportion of leavers and employee contact behavior, so that enterprises can more accurately assess the transmission risk of a certain type of disease. The introduction of this index provides an important decision-making basis for health management departments. When high-risk areas or high-risk groups are found, effective prevention and control measures can be taken quickly to further avoid the spread of the disease. In general, step S2 further improves the level of infectious disease risk assessment in industrial parks through real-time data monitoring, accurate disease classification and proportion analysis, combined with the construction of contact factors and infectious risk indexes. This multi-dimensional analysis method ensures that enterprises have a comprehensive grasp of the health status of employees, and can make effective health intervention measures in a timely manner, reduce the possibility of rapid spread of diseases in the park, and effectively ensure the healthy operation of the park.

[0087] It should be noted that the incidence of different types of disease states It is a factor that reflects the prevalent level of infectious diseases in the park. In the above formula of infectious risk index Cfxs under different types of disease states, the incidence rate under different types of disease states is divided by , the infectious disease risk index can be standardized to facilitate comparison between different regions. If the incidence of infectious diseases in a region is high, the risk index will be relatively high even if other factors are the same. Therefore, the incidence rate in the denominator can reflect relative risk rather than absolute risk; in areas with high incidence rates, although the leave rate or exposure risk may be high, the risk index may still be relatively low due to the prevalence of infectious diseases in the region. Dividing by the incidence rate can help identify the relative risk posed by employee leave data and exposure risk given the prevalence of infectious diseases. In other words, the incidence rate of infectious diseases affects the standardization of the risk index. The purpose of dividing by the incidence rate is to eliminate its interference with risk assessment in the context of high incidence rates, so as to more accurately reflect the relative risk posed by employee leave data and exposure risks. In areas with high incidence rates, the infectious disease risk index will be lower because the contribution of specific exposure and health data to the risk may be relatively small in the context of relatively high disease prevalence.

[0088] Example 4

[0089] Please refer to Figure 1 , specifically: S3 specifically includes:

[0090] S31. Use the time series analysis method to analyze the influence of the corresponding type of sick leave on the infection risk index Cfxs, so as to obtain the correlation coefficient Gxxs under the corresponding type of sick leave state, which is obtained in the following way:

[0091] ;

[0092] In the formula, It is expressed as the ratio of the number of people taking sick leave of the corresponding type in the k-th analysis time series to the number of people taking sick leave. It is expressed as the infection risk index of the corresponding disease state in the k-th analysis time series, It is expressed as the standard deviation of the proportion of the number of people taking sick leave under the corresponding type of sick leave to the number of people taking sick leave. It is expressed as the standard deviation of the infection risk index under the corresponding type of disease state, Expressed as and The covariance of

[0093] S32. Preset a safety threshold W, and compare the correlation coefficient Gxxs under the corresponding type of sick leave status with the safety threshold W to perform a preliminary health screening operation to determine whether there is a risk of transmission of the corresponding disease in the current industrial park. The specific determination content is as follows:

[0094] If the correlation coefficient Gxxs exceeds the safety threshold W, it will be judged that there is a risk of the spread of the corresponding disease in the current industrial park, and an area reduction instruction will be issued to the outside, and the corresponding disease will be marked as an abnormal disease;

[0095] If the correlation coefficient Gxxs does not exceed the safety threshold W, it will be judged that there is no risk of transmission of the corresponding disease in the current industrial park.

[0096] S4 specifically includes:

[0097] S41. Randomly set n groups of cluster centers, and combine with the abnormal diseases obtained in S32 to perform correlation analysis on the abnormal diseases in various departments in the industrial park, and calculate the correlation coefficient Gxxs corresponding to the corresponding abnormal diseases in each department according to the method of obtaining the correlation coefficient Gxxs under the corresponding type of sick leave status; and preliminarily distribute the correlation coefficient Gxxs corresponding to the corresponding abnormal diseases in each department to each group of cluster centers to calculate the distance from the correlation coefficient Gxxs corresponding to the corresponding abnormal diseases in each department to all cluster centers, wherein each group of cluster centers is represented by the average correlation coefficient corresponding to the corresponding abnormal diseases in each cluster, and the average correlation coefficient corresponding to the corresponding abnormal diseases in each cluster is preliminarily randomly set;

[0098] S42. Use the Euclidean distance algorithm to calculate the distance from the correlation coefficient Gxxs corresponding to the abnormal disease in each department to the center of all clusters, and record it as the distance Jz, which is specifically obtained by the following method:

[0099] ;

[0100] In the formula, Expressed as The correlation coefficient corresponding to the g-th abnormal disease in a department, It is represented as the correlation coefficient corresponding to the g-th abnormal disease in the center of the R-th cluster. It should be noted that It represents the numbers of all departments in the industrial park.

[0101] S4 also includes:

[0102] S43. According to the calculated distances from the correlation coefficients Gxxs corresponding to the corresponding abnormal diseases in each department to all cluster centers, the correlation coefficients Gxxs corresponding to the corresponding abnormal diseases in each department are assigned to the nearest cluster center to calculate the mean value of the correlation coefficients Gxxs corresponding to the corresponding abnormal diseases in all departments in each cluster, and the mean value of the correlation coefficients Gxxs corresponding to the corresponding abnormal diseases in all departments in each cluster currently calculated is used as the new cluster center.

[0103] S44, repeating steps S41, S42 and S43 until the preset n groups of cluster centers no longer change, stopping the repetitive operation, obtaining the final cluster center, and finally determining the corresponding departments and the number of departments in each cluster center.

[0104] In this embodiment, in S31, through the time series analysis method, combined with the impact of different types of sick leave on the infectious risk index Cfxs, the correlation coefficient Gxxs under the corresponding type of sick leave state is calculated. This calculation method based on the covariance between the proportion of sick leave and the infectious risk index can dynamically track the impact of sick leave at different time points on the risk of disease transmission, improve the ability to predict the trend of disease transmission, and enable managers to accurately grasp the temporal characteristics of disease transmission and discover potential risks early. S32 introduces the setting of the safety threshold W, and compares the calculated correlation coefficient Gxxs with the safety threshold. Once the correlation coefficient Gxxs exceeds the threshold, the system can immediately identify the potential disease transmission risk in the industrial park, issue a regional reduction instruction and mark it as an abnormal disease. This mechanism can not only quickly screen out potential disease transmission threats, but also ensure real-time monitoring and rapid response to abnormal diseases, effectively improving the disease prevention and control efficiency of the park. In step S4, by randomly setting n cluster centers, the distribution of abnormal diseases in various departments is analyzed in combination with the correlation coefficient Gxxs. The introduction of the Euclidean distance algorithm effectively calculates the distance between the correlation coefficient Gxxs of the corresponding abnormal disease in each department and the cluster center, and finally allocates the department to the nearest cluster center by minimizing the distance. This process not only realizes the reasonable division of the disease risk level of each department, but also dynamically adjusts the position of the cluster center to ensure that the correlation coefficient of the disease risk in each cluster is balanced, thereby forming a reasonable risk area division task;

[0105] In S43 and S44, the system continuously recalculates the mean of the correlation coefficient of all departments in the cluster through iterative operations, and uses it as the new cluster center until the cluster center no longer changes, and finally determines the department and number of departments in each cluster center. This dynamic iterative optimization process ensures the accuracy of the division, making the disease risk division of different areas in the industrial park more scientific and effective. By adjusting the cluster center position multiple times, managers can accurately identify each high-risk area and formulate corresponding prevention and control measures. The final determination of the cluster center and each department not only provides accurate disease risk area division for the safety management of the industrial park, but also can formulate corresponding prevention and control strategies for the specific risk level of each area, thereby effectively reducing the possibility of disease transmission and ensuring the healthy operation of the park. In summary, this method improves the monitoring accuracy of disease risks and realizes efficient and dynamic risk area division through time series analysis, calculation of correlation coefficients, setting of cluster centers and iterative optimization operations. This innovative method helps industrial parks to quickly identify disease transmission risks and take targeted prevention and control measures, thereby improving the overall health and safety management capabilities of the park as much as possible.

[0106] Example 5

[0107] Please refer to Figure 1 Specifically, S4 also includes:

[0108] S45. According to the corresponding departments and the number of departments in each cluster center, the overall correlation coefficient Gxx of the corresponding abnormal diseases in each cluster center is re-determined. The specific acquisition method is as follows:

[0109] ;

[0110] Where P represents the number of departments in each cluster center, c=1, 2, 3, ..., P, It is represented by the correlation coefficient corresponding to the corresponding abnormal disease in the cth department in each cluster center. It should be noted that It represents the numbers of all departments in the corresponding cluster center;

[0111] S5 specifically includes:

[0112] S51, comparing the overall correlation coefficients Gxx of the corresponding abnormal diseases in each cluster center, to screen out the value with the largest value again from the overall correlation coefficients Gxx of the corresponding abnormal diseases in the n groups of cluster centers, and regard the cluster center corresponding to the overall correlation coefficient Gxx with the largest value as a dangerous area, so as to divide the entire industrial park into safety areas;

[0113] S52. Take corresponding prevention and control measures for dangerous areas. The specific prevention and control measures are as follows: immediately require employees to wear personal protective equipment, including masks and gloves, and change them regularly. Prioritize vaccination for employees in dangerous areas, especially the promotion of vaccines for specific infectious diseases, so as to establish a group immunity barrier. At the same time, carry out disinfection tasks regularly, especially for equipment, door handles, stair handrails and other locations that employees frequently touch, increase the frequency of disinfection, and for dangerous areas, adopt staggered get off work and rest hours to reduce the gathering of high-density people, and reduce the risk of cross-infection by reducing the number of employees on site at the same time. For places with poor air circulation, strengthen ventilation measures or install air filtration equipment. In high-risk areas, ensure good ventilation conditions, and use high-efficiency air filters (HEPA) to purify the air when necessary to reduce the possibility of airborne pathogens.

[0114] In this embodiment, step S45 ensures accurate consideration of the number of departments in each cluster center by recalculating the overall correlation coefficient Gxx of the corresponding abnormal diseases in each cluster center. This method provides a more comprehensive assessment of the overall risk in each cluster center by integrating the disease correlation coefficients in each department. Through this optimized identification, it is possible to accurately determine which areas have a higher risk of infection and provide a scientific basis for subsequent prevention and control measures. Step S51 compares the overall correlation coefficient Gxx in each cluster center, screens out the area with the largest value, and identifies it as a dangerous area. This method ensures that the identification of dangerous areas is more accurate, so that targeted prevention and control measures can be taken. By marking the area with the greatest risk of infection as a dangerous area, efficient and centralized deployment of prevention and control resources can be further achieved. The prevention and control measures in step S52 cover all aspects from personal protection to environmental disinfection. Specific measures include requiring employees to wear personal protective equipment, priority vaccination, regular disinfection, and improved ventilation conditions. In particular, measures such as staggered get off work and rest, increased disinfection frequency, and optimized air circulation are taken in dangerous areas. These measures effectively reduce the risk of cross infection and further improve the comprehensive effect of prevention and control work. Through the above measures, the park not only helps prevent the spread of the disease, but also ensures the health and safety of employees and reduces production and operational losses caused by the disease.

[0115] Example 6

[0116] Please refer to Figure 2 ,Specifically: A system for industrial health and safety risk data assessment includes a data collection module, a ,propagation risk analysis module, an impact module, a regional property analysis module and a ,management module;

[0117] The data collection module is used to obtain relevant attendance data information based on the attendance status of each employee in the industrial park provided by the human resources department, and based on the relevant attendance data information, track the reasons for employees taking leave, and obtain relevant reason difference data information, and generate a personnel statistical data set after dimensionless processing;

[0118] The transmission risk analysis module is used to extract relevant sick leave reasons based on the relevant reason difference data information in the personnel statistical data set, and classify the relevant sick leave reasons to obtain a disease type set, and combine the relevant attendance data information to construct a transmission risk index Cfxs;

[0119] The impact module is used to analyze the impact of the corresponding type of sick leave on the infectious risk index Cfxs by using a time series analysis method to obtain a correlation coefficient Gxxs, and based on the value of the correlation coefficient Gxxs, perform a preliminary health screening operation. If an abnormal result is screened out, an area reduction instruction is issued;

[0120] The regional property analysis module is used to randomly set n groups of cluster centers after receiving the regional reduction instruction, and combine the correlation coefficient Gxxs obtained in S3 to determine the number of departments in each cluster center after iterative operation, and re-determine the overall correlation coefficient Gxx of the corresponding abnormal disease in each cluster center according to the number of departments in each cluster center;

[0121] The management module is used to divide the entire industrial park into safety areas according to the overall correlation coefficient Gxx of the corresponding abnormal diseases in each cluster center, and take corresponding prevention and control measures according to the division results.

[0122] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for industrial health and safety risk data assessment, characterized by: The following steps are included: S1. According to the attendance information of each employee in the industrial park provided by the human resources department, relevant attendance data information is obtained, and based on the relevant attendance data information, the reasons for employees taking leave are tracked, and the relevant reason difference data information is obtained. After dimensionless processing, a personnel statistical data set is generated; S2. Extract the relevant sick leave reasons according to the relevant reason difference data information in the personnel statistical data set, and classify the relevant sick leave reasons to obtain the disease type set, and combine with the relevant attendance data information to construct the infection risk index Cfxs; S3. Use the time series analysis method to analyze the impact of the corresponding type of sick leave on the infectious risk index Cfxs to obtain the correlation coefficient Gxxs, and perform preliminary health screening operations based on the correlation coefficient Gxxs value. If abnormal results are found, issue an area reduction instruction; S3 specifically includes: S31. Use the time series analysis method to analyze the influence of the corresponding type of sick leave on the infection risk index Cfxs, so as to obtain the correlation coefficient Gxxs under the corresponding type of sick leave state, which is obtained in the following way: ； In the formula, It is expressed as the ratio of the number of people taking sick leave of the corresponding type in the k-th analysis time series to the number of people taking sick leave. It is expressed as the infection risk index of the corresponding disease state in the k-th analysis time series, It is expressed as the standard deviation of the proportion of the number of people taking sick leave under the corresponding type of sick leave to the number of people taking sick leave. It is expressed as the standard deviation of the infection risk index under the corresponding type of disease state, Expressed as and The covariance of S32. Preset a safety threshold W, and compare the correlation coefficient Gxxs under the corresponding type of sick leave status with the safety threshold W to perform a preliminary health screening operation to determine whether there is a risk of transmission of the corresponding disease in the current industrial park. The specific determination content is as follows: If the correlation coefficient Gxxs exceeds the safety threshold W, it will be judged that there is a risk of the spread of the corresponding disease in the current industrial park, and an area reduction instruction will be issued to the outside, and the corresponding disease will be marked as an abnormal disease; If the correlation coefficient Gxxs does not exceed the safety threshold W, it will be judged that there is no risk of transmission of the corresponding disease in the current industrial park; S4, after receiving the regional reduction instruction, randomly set n groups of cluster centers, and combine with the correlation coefficient Gxxs obtained in S3, after iterative operation, to determine the number of departments in each cluster center, and according to the number of departments in each cluster center, re-determine the overall correlation coefficient Gxx of the corresponding abnormal disease in each cluster center; S4 specifically includes: S41. Randomly set n groups of cluster centers, and combine with the abnormal diseases obtained in S32 to perform correlation analysis on the abnormal diseases in various departments in the industrial park, and calculate the correlation coefficient Gxxs corresponding to the corresponding abnormal diseases in each department according to the method of obtaining the correlation coefficient Gxxs under the corresponding type of sick leave status; and preliminarily distribute the correlation coefficient Gxxs corresponding to the corresponding abnormal diseases in each department to each group of cluster centers to calculate the distance from the correlation coefficient Gxxs corresponding to the corresponding abnormal diseases in each department to all cluster centers, wherein each group of cluster centers is represented by the average correlation coefficient corresponding to the corresponding abnormal diseases in each cluster, and the average correlation coefficient corresponding to the corresponding abnormal diseases in each cluster is preliminarily randomly set; S42. Use the Euclidean distance algorithm to calculate the distance from the correlation coefficient Gxxs corresponding to the abnormal disease in each department to the center of all clusters, and record it as the distance Jz, which is specifically obtained by the following method: ； In the formula, Expressed as The correlation coefficient corresponding to the g-th abnormal disease in a department, It is expressed as the correlation coefficient corresponding to the g-th abnormal disease in the center of the R-th cluster; S4 also includes: S43. According to the calculated distances from the correlation coefficients Gxxs corresponding to the corresponding abnormal diseases in each department to all cluster centers, the correlation coefficients Gxxs corresponding to the corresponding abnormal diseases in each department are assigned to the nearest cluster center to calculate the mean value of the correlation coefficients Gxxs corresponding to the corresponding abnormal diseases in all departments in each cluster, and the mean value of the correlation coefficients Gxxs corresponding to the corresponding abnormal diseases in all departments in each cluster currently calculated is used as the new cluster center. S44, repeating steps S41, S42 and S43 until the preset n cluster centers no longer change, stopping the repetitive operation, obtaining the final cluster center, and finally determining the corresponding department and the number of departments in each cluster center; S4 also includes: S45. According to the corresponding departments and the number of departments in each cluster center, the overall correlation coefficient Gxx of the corresponding abnormal diseases in each cluster center is re-determined. The specific acquisition method is as follows: ； Where P represents the number of departments in each cluster center, c=1, 2, 3, ..., P, It is expressed as the correlation coefficient corresponding to the corresponding abnormal disease in the cth department in each cluster center; S5. Based on the overall correlation coefficient Gxx of the corresponding abnormal diseases in each cluster center obtained in S4, the entire industrial park is divided into safety areas, and corresponding prevention and control measures are taken according to the division results.

2. The method for industrial health and safety risk data assessment according to claim 1, characterized in that: S1 specifically includes: S11. Collect relevant attendance data information of all employees in the industrial park from the human resources department in advance, wherein the relevant attendance data information includes the attendance times, lateness times, early departure times and leave times of each employee in the industrial park, and is accompanied by the employee ID, name, position and department of each employee; use statistical algorithms to obtain the total number of leave requests Zs; S12. Based on the relevant attendance data information collected in S11, the reasons for the employees taking leave are tracked and recorded to obtain the difference data information of the relevant reasons for the employees taking leave, wherein the difference data information of the relevant reasons includes the reasons for the leave of different employees taking leave; using statistical algorithms, the number of people taking leave Qs under different types of disease states, the incidence of different types of disease states and the number of people who requested sick leave, Bqi; S13. Pre-process the relevant attendance data information and relevant cause difference data information to generate a personnel statistical data set, and use dimensionless technology to convert data of different dimensions in the personnel statistical data set to the same scale range.

3. The method for industrial health and safety risk data assessment according to claim 2, characterized in that: S2 specifically includes: S21. Extracting relevant sick leave reasons according to relevant reason difference data information in the personnel statistical data set, and classifying the relevant sick leave reasons to obtain a disease type set, wherein the disease type set includes different types of diseases; S22. According to the disease type set, calculate the ratio of the number of people who take leave due to different types of diseases to the total number of people who take leave, Jqs, which can be obtained by: ; S23. During the operation of the industrial park, the working status of employees is monitored in real time, and relevant work data is obtained, wherein the relevant work data includes the number of contacts between each employee Jccs and the duration of each contact Jsc; based on the relevant work data, a contact factor Jcyz is obtained, wherein the contact factor Jcyz is obtained by the following formula: ； In the formula, m represents the total number of employees, i=1, 2, 3, ..., m, It is represented as the number of contacts of the ith employee, and T is the monitoring period.

4. The method for industrial health and safety risk data assessment according to claim 3, characterized in that: S2 also includes: S24. Based on S22 and S23, construct the infection risk index Cfxs under different types of disease states, which can be obtained in the following way: ； In the formula, It is expressed as the ratio of the number of people who take leave due to the j-th type of disease to the total number of people who take leave. It is represented by the incidence rate of the j-th type of disease, and Bqi is represented by the number of people who take sick leave.

5. The method for industrial health and safety risk data assessment according to claim 1, characterized in that: S5 specifically includes: S51, comparing the overall correlation coefficients Gxx of the corresponding abnormal diseases in each cluster center, to screen out the value with the largest value again from the overall correlation coefficients Gxx of the corresponding abnormal diseases in the n groups of cluster centers, and regard the cluster center corresponding to the overall correlation coefficient Gxx with the largest value as a dangerous area, so as to divide the entire industrial park into safety areas; S52. Take corresponding prevention and control measures for dangerous areas. The specific prevention and control measures are: immediately require employees to wear personal protective equipment, including masks and gloves, and replace them regularly. Give priority to vaccinating employees in dangerous areas to establish a herd immunity barrier. At the same time, carry out disinfection tasks regularly, and adopt staggered get off work and rest hours for dangerous areas.

6. A system for industrial health and safety risk data assessment, used to implement the method for industrial health and safety risk data assessment as described in any one of claims 1 to 5, characterized in that: It includes data collection module, transmission risk analysis module, impact module, regional nature analysis module and management module; The data collection module is used to obtain relevant attendance data information based on the attendance status of each employee in the industrial park provided by the human resources department, and based on the relevant attendance data information, track the reasons for employees taking leave, and obtain relevant reason difference data information, and generate a personnel statistical data set after dimensionless processing; The transmission risk analysis module is used to extract relevant sick leave reasons based on the relevant reason difference data information in the personnel statistical data set, and classify the relevant sick leave reasons to obtain a disease type set, and combine the relevant attendance data information to construct a transmission risk index Cfxs; The impact module is used to analyze the impact of the corresponding type of sick leave on the infectious risk index Cfxs by using a time series analysis method to obtain a correlation coefficient Gxxs, and based on the value of the correlation coefficient Gxxs, perform a preliminary health screening operation. If an abnormal result is screened out, an area reduction instruction is issued; The regional property analysis module is used to randomly set n groups of cluster centers after receiving the regional reduction instruction, and combine the correlation coefficient Gxxs obtained in S3 to determine the number of departments in each cluster center after iterative operation, and re-determine the overall correlation coefficient Gxx of the corresponding abnormal disease in each cluster center according to the number of departments in each cluster center; The management module is used to divide the entire industrial park into safety areas according to the overall correlation coefficient Gxx of the corresponding abnormal diseases in each cluster center, and take corresponding prevention and control measures according to the division results.

Images